基于IGAN-IChOA的主动配电网源储双层优化配置

Bi-Level Planning of Distributed Energy Storage Systems in Active Grids Enabled by IGAN-IChOA Synergy

摘要

针对风光出力随机性与分布式电源(DG: Distributed Generation)高渗透率并网对电网的冲击, 融合改进生成对抗网络(IGAN: Improved Generative Adversarial Network)和改进黑猩猩优化算法(IChOA: Improved Chimpanzee Optimization Algorithm), 构建主动配电网源储双层优化配置模型。首先, 采用IGAN生成风光典型出力场景表征其不确定性, 进而构建含电压质量指标的源储双层优化架构: 上层由IChOA优化确定储能系统(ESS: Energy Storage Systems)与DG的容量及位置配置方案, 下层采用二阶锥规划(SOCP: Second-Order Cone Programming)求解储能最优日内调度策略。最后, 经IEEE33节点系统验证表明, 该协同策略可显著降低系统年化成本与网损, 改善电压水平, 有效规避电压越限和DG功率波动问题。

Abstract

In response to the impact of the randomness of wind and solar power generation and the high penetration rate of DG (Distributed Generation) on the grid, the IGAN (Improved Generative Adversarial Network) and the IChOA (Improved Chimpanzee Optimization Algorithm) are integrated to construct a source-storage two-layer optimal configuration model for active distribution networks. Firstly, IGAN is used to generate typical wind and solar power generation scenarios to represent their uncertainty. Then, a source-storage two-layer optimization architecture containing voltage quality indicators is constructed. The upper layer uses IChOA to optimize the capacity and location configuration schemes of ESS (Energy Storage Systems) and DG, and the lower layer uses SOCP (Second-Order Cone Programming) to solve the optimal daily dispatch strategy of energy storage. Finally, the IEEE 33-node system verification shows that this collaborative strategy can significantly reduce the annualized cost and network loss of the system, improve the voltage level, and effectively avoid voltage limit violations and DG power fluctuations.

关键词

主动配电网 / 改进生成对抗网络 / 改进黑猩猩优化算法 / 分布式电源 / 储能系统

Key words

active distribution network / generative adversarial networks / improved chimpanzee optimization algorithm / distributed generation(DG) / energy storage system(ESS)

参考文献

[1] 王子辉, 贾燕冰, 李彦晨, 等. 计及电能质量影响的主动配电网光储容量优化[J]. 电网技术, 2024, 48(2): 607-620.

[2] WANG Z H, JIA Y B, LI Y C, et al. Optimization of Photovoltaic Storage Capacity in Active Distribution Networks Considering the Impact of Power Quality[J]. Power System Technology, 2024, 48(2): 607-620.

[3] 米阳, 周杰, 卢长坤, 等. 基于改进生成对抗网络与碳足迹的配电网多目标双层规划[J]. 中国电机工程学报, 2024, 44(21): 8421-8435.

[4] MI Y, ZHOU J, LU C K, et al. Multi—Objective Bilayer Programming of Distribution Network Based on Improved Generative Adversarial Network and Carbon Footprint[J]. Proceedings of the CSEE, 2024, 44(21): 8421-8435.

[5] 徐熠玮, 陈刚. 基于改进GAN算法的文本匹配生成图像模型[J]. 吉林大学学报(信息科学版), 2025, 43(2): 258-264.

[6] XU Y W, CHEN G. Text Matching Image Generation Model Based on Improved GAN Algorithm[J]. Journal of Jilin University (Information Science Edition), 2025, 43(2): 258-264.

[7] 姜囡, 庞永恒, 高爽. 基于注意力机制语谱图特征提取的语音识别[J]. 吉林大学学报(理学版), 2024, 62(2): 320-330.

[8] JIANG N, PANG Y H, GAO S. Speech Recognition Based on Attention Mechanism Spectrogram Feature Extraction[J]. Journal of Jilin University (Science Edition), 2024, 62(2): 320-330.

[9] 周丰丰, 张金楷. 具有局部和全局注意力机制的图注意力网络学习单样本组学数据表征[J]. 吉林大学学报(理学版), 2023, 61(6): 1351-1357.

