Publikationer från Malmö universitet
Ändra sökning
Avgränsa sökresultatet
123 101 - 142 av 142
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 101.
    Olsson, Helena Holmström
    et al.
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Bosch, Jan
    Singing the Praise of Empowerment: Or Paying the Cost of Chaos2018Ingår i: Proceedings of the EUROMICRO Conference, IEEE, 2018, s. 17-21Konferensbidrag (Refereegranskat)
    Abstract [en]

    Empowerment is based on the belief that employees have the ability, and the desire, to shoulder more responsibility and perform better when given freedom. In an empowered organization, authority is given to employees with the intent to increase responsiveness to customers, improve decision-making power and to increase team motivation and skills. However, while most studies picture empowerment as the "ideal state" and the place where all organizations strive to be, our research shows that fully empowered teams without strategic guidance suffer from a number of problems. Based on multi-case study research in eleven software-intensive companies, we see that companies need to allow for different levels of empowerment depending on what they aim to achieve, characteristics of the industry domain, the business model and other factors, and that strategic guidance is critical to set direction and for avoiding chaos. To help companies approach the optimal level of empowerment, we provide a framework consisting of two inter-connected models that help companies to, rather than staying in their current hierarchical structures, transition to a level of empowerment that maximizes business value and performance.

  • 102.
    Olsson, Helena Holmström
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    Bosch, Jan
    Katumba, Brian
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    User Dimensions in 'Internet of Things' Systems: The UDIT Model2016Ingår i: Software Business: 7th International Conference, ICSOB 2016, Ljubljana, Slovenia, June 13-14, 2016, Proceedings, Springer, 2016, s. 161-168Konferensbidrag (Refereegranskat)
    Abstract [en]

    'Internet of Things' (IoT) systems are fundamentally changing the way in which we interact and perceive technology. In this paper, we focus on two dimensions of IoT systems; (1) the IoT user interface and (2) the IoT ecosystem. We develop a model that identifies how data is presented to users and how users interact with the system, and the level at which systems interconnect with, and collects data from, external systems. Companies can use the model to map their systems according to the dimensions in order to: (1) identify current state of their systems, (2) identify desired state and (3) better understand the steps necessary to develop more advanced IoT systems. We evaluate the dimensions in five case companies and provide empirical evidence on the transition towards increasingly advanced IoT systems.

  • 103.
    Olsson Holmström, Helena
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT). Malmö högskola, Internet of Things and People (IOTAP).
    So Much Data - So Little Value: A multi-case study on improving the impact of data-driven development practices2017Ingår i: 20th Conferencia Iberoamericanaen Software Engineering (CIbSE 2017), CIBSE , 2017, s. 249-262Konferensbidrag (Refereegranskat)
  • 104.
    Olsson Holmström, Helena
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    The ‘Three Layer Ecosystem Strategy Model’ (TeLESM)2015Ingår i: Proceedings of the1st Scandinavian Workshop on theEngineering of Systems-of-Systems(SWESoS 2015), Swedish Institute of Computer Science (SICS) , 2015Konferensbidrag (Refereegranskat)
  • 105.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS).
    Bosch, Jan
    Collaborative Innovation: A Model For Selecting The Optimal Ecosystem Innovation Strategy2016Ingår i: 2016 42th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), IEEE, 2016, s. 206-213Konferensbidrag (Refereegranskat)
    Abstract [en]

    Traditionally, innovation initiatives in software-intensive systems companies are viewed as either internal innovation, such as technology driven innovation based on ideas generated within a company, as collaborative innovation where a number of stakeholders co-create value, or as external innovation in which companies adopt strategies to capture and expand on ideas created by other stakeholders. However, and based on longitudinal case study research in six software-intense companies in the embedded systems domain, we see that most innovation strategies involve a mix of internal, collaborative and external elements. Due to the dichotomy in approaches however, companies often fail to select the optimal innovation strategy for the specific innovation challenge at hand. As a result, innovation initiatives suffer and companies and their ecosystem partners cannot fully capitalize on the value created. In this paper, we present a conceptual framework in which we identify twelve different ecosystem-centric innovation strategies. For each strategy, we identify the internal, the collaborative and the external elements. Also, and based on our empirical findings, we provide guidelines on the optimal selection of strategies.

  • 106.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    Bosch, Jan
    Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden.
    Ecosystem-Driven Software Development: A case study on the emerging challenges in inter-organizational R&D2014Ingår i: ICSOB 2014: Software Business. Towards Continuous Value Delivery, Springer, 2014, s. 16-26Konferensbidrag (Refereegranskat)
    Abstract [en]

    Most companies today experience a situation in which they are part of a complex business ecosystem of stakeholders that influence business outcomes. Especially for companies transitioning from selling products to becoming systems, solutions and services providers, this is causing a significant shift in their business strategies and relationships. Instead of focusing on internal processes, companies need to strategically position themselves in a dynamic network of actors to accelerate synergies and value co-creation. However, while this shift in business strategy is inevitable, it is not without challenges. An understanding for how to align internal, as well as external processes is critical, as well as a careful assessment on how to establish strategic partnerships in a dynamic network of interests. Based on on-going research, this paper outlines the emerging challenges that most software development companies face when adopting an ecosystem-driven approach, and the different mitigation strategies to manage these.

  • 107.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS).
    Bosch, Jan
    From ad hoc to strategic ecosystem management: the "Three-Layer Ecosystem Strategy Model" (TeLESM)2017Ingår i: Journal of Software: Evolution and Process, ISSN 2047-7473, E-ISSN 2047-7481, Vol. 29, nr 7, artikel-id e1876Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Recently, business ecosystems have been recognized as one of the most interesting phenomenon in software engineering research. Companies experience a paradigm shift where product development and innovation is moving outside the boundaries of the firm and where networks of stakeholders join forces to co-create value. While there is prominent research focusing on the managerial perspective of business ecosystems, few studies provide strategic guidance for how to intentionally manage the different ecosystems that companies operate in. Therefore, and on the basis of multicase study research, we provide empirical evidence on the challenges that software-intensive companies experience in relation to the different types of business ecosystems they operate in. We conduct a state-of-the-art literature review to identify strategies that are used to manage ecosystem engagements, and we develop a conceptual model in which we identify strategies for managing the innovation ecosystem, the differentiating ecosystem, and the commoditizing ecosystem. By categorising the different strategies in relation to the different types of ecosystems for which they are valid, the three-layer ecosystem strategy model provides comprehensive support for strategy selection. We validate the use of the identified strategies in 6 software-intensive case companies, and we provide empirical insights on the relevance and the desired use of these strategies as experienced by the case companies.

