基于数据驱动的非全实时观测配电网无功优化方法

doi:10.12204/j.issn.1000-7229.2021.02.009

摘要/Abstract

摘要：

现阶段配电网中量测设备覆盖率较低,只有部分节点的负荷数据可以实时采集得到,因此在配电网中进行实时无功优化时无法使用基于潮流计算的优化方法。考虑到以上情况,文章提出了一种基于数据驱动的非全实时观测配电网无功优化方法。该方法基于历史运行数据使用最优潮流离线生成无功优化策略,并通过训练神经网络构建可实时量测节点负荷数据和无功优化策略间的映射关系,实现对非全实时观测配电网的实时无功优化。最后基于改造的IEEE 33节点系统,将所提方法与传统九区图无功优化方法作对比,验证了所提方法的有效性。

关键词: 神经网络, 配电网, 无功优化, 数据驱动

Abstract:

At present, the coverage of measuring equipment in distribution network is low, so only part of the nodes’ load data can be collected in real time. This situation makes it impossible to use the optimization based on power flow calculation in the real-time reactive power optimization of distribution network. Considering the above situation, this paper proposes a data-driven reactive power optimization method based on partial real-time visible distribution network. According to the historical operation data, the optimal power flow is used to generate the reactive power optimization strategy offline, and the mapping between the real-time measured node load data and the reactive power optimization strategy is established by training the neural network to realize the real-time reactive power optimization of the partial real-time visible distribution network. Finally, in the modified IEEE 33-bus system, the proposed method is compared with the 9-zone diagram method to verify the effectiveness of the proposed method.

Key words: neural network, distribution network, reactive power optimization, data-driven

中图分类号:

TM712

王珺, 田恩东, 马建, 窦晓波, 刘之涵. 基于数据驱动的非全实时观测配电网无功优化方法[J]. 电力建设, 2021, 42(2): 68-76.

WANG Jun, TIAN Endong, MA Jian, DOU Xiaobo, LIU Zhihan. Reactive Power Optimization of Partial Real-Time Visible Distribution Network Based on Data Driven[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(2): 68-76.

图/表 14

图1 配电网非全实时观测无功优化框架

Fig.1 Framework of the reactive power optimization of partial real-time visible distribution network

