基于多智能体系统微电网分布式控制研究

Research on Distributed Control of Microgrid Based on Multi-agent System

基于为了克服传统集中式控制策略计算量大、对系统通讯依赖强等缺点,文中提出了基于多智能体系统的分布式控制策略,采用有、无领导者一致性算法来解决经济调度问题。以各个微源的增量成本作为一致性变量,通过相邻微源间的相互通信,最终在满足各个微源达到增量成本一致的同时实现整个系统效益最优的经济目标。算例仿真验证了分布式一致性算法的有效性,研究收敛系数、通讯拓扑结构对算法收敛速度和动态性能的影响,并通过有领导者一致性算法与无领导者一致性算法的仿真结果进行对比,验证无领导者一致性算法的优势。

In order to overcome the shortcomings of traditional centralized control strategy,such as large amount of calculation,strong dependence on the system communication. This paper proposes a distributed con-trol strategy based on multi-agent system to solve the economic dispatch problem. We use consensus algorithm with and without leader for economic dispatch problems of microgrid. With the incremental cost of each micro source as consistent variables,through mutual communication between adjacent micro sources. Finally,each micro source meets equal incremental costs and the system achieves the optimal economic objective. The simula-tion verifies the validity of the distributed algorithm. The influence of convergence coefficient and communica-tion topology on convergence speed and dynamic performance of the algorithm is studied,and comparisons between consensus algorithm with and without the leader verify the advantages of no leader consensus algorithm.