  • 108.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Teknik och samhälle (TS). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    From Opinions to Data-Driven Software R&D: A Multi-Case Study On How To Close The 'Open Loop' Problem2014Ingår i: Proceedings of the Euromicro Conference, IEEE, 2014, s. 9-16Konferensbidrag (Refereegranskat)
    Abstract [en]

    In most software development companies the road mapping and requirements prioritization process is a complex process in which product management experiences difficulties in getting timely and accurate customer feedback. The feedback loop from customers is slow and often there is a lack of mechanisms that allow for efficient customer data collection and analysis. As a result, there is the risk that requirements prioritization becomes opinion-based rather than data-driven, and that R&D investments are made without an accurate way of continuously validating whether they correspond to customer needs. We call this phenomenon the 'open loop' problem, referring to the challenges for product management to get accurate and timely feedback from customers. To address this problem, we develop the HYPEX model (Hypothesis Experiment Data-Driven Development) that supports companies in running feature experiments to shorten customer feedback loops. We evaluate the model in three software development companies and observe how feature experiments increase the opportunity for data-driven software development.

  • 109.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    From Requirements To Continuous Re-prioritization Of Hypotheses2016Ingår i: Proceedings of the International Workshop on Continuous Software Evolution and Delivery (CSED '16), ACM Digital Library, 2016, s. 63-69Konferensbidrag (Refereegranskat)
    Abstract [en]

    Typically, customer feedback collected in the prestudy, and during the early stages of software development, determines what new features to develop. However, once the decision to develop a new feature is taken, companies stop validating if this feature adds value to its intended customers. Instead, focus is shifted towards developing and implementing the feature. As a result, re-prioritization of feature content is rare, and companies find it difficult to continuously assess and validate feature value. In this paper, we explore the data collection practices in five software development companies. We introduce a model that allows continuous re-prioritization of features. Our model advocates a development approach in which requirements are viewed as hypotheses that need to be continuously validated, and where customer feedback is used to continuously re-prioritize feature content. We identify how the model helps companies transition from early specification of requirements towards continuous re-prioritization of hypotheses.

  • 110.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    Bosch, Jan
    No More Bosses?: A multi-case study on the emerging use of non-hierarchical principles in large-scale software development2016Ingår i: Product-focused software process improvement: 17th international conference PROFES 2016, Springer, 2016, s. 86-101Konferensbidrag (Refereegranskat)
  • 111.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Teknik och samhälle (TS).
    Bosch, Jan
    Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden.
    Post-deployment Data Collection in Software-Intensive Embedded Products2013Ingår i: Software Business: From Physical Products to Software Services and Solutions, Springer, 2013, s. 79-89Konferensbidrag (Refereegranskat)
    Abstract [en]

    To stay competitive, software development companies need to constantly evolve their software development practices. Companies that succeed in shortening customer feedback loops, minimizing the time between customer proof points and learn from customer usage data will be able to accelerate innovation and improve the accuracy of their development investments. While contemporary research reports on a number of well-established techniques for actively involving customers before and during development, there is less evidence on how to successfully use post-deployment customer data as input to the development process. As a result, companies invest significantly in development efforts without having an accurate way of continuously validating whether the functionality they develop is of direct value to customers once the product is taken into use. In this paper, we explore techniques for involving customers and for collecting customer data in pre-development, during development and in the post-deployment phase of software development. We do so by studying three software development companies involved in large-scale development of embedded software. We present an inventory of the techniques they use for collecting customer feedback and we outline the key opportunities for more effective development and evolution based on post-deployment data collection.

  • 112.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    Self-Learning, Self-Actuation and Decentralized Control: How Emergent System Capabilities Change Software Development2016Ingår i: Proceedings of the 2nd edition of Swedish Workshop on the Engineering of Systems of Systems(SWESOS 2016), Department of computer science and engineering, Chalmers; University of Gothenburg , 2016, s. 30-33Konferensbidrag (Refereegranskat)
    Abstract [en]

    With recent and rapid advances in areas such as online games, embedded systems and Internet of Things,the traditional notion of what constitutes a system is fundamentally changing.Similarly to Systems of Systems (SoS) these systems are heterogeneous, autonomous and allow dynamic and emergent configurations that evolve and adjust over time. Also, these systems allow automated optimization of system performance.Regarded as the new digital business paradigm, these types of systems offer fundamentally new ways for software development companies in their service-and value creation. At the same time, they present challenges in these organizations. In this paper, and based on multiple case study research in three different domains, we identify emergent system characteristics that pose new challenges on software development and we outline the transition towards new ways-of-working in software development.

  • 113.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS).
    Bosch, Jan
    Strategic Ecosystem Management: A Multi-case Study in the B2B Domain2015Ingår i: Product-Focused Software Process Improvement: 16th International Conference, PROFES 2015, Bolzano, Italy, December 2-4, 2015, Proceedings, Springer, 2015, s. 3-15Konferensbidrag (Refereegranskat)
    Abstract [en]

    In today's business environment, value creation is a collaborative effort in which companies depend on a number of external stakeholders. This implies a shift towards inter-organizational relationships and dependencies between companies. In this shift, companies seek strategies for how to effectively coordinate standardization efforts, share maintenance costs, and engage in open innovation initiatives, while at the same time increase control and accelerate development of differentiating functionality. On the basis of a multi-case study in six B2B software development companies, this paper explores the challenges involved in managing different ecosystem types. Based on the 'Three Layer Product Model' [1], we distinguish between innovation ecosystems, differentiating ecosystems and commoditizing ecosystems. We outline the challenges the companies experience in managing these, and we develop a model in which we identify the characteristics of each ecosystem type. Our model helps companies manage the different ecosystems they operate in. Finally, we present a framework in which we categorize the strategies employed by the case companies depending on the competitiveness of a specific product or product category.

