基于可进化PID的含电动汽车孤岛微电网负荷频率控制策略

A Load Frequency Control Strategy of Island Microgrid with V2G Based on Evolutionary-PID

电动汽车(electric vehicle,EV)作为具有车网互动(vehicle-to-grid,V2G)能力的移动储能组件,为微电网的频率稳定提供了更为灵活的控制方案。但是,分布式电源与电动汽车所具有的强非线性,也给微电网频率控制带来了新的挑战。为此,提出了一种基于可进化PID的含电动汽车微电网频率控制策略。首先,考虑电动汽车移动性和用户充电行为随机性,以及电动汽车充电站容量在日内的阶段性突变,建立了由电动汽车充电站、微型燃气轮机与分布式电源组成的微电网系统。其次,将PID与深度确定性策略梯度(DDPG)算法进行互补,形成可进化PID控制器,根据微电网系统实际情况完成状态空间、动作空间与奖励函数的设计,从而对PID控制器实现自适应权重参数的调整,有效解决了电动汽车与随机扰动所带来的强非线性影响。最后,仿真结果表明:与传统PID算法相比,可进化PID控制器不仅能够更有效地抑制强随机扰动所引起的频率波动,还可以更好地适用于系统参数和结构随时间发生变化的复杂工况。

As a mobile energy storage component with V2G capability,electric vehicles(EVs)provide a more flexible control scheme for the frequency stability of microgrids.However,the strong nonlinearity of distributed power supply and EVs also brings new challenges to microgrid frequency control.Therefore,a load frequency control strategy of island microgrid with V2G based on evolutionary-PID is proposed in this paper.First,considering the mobility of EVs and randomness of user charging behavior,as well as the phased mutation of the capacity of EVs station during the day,a microgrid system composed of EVs,micro gas turbine,and distributed power supply is established.Then,PID and DDPG algorithms are complementary to form a evolutionary-PID controller.According to the actual situation of the microgrid system,the design of state space,action space,and reward function is completed,to realize the adjustment of adaptive weight parameters of the PID controller,which effectively solves the strong nonlinear influence brought by EVs and random disturbance.Finally,the simulation results show that compared with the traditional control algorithm,the evolutionary-PID controller can not only suppress the frequency fluctuation caused by strong random disturbance more effectively,but also better adapt to complex working conditions where the system parameters and structure change strongly nonlinear with time.