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.
This paper proposes a self-organizing fully decentralized solution for the service assembly problem, whose goal is to guarantee a good overall quality for the delivered services, ensuring at the same time fairness among the participating peers. The main features of our solution are: (i) the use of a gossip protocol to support decentralized information dissemination and decision making, and (ii) the use of a reinforcement learning approach to make each peer able to learn from its experience the service selection rule to be followed, thus overcoming the lack of global knowledge. Besides, we explicitly take into account load-dependent quality attributes, which lead to the definition of a service selection rule that drives the system away from overloading conditions that could adversely affect quality and fairness. Simulation experiments show that our solution self-adapts to occurring variations by quickly converging to viable assemblies maintaining the specified quality and fairness objectives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.