  • 114.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS).
    Bosch, Jan
    Strategic Ecosystem Management: A multi-case study on challenges and strategies for different ecosystem types2015Ingår i: Proceedings 41st Euromicro Conference On Software Engineering and advanced applications Seaa 2015, IEEE, 2015, s. 398-401Konferensbidrag (Refereegranskat)
    Abstract [en]

    In today's business environment, value creation is a collaborative effort in which companies depend on a number of external stakeholders. This implies a shift towards inter-organizational relationships and dependencies between companies. In this shift, companies seek strategies for how to effectively coordinate standardization efforts, share maintenance costs, and engage in open innovation initiatives, while at the same time increase control and accelerate development of differentiating functionality. On the basis of a multi-case study in six B2B software development companies, this paper explores the challenges involved in managing different ecosystem types. Based on the 'Three Layer Product Model' [1], we distinguish between innovation ecosystems, differentiating ecosystems and commoditizing ecosystems. We outline the challenges the companies experience in managing these, and we develop a model in which we identify the drivers, the purpose, the stakeholders and the characteristics of each ecosystem type.

  • 115.
    Olsson Holmström, Helena
    et al.
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Bosch, Jan
    Chalmers.
    The Five Purposes of Value Modeling2020Ingår i: 2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), IEEE, 2020, s. 110-119Konferensbidrag (Refereegranskat)
    Abstract [en]

    Data driven and experimental development practices provide effective means for companies to adopt a customer and market-centric way-of-working. In online companies, controlled experimentation is the primary technique to measure how customers respond to variants of deployed software. Over the recent years, and due to increasing connectivity and data collection from products in the field, these practices are being adopted also in software-intensive embedded systems companies. In these companies, experiments are run on selected instances of the system or as comparisons of previously computed data to ensure value delivery to customers, improve quality and explore new value propositions. However, to utilize the benefits of data- driven and experimental development practices, companies need to define what value factors to optimize for. For highly complex embedded systems with thousands of parameters, and with people at different levels in the organization having different opinions about the value of features, this is a challenging task. In this paper, we report on longitudinal multi-case study research in which we explore value modeling as a technique to help people in development, in product management and on the business level to align interests and agree on value factors. Based on this work, we identify five purposes of value modeling and how this technique helps accelerate critical activities in an organization. The contribution of this paper is three-fold. First, we provide empirical evidence for how value modeling is an effective technique to help companies define what to optimize for. Second, we identify five purposes of value modeling. Third, we identify the key challenges that the case companies experience when applying value modeling.

  • 116.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    Bosch, Jan
    The HYPEX Model: From Opinions to Data-Driven Software Development2014Ingår i: Continuous Software Engineering / [ed] Jan Bosch, Springer, 2014, s. 155-164Kapitel i bok, del av antologi (Övrigt vetenskapligt)
    Abstract [en]

    While innovation, such as development of new features, is critical for any organization, it is hard to get right. In both our case companies, the selection of ideas is usually driven by previous experiences, and very often the process becomes politicized and based on peoples’ opinions. To address this, we present the Hypothesis Experiment Data-Driven Development (HYPEX) model. Our model is an alternative development process that helps companies shorten the feedback loop to customers. The model supports companies in running feature experiments and advocates development of small parts of features that are continuously evaluated with customers. In our study we validate the model in two software development companies. Although the companies involved in the study have not yet completed a full experiment cycle, we see that feature experiments are beneficial for improving at least four activities within the companies: (1) data-driven development (the ease of collecting customer feedback allows for a real-time connection between the quantified business goals of the organization and the operational metrics collected from the installed customer base), (2) customer responsiveness (the ease of collecting customer feedback allows product management to respond rapidly and dynamically to any changes to the use of the products, as well as to emerging customer requests), (3) R&D efficiency (the ease of collecting customer feedback gives the development teams a real-time goal and metrics to strive for and provides focus for their work), and (4) R&D accuracy (the ease of collecting customer feedback enables the development teams to align their efforts with what the customers appreciate the most). The HYPEX model is a development process that helps software development companies move away from building large chunks of functionality with little feedback from customers and instead continuously validate with customers that the functionality under development is of value to customers.

  • 117.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    Towards Agile And Beyond: An empirical account on the challenges involved when advancing software development practices2014Ingår i: XP 2014: Agile Processes in Software Engineering and Extreme Programming, Springer, 2014, s. 327-335Konferensbidrag (Refereegranskat)
    Abstract [en]

    During the last decade, the vast majority of software companies have adopted agile development practices. Now companies are looking to move beyond agile and further advance their practices. In this paper, we report on the experiences of a company in the embedded systems domain that is adopting agile practices with the intention to move beyond agile and towards continuous deployment of software. Based on case study research involving group interviews and a web-based survey, we identify challenges in relation to (1) the adoption of agile practices, (2) testing practices, (3) continuous deployment, and (4) customer validation.

  • 118.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    Towards Continuous Customer Validation: A Conceptual Model for Combining Qualitative Customer Feedback with Quantitative Customer Observation2015Ingår i: Software Business: 6th International Conference, ICSOB 2015, Braga, Portugal, June 10-12, 2015, Proceedings, Springer, 2015, s. 154-166Konferensbidrag (Refereegranskat)
    Abstract [en]

    Software-intensive product companies are becoming increasingly data-driven as can be witnessed by the big data and Internet of Things trends. However, optimally prioritizing customer needs in a mass-market context is notoriously difficult. While most companies use product owners or managers to represent the customer, research shows that the prioritization made is far from optimal. In earlier research, we have coined the term 'the open loop problem' to characterize this challenge. For instance, research shows that up to half of all the features in products are never used. This paper presents a conceptual model that emphasizes the need for combining qualitative feedback in early stages of development with quantitative customer observation in later stages of development. Our model is inductively derived from an 18 months close collaboration with six large global software-intensive companies.

  • 119.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    Towards Continuous Validation of Customer Value2015Ingår i: XP '15 workshops Scientific Workshop Proceedings of the XP2015, ACM Digital Library, 2015, artikel-id 3Konferensbidrag (Refereegranskat)
    Abstract [en]

    While close customer collaboration is highlighted as a distinguishing characteristic in agile development, difficulties arise in large-scale agile development where the product owner can no longer represent the different needs of a large customer base. While most companies use the role of a product owner to represent the customer base, experiences show that prioritizations that are made are far from optimal. Also, once the decision to develop a feature has been taken, companies stop to continuously validate if this feature adds value to the large customer base. As experienced in the case companies we work with, re-prioritization of feature content is difficult once development has started, resulting in R&D investments in development of features that have no proven customer value. In this paper, and based on our experiences from working with five B2B software development companies, we present a conceptual model in which qualitative and quantitative customer feedback techniques allow for continuous validation and re-prioritization of feature content. In this way, large-scale software development companies can significantly improve responsiveness to customers throughout the development cycle, while at the same time increase accuracy of their development efforts.

