基于神经网络PID的压缩空气储能功率跟踪控制策略

发电技术

• • 下一篇

基于神经网络PID的压缩空气储能功率跟踪控制策略

刘庭响^1,2，陈来军³，李正曦^1,2，崔森^3,4*，刘瀚琛³，王恺^1,2

1．国网青海省电力公司经济技术研究院，青海省西宁市 810008；2．国网青海省电力公司，青海省西宁市 810000；3．清华大学电机工程与应用电子技术系，北京市海淀区 100084；4．新型电力系统运行与控制全国重点实验室（清华大学），北京市海淀区 100084

基金资助:
国家自然科学基金项目(52407115)；国网青海省电力公司科技项目资助(SGQHJY00NYJS2400275)；中国博士后科学基金(2025M770485)

Power Tracking Control Strategy for Compressed Air Energy Storage Based on Neural Network PID

LIU Tingxiang^1,2, CHEN Laijun³, LI Zhengxi^1,2, CUI Sen^3,4*, LIU Hanchen³, WANG Kai^1,2

1. Economic and Technical Research Institute, State Grid Qinghai Electric Power Company, Xining 810008, Qinghai Province, China; 2. State Grid Qinghai Electric Power Company, Xining 810000, Qinghai Province, China; 3. Department of Electrical Engineering, Tsinghua University, Haidian District, Beijing 100084, China; 4. State Key Laboratory of Power System Operation and Control (Tsinghua University), Haidian District, Beijing 100084, China

Supported by:
Project Supported by National Natural Science Foundation of China (52407115); State Grid Qinghai Electric Power Company Science and Technology Project (SGQHJY00NYJS2400275); China Postdoctoral Science Foundation (2025M770485).

摘要/Abstract

摘要： 【目的】在高比例可再生能源并网背景下，风光出力不确定性对电网安全稳定运行提出了挑战。压缩空气储能(compressed air energy storage，CAES)凭借其高灵活性、转速可调特性，能够快速响应电网功率指令并有效平抑波动。然而，传统控制策略难以适应CAES多变量和复杂工况，功率跟踪效果不佳。针对该问题，提出了基于神经网络PID的CAES功率跟踪控制策略。【方法】首先，构建透平侧动态模型，表征无功功率与励磁电压、有功功率与质量流量之间的动态关系；其次，设计基于神经网络PID的控制框架，通过在线自适应整定参数，实现无超调功率精确跟踪控制。最后，通过MATLAB/Simulink仿真验证了该策略在功率跟踪方面的响应性能。【结果】相较于传统PID控制，在连续负荷波动工况下有功功率动态偏差降幅达22.7%，无功功率动态偏差降低至0.66%。【结论】所提策略实现了对功率指令信号的快速无超调跟踪，为高比例新能源电网提供了一种实用化的功率跟踪控制解决方案。

关键词: 可再生能源, 电网, 压缩空气储能, 功率跟踪, 神经网络, PID控制

Abstract: [Objectives] Against the backdrop of high-proportion renewable energy integration, the uncertainty in wind and solar power output poses challenges to the safe and stable operation of the power grid. Compressed air energy storage (CAES), with its high flexibility and adjustable rotational speed characteristics, can rapidly respond to grid power commands and effectively suppress fluctuations. However, traditional control strategies struggle to adapt to the multi-variable and complex operating conditions of CAES, resulting in suboptimal power tracking performance. To address this issue, a power tracking control strategy for CAES based on neural network PID is proposed. [Methods] First, a turbine-side dynamic model is constructed to characterize the dynamic relationships between reactive power and excitation voltage, as well as between active power and mass flow rate. Subsequently, a control framework based on neural network PID is designed to achieve precise power tracking control without overshoot through online adaptive parameter tuning. Finally, the response performance of this strategy in power tracking is validated through MATLAB/Simulink simulation. [Results] Compared to traditional PID control, dynamic active power deviation decreases by 22.7% and reactive power deviation reduces to 0.66% under continuous load fluctuations.[Conclusions] The proposed strategy achieves rapid, overshoot-free tracking of power command signals, providing a practical power tracking control solution for power grids with high-proportion renewable energy.

