Distributionally Robust Optimal Allocation for Capacity Distribution of Photovoltaic and Energy Storage Units in Standalone Microgrid Based on Generative Adversarial Network

LI Yunhong; XU Xiaoyuan; YAN Zheng

doi:10.7500/AEPS20220302005

您当前的位置：

首页 >

文章列表页 >

Distributionally Robust Optimal Allocation for Capacity Distribution of Photovoltaic and Energy Storage Units in Standalone Microgrid Based on Generative Adversarial Network

Basic Research | 更新时间：2025-06-16

- Distributionally Robust Optimal Allocation for Capacity Distribution of Photovoltaic and Energy Storage Units in Standalone Microgrid Based on Generative Adversarial Network
- Automation of Electric Power Systems Vol. 47, Issue 7, Pages: 51-62(2023)
- 作者机构：
  
  电力传输与功率变换控制教育部重点实验室（上海交通大学），上海市 200240
- 作者简介：
- 基金信息：
- DOI：10.7500/AEPS20220302005
  CLC：
- Received：02 March 2022，
  
  Revised：2022-06-07，
  
  Published Online：07 November 2022，
  
  Published：10 April 2023
- 稿件说明：
移动端阅览
李运鸿,徐潇源,严正.基于生成对抗网络的独立微电网光-储容量分布鲁棒优化配置[J].电力系统自动化,2023,47(7):51-62.

LI Yunhong,XU Xiaoyuan,YAN Zheng.Distributionally Robust Optimal Allocation for Capacity Distribution of Photovoltaic and Energy Storage Units in Standalone Microgrid Based on Generative Adversarial Network[J].Automation of Electric Power Systems,2023,47(7):51-62.
李运鸿,徐潇源,严正.基于生成对抗网络的独立微电网光-储容量分布鲁棒优化配置[J].电力系统自动化,2023,47(7):51-62. DOI： 10.7500/AEPS20220302005.

LI Yunhong,XU Xiaoyuan,YAN Zheng.Distributionally Robust Optimal Allocation for Capacity Distribution of Photovoltaic and Energy Storage Units in Standalone Microgrid Based on Generative Adversarial Network[J].Automation of Electric Power Systems,2023,47(7):51-62. DOI： 10.7500/AEPS20220302005.

摘要

针对微电网中分布式可再生能源的不确定性，可采用机会约束随机规划刻画系统运行风险。现有研究通常基于解析变换或者典型场景处理机会约束问题，但前者依赖于特定的概率分布，而后者中的预设场景与实际场景可能存在偏差，会导致无法满足预设运行风险的难题。对此，提出一种融合数据生成技术的分布鲁棒优化方法解决独立微电网光伏-储能容量配置问题，以平衡电源配置经济性与微电网运行风险。首先，提出基于改进生成对抗网络（GAN）的光伏出力场景生成方法，以提高GAN模型训练和场景生成效率；其次，采用

-散度衡量GAN生成数据与真实数据之间的偏差，采用分布鲁棒机会约束条件刻画相应光伏-储能容量下的微电网运行风险；再次，提出基于变差距离、抽样平均近似原理以及线性化技术的分布鲁棒优化问题求解方法，在充分利用GAN生成场景的同时保证优化问题求解效率；最后，采用33节点和123节点系统进行仿真分析，以验证所提方法的有效性。

Abstract

For the uncertainty of distributed renewable energy in the microgrid

the chance-constrained stochastic programming can be used to describe the system operation risk. In the current research

the analytic transformation or selecting typical scenarios is the common strategy to solve the chance-constrained problems. However

the former relies on particular probability distribution functions and the latter’s preset scenarios may deviate from the actual scenarios

which will lead to the problem that the preset operation risks cannot be met. A distributionally robust optimization method integrating data generation technology is proposed to solve the problem of capacity distribution of photovoltaic and energy storage units in the standalone microgrid

to balance the economy of power supply allocation and the operation risk of the microgrid. First

a photovoltaic output scenario generation method based on an improved generative adversarial network (GAN) is proposed to improve the efficiency of GAN model training and scenario generation. Secondly

the

-divergence is used to measure the deviation between the generated data of GAN and real data

and the distributionally robust chance constraint is used to describe the microgrid operation risk under the corresponding photovoltaic and energy storage capacity. Then

a distributionally robust optimization method based on variation distance

sample average approximation principle and linearization technology is proposed to ensure the efficiency in solving the optimization problem while making full use of the scenarios generated by GAN. Finally

the 33-bus and 123-bus systems are used for the simulation analysis to verify the effectiveness of the proposed method.

关键词

Keywords

references

国家能源局 . 2021年前三季度全国光伏发电建设运行情况［EB/OL］.［ 2022-01-05 ］. http：//www.nea.gov.cn/2021-10/25/c_1310267679.htm http://www.nea.gov.cn/2021-10/25/c_1310267679.htm .

National Energy Administration . Construction and operation of national photovoltaic power generation in the first three quarters of 2021 ［EB/OL］. ［ 2022-01-05 ］. http：//www.nea.gov.cn/2021-10/25/c_1310267679.htm http://www.nea.gov.cn/2021-10/25/c_1310267679.htm .