  • 120.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    Bosch, Jan
    Towards Data-Driven Product Development: A Multiple Case Study on Post-Deployment Data Usage in Software-Intensive Embedded Systems2013Ingår i: LESS 2013: Lean Enterprise Software and Systems, Springer, 2013, s. 152-164Konferensbidrag (Refereegranskat)
    Abstract [en]

    Today, products within telecommunication, transportation, consumer electronics, home automation, security etc. involve an increasing amount of software. As a result, organizations that have a tradition within hardware development are transforming to become software-intensive organizations. This implies products where software constitutes the majority of functionality, costs, future investments, and potential. While this shift poses a number of challenges, it brings with it opportunities as well. One of these opportunities is to collect product data in order to learn about product use, to inform product management decisions, and for improving already deployed products. In this paper, we focus on the opportunity to use post-deployment data, i.e. data that is generated while products are used, as a basis for product improvement and new product development. We do so by studying three software development companies involved in large-scale development of embedded software. In our study, we highlight limitations in post-deployment data usage and we conclude that post-deployment data remains an untapped resource for most companies. The contribution of the paper is two-fold. First, we present key opportunities for more effective product development based on post-deployment data usage. Second, we propose a framework for organizations interested in advancing their use of post-deployment product data.

  • 121.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    Towards 'Human/System Synergistic Development': How Emergent System Characteristics Change Software Development2016Ingår i: Software Business: 7th International Conference, ICSOB 2016, Ljubljana, Slovenia, June 13-14, 2016, Proceedings, Springer, 2016, s. 153-160Konferensbidrag (Refereegranskat)
    Abstract [en]

    With recent and rapid advances in areas such as online games, embedded systems and Internet of Things, the traditional notion of what constitutes a system, as well as how a system is typically developed, is fundamentally changing. Instead of systems that are specified upfront, and for which there are pre-defined purposes and tasks, we are increasingly experiencing a situation in which interconnectivity and emergent configurations of systems allow dynamic system capabilities that evolve and adjust over time. Regarded as the new digital business paradigm, these types of systems offer fundamentally new ways for software development companies in their service-and value creation. At the same time, they present challenges in these organizations. In this paper, and based on multiple case study research in three different domains, we identify emergent system characteristics that pose new challenges on software development. We present a model that outlines the transition from traditional development towards 'Human/System Synergistic Development' (HuSySD), in which software development is a joint effort between software development teams and intelligent systems.

  • 122.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Teknik och samhälle (TS).
    Bosch, Jan
    Alahyari, Hiva
    Customer-Specific Teams for Agile Evolution of Large-Scale Embedded Systems2013Ingår i: 39th Euromicro Conference of Software Engineering Advanced Applications (SEAA), 2013, s. 82-89Konferensbidrag (Refereegranskat)
    Abstract [en]

    For more than a decade, agile methods have shown successful for increasing responsiveness to customer needs. As a major characteristic, agile methods advocate close customer collaboration in the early phases of software development. However, research on how to maintain agile ways of working during software evolution is scarce. In this paper, we address the need to establish and maintain agile ways of working during software evolution. We direct our attention to large-scale software development where development companies struggle to meet the needs of a large customer base. The contribution of this paper is two-fold. First, we propose customer-specific teams as a way to reap the benefits of agile methods in the evolution phase of large-scale software development. Second, we confirm the use of these teams as successful for improving customer responsiveness, customer satisfaction and feature quality in the subsequent phases of software evolution.

    Ladda ner fulltext (pdf)
    FULLTEXT01
  • 123.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS).
    Bosch, Jan
    Fabijan, Aleksander
    Malmö högskola, Fakulteten för teknik och samhälle (TS).
    Experimentation that Matters: A Multi-case Study on the Challenges with A/B Testing2017Ingår i: Software Business: 8th International Conference, ICSOB 2017, Essen, Germany, June 12-13, 2017, Proceedings, Springer, 2017, s. 179-185Konferensbidrag (Refereegranskat)
    Abstract [en]

    From having been exclusive for companies in the online domain, feature experiments are becoming increasingly important for software-intensive companies also in other domains. Today, companies run experiments, such as e.g. A/B tests, to optimize product performance and to learn about user behaviors, as well as to guide product development and innovation. However, although experimentation with customers has become an effective mechanism to improve products and increase revenue, companies struggle with how to leverage the results of the experiments they run. In this paper, we study the reasons for this and we identify three key challenges that make feature experimentation a difficult task. Our research reveals the following challenges: (1) the impact of experiments doesn't scale, (2) business KPIs and team level metrics are not aligned and (3) it is unclear if the available solutions are applicable across domains.

  • 124.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV). Malmö högskola, Internet of Things and People (IOTAP).
    Bosch, Jan
    Katumba, Brian
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV). Malmö högskola, Internet of Things and People (IOTAP).
    Exploring IoT User Dimensions: A multi-case study on user interactions in ‘Internet of Things’ Systems2016Ingår i: Product-focused software process improvement: 17th international conference PROFES 2016, Springer, 2016, s. 477-484Konferensbidrag (Refereegranskat)
  • 125.
    Olsson Holmström, Helena
    et al.
    Malmö högskola, Teknik och samhälle (TS).
    Börjesson Sandberg, Anna
    Bosch, Jan
    Alahyari, Hiva
    Scale and Responsiveness in Large-Scale Software Development2014Ingår i: IEEE Software, ISSN 0740-7459, E-ISSN 1937-4194, Vol. 31, nr 5, s. 87-93Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In large-scale software development, there is typically a conflict between being responsive to individual customers, while at the same time achieving scale in terms of delivering a high number of features to a large customer base. Most often, organizations focus on scale and individual customer requests are viewed as problematic since they add complexity to product variation and version control. Here, we explore the use of customer-specific teams as a means to address this conflict. First, we verify the use of customer-specific teams as successful for improving customer responsiveness, customer satisfaction and feature quality through a case study at Ericsson. Second, we identify three approaches for how to organize feature development, and recommendations on how software development companies can efficiently use these to improve their practices. Third, we observe new business opportunities that arise when using customer-specific teams.

