By the same authors

On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Standard

On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework. / Gerasimou, Simos; D’Angelo, Mirko; Ghahremani, Sona; Grohmann, Johannes; Nunes, Ingrid; Pournaras, Evangelos; Tomforde, Sven.

14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems. 2019.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Gerasimou, S, D’Angelo, M, Ghahremani, S, Grohmann, J, Nunes, I, Pournaras, E & Tomforde, S 2019, On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework. in 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems.

APA

Gerasimou, S., D’Angelo, M., Ghahremani, S., Grohmann, J., Nunes, I., Pournaras, E., & Tomforde, S. (Accepted/In press). On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework. In 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems

Vancouver

Gerasimou S, D’Angelo M, Ghahremani S, Grohmann J, Nunes I, Pournaras E et al. On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework. In 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems. 2019

Author

Gerasimou, Simos ; D’Angelo, Mirko ; Ghahremani, Sona ; Grohmann, Johannes ; Nunes, Ingrid ; Pournaras, Evangelos ; Tomforde, Sven. / On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework. 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems. 2019.

Bibtex - Download

@inproceedings{b3d229a7929743e0a53bef395f0e0fe1,
title = "On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework",
abstract = "Collective self-adaptive systems (CSAS) are distributed and interconnected systems composed of multiple agents that can perform complex tasks such as environmental data collection, search and rescue operations, and discovery of natural resources. By providing individual agents with learning capabilities, CSAS can cope with challenges related to distributed sensing and decision-making and operate in uncertain environments. This unique characteristic of CSAS enables the collective to exhibit robust behaviour while achieving system-wide and agent-specific goals. Although learning has been explored in many CSAS applications, selecting suitable learning models and techniques remains a significant challenge that is heavily influenced by expert knowledge. We address this gap by performing a multifaceted analysis of existing CSAS with learning capabilities reported in the literature. Based on this analysis, we introduce a 3D framework that illustrates the learning aspects of CSAS considering the dimensions of autonomy, knowledge access, and behaviour, and facilitates the selection of learning techniques and models. Finally, using example applications from this analysis, we derive open challenges and highlight the need for research on collaborative, resilient and privacy-aware mechanisms for CSAS.",
keywords = "self-adaptive systems, multi-agent systems, learning, taxonomy, autonomic systems, distributed systems",
author = "Simos Gerasimou and Mirko D{\textquoteright}Angelo and Sona Ghahremani and Johannes Grohmann and Ingrid Nunes and Evangelos Pournaras and Sven Tomforde",
year = "2019",
month = mar,
day = "22",
language = "English",
booktitle = "14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - On Learning in Collective Self-adaptive Systems: State of Practice and a 3D Framework

AU - Gerasimou, Simos

AU - D’Angelo, Mirko

AU - Ghahremani, Sona

AU - Grohmann, Johannes

AU - Nunes, Ingrid

AU - Pournaras, Evangelos

AU - Tomforde, Sven

PY - 2019/3/22

Y1 - 2019/3/22

N2 - Collective self-adaptive systems (CSAS) are distributed and interconnected systems composed of multiple agents that can perform complex tasks such as environmental data collection, search and rescue operations, and discovery of natural resources. By providing individual agents with learning capabilities, CSAS can cope with challenges related to distributed sensing and decision-making and operate in uncertain environments. This unique characteristic of CSAS enables the collective to exhibit robust behaviour while achieving system-wide and agent-specific goals. Although learning has been explored in many CSAS applications, selecting suitable learning models and techniques remains a significant challenge that is heavily influenced by expert knowledge. We address this gap by performing a multifaceted analysis of existing CSAS with learning capabilities reported in the literature. Based on this analysis, we introduce a 3D framework that illustrates the learning aspects of CSAS considering the dimensions of autonomy, knowledge access, and behaviour, and facilitates the selection of learning techniques and models. Finally, using example applications from this analysis, we derive open challenges and highlight the need for research on collaborative, resilient and privacy-aware mechanisms for CSAS.

AB - Collective self-adaptive systems (CSAS) are distributed and interconnected systems composed of multiple agents that can perform complex tasks such as environmental data collection, search and rescue operations, and discovery of natural resources. By providing individual agents with learning capabilities, CSAS can cope with challenges related to distributed sensing and decision-making and operate in uncertain environments. This unique characteristic of CSAS enables the collective to exhibit robust behaviour while achieving system-wide and agent-specific goals. Although learning has been explored in many CSAS applications, selecting suitable learning models and techniques remains a significant challenge that is heavily influenced by expert knowledge. We address this gap by performing a multifaceted analysis of existing CSAS with learning capabilities reported in the literature. Based on this analysis, we introduce a 3D framework that illustrates the learning aspects of CSAS considering the dimensions of autonomy, knowledge access, and behaviour, and facilitates the selection of learning techniques and models. Finally, using example applications from this analysis, we derive open challenges and highlight the need for research on collaborative, resilient and privacy-aware mechanisms for CSAS.

KW - self-adaptive systems

KW - multi-agent systems

KW - learning

KW - taxonomy

KW - autonomic systems

KW - distributed systems

M3 - Conference contribution

BT - 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems

ER -