%0 Conference Proceedings
%T Reinforcement Learning Techniques for Decentralized Self-adaptive Service Assembly
%+ Linnaeus University
%+ Università degli Studi di Roma Tor Vergata [Roma] = University of Rome Tor Vergata
%+ Politecnico di Milano [Milan] (POLIMI)
%A Caporuscio, M.
%A D’angelo, M.
%A Grassi, V.
%A Mirandola, R.
%Z Part 2: Adaptation
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 5th European Conference on Service-Oriented and Cloud Computing (ESOCC)
%C Vienna, Austria
%Y Marco Aiello
%Y Einar Broch Johnsen
%Y Schahram Dustdar
%Y Ilche Georgievski
%I Springer International Publishing
%3 Service-Oriented and Cloud Computing
%V LNCS-9846
%P 53-68
%8 2016-09-05
%D 2016
%R 10.1007/978-3-319-44482-6_4
%Z Computer Science [cs]Conference papers
%X 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.
%G English
%Z TC 2
%Z WG 2.14
%2 https://inria.hal.science/hal-01638593/document
%2 https://inria.hal.science/hal-01638593/file/416679_1_En_4_Chapter.pdf
%L hal-01638593
%U https://inria.hal.science/hal-01638593
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-ESOCC
%~ IFIP-TC2
%~ IFIP-LNCS-9846
%~ IFIP-WG2-14