  • 126.
    Ouhaichi, Hamza
    et al.
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Bosch, Jan
    Chalmers University of TechnologyGothenburgSweden.
    Dynamic Data Management for Machine Learning in Embedded Systems: A Case Study2019Ingår i: Software Business: 10th International Conference, ICSOB 2019, Jyväskylä, Finland, November 18–20, 2019, Proceedings / [ed] Sami Hyrynsalmi; Mari Suoranta; Anh Nguyen-Duc; Pasi Tyrväinen; Pekka Abrahamsson, Springer, 2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    Dynamic data and continuously evolving sets of records are essential for a wide variety of today’s data management applications. Such applications range from large, social, content-driven Internet applications, to highly focused data processing verticals like data intensive science, telecommunications and intelligence applications. However, the dynamic and multimodal nature of data makes it challenging to transform it into machine-readable and machine-interpretable forms. In this paper, we report on an action research study that we conducted in collaboration with a multinational company in the embedded systems domain. In our study, and in the context of a real-world industrial application of dynamic data management, we provide insights to data science community and research to guide discussions and future research into dynamic data management in embedded systems. Our study identifies the key challenges in the phases of data collection, data storage and data cleaning that can significantly impact the overall performance of the system.

  • 127.
    Raj, Aiswarya
    et al.
    Chalmers Univ Technol, Gothenburg, Sweden..
    Bosch, Jan
    Chalmers Univ Technol, Gothenburg, Sweden..
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Wang, Tian J.
    Ericsson, Gothenburg, Sweden..
    Modelling Data Pipelines2020Ingår i: 2020 46TH EUROMICRO CONFERENCE ON SOFTWARE ENGINEERING AND ADVANCED APPLICATIONS (SEAA 2020) / [ed] Martini, A Wimmer, M Skavhaug, A, IEEE, 2020, s. 13-20Konferensbidrag (Refereegranskat)
    Abstract [en]

    Data is the new currency and key to success. However, collecting high-quality data from multiple distributed sources requires much effort. In addition, there are several other challenges involved while transporting data from its source to the destination. Data pipelines are implemented in order to increase the overall efficiency of data-flow from the source to the destination since it is automated and reduces the human involvement which is required otherwise. Despite existing research on ETL (Extract-Transform-Load) and ELT (Extract-Load-Transform) pipelines, the research on this topic is limited. ETL/ELT pipelines are abstract representations of the end-to-end data pipelines. To utilize the full potential of the data pipeline, we should understand the activities in it and how they are connected in an end-to-end data pipeline. This study gives an overview of how to design a conceptual model of data pipeline which can be further used as a language of communication between different data teams. Furthermore, it can be used for automation of monitoring, fault detection, mitigation and alarming at different steps of data pipeline.

  • 128.
    Raj, Aiswarya M.
    et al.
    Chalmers Univ Technol, Gothenburg, Sweden..
    Bosch, Jan
    Chalmers Univ Technol, Gothenburg, Sweden..
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Jansson, Anders
    CEVT, Gothenburg, Sweden..
    On the Impact of ML use cases on Industrial Data Pipelines2021Ingår i: 2021 28TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE (APSEC 2021), IEEE, 2021, s. 463-472Konferensbidrag (Refereegranskat)
    Abstract [en]

    The impact of the Artificial Intelligence revolution is undoubtedly substantial in our society, life, firms, and employment. With data being a critical element, organizations are working towards obtaining high-quality data to train their AI models. Although data, data management, and data pipelines are part of industrial practice even before the introduction of ML models, the significance of data increased further with the advent of ML models, which force data pipeline developers to go beyond the traditional focus on data quality. The objective of this study is to analyze the impact of ML use cases on data pipelines. We assume that the data pipelines that serve ML models are given more importance compared to the conventional data pipelines. We report on a study that we conducted by observing software teams at three companies as they develop both conventional(Non-ML) data pipelines and data pipelines that serve ML-based applications. We study six data pipelines from three companies and categorize them based on their criticality and purpose. Further, we identify the determinants that can be used to compare the development and maintenance of these data pipelines. Finally, we map these factors in a two-dimensional space to illustrate their importance on a scale of low, moderate, and high.

  • 129.
    Raj, Aiswarya M.
    et al.
    Chalmers.
    Bosch, Jan
    Chalmers.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Wang, Tian J.
    Ericsson, Gothenburg, Sweden..
    Towards Automated Detection of Data Pipeline Faults2020Ingår i: 2020 27TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE (APSEC 2020), IEEE, 2020, s. 346-355Konferensbidrag (Refereegranskat)
    Abstract [en]

    Data pipelines play an important role throughout the data management process. It automates the steps ranging from data generation to data reception thereby reducing the human intervention. A failure or fault in a single step of a data pipeline has cascading effects that might result in hours of manual intervention and clean-up. Data pipeline failure due to faults at different stages of data pipelines is a common challenge that eventually leads to significant performance degradation of data-intensive systems. To ensure early detection of these faults and to increase the quality of the data products, continuous monitoring and fault detection mechanism should be included in the data pipeline. In this study, we have explored the need for incorporating automated fault detection mechanisms and mitigation strategies at different stages of the data pipeline. Further, we identified faults at different stages of the data pipeline and possible mitigation strategies that can be adopted for reducing the impact of data pipeline faults thereby improving the quality of data products. The idea of incorporating fault detection and mitigation strategies is validated by realizing a small part of the data pipeline using action research in the analytics team at a large software-intensive organization within the telecommunication domain.

  • 130. Sauvola, Tanja
    et al.
    Lwakatare, Lucy Ellen
    Karvonen, Teemu
    Kuvaja, Pasi
    Olsson Holmström, Helena
    Malmö högskola, Fakulteten för teknik och samhälle (TS).
    Bosch, Jan
    Oivo, Markku
    Towards Customer-Centric Software Development: A Multiple-Case Study2015Ingår i: Proceedings 41st Euromicro Conference On Software Engineering and advanced applications Seaa 2015, IEEE, 2015, s. 9-17Konferensbidrag (Refereegranskat)
    Abstract [en]

    Customer involvement in software development is essential for building successful software products. Incremental improvements and enhancements of software require an in-depth and continuous understanding of customer needs. Also, mechanisms for managing customer feedback data need to be in place. However, previous research shows that the feedback loops from customers are slow and the process for obtaining timely feedback is challenging. In this study, we investigate customer feedback mechanisms and the ways in which customer data can be used to inform continuous improvement of software products. The contribution of this paper is twofold. First, we present a multiplecase study conducted in five Finnish software companies, where we identify how customer feedback data is collected and used in different product development activities. Second, we provide an explanatory 'customer touchpoint' (CTP) model which provides an overall understanding of customer feedback data collection and the related challenges in the case companies during software development.

