CAJ | 학술논문

由于包含微源的多样性及运行模式的多样性，微网的二次频率控制面临着系统参数不确定性的挑战。文中提出了在多代理(Agent)分层混合控制模型中嵌入一种基于 Q 学习的智能算法。首先，动态预测出微网系统实时二次调频功率缺额值。其次，同时考虑微网运行经济性和环境效益，并采用模糊化方法和粒子群优化算法实现二次调度功率的分配。最后，在 C++Builder 环境下搭建了包括不同微源的本地层 Agent 和具有不同控制功能的中央层 Agent 的微网混合能量管理仿真平台，结果证明了所提出的基于 Q 学习的微网二次频率自适应控制器可以自适应微网系统结构及其参数的动态变化，实现微网二次调频的智能控制。
유우포함미원적다양성급운행모식적다양성，미망적이차빈솔공제면림착계통삼수불학정성적도전。문중제출료재다대리(Agent)분층혼합공제모형중감입일충기우 Q 학습적지능산법。수선，동태예측출미망계통실시이차조빈공솔결액치。기차，동시고필미망운행경제성화배경효익，병채용모호화방법화입자군우화산법실현이차조도공솔적분배。최후，재 C++Builder 배경하탑건료포괄불동미원적본지층 Agent 화구유불동공제공능적중앙층 Agent 적미망혼합능량관리방진평태，결과증명료소제출적기우 Q 학습적미망이차빈솔자괄응공제기가이자괄응미망계통결구급기삼수적동태변화，실현미망이차조빈적지능공제。
Because of the diversity of micro-sources and operation modes in a microgrid,secondary frequency control faces great challenges from the uncertainty of system parameters of the microgrid.To solve the problem,a Q-learning intelligent algorithm integrated in the hierarchical multi-agent model is proposed.Firstly,by the proposed method,the power to be regulated,which is called the microgrid regulation error (MRE),is dynamically calculated in the secondary control for real-time operation.Secondly,the generation schedule of distributed generators and batteries is modified in real-time with the MRE by the fuzzy theory and particle swarm optimization method by taking both economy and environmental benefits into consideration.Finally, a Q-learning algorithm based multi-agent hybrid energy management system for the microgrid simulation platform in terms of client-server frame is established in C++ Builder.Simulation results have verified that by the proposed Q-Learning method,secondary intelligent and adaptive frequency control is realized under the condition of variable structure and parameters in the microgrid.