结合卷积自编码器（CAE）与条件生成对抗网络（CGAN）,提出一种考虑风电时空相关性成本控制下的配电网多场景运行优化方法。针对含多区域风电集群接入的配电网系统,利用CAE提取风电出力历史数据的时空相关特征,将其作为CGAN的条件值输入进行风电出力场景生成,并采用K-Medoids聚类方法进行场景缩减,获得风电时空相关出力典型场景集。在此基础上,以系统运行经济性最优为目标建立配电网优化运行模型,进而求解配电网的最优潮流分布。最后,基于IEEE 33节点配电系统进行仿真分析,算例结果表明,所提方法能有效兼顾系统运行经济性和电能质量,进一步提高配电网对风电的消纳能力。
Abstract
This paper combines convolutional autoencoders （CAE） and conditional generative adversarial networks （CGAN） to propose a multi-scenario operation optimization method for distribution networks that considers the spatiotemporal correlation of wind power and cost control. For the distribution network system with multi-regional wind power cluster access, CAE is used to extract the spatiotemporal correlation features of wind power output historical data, which is used as the condition value input of CGAN to generate wind power output scenarios, and the K-Medoids clustering method is adopted for scene reduction, to obtain a set of typical scenarios of wind power spatiotemporally related output. On this basis, a distribution network operation optimization model is established to optimize system operation economics, and then the optimal power flow distribution of the distribution network is solved. Finally, simulation analysis is conducted based on the IEEE 33-node power distribution system. The example results show that the proposed method can effectively take into account system operation economy and power quality, and further improve the distribution network’s ability to absorb wind power.
关键词
风力发电 /
配电网 /
时空数据 /
成本控制 /
运行优化
Key words
wind power /
distribution networks /
spatial-temporal data /
cost control /
operation optimization
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 董骁翀, 张姝, 李烨, 等. 电力系统中时序场景生成和约简方法研究综述[J]. 电网技术,2023, 47(2): 709-721.
DONG X C, ZHANG S, LI Y, et al.Review of power system temporal scenario generation and reduction methods[J]. Power system technology, 2023, 47(2): 709-721.
[2] 陈倩, 王维庆, 王海云. 含分布式能源的配电网双层优化运行策略[J]. 太阳能学报, 2022, 43(10): 507-517.
CHEN Q, WANG W Q, WANG H Y.Bi-level optimal operation strategy of distribution network with distributed energy[J]. Acta energiae solaris sinica, 2022, 43(10): 507-517.
[3] YE L, LI Y L, PEI M, et al.A novel integrated method for short-term wind power forecasting based on fluctuation clustering and history matching[J]. Applied energy, 2022, 327: 120131.
[4] 张海华, 刘福才. 考虑风电消纳的区域综合能源系统优化运行分析[J]. 太阳能学报, 2023, 44(10): 585.
ZHANG H H, LIU F C.Optimal operation analysis of regional comprehensive energy system considering wind power consumption[J]. Acta energiae solaris sinica, 2023, 44(10): 585.
[5] 李英量, 董志伟, 白博旭, 等. 含风电并网的源荷双层机组优化组合模型[J]. 太阳能学报, 2024, 45(3): 399-407.
LI Y L, DONG Z W, BAI B X, et al.Optimal combination model of two-layer source-load unit with wind power grid connection[J]. Acta energiae solaris sinica, 2024, 45(3): 399-407.
[6] 张宇, 何衍林, 吴铁洲, 等. 应用于风电消纳的负荷聚合商协同运营策略[J]. 中国科技论文, 2020, 15(10): 1190-1195.
ZHANG Y, HE Y L, WU T Z, et al.Cooperative operation strategy of load aggregator applied to wind power consumption[J]. China sciencepaper, 2020, 15(10): 1190-1195.
[7] WU L, SHAHIDEHPOUR M, LI Z Y.Comparison of scenario-based and interval optimization approaches to stochastic SCUC[J]. IEEE transactions on power systems, 2012, 27(2): 913-921.
[8] 胡弘, 韦化, 李昭昱. 风电接入下核电参与电力系统调峰的协调优化模型[J]. 电力自动化设备, 2020, 40(5): 31-39.
HU H, WEI H, LI Z Y.Coordinated optimization model considering nuclear power participating in peak load regulation of power system with wind power[J]. Electric power automation equipment, 2020, 40(5): 31-39.
[9] PENG C H, XIE P, PAN L, et al.Flexible robust optimization dispatch for hybrid wind/photovoltaic/hydro/thermal power system[J]. IEEE transactions on smart grid, 2016, 7(2): 751-762.
[10] FANG X, CUI H T, YUAN H Y, et al.Distributionally-robust chance constrained and interval optimization for integrated electricity and natural gas systems optimal power flow with wind uncertainties[J]. Applied energy, 2019, 252: 113420.
[11] 顾洁, 刘书琪, 胡玉, 等. 基于深度卷积生成对抗网络场景生成的间歇式分布式电源优化配置[J]. 电网技术, 2021, 45(5): 1742-1751.
GU J, LIU S Q, HU Y, et al.Optimal allocation of intermittent distributed generation based on deep convolutions generative adversarial network in scenario generation[J]. Power system technology, 2021, 45(5): 1742-1751.
[12] 苗洛源, 彭勇刚, 胡丹尔, 等. 基于自编码器-受限时序卷积网络的数据驱动配电网无功优化策略[J]. 高电压技术, 2024, 50(9): 4058-4068.
MIAO L Y, PENG Y G, HU D E, et al.Data-driven reactive power optimization strategy of distribution network based on autoencoder constrained temporal convolutional networks[J]. High voltage engineering, 2024, 50(9): 4058-4068.
[13] 程卓, 许仪勋, 李泽霜. 基于改进生成对抗网络生成风光场景的微电网多时间尺度优化调度策略研究[J]. 现代电力, 2024, 41(4): 642-651.
CHENG Z, XU Y X, LI Z S.Research on multi-time scale optimization scheduling strategy of microgrid based on improved generative adversarial network for wind and PV power scenario generation[J]. Modern electric power, 2024, 41(4): 642-651.
[14] 钱涛, 任孟极, 邵成成, 等. 基于深度学习考虑出行模式的电动汽车充电负荷场景生成[J]. 电力系统自动化, 2022, 46(12): 67-75.
QIAN T, REN M J, SHAO C C, et al.Deep-learning-based electric vehicle charging load scenario generation considering travel mode[J]. Automation of electric power systems, 2022, 46(12): 67-75.
[15] WANG X, GUO Q, TU C M, et al.A two-stage optimal strategy for flexible interconnection distribution network considering the loss characteristic of key equipment[J]. International journal of electrical power & energy systems, 2023, 152: 109232.
[16] 郭凯, 阿敏夫, 雅斯太, 等. 计及碳交易-绿证和储能成本的含风光发电的电力系统优化调度[J]. 内蒙古电力技术, 2023, 41(4): 1-7.
GUO K, A M F , YA S T, et al. Optimized dispatching of power system including wind and solar power generation considering carbon trading-green certificate and energy storage cost[J]. Inner Mongolia electric power, 2023, 41(4): 1-7.
基金
国网甘肃省电力公司科技项目（SGGSSDXSCWJS2311082）
PDF(2042 KB)