  • 131. Sekileto, Nelson
    et al.
    Evbota, Felix
    Knauss, Eric
    Sandberg, Anna
    Chaudron, Michel
    Olsson Holmström, Helena
    Malmö högskola, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap (DV).
    Technical Dependency Challenges in Large-Scale Agile Development2014Ingår i: Agile Processes in Software Engineering and Extreme Programming. XP 2014., Springer, 2014, s. 46-61Konferensbidrag (Refereegranskat)
    Abstract [en]

    This qualitative study investigates challenges associated with technical dependencies and their communication. Such challenges frequently occur when agile practices are scaled to large-scale software development. The use of thematic analysis on semi-structured interviews revealed five challenges: planning, task prioritization, knowledge sharing, code quality, and integration. More importantly, these challenges interact with one another and can lead to a domino effect or vicious circle. If an organization struggles with one challenge, it is likely that the other challenges become problematic as well. This situation can have a significant impact on process and product quality. Our recommendations focus on improving planning and knowledge sharing (with practices such as scrum-of-scrums, continuous integration, open space technology) to break the vicious circle, and to reestablish effective communication across teams, which will then enable large-scale companies to achieve the benefits of large-scale agility.

  • 132.
    Zhang, H.
    et al.
    Chalmers University of Technology.
    Bosch, J.
    Chalmers University of Technology.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    End-to-End Federated Learning for Autonomous Driving Vehicles2021Ingår i: Proceedings of the International Joint Conference on Neural Networks, IEEE, 2021Konferensbidrag (Refereegranskat)
    Abstract [en]

    In recent years, with the development of computation capability in devices, companies are eager to investigate and utilize suitable ML/DL methods to improve their service quality. However, with the traditional learning strategy, companies need to first build up a powerful data center to collect and analyze data from the edge and then perform centralized model training, which turns out to be inefficient. Federated Learning has been introduced to solve this challenge. Because of its characteristics such as model-only exchange and parallel training, the technique can not only preserve user data privacy but also accelerate model training speed. The method can easily handle real-time data generated from the edge without taking up a lot of valuable network transmission resources. In this paper, we introduce an approach to end-to-end on-device Machine Learning by utilizing Federated Learning. We validate our approach with an important industrial use case in the field of autonomous driving vehicles, the wheel steering angle prediction. Our results show that Federated Learning can significantly improve the quality of local edge models and also reach the same accuracy level as compared to the traditional centralized Machine Learning approach without its negative effects. Furthermore, Federated Learning can accelerate model training speed and reduce the communication overhead, which proves that this approach has great strength when deploying ML/DL components to various real-world embedded systems.

  • 133.
    Zhang, H.
    et al.
    Chalmers University of Technology.
    Bosch, J.
    Chalmers University of Technology.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Engineering Federated Learning Systems: A Literature Review2021Ingår i: Software Business: 11th International Conference, ICSOB 2020, Karlskrona, Sweden, November 16–18, 2020, Proceedings / [ed] Eriks Klotins; Krzysztof Wnuk, Springer, 2021, s. 210-218Konferensbidrag (Refereegranskat)
    Abstract [en]

    With the increasing attention on Machine Learning applications, more and more companies are involved in implementing AI components into their software products in order to improve the service quality. With the rapid growth of distributed edge devices, Federated Learning has been introduced as a distributed learning technique, which enables model training in a large decentralized network without exchanging collected edge data. The method can not only preserve sensitive user data privacy but also save a large amount of data transmission bandwidth and the budget cost of computation equipment. In this paper, we provide a state-of-the-art overview of the empirical results reported in the existing literature regarding Federated Learning. According to the problems they expressed and solved, we then categorize those deployments into different application domains, identify their challenges and then propose six open research questions. 

  • 134.
    Zhang, H.
    et al.
    Chalmers University of Technology, Gothenburg, Sweden.
    Bosch, J.
    Chalmers University of Technology, Gothenburg, Sweden.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Koppisetty, A. C.
    Volvo Car Corporation, Gothenburg, Sweden.
    AF-DNDF: Asynchronous Federated Learning of Deep Neural Decision Forests2021Ingår i: Proceedings - 2021 47th Euromicro Conference on Software Engineering and Advanced Applications, SEAA 2021, IEEE, 2021, s. 308-315Konferensbidrag (Refereegranskat)
    Abstract [en]

    In recent years, with more edge devices being put into use, the amount of data that is created, transmitted and stored is increasing exponentially. Moreover, due to the development of machine learning algorithms, modern software-intensive systems are able to take advantage of the data to further improve their service quality. However, it is expensive and inefficient to transmit large amounts of data to a central location for the purpose of training and deploying machine learning models. Data transfer from edge devices across the globe to central locations may also raise privacy and concerns related to local data regulations. As a distributed learning approach, Federated Learning has been introduced to tackle those challenges. Since Federated Learning simply exchanges locally trained machine learning models rather than the entire data set throughout the training process, the method not only protects user data privacy but also improves model training efficiency. In this paper, we have investigated an advanced machine learning algorithm, Deep Neural Decision Forests (DNDF), which unites classification trees with the representation learning functionality from deep convolutional neural networks. In this paper, we propose a novel algorithm, AF-DNDF which extends DNDF with an asynchronous federated aggregation protocol. Based on the local quality of each classification tree, our architecture can select and combine the optimal groups of decision trees from multiple local devices. The introduction of the asynchronous protocol enables the algorithm to be deployed in the industrial context with heterogeneous hardware settings. Our AF-DNDF architecture is validated in an automotive industrial use case focusing on road objects recognition and demonstrated by an empirical experiment with two different data sets. The experimental results show that our AF-DNDF algorithm significantly reduces the communication overhead and accelerates model training speed without sacrificing model classification performance. The algorithm can reach the same classification accuracy as the commonly used centralized machine learning methods but also greatly improve local edge model quality.

  • 135.
    Zhang, Hongyi
    et al.
    Chalmers.
    Bosch, Jan
    Chalmers.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Federated Learning Systems: Architecture Alternatives2020Ingår i: 2020 27TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE (APSEC 2020), IEEE, 2020, s. 385-394Konferensbidrag (Refereegranskat)
    Abstract [en]

    Machine Learning (ML) and Artificial Intelligence (AI) have increasingly gained attention in research and industry. Federated Learning, as an approach to distributed learning, shows its potential with the increasing number of devices on the edge and the development of computing power. However, most of the current Federated Learning systems apply a single-server centralized architecture, which may cause several critical problems, such as the single-point of failure as well as scaling and performance problems. In this paper, we propose and compare four architecture alternatives for a Federated Learning system, i.e. centralized, hierarchical, regional and decentralized architectures. We conduct the study by using two well-known data sets and measuring several system performance metrics for all four alternatives. Our results suggest scenarios and use cases which are suitable for each alternative. In addition, we investigate the trade-off between communication latency, model evolution time and the model classification performance, which is crucial to applying the results into real-world industrial systems.

