数字孪生驱动下微电网多智能体协调控制优化

Optimization of Multi-Agent Coordinated Control of Microgrid Driven by Digital Twin

传统微电网系统设备分时控制能力差,存在协同控制不足的问题。对此,提出采用思维进化算法优化多智能体控制系统。首先基于“源-网-荷-储”概念提出微电网多智能体模型,并优化目标环保成本与运维成本;然后在数据分析的基础上,通过历史光伏发电功率数据与当日气象数据,构建分布式“源”功率预测模型;最后采用思维进化算法对智能体种群调度策略的适应值进行趋同异化优化,迭代出最优种群调度策略。功率预测仿真结果表明,在类簇为3时,模型具有最高的预测精确性,较传统预测方法精度提升了5.6%;控制策略仿真结果表明,MEA算法的微电网协调控制决策优化后,提高多智能体协同控制能力,降低了环保成本与运维成本。

The traditional microgrid system equipment has poor time-sharing control ability and insufficient col⁃laborative control.In this paper,a Mind Evolutionary Algorithm(MEA)is proposed to optimize the multi-agent con⁃trol system.Firstly,based on the concept of"source-network-load-storage",a multi-agent model of microgrid was proposed,and the target environmental protection cost and operation and maintenance cost were optimized.Then,on the basis of data analysis,a distributed"source"power prediction model was constructed through historical photovol⁃taic power generation data and meteorological data of the day Finally,the mind evolutionary algorithm was used to op⁃timize the fitness value of the scheduling strategy of the agent population by convergence and dissimilation,and the optimal population scheduling strategy was iterated.The simulation results of power prediction show that the model has the highest prediction accuracy when the cluster number is 3,and the accuracy is improved by 5.6%compared with the traditional prediction method.The simulation results of the control strategy show that the coordinated control decision optimization of the MEA algorithm for microgrid improves the collaborative control ability of multi-agents,and reduces the cost of environmental protection and operation and maintenance.