图2 神经网络无功优化模块

Fig.2 Reactive power optimization module based on neural network

图3 日内优化与定时更新流程

Fig.3 Flow chart of daily optimization and regular update

图4 加入DG的IEEE 33节点算例

Fig.4 Modified IEEE 33-node case with DGs

表1 节点编号与负荷类型的关系

Table 1 Node number and load type

图5 系统负荷曲线与DG出力曲线

Fig.5 Load curve and output curves of DGs

图6 BP神经网络训练过程

Fig.6 Training process of BP neural network

表2 神经网络输出的相对误差

Table 2 Relative error of neural network output%

表3 电容器投入数量的绝对误差

Table 3 Absolute error of capacitor input quantity%

图7 无功优化前后网损对比

Fig.7 Comparison of network loss before and after reactive power optimization

图8 无功优化前后节点电压

Fig.8 Node voltage before and after reactive power optimization

图9 不同无功优化方法的节点电压分布

Fig.9 Node voltage profiles under different reactive power optimization methods

表4 不同实时观测率情况下的节点性质设置

Table 4 Node properties under different real-time observation rates

图10 不同实时观测率下的电压控制效果

Fig.10 Voltage control effect under different real-time observation rates

参考文献 20

[1]	DING T, LIU S Y, YUAN W, et al. A two-stage robust reactive power optimization considering uncertain wind power integration in active distribution networks[J]. IEEE Transactions on Sustainable Energy, 2016,7(1):301-311.
[2]	WECKX S, GONZALEZ C, DRIESEN J. Combined central and local active and reactive power control of PV inverters[J]. IEEE Transactions on Sustainable Energy, 2014,5(3):776-784.
[3]	王志强, 方正, 刘文霞, 等. 基于概率多场景的柔性配电网鲁棒运行优化[J]. 电力自动化设备, 2019,39(7):37-44.
	WANG Zhiqiang, FANG Zheng, LIU Wenxia, et al. Robust operation optimization of flexible distribution network based on probabilistic multi-scenario[J]. Electric Power Automation Equipment, 2019,39(7):37-44.
[4]	刘公博, 颜文涛, 张文斌, 等. 含分布式电源的配电网动态无功优化调度方法[J]. 电力系统自动化, 2015,39(15):49-54.
	LIU Gongbo, YAN Wentao, ZHANG Wenbin, et al. Optimization and dispatching method of dynamic reactive power in distribution network with distributed generators[J]. Automation of Electric Power Systems, 2015,39(15):49-54.
[5]	程杉, 陈民铀, 黄薏宸. 含分布式发电的配电网多目标无功优化策略研究[J]. 电力系统保护与控制, 2013,41(10):45-50.
	CHENG Shan, CHEN Minyou, HUANG Yichen. Multi-objective reactive power optimization of distribution system penetrated with distributed generation[J]. Power System Protection and Control, 2013,41(10):45-50.
[6]	储琳琳, 张宇俊, 刘云晖, 等. 计及分布式电源随机出力的配电网多目标无功优化[J]. 电器与能效管理技术, 2019(12):42-48.
	CHU Linlin, ZHANG Yujun, LIU Yunhui, et al. Multi-objective reactive power optimization of distribution networks considering random outputs of distributed generations[J]. Electrical & Energy Management Technology, 2019(12):42-48.
[7]	汪文达, 崔雪, 马兴, 等. 考虑多个风电机组接入配电网的多目标无功优化[J]. 电网技术, 2015,39(7):1860-1865.
	WANG Wenda, CUI Xue, MA Xing, et al. Multi-objective optimal reactive power flow of distribution network with multiple wind turbines[J]. Power System Technology, 2015,39(7):1860-1865.
[8]	曹益奇, 白晓清, 王婷婷, 等. 计及分布式电源随机出力的三相配电网可调鲁棒无功优化[J]. 电网技术, 2018,42(4):1217-1225.
	CAO Yiqi, BAI Xiaoqing, WANG Tingting, et al. Adjustable robust reactive power optimization considering random distributed power integration in three-phase distribution network[J]. Power System Technology, 2018,42(4):1217-1225.
[9]	LIN C H, WU W C, ZHANG B M, et al. Decentralized reactive power optimization method for transmission and distribution networks accommodating large-scale DG integration[J]. IEEE Transactions on Sustainable Energy, 2017,8(1):363-373.
[10]	VLACHOGIANNIS J G, HATZIARGYRIOU N D. Reinforcement learning for reactive power control[J]. IEEE Transactions on Power Systems, 2004,19(3):1317-1325.
[11]	孙国忠. 基于渐进学习理论的配电网无功电压控制方法研究[D]. 济南: 山东大学, 2014.
	SUN Guozhong. Research on the approach of the reactive power and voltage control of distribution network based on incremental learning theory[D]. Jinan: Shandong University, 2014.
[12]	刘科研, 季玉琦, 陆凌芝, 等. 基于负荷分布匹配与熵权法的配电网无功优化[J]. 电网技术, 2017,41(12):3980-3988.
	LIU Keyan, JI Yuqi, LU Lingzhi, et al. Reactive power optimization in distribution network based on load distribution matching and entropy weight method[J]. Power System Technology, 2017,41(12):3980-3988.
[13]	邵美阳, 吴俊勇, 石琛, 等. 基于数据驱动和深度置信网络的配电网无功优化[J]. 电网技术, 2019,43(6):1874-1885.
	SHAO Meiyang, WU Junyong, SHI Chen, et al. Reactive power optimization of distribution network based on data driven and deep belief network[J]. Power System Technology, 2019,43(6):1874-1885.
[14]	张宇精, 乔颖, 鲁宗相, 等. 含高比例分布式电源接入的低感知度配电网电压控制方法[J]. 电网技术, 2019,43(5):1528-1535.
	ZHANG Yujing, QIAO Ying, LU Zongxiang, et al. Voltage control for partially visible distribution networks with high DG penetration[J]. Power System Technology, 2019,43(5):1528-1535.
[15]	SUN Y C, VENUGOPAL V, BRANDT A R. Short-term solar power forecast with deep learning: Exploring optimal input and output configuration[J]. Solar Energy, 2019,188:730-741.
[16]	LI W L, MONTI A, PONCI F. Fault detection and classification in medium voltage DC shipboard power systems with wavelets and artificial neural networks[J]. IEEE Transactions on Instrumentation and Measurement, 2014,63(11):2651-2665.
[17]	YU J J Q, LAM A Y S, HILL D J, et al. Delay aware intelligent transient stability assessment system[J]. IEEE Access, 2017,5:17230-17239.
[18]	MACKAY D J C. Bayesian interpolation[J]. Neural Computation, 1992,4(3):415-447.
[19]	陈泓榆. 泉州供电公司电力负荷特性及需求侧管理办法的研究[D]. 泉州: 华侨大学, 2015.
	CHEN Hongyu. The research on power user load characteristic and the demand side management regulations of Quanzhou power supply company[D]. Quanzhou: Huaqiao University, 2015.
[20]	DOU X B, DUAN X M, HU Q R, et al. A nonintrusive control strategy using voltage and reactive power for distribution systems based on PV and the nine-zone diagram[J]. International Journal of Electrical Power & Energy Systems, 2019,105:89-97.