  • 136.
    Zhang, Hongyi
    et al.
    Chalmers University of Technology, Gothenburg, Sweden.
    Bosch, Jan
    Chalmers University of Technology, Gothenburg, Sweden.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    QuaFedAsync: Quality-based Asynchronous Federated Learning for the Embedded Systems2023Ingår i: 2023 49th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), Institute of Electrical and Electronics Engineers (IEEE), 2023Konferensbidrag (Refereegranskat)
    Abstract [en]

    In recent years, Federated Learning, as an approach to distributed learning, has shown its potential with the increasing number of devices on the edge and the development of computing power. The method enables large-scale training on the device that creates the data but with the sensitive data remaining within the data’s owner. In reality, however, the vast majority of enterprises have the problem of low data volume and poor model quality to support the implementation of Federated Learning methods. Learning quality assurance for edge devices is still the major issue which prevents Federated Learning to be applied in industrial contexts, especially in safety-critical applications. In this paper, we propose a quality-based asynchronous Federated Learning algorithm (QuaFedAsync) to address these challenges. We report on a study in which we used two well-known data sets, i.e., DDAD and KITTI datasets, and validate the proposed algorithm on an industrial use case concerned with monocular depth estimation in the automotive domain. Our results show that the proposed algorithm significantly improves the prediction performance compared to the commonly applied aggregation protocols while maintaining the same level of accuracy as centralized machine learning. Based on the results, we prove the learning efficiency and robustness when applying the algorithm to industrial scenarios.

  • 137.
    Zhang, Hongyi
    et al.
    Chalmers Univ Technol, Gothenburg, Sweden..
    Bosch, Jan
    Chalmers Univ Technol, Gothenburg, Sweden..
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Real-time End-to-End Federated Learning: An Automotive Case Study2021Ingår i: 2021 IEEE 45TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE (COMPSAC 2021) / [ed] Chan, WK Claycomb, B Takakura, H Yang, JJ Teranishi, Y Towey, D Segura, S Shahriar, H Reisman, S Ahamed, SI, IEEE, 2021, s. 459-468Konferensbidrag (Refereegranskat)
    Abstract [en]

    With the development and the increasing interests in ML/DL fields, companies are eager to apply Machine Learning/Deep Learning approaches to increase service quality and customer experience. Federated Learning was implemented as an effective model training method for distributing and accelerating time-consuming model training while protecting user data privacy. However, common Federated Learning approaches, on the other hand, use a synchronous protocol to conduct model aggregation, which is inflexible and unable to adapt to rapidly changing environments and heterogeneous hardware settings in real-world scenarios. In this paper, we present an approach to real-time end-to-end Federated Learning combined with a novel asynchronous model aggregation protocol. Our method is validated in an industrial use case in the automotive domain, focusing on steering wheel angle prediction for autonomous driving. Our findings show that asynchronous Federated Learning can significantly improve the prediction performance of local edge models while maintaining the same level of accuracy as centralized machine learning. Furthermore, by using a sliding training window, the approach can minimize communication overhead, accelerate model training speed and consume real-time streaming data, proving high efficiency when deploying ML/DL components to heterogeneous real-world embedded systems.

  • 138.
    Zhang, Hongyi
    et al.
    Chalmers Univ Technol, Horselgangen 11, S-41296 Gothenburg, Sweden..
    Dakkak, Anas
    Ericsson AB, Torshamnsgatan 21, S-16483 Stockholm, Sweden..
    Mattos, David Issa
    Chalmers Univ Technol, Horselgangen 11, S-41296 Gothenburg, Sweden..
    Bosch, Jan
    Chalmers Univ Technol, Horselgangen 11, S-41296 Gothenburg, Sweden..
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Towards Federated Learning: A Case Study in the Telecommunication Domain2021Ingår i: SOFTWARE BUSINESS (ICSOB 2021) / [ed] Wang, X Martini, A NguyenDuc, A Stray, V, Springer, 2021, Vol. 434, s. 238-253Konferensbidrag (Refereegranskat)
    Abstract [en]

    Federated Learning, as a distributed learning technique, has emerged with the improvement of the performance of IoT and edge devices. The emergence of this learning method alters the situation in which data must be centrally uploaded to the cloud for processing and maximizes the utilization of edge devices' computing and storage capabilities. The learning approach eliminates the need to upload large amounts of local data and reduces data transfer latency with local data processing. Since the Federated Learning technique does not require centralized data for model training, it is better suited to edge learning scenarios in which nodes have limited data. However, despite the fact that Federated Learning has significant benefits, we discovered that companies struggle with integrating Federated Learning components into their systems. In this paper, we present case study research that describes reasons why companies anticipate Federated Learning as an applicable technique. Secondly, we summarize the services that a complete Federated Learning system needs to support in industrial scenarios and then identify the key challenges for industries to adopt and transition to Federated Learning. Finally, based on our empirical findings, we suggest five criteria for companies implementing reliable Federated Learning systems.

  • 139.
    Zhang, Hongyi
    et al.
    Chalmers Univ Technol, Gothenburg, Sweden..
    Li, Jingya
    Ericsson, Ericsson Res, Gothenburg, Sweden..
    Qi, Zhiqiang
    Ericsson, Ericsson Res, Gothenburg, Sweden..
    Aronsson, Anders
    Ericsson, Ericsson Res, Gothenburg, Sweden..
    Bosch, Jan
    Chalmers Univ Technol, Gothenburg, Sweden..
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Deep Reinforcement Learning for Multiple Agents in a Decentralized Architecture: A Case Study in the Telecommunication Domain2023Ingår i: 2023 IEEE 20TH INTERNATIONAL CONFERENCE ON SOFTWARE ARCHITECTURE COMPANION, ICSA-C, IEEE COMPUTER SOC , 2023, s. 183-186Konferensbidrag (Refereegranskat)
    Abstract [en]

    Deep reinforcement learning has made significant development in recent years, and it is currently applied not only in simulators and games but also in embedded systems. However, when implemented in a real-world context, reinforcement learning is frequently shown to be unstable and incapable of adapting to realistic situations, particularly when directing a large number of agents. In this paper, we develop a decentralized architecture for reinforcement learning to allow multiple agents to learn optimal control policies on their own devices of the same kind but in varied environments. For such multiple agents, the traditional centralized learning algorithm usually requires a costly or time-consuming effort to develop the best-regulating policy and is incapable of scaling to a large-scale system. To address this issue, we propose a decentralized reinforcement learning algorithm (DecRL) and information exchange scheme for each individual device, in which each agent shares the individual learning experience and information with other agents based on local model training. We incorporate the algorithm into each agent in the proposed collaborative architecture and validate it in the telecommunication domain under emergency conditions, in which a macro base station (BS) is broken due to a natural disaster, and three unmanned aerial vehicles carrying BSs (UAV-BSs) are deployed to provide temporary coverage for missioncritical (MC) users in the disaster area. Based on the findings, we show that the proposed decentralized reinforcement learning algorithm can successfully support multi-agent learning, while the learning speed and service quality can be further enhanced.

