A unified time scale intelligent control algorithm for microgrid based on extreme dynamic programming

Abstract

Benefiting from the progress of power electronics technology, distributed generation technology is developing rapidly. Since microgrids cannot rely on traditional multi-time scale control strategies to ensure the high-quality frequency stability control and economic dispatch in the same time scale, this paper proposes an extreme dynamic programming algorithm. The proposed algorithm takes an adaptive dynamic programming algorithm as the framework, an extreme learning machine as a kernel of the evaluation module, a model module, an implementation module and a new prediction module. The resulting unified time scale intelligent control algorithm better realizes the combined functions of 'droop control + automatic generation control + economic dispatch' in the traditional opermode. Finally, in order to verify the effectiveness of the proposed algorithm, a microgrid model of 8 nodes is simulated. The results confirm the feasibility and validity of the proposed extreme dynamic programming algorithm.