Abstract
The cooperation of agents in smart grids to form coalitions could bring benefit both for agent itself and the distribution power system. To tackle the problem as a game of partition form function poses significant computing challenges due to the huge search space for the optimization problem. In this paper, we propose a stochastic optimization approach using Population Based Incremental Learning (PBIL) algorithm with top-k Merit Weighting and a customized strategy for choosing the initial probability to solve the problem. Empirical results show that the proposed algorithm gives competitive performance compared with a few stochastic optimization algorithms.