鲁卓欣，徐潇源，严正，等 . 不确定性环境下数据驱动的电力系统优化调度方法综述［J］. 电力系统自动化， 2020 ， 44 （ 21 ）： 172 - 183 .

LU Zhuoxin ， XU Xiaoyuan ， YAN Zheng ， et al . Overview on data-driven optimal scheduling methods of power system in uncertain environment ［J］. Automation of Electric Power Systems ， 2020 ， 44 （ 21 ）： 172 - 183 .

周京华，翁志鹏，宋晓通 . 兼顾可靠性与经济性的孤岛型光储微电网容量配置方法［J］. 电力系统自动化， 2021 ， 45 （ 8 ）： 166 - 174 .

ZHOU Jinghua ， WENG Zhipeng ， SONG Xiaotong . Capacity configuration method of islanded microgrid with photovoltaic and energy storage system considering reliability and economy ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 8 ）： 166 - 174 .

徐潇源，王晗，严正，等 . 能源转型背景下电力系统不确定性及应对方法综述［J］. 电力系统自动化， 2021 ， 45 （ 16 ）： 2 - 13 .

XU Xiaoyuan ， WANG Han ， YAN Zheng ， et al . Overview of power system uncertainty and its solutions under energy transition ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 16 ）： 2 - 13 .

林少伯，韩民晓，赵国鹏，等 . 基于随机预测误差的分布式光伏配网储能系统容量配置方法［J］. 中国电机工程学报， 2013 ， 33 （ 4 ）： 25 - 33 .

LIN Shaobo ， HAN Minxiao ， ZHAO Guopeng ， et al . Capacity allocation of energy storage in distributed photovoltaic power system based on stochastic prediction error ［J］. Proceedings of the CSEE ， 2013 ， 33 （ 4 ）： 25 - 33 .

ASENSIO M ， MENESES DE QUEVEDO P ， MUÑOZ-DELGADO G ， et al . Joint distribution network and renewable energy expansion planning considering demand response and energy storage—part Ⅱ： numerical results ［J］. IEEE Transactions on Smart Grid ， 2018 ， 9 （ 2 ）： 667 - 675 .

ZHANG B ， DEHGHANIAN P ， KEZUNOVIC M . Optimal allocation of PV generation and battery storage for enhanced resilience ［J］. IEEE Transactions on Smart Grid ， 2019 ， 10 （ 1 ）： 535 - 545 .

XU X Y ， YAN Z ， SHAHIDEHPOUR M ， et al . Data-driven risk-averse two-stage optimal stochastic scheduling of energy and reserve with correlated wind power ［J］. IEEE Transactions on Sustainable Energy ， 2020 ， 11 （ 1 ）： 436 - 447 .

刘思夷，赵波，汪湘晋，等 . 基于Benders分解的独立型微电网鲁棒优化容量配置模型［J］. 电力系统自动化， 2017 ， 41 （ 21 ）： 119 - 126 .

LIU Siyi ， ZHAO Bo ， WANG Xiangjin ， et al . Capacity configuration model for robust optimization of stand-alone microgrid based on Benders decomposition ［J］. Automation of Electric Power Systems ， 2017 ， 41 （ 21 ）： 119 - 126 .

CHEN X ， WU W C ， ZHANG B M ， et al . Data-driven DG capacity assessment method for active distribution networks ［J］. IEEE Transactions on Power Systems ， 2017 ， 32 （ 5 ）： 3946 - 3957 .

ZARE A ， CHUNG C Y ， ZHAN J P ， et al . A distributionally robust chance-constrained MILP model for multistage distribution system planning with uncertain renewables and loads ［J］. IEEE Transactions on Power Systems ， 2018 ， 33 （ 5 ）： 5248 - 5262 .

LU Z X ， XU X Y ， YAN Z . Data-driven stochastic programming for energy storage system planning in high PV-penetrated distribution network ［J］. International Journal of Electrical Power & Energy Systems ， 2020 ， 123 ： 106326 .

CHEN X ， WU W C ， ZHANG B M . Robust restoration method for active distribution networks ［J］. IEEE Transactions on Power Systems ， 2016 ， 31 （ 5 ）： 4005 - 4015 .

BARAN M ， WU F F . Optimal sizing of capacitors placed on a radial distribution system ［J］. IEEE Transactions on Power Delivery ， 1989 ， 4 （ 1 ）： 735 - 743 .

白凯峰，顾洁，彭虹桥，等 . 融合风光出力场景生成的多能互补微网系统优化配置［J］. 电力系统自动化， 2018 ， 42 （ 15 ）： 133 - 141 .

BAI Kaifeng ， GU Jie ， PENG Hongqiao ， et al . Optimal allocation for multi-energy complementary microgrid based on scenario generation of wind power and photovoltaic output ［J］. Automation of Electric Power Systems ， 2018 ， 42 （ 15 ）： 133 - 141 .