  • 140.
    Zhang, Hongyi
    et al.
    Chalmers University of Technology,Gothenburg,Sweden.
    Li, Jingya
    Ericsson,Ericsson Research.
    Qi, Zhiqiang
    Ericsson,Ericsson Research.
    Aronsson, Anders
    Ericsson,Ericsson Research.
    Bosch, Jan
    Chalmers University of Technology,Gothenburg,Sweden.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Multi-Agent Reinforcement Learning in Dynamic Industrial Context2023Ingår i: 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), Institute of Electrical and Electronics Engineers (IEEE), 2023Konferensbidrag (Refereegranskat)
    Abstract [en]

    Deep reinforcement learning has advanced signifi-cantly in recent years, and it is now used in embedded systems in addition to simulators and games. Reinforcement Learning (RL) algorithms are currently being used to enhance device operation so that they can learn on their own and offer clients better services. It has recently been studied in a variety of industrial applications. However, reinforcement learning, especially when controlling a large number of agents in an industrial environment, has been demonstrated to be unstable and unable to adapt to realistic situations when used in a real-world setting. To address this problem, the goal of this study is to enable multiple reinforcement learning agents to independently learn control policies on their own in dynamic industrial contexts. In order to solve the problem, we propose a dynamic multi-agent reinforcement learning (dynamic multi-RL) method along with adaptive exploration (AE) and vector-based action selection (VAS) techniques for accelerating model convergence and adapting to a complex industrial environment. The proposed algorithm is tested for validation in emergency situations within the telecommunications industry. In such circumstances, three unmanned aerial vehicles (UAV-BSs) are used to provide temporary coverage to mission-critical (MC) customers in disaster zones when the original serving base station (BS) is destroyed by natural disasters. The algorithm directs the participating agents automatically to enhance service quality. Our findings demonstrate that the proposed dynamic multi-RL algorithm can proficiently manage the learning of multiple agents and adjust to dynamic industrial environments. Additionally, it enhances learning speed and improves the quality of service.

  • 141.
    Zhang, Hongyi
    et al.
    Chalmers Univ Technol, Gothenburg, Sweden..
    Li, Jingya
    Ericsson, Ericsson Research, Stockholm, Sweden..
    Qi, Zhiqiang
    Ericsson, Ericsson Research, Stockholm, Sweden..
    Lin, Xingqin
    Ericsson, Ericsson Research, Stockholm, Sweden..
    Aronsson, Anders
    Ericsson, Ericsson Research, Stockholm, Sweden..
    Bosch, Jan
    Chalmers Univ Technol, Gothenburg, Sweden..
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Autonomous Navigation and Configuration of Integrated Access Backhauling for UAV Base Station Using Reinforcement Learning2022Ingår i: 2022 IEEE future networks world forum: 2022 FNWF, IEEE, 2022, s. 184-189Konferensbidrag (Refereegranskat)
    Abstract [en]

    Fast and reliable connectivity is essential to enhance situational awareness and operational efficiency for public safety mission-critical (MC) users. In emergency or disaster circumstances, where existing cellular network coverage and capacity may not be available to meet MC communication demands, deployable-network-based solutions such as cells-on-wheels/wings can be utilized swiftly to ensure reliable connection for MC users. In this paper, we consider a scenario where a macro base station (BS) is destroyed due to a natural disaster and an unmanned aerial vehicle carrying BS (UAV-BS) is set up to provide temporary coverage for users in the disaster area. The UAV-BS is integrated into the mobile network using the 5G integrated access and backhaul (IAB) technology. We propose a framework and signalling procedure for applying machine learning to this use case. A deep reinforcement learning algorithm is designed to jointly optimize the access and backhaul antenna tilt as well as the three-dimensional location of the UAV-BS in order to best serve the on-ground MC users while maintaining a good backhaul connection. Our result shows that the proposed algorithm can autonomously navigate and configure the UAV-BS to improve the throughput and reduce the drop rate of MC users.

  • 142.
    Zhang, Hongyi
    et al.
    Chalmers University of Technology,Gothenburg,Sweden.
    Li, Jingya
    Ericsson Research,Ericsson.
    Qi, Zhiqiang
    Ericsson Research,Ericsson.
    Lin, Xingqin
    Ericsson Research,Ericsson.
    Aronsson, Anders
    Ericsson Research,Ericsson.
    Bosch, Jan
    Chalmers University of Technology,Gothenburg,Sweden.
    Olsson, Helena Holmström
    Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).
    Deep Reinforcement Learning in a Dynamic Environment: A Case Study in the Telecommunication Industry2022Ingår i: 2022 48th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), Institute of Electrical and Electronics Engineers (IEEE), 2022Konferensbidrag (Refereegranskat)
    Abstract [en]

    Reinforcement learning, particularly deep reinforcement learning, has made remarkable progress in recent years and is now used not only in simulators and games but is also making its way into embedded systems as another software-intensive domain. However, when implemented in a real-world context, reinforcement learning is typically shown to be fragile and incapable of adapting to dynamic environments. In this paper, we provide a novel dynamic reinforcement learning algorithm for adapting to complex industrial situations. We apply and validate our approach using a telecommunications use case. The proposed algorithm can dynamically adjust the position and antenna tilt of a drone-based base station to maintain reliable wireless connectivity for mission-critical users. When compared to traditional reinforcement learning approaches, the dynamic reinforcement learning algorithm improves the overall service performance of a drone-based base station by roughly 20%. Our results demonstrate that the algorithm can quickly evolve and continuously adapt to the complex dynamic industrial environment.

123 101 - 142 av 142
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf