Distributed learning algorithms for scheduling games in the future smart grid

Game theory is a key analytical tool to design Demand-Side Management (DSM) systems, since it can be used to model the complex interactions among the independent actors of the smart grids. In this paper, we propose two learning algorithms to enable the players of game theoretic DSM frameworks to autonomously converge to the Nash equilibria of the game, and we evaluate their performance based on real instances of the problem.