Multiple objective optimal operation of power system using learning automata

A learning automaton is an automaton to update systematically the strategy for enhancing the performance in response to the output results, and several schemes of learning automata have been presented. Both the generation cost for economical operation and the modal performance measure for stable operation of the power system are considered as performance indices for optimization simultaneously. In this paper, variable structure learning automata are applied to achieving a best compromise solution between an optimal solution for economical operation and an optimal solution for stable operation of the power system under the circumstance that the loads vary randomly. It is shown that learning automata are applied satisfactorily to the multiobjective optimization problem for obtaining the best tradeoff among the conflicting economy and stability objectives of power systems