SEAMS 2019
Sat 25 - Sun 26 May 2019 Montreal, QC, Canada
co-located with ICSE 2019
Sat 25 May 2019 11:25 - 11:50 at Duluth - Learning Chair(s): Rogério de Lemos

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 multi-dimensional analysis of the state-of-the-art research in CSAS with learning capabilities. 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.

Sat 25 May

Displayed time zone: Eastern Time (US & Canada) change

11:00 - 12:25
LearningSEAMS 2019 at Duluth
Chair(s): Rogério de Lemos University of Kent, UK
11:00
25m
Talk
Efficient Analysis of Large Adaptation Spaces Self-Adaptive Systems using Machine LearningLong Paper
SEAMS 2019
Federico Quin Katholieke Universiteit Leuven, Danny Weyns KU Leuven, Thomas Bamelis Katholieke Universiteit Leuven, Sarpreet Singh Buttar Linnaeus University, Sam Michiels Katholieke Universiteit Leuven
11:25
25m
Talk
On Learning in Collective Self-adaptive Systems: State of Practice and a 3D FrameworkLong Paper
SEAMS 2019
Mirko D'Angelo Linnaeus University, Sweden, Simos Gerasimou , Sona Ghahremani Hasso Plattner Institute, University of Potsdam, Johannes Grohmann University of Wurzburg, Ingrid Nunes Universidade Federal do Rio Grande do Sul (UFRGS), Brazil, Evangelos Pournaras ETH Zurich, Switzerland, Sven Tomforde Universitat Kassel
Pre-print
11:50
20m
Talk
Using Unstructured Data to Improve the Continuous Planning of Critical Processes Involving HumansNIER
SEAMS 2019
Colin Paterson , Radu Calinescu University of York, UK, Suresh Manandhar University of York, UK, Di Wang University of York, UK
12:10
15m
Talk
TRAPPed in Traffic? A Self-Adaptive Framework for Decentralized Traffic OptimizationArtifactReusable
SEAMS 2019
Ilias Gerostathopoulos Technical University of Munich, Evangelos Pournaras ETH Zurich, Switzerland
Pre-print