Key words: renewable energy, power grid, compressed air energy storage, power tracking, neural network, PID control

刘庭响, 陈来军, 李正曦, 崔森, 刘瀚琛, 王恺. 基于神经网络PID的压缩空气储能功率跟踪控制策略[J]. 发电技术.

LIU Tingxiang, CHEN Laijun, LI Zhengxi, CUI Sen, LIU Hanchen, WANG Kai. Power Tracking Control Strategy for Compressed Air Energy Storage Based on Neural Network PID[J]. Power Generation Technology.

[1]	李骁, 郝雨辰, 罗凯明, 朱伟民, 李浩, 郭斌琪. 计及储能参与的区域电网自动发电控制调控策略[J]. 发电技术, 2026, 47(2): 315-324.
[2]	王明琦, 夏向阳, 赵晓悦, 黄如, 邓化龙, 刘代飞, 蔡昱宽. 计及电池荷电状态的储能系统控制策略优化研究[J]. 发电技术, 2026, 47(2): 395-405.
[3]	李欣, 韦古强, 强同波, 郑刚基, 陈六彪, 季伟. 压缩空气储能与氢能耦合系统的研究进展[J]. 发电技术, 2026, 47(2): 406-421.
[4]	李涛, 张春, 胡添诚. 基于模糊自抗扰的光储预同步虚拟同步发电机并网策略[J]. 发电技术, 2026, 47(1): 111-121.
[5]	胡泽灵, 郝俊红, 巨陈治, 马腾宇, 窦真兰, 李双江. 基于标准热阻法的压缩空气储能系统整体建模及能-㶲分析[J]. 发电技术, 2026, 47(1): 122-132.
[6]	史宏思, 孙新伟, 王凯. 基于电化学阻抗谱的锂离子电池健康状态估计[J]. 发电技术, 2026, 47(1): 133-144.
[7]	吴宇轩, 欧阳森, 杨向宇, 陈汉栋, 黎人玮, 廖键. 基于改进支持向量机的有源配电网单相断线故障检测方法[J]. 发电技术, 2026, 47(1): 185-194.
[8]	刘素梅, 徐文成, 孙曦冉, 余非, 胡春鹤. 交直流微电网互联变换器功率协调自抗扰控制策略[J]. 发电技术, 2026, 47(1): 195-203.
[9]	熊永康, 杜昀, 曾振锋, 舒展, 辛建波, 宋冠宏. 台风灾害下分布式资源协同配置的配电网弹性提升策略[J]. 发电技术, 2026, 47(1): 204-213.
[10]	刘可文, 侯朗博, 孙昊, 陈衡. 含高密度光伏与储能的配电网多目标优化调度策略[J]. 发电技术, 2026, 47(1): 214-224.
[11]	赵玲芳, 孙喜, 杨昊, 窦南南, 董贝贝. 固体氧化物电解池技术产业化发展研究进展[J]. 发电技术, 2026, 47(1): 38-52.
[12]	韩斌, 曾志祥, 孔繁新, 谢楠, 刘志强. 基于多层感知器神经网络的风机叶片覆冰预测模型研究[J]. 发电技术, 2026, 47(1): 65-74.
[13]	王志康, 张儒琪, 袁少可, 韩东江, 隋军. 有机朗肯-蒸汽压缩循环系统研究进展[J]. 发电技术, 2025, 46(6): 1059-1073.
[14]	罗斌, 白小龙, 臧天磊, 黄燕, 张琳, 李萌, 张雪霞, 蒋永龙. 风光水互补发电系统研究综述[J]. 发电技术, 2025, 46(6): 1097-1111.
[15]	王曦, 陈心怡. 一种基于时序卷积网络-Transformer的海上风电功率预测方法[J]. 发电技术, 2025, 46(6): 1123-1132.