基于深度强化学习的多能互补发电系统负荷频率控制策略  

Load Frequency Control Strategy of Hybrid Power Generation System:a Deep Reinforcement Learning—Based Approach

作　　者：梁煜东 陈峦[1] 张国洲 任曼曼 胡维昊 Liang Yudong;Chen Luan;Zhang Guozhou;Ren Manman;Hu Weihao(Key Laboratory of Wide-area Mearsurement and Control on Power System of Sichuan Province,University of Electronic Science and Technology of China,Chengdu,611731,China;State grid Anhui Electric Power Co.Ltd,Electric Power Research Institute,Hefei,230000,China)

机构地区：[1]电子科技大学电力系统广域测量与控制四川省重点实验室,成都611731 [2]国网安徽省电力有限公司电力科学研究院,合肥230000

出　　处：《电工技术学报》2022年第7期1768-1779,共12页Transactions of China Electrotechnical Society

基　　金：国家重点研发计划(2018YFE0127600);四川省科技计划(2018HH0146)资助项目。

摘　　要：针对大规模可再生能源接入电网引发的系统调频性能下降的问题,该文提出一种基于数据驱动的风火储多能互补发电系统负荷频率控制方法。首先,通过机理分析建立多区域混合发电系统的数学模型;其次,构建含控制性能标准(CPS)、风电机组弃风(P_(icast))和动态性能指标的奖励函数,将负荷频率控制问题转换为最大化奖励函数问题,并引入深度确定性策略梯度算法进行求解,通过预学习和在线应用,获得风电机组实际出力情况下的最优自适应协调频率控制策略;最后,从中长期控制性能入手进行分析,通过加入连续阶跃扰动或实际风速扰动仿真,验证所提出方法在改进负荷频率控制性能上的有效性和可行性。仿真结果表明,系统发生扰动时,储能设备的引入及所提的深度确定性策略梯度算法不仅能够更加有效地抑制波动,而且能够在缩短完成负荷频率控制所需调节时间的同时最大限度地减少弃风,提高风电消纳的比例。To solve the problem of frequency modulation performance degradation caused by largescale renewable energy access to the power grid,this paper proposes a data-driven load frequency coordinated optimization control method for hybrid energy system consisted of wind,thermal power and energy storage.Firstly,this paper establishes a mathematical model of the multi-area hybrid energy system through mechanism analysis.Secondly,a reward function with control performance standard(CPS),wind power casting and dynamic performance index is established.The load frequency control problem is transformed into a maximum reward function problem,and the deep deterministic policy gradient(DDPG)algorithm is introduced to solve this problem.Through pre-learning and online application,the optimal adaptive coordinated control strategy can be obtained under acturl output of wind turbine.Finally,the performance of the proposed method in improving the performance of load frequency control(LFC)is verified by adding continuous stepped disturbance and actual wind speed disturbance.Simulation results show that when the power system is disturbed,the introduction of energy storage equipment and the proposed method can not only suppress fluctuations effectively,but also shorten the adjustment time required by LFC and increase the proportion of wind power consumption.

关 键 词：多能互补发电系统 负荷频率控制 深度确定性策略梯度算法 控制性能标准(CPS)指标 

分 类 号：TM744[电气工程—电力系统及自动化]