期刊文献+

基于增强学习算法的微电网智能频率协调控制策略 被引量:1

Strategy of Intelligent Frequency Coordination Control for Microgrid Based on Reinforcement Learning Algorithm
下载PDF
导出
摘要 随着清洁能源发电比例的增加,为了减轻微电网发电的随机性以及不确定性带来的影响,提高供电可靠性,对于微电网进行频率控制显得尤为重要。由于储能系统可以灵活存储或释放电能,利用增强学习算法的智能控制策略,调整光伏发电接入微电网时的微型燃气轮机以及储能系统的功率输出,从而抑制微电网频率波动。分析了微电网中各个部分的传递函数,推导了各部分的功率输出关系,开发了一类基于增强学习算法的控制器用于微电网的频率控制,仿真结果验证了该智能控制策略的可行性,可有效抑制微电网由于光伏发电不确定性引起的频率波动。 With the increase in the proportion of clean energy power generation, in order to reduce the influence of randomness and uncertainty of microgrid power generation and improve the reliability of power supply, it is particularly important to control the frequency of microgrids.Since the energy storage system can flexibly store or release electric energy, the intelligent control strategy of reinforcement learning is used to adjust the power output of the micro gas turbine and the energy storage system when the photovoltaic power generation is connected to the microgrid, thereby suppressing the frequency fluctuation of the microgrid. The transfer function of each part in the microgrid is analyzed, the power output relationship of each part is deduced, and a kind of output feedback controller is developed for the frequency control of the microgrid. The simulation results verify the feasibility of the intelligent control strategy, which can effectively suppress frequency fluctuations of microgrids due to uncertainty in photovoltaic power generation.
作者 姜展鹏 刘洋 刘守恒 郝立超 JIANG Zhanpeng;LIU Yang;LIU Shouheng;HAO Lichao(College of Electrical Engineering,Shenyang University of Technology,Shenyang,Liaoning 110870,China;CPI Northeast New Energy Development Co.,Ltd.,Shenyang,Liaoning 110170,China)
出处 《东北电力技术》 2023年第2期1-5,共5页 Northeast Electric Power Technology
基金 辽宁省教育厅科学技术研究项目(LQGD2020001)。
关键词 增强学习 微电网 光伏发电 频率波动 reinforcement learning microgrid photovoltaic power generation frequency fluctuation
  • 相关文献

参考文献6

二级参考文献59

  • 1Y.N.KOU,J.H.ZHENG,Zhigang LI,Q.H.WU.Many-objective optimization for coordinated operation of integrated electricity and gas network[J].Journal of Modern Power Systems and Clean Energy,2017,5(3):350-363. 被引量:21
  • 2P.J.Werbos."Approximate dynamic programming for real-time control and neural modeling,"[].Handbook of IntelligentControl:NeuralFuzzyand Approaches.1992 被引量:1
  • 3F.L.Lewis,V.L.Syrmos.Optimal Control[]..1995 被引量:1
  • 4G.K.Venayagamoorthy."Adaptive critic design based neuro-controllers for turbo generator control,"[]..1999 被引量:1
  • 5Werbos,P.J.Advanced forecasting methods for global crisis warning and models of intelligence[].General Systems Yearbook.1977 被引量:1
  • 6R. E. Bellman.Dynamic Programming[]..1957 被引量:1
  • 7Dreyfus S,Law A.The Art and Theory of Dynamic Programming[]..1977 被引量:1
  • 8Jennie Si,Yu-Tsung Wang.On-line learning control by association and reinforcement[C].Proceedings of the IEEE-INNS-ENNS InternationalJoint Conference on Neural Networks(UCNN’) Italy.2000 被引量:1
  • 9Wenxin Liu,Venayagamoorthy G K,Wunch DC.A heuristic-dynamic-programming-based powersystemstabilizer for a turbogenerator in a single-ma-chine power system[].IEEE Transactions on Industry Applications.2005 被引量:1
  • 10Venayagamoorthy,G.K,Wunsch,D.C.,II Harley,R.G.Neurocontroi of Turbogenerators with Adaptive Critic Designs[].africon IEEE. 被引量:1

共引文献74

同被引文献18

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部