GOODFELLOW I J ， POUGET-ABADIE J ， MIRZA M ， et al . Generative adversarial networks ［EB/OL］. ［ 2022-01-05 ］. https：//arxiv.org/abs/1406.2661 https://arxiv.org/abs/1406.2661 .

ARJOVSKY M ， CHINTALA S ， BOTTOU L . Wasserstein generative adversarial networks ［C］// Proceedings of the 34th International Conference on Machine Learning ， August 6-11 ， 2017 ， Sydney， Australia ： 214 - 223 .

MIRZA M ， OSINDERO S . Conditional generative adversarial nets ［EB/OL］. ［ 2022-01-05 ］. http：//arxiv.org/abs/1411.1784 http://arxiv.org/abs/1411.1784 ．

JIANG R W ， GUAN Y P . Data-driven chance constrained stochastic program ［J］. Mathematical Programming ， 2016 ， 158 （ 1/2 ）： 291 - 327 .

CHARNES A ， COOPER W W . Chance-constrained programming ［J］. Management Science ， 1959 ， 6 （ 1 ）： 73 - 79 ．

PAGNONCELLI B K ， AHMED S ， SHAPIRO A . Sample average approximation method for chance constrained programming： theory and applications ［J］. Journal of Optimization Theory and Applications ， 2009 ， 142 （ 2 ）： 399 - 416 .

王群，董文略，杨莉 . 基于Wasserstein距离和改进K-medoids聚类的风电/光伏经典场景集生成算法［J］. 中国电机工程学报， 2015 ， 35 （ 11 ）： 2654 - 2661 .

WANG Qun ， DONG Wenlue ， YANG Li . A wind power/photovoltaic typical scenario set generation algorithm based on Wasserstein distance metric and revised K-medoids cluster ［J］. Proceedings of the CSEE ， 2015 ， 35 （ 11 ）： 2654 - 2661 .

ZHAO S P ， YOU F Q . Distributionally robust chance constrained programming with generative adversarial networks （GANs）［EB/OL］. ［ 2022-01-05 ］. https：//arxiv.org/abs/2002.12486 https://arxiv.org/abs/2002.12486 .

ZHANG Y ， WANG J X ， ZENG B ， et al . Chance-constrained two-stage unit commitment under uncertain load and wind power output using bilinear benders decomposition ［J］. IEEE Transactions on Power Systems ， 2017 ， 32 （ 5 ）： 3637 - 3647 .

MCCORMICK G P . Computability of global solutions to factorable nonconvex programs： Part Ⅰ—convex underestimating problems ［J］. Mathematical Programming ， 1976 ， 10 （ 1 ）： 147 - 175 .

AHMED S ， SHAPIRO A ， SHAPIRO E . The sample average approximation method for stochastic programs with integer recourse ［EB/OL］. ［ 2022-01-05 ］. https：//citeseerx.ist.psu.edu/viewdoc/download？doi=10.1.1.5.3721&rep=rep1&type=pdf https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.5.3721&rep=rep1&type=pdf .

CHEN Y Z ， WANG Y S ， KIRSCHEN D ， et al . Model-free renewable scenario generation using generative adversarial networks ［J］. IEEE Transactions on Power Systems ， 2018 ， 33 （ 3 ）： 3265 - 3275 .

王守相，陈海文，李小平，等 . 风电和光伏随机场景生成的条件变分自动编码器方法［J］. 电网技术， 2018 ， 42 （ 6 ）： 1860 - 1869 .

WANG Shouxiang ， CHEN Haiwen ， LI Xiaoping ， et al . Conditional variational automatic encoder method for stochastic scenario generation of wind power and photovoltaic system ［J］. Power System Technology ， 2018 ， 42 （ 6 ）： 1860 - 1869 .

丁明，王波，赵波，等 . 独立风光柴储微网系统容量优化配置［J］. 电网技术， 2013 ， 37 （ 3 ）： 575 - 581 .

DING Ming ， WANG Bo ， ZHAO Bo ， et al . Configuration optimization of capacity of standalone PV-wind-diesel-battery hybrid microgrid ［J］. Power System Technology ， 2013 ， 37 （ 3 ）： 575 - 581 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dual-data-model-driven Distributionally Robust Optimal Scheduling of Renewable Energy Microgrid

Bi-layer Uncertainty Economic Scheduling for Port Multi-energy Microgrid with Cascade Utilization of Cold Energy

Distributionally Robust Optimization Method for Substation Planning Considering Incentive-based Response Uncertainty

Distributionally Robust Optimization Model of Hosting Capability for Distributed Generators in Flexible Interconnected Distribution Network

Related Author

GUO Fanghong

FENG Xiurong

YANG Hao

TANG Yajie

WANG Lei

HOU Hui

XIE Yingbiao

GAN Ming

Related Institution

School of Information Engineering, Zhejiang University of Technology

Electric Power Research Institute of State Grid Zhejiang Electric Power Co., Ltd.

School of Control Science and Engineering, Zhejiang University

School of Automation, Wuhan University of Technology

Shenzhen Research Institute, Wuhan University of Technology

⁰