在挖掘双馈型抽水蓄能（DFIM-PSH）机组调频能力的基础上,提出一种基于改进深度确定性策略梯度（DDPG）算法的系统频率控制方法。首先,基于所确定的DFIM-PSH机组在发电与抽水工况下的频率控制环节,构建考虑风电接入的含DFIM-PSH单区域系统频率控制模型。其次,在考虑机组运行约束的基础上以最小化系统频率偏差及调频出力为目标,引入DDPG算法对各机组的AGC控制指令进行优化。通过在预学习中同时引入随机外部扰动与模型参数变化,提高AGC控制器在具有强不确定性环境中的适应性。最后,在仿真验证DFIM-PSH调频优势的基础上,在不同风电接入及扰动等多场景进行仿真分析,结果表明,所提频率控制方法能有效改善新型电力系统的频率特性且具有强鲁棒性。
Abstract
On the basis of exploring the frequency regulation ability of doubly-fed induction machine pumped storage hydro （DFIM-PSH） unit, a system frequency control method based on improved deep deterministic policy gradient （DDPG） algorithm is proposed. Firstly, based on the frequency regulation links of DFIM-PSH in generating and pumping modes, the frequency control model of single-region system with DFIM-PSH considering wind power integration is constructed. Secondly, aiming at minimizing the system frequency deviation and unit’s output for frequency regulation, improved DDPG algorithm is introduced to optimize the AGC instructions of each unit taking the unit’s operating constraints into account. By introducing random external disturbances and model parameter changes in the pre-learning process, the adaptability of AGC controller in environment with strong uncertainty is improved. Finally, on the basis of verifying the advantages of DFIM-PSH, simulations under different wind power integration and disturbance scenarios are carried out. The results show that the proposed frequency control method can effectively improve the frequency characteristics of power system and has strong robustness.
关键词
抽水蓄能机组 /
鲁棒性（控制系统） /
频率控制 /
深度确定性策略梯度算法 /
新型电力系统
Key words
pumped storage power plants /
robustness（control systems） /
electric frequency control /
deep deterministic policy gradient algorithm /
novel power system
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 张子扬, 张宁, 杜尔顺, 等. 双高电力系统频率安全问题评述及其应对措施[J]. 中国电机工程学报, 2022, 42(1): 1-25.
ZHANG Z Y, ZHANG N, DU E S, et al.Review and countermeasures on frequency security issues of power systems with high shares of renewables and power electronics[J]. Proceedings of the CSEE, 2022, 42(1): 1-25.
[2] 张剑云, 李明节. 新能源高渗透的电力系统频率特性分析[J]. 中国电机工程学报, 2020, 40(11): 3498-3507.
ZHANG J Y, LI M J.Analysis of the frequency characteristic of the power systems highly penetrated by new energy generation[J]. Proceedings of the CSEE, 2020, 40(11): 3498-3507.
[3] SCHMIDT J, KEMMETMÜLLER W, KUGI A. Modeling and static optimization of a variable speed pumped storage power plant[J]. Renewable energy, 2017, 111: 38-51.
[4] ALIZADEH BIDGOLI M, YANG W J, AHMADIAN A.DFIM versus synchronous machine for variable speed pumped storage hydropower plants: a comparative evaluation of technical performance[J]. Renewable energy, 2020, 159: 72-86.
[5] 陈亚红, 邓长虹, 刘玉杰, 等. 抽水工况双馈可变速抽蓄机组机电暂态建模及有功-频率耦合特性[J]. 中国电机工程学报, 2022, 42(3): 942-957.
CHEN Y H, DENG C H, LIU Y J, et al.Electromechanical transient modelling and active power-frequency coupling characteristics of doubly-fed variable speed pumped storage under pumping mode[J]. Proceedings of the CSEE, 2022, 42(3): 942-957.
[6] SHI L J, LAO W J, WU F, et al.Frequency regulation control and parameter optimization of doubly-fed induction machine pumped storage hydro unit[J]. IEEE access, 2022, 10: 102586-102598.
[7] 胡泽春, 罗浩成. 大规模可再生能源接入背景下自动发电控制研究现状与展望[J]. 电力系统自动化, 2018, 42(8): 2-15.
HU Z C, LUO H C.Research status and prospect of automatic generation control with integration of large-scale renewable energy[J]. Automation of electric power systems, 2018, 42(8): 2-15.
[8] 赵源筱. 含高比例可再生能源电力系统自动发电控制策略研究[D]. 杭州: 浙江大学, 2021.
ZHAO Y X.Research on automatic generation control strategies for large scale renewable energy integrated power systems[D]. Hangzhou: Zhejiang University, 2021.
[9] YAN Z M, XU Y.Data-driven load frequency control for stochastic power systems: a deep reinforcement learning method with continuous action search[J]. IEEE transactions on power systems, 2019, 34(2): 1653-1656.
[10] YAN Z M, XU Y.A multi-agent deep reinforcement learning method for cooperative load frequency control of a multi-area power system[J]. IEEE transactions on power systems, 2020, 35(6): 4599-4608.
[11] 范培潇, 柯松, 杨军, 等. 基于改进多智能体深度确定性策略梯度的多微网负荷频率协同控制策略[J]. 电网技术, 2022, 46(9): 3504-3515.
FAN P X, KE S, YANG J, et al.Load frequency coordinated control strategy of multi-microgrid based on improved MA-DDPG[J]. Power system technology, 2022, 46(9): 3504-3515.
[12] 陈宗遥, 卜旭辉, 郭金丽. 基于神经网络的数据驱动互联电力系统负荷频率控制[J]. 电工技术学报, 2022, 37(21): 5451-5461.
CHEN Z Y, BU X H, GUO J L.Neural network based data-driven load frequency control for interconnected power systems[J]. Transactions of China Electrotechnical Society, 2022, 37(21): 5451-5461.
[13] 梁煜东, 陈峦, 张国洲, 等. 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[J]. 电工技术学报, 2022, 37(7): 1768-1779.
LIANG Y D, CHEN L, ZHANG G Z, et al.Load frequency control strategy of hybrid power generation system: a deep reinforcement learning-based approach[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1768-1779.
[14] LI J W, YU T, ZHANG X S.Coordinated automatic generation control of interconnected power system with imitation guided exploration multi-agent deep reinforcement learning[J]. International journal of electrical power & energy systems, 2022, 136: 107471.
[15] 许益恩, 杨德健, 郑太英, 等. 计及电网频率偏差的双馈风电机组频率控制策略[J]. 太阳能学报, 2022, 43(10): 229-235.
XU Y E, YANG D J, ZHENG T Y, et al.Frequency control strategy of doubly-fed wind generators considering grid frequency deviation[J]. Acta energiae solaris sinica, 2022, 43(10): 229-235.
[16] 颜湘武, 孙雪薇, 崔森, 等. 考虑系统频率连续波动与二次跌落的双馈风力发电机组虚拟惯量通用控制策略[J]. 太阳能学报, 2021, 42(11): 247-254.
YAN X W, SUN X W, CUI S, et al.Virtual inertia general control strategy of DFIG-based wind turbine considering continuous fluctuation of system frequency and second frequency drop[J]. Acta energiae solaris sinica, 2021, 42(11): 247-254.
基金
智能电网保护和运行控制国家重点实验室（SGNR0000KJJS2200297）; 国家自然科学基金中英合作项目（52061635102）
PDF(3155 KB)