[10] ZHOU F F, ZHANG J K. Graph Attention Networks with Local and Global Attention Mechanisms Learn Single—Sample Omics Data Representation[J]. Journal of Jilin University (Science Edition), 2023, 61(6): 1351-1357.

[11] 胥桂仙, 刘兰寅, 张廷, 等. 基于预训练模型和图神经网络的藏文文本分类研究[J]. 东北师大学报(自然科学版), 2023, 55(1): 52-64.

[12] XU G X, LIU L Y, ZHANG T, et al. Research on Tibetan Text Classification Based on Pre—Trained Model and Graph Neural Network[J]. Journal of Northeast Normal University (Natural Science Edition), 2023, 55(1): 52-64.

[13] 葛延良, 孙笑笑, 王冬梅, 等. 基于循环生成对抗网络的人脸素描合成网络设计[J]. 吉林大学学报(信息科学版), 2023, 41(1): 76-83.

[14] GE Y L, SUN X X, WANG D M, et al. Design of Face Sketch Synthesis Network Based on Cyclic Generative Adversarial Network[J]. Journal of Jilin University (Information Science Edition), 2023, 41(1): 76-83.

[15] 刘远红, 王庆龙, 张文华, 等. 基于改进生成对抗网络的抽油机故障诊断方法[J]. 吉林大学学报(信息科学版), 2022, 40(6): 963-969.

[16] LIU Y H, WANG Q L, ZHANG W H, et al. Fault Diagnosis Method of Pumping Unit Based on Improved Generative Adversarial Network[J]. Journal of Jilin University (Information Science Edition), 2022, 40(6): 963-969.

[17] 胡伟, 杨硕. 考虑配电网脆弱性的储能双层优化配置模型[J]. 智慧电力, 2024, 52(6): 1-8.

[18] HU W, YANG S. Two—Layer Optimal Configuration Model of Energy Storage Considering the Vulnerability of Distribution Network[J]. Smart Power, 2024, 52(6): 1-8.

[19] PING L, HENAN D, GUANFENG Z, et al. Research on Loss Reduction Strategy of Distribution Network Based on Distributed Generation Site Selection and Capacity[J]. Energy Reports, 2023, 9(S8): 1001-1012.

[20] 刘自发, 于普洋, 李颉雨. 计及运行特性的配电网分布式电源与广义储能规划[J]. 电力自动化设备, 2023, 43(3): 72-79.

[21] LIU Z F, YU P Y, LI J Y. Planning of Distributed Power Sources and Generalized Energy Storage in Distribution Networks Considering Operational Characteristics[J]. Electric Power Automation Equipment, 2023, 43(3): 72-79.

[22] 李振坤, 徐廷君. 考虑“源储荷”协同的主动配电网双层优化配置[J]. 智慧电力, 2025, 53(3): 77-83.

[23] LI Z K, XU T J. Two—Layer Optimal Configuration of Active Distribution Network Considering Synergy of “Source—Storage—Load”[J]. Smart Power, 2025, 53(3): 77-83.

[24] 周强, 姚朴. 考虑需求响应的分布式光伏储能系统双层优化配置[J]. 能源与环保, 2025, 47(1): 155-160.

[25] ZHOU Q, YAO P. Considering Demand Response of Double Layer Distributed Photovoltaic Energy Storage Systems[J]. China Energy and Environmental Protection, 2025, 47(1): 155-160.

[26] 赵新刚, 王桢. 基于改进MOEA/D算法的含可再生能源系统协同优化调度[J]. 吉林大学学报(工学版), 2024, 54(4): 1129-1135.

[27] ZHAO X G, WANG Z. Cooperative Optimal Scheduling of Systems with Renewable Energy Based on the Improved MOEA/D Algorithm[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54(4): 1129-1135.

[28] 高金兰, 侯学才, 刁楠, 等. 储能运营商和电动汽车利益的配电网双层优化方法[J]. 吉林大学学报(信息科学版), 2023, 41(4): 685-692.

[29] GAO J L, HOU X C, DIAO N, et al. Two—Layer Optimization Method of Distribution Network for the Interests of Energy Storage Operators and Electric Vehicles[J]. Journal of Jilin University (Information Science Edition), 2023, 41(4): 685-692.

基金资助

东北石油大学科研基金资助项目(2019YDL-10)