基于EWM-AHP-BP神经网络的地区电网电压无功组合评价

doi:10.16182/j.issn1004731x.joss.21-1329

摘要/Abstract

摘要：

为量化评估新能源接入对地区电网电压无功运行状态的影响，提出一种基于EWM-AHP-BP(entropy weight method- analytic hierarchy process-BP)神经网络的地区电网电压无功组合评价方法。建立考虑电压合格率、电压波动、功率因数合格率、无功储备4项指标的电压无功综合评价模型，通过新能源与负荷运行数据聚类划分典型场景，采用熵权-层次分析组合方法对多场景下的评价模型打分，评价结果作为BP神经网络的样本进行训练。提出的组合评价方法简化了多目标评价的指标权重计算过程，实现了权重随数据变化的自适应调整，有效提升了计算效率。以某实际地区电网为例进行仿真，对历史数据进行样本训练和评价分析，验证了该方法的有效性。

关键词: 新能源, 电压无功, 组合评价, 典型场景, BP神经网络

Abstract:

In order to quantitatively evaluate the influence of renewable energy access on voltage and reactive power operation, a combinational evaluation method of voltage and reactive power based on EWM-AHP-BP neural network is proposed to carry out the multi-objective evaluation weight calculation. Considering voltage qualified rate, voltage fluctuation, power factor qualified rate and reactive power reserve, the comprehensive evaluation model is established. The operation data of renewable energy and power load are clustered to divide the typical scenarios and the evaluation model under multiple scenarios is scored by the combination method of entropy weight method and analytic hierarchy process. The evaluation results are trained as samples of BP neural network. The proposed method simplifies the weight calculation process of multi-objective evaluation, realizes the adaptive adjustment of weight with the change of samples and effectively improves the calculation efficiency. The effectiveness of the proposed method is verified by the simulation on an actual regional power grid and the sample training and evaluation analysis of historical data.

Key words: renewable energy, voltage and reactive power, combinational evaluation, typical scenarios, BP neural networks

中图分类号:

TP714

季玉琦, 谢欢, 史少彧, 和萍, 金楠, 王惠丽. 基于EWM-AHP-BP神经网络的地区电网电压无功组合评价[J]. 系统仿真学报, 2023, 35(4): 843-852.

Yuqi Ji, Huan Xie, Shaoyu Shi, Ping He, Nan Jin, Huili Wang. Voltage and Reactive Power Combinational Evaluation of Regional Power Grid Based on EWM-AHP-BP Neural Network[J]. Journal of System Simulation, 2023, 35(4): 843-852.

图/表 17

图1

图2

图3

图4

图5

表1

图6

图7

表2

图8

图9

图10

表3

表4

表5

图11

表6

参考文献 19

1	孙伟卿, 宋赫, 韩冬, 等. 火电深度调峰改造近似动态规划方法[J]. 系统仿真学报, 2021, 33(6): 1415-1426.
	Sun Weiqing, Song He, Han Dong, et al. Deep Peak-shaving Transformation Planning of Thermal Power Units Based on Approximate Dynamic Programming[J]. Journal of System Simulation, 2021, 33(6): 1415-1426.
2	Badal Faisal R, Das Purnima, Sarker Subrata K, et al. A Survey on Control Issues in Renewable Energy Integration and Microgrid[J]. Protection and Control of Modern Power Systems(S2367-2617), 2019, 4(4): 87-113.
3	Li Jihong, Huang Hongyang, Lou Boliang, et al. Wind Farm Reactive Power and Voltage Control Strategy Based on Adaptive Discrete Binary Particle Swarm Optimization Algorithm[C]//2019 IEEE Asia Power and Energy Engineering Conference. Chengdu, China: IEEE, 2019: 99-102.
4	林捷, 王云柳, 黄辉, 等. 自动电压控制下的地区电网电压无功运行状态评估指标体系[J]. 电力系统保护与控制, 2016, 44(13): 123-129.
	Lin Jie, Wang Yunliu, Huang Hui, et al. An Index System for Voltage and Reactive Power Operation Status Evaluation in Regional Power Grid Under Automatic Voltage Control[J]. Power System Protection and Control, 2016, 44(13): 123-129.
5	邓应松, 谢国财, 胡亚平, 等. 地区电网AVC控制策略评价体系[J]. 电力电容器与无功补偿, 2017, 38(2): 69-75.
	Deng Yingsong, Xie Guocai, Hu Yaping, et al. Evaluation System of AVC Control Strategy of Regional Grid[J]. Power Capacitor & Reactive Power Compensation, 2017, 38(2): 69-75.
6	南钰, 宋瑞卿. 基于新能源消纳能力的开封电网无功支撑评价[J]. 价值工程, 2019, 38(25): 198-201.
	Yu Nan, Song Ruiqing. Reactive Power Support Evaluation of Kaifeng Power Grid Based on New Energy Absorption Capability[J]. Value Engineering, 2019, 38(25): 198-201.
7	陈岩, 靳伟, 王文宾, 等. 兼顾区域自律和消纳品质的配电网新能源消纳能力分析方法[J]. 中国电力, 2021, 54(9): 143-155.
	Chen Yan, Jin Wei, Wang Wenbin, et al. Analyzing Method of the Absorption Capability of New Energy in Distribution Network with Consideration of Regional Self-discipline and Absorption Quality[J]. Electric Power, 2021, 54(9): 143-155.
8	刘丽军, 笪超, 罗宁, 等. 基于出力曲线聚合与区间潮流典型场景耐受度评价的新能源发电规划方法[J]. 中国电机工程学报, 2020, 40(14): 4400- 4410, 4721.
	Liu Lijun, Chao Da, Luo Ning, et al. A Planning Method of Renewable Distributed Generation Based on Polymerization of Output Curves and Tolerance Evaluation of Typical Scene in Interval Power Flow[J]. Proceedings of the CSEE, 2020, 40(14): 4400-4410, 4721.
9	陈垚煜, 江全元, 周自强, 等. 考虑典型场景的配电网调控方案灵活性评估方法[J]. 电力建设, 2019, 40(7): 34-40.
	Chen Yaoyu, Jiang Quanyuan, Zhou Ziqiang, et al. An Evaluation Method on the Flexibility of Regulation Methods in Distribution Network Considering Typical Scene Sets[J]. Electric Power Construction, 2019, 40(7): 34-40.
10	李娟, 李保安, 方晗, 等. 基于AHP-熵权法的发明专利价值评估—以丰田开放专利为例[J]. 情报杂志, 2020, 39(5): 59-63.
	Li Juan, Li Baoan, Fang Han, et al. Evaluation of Invention Patent Value Based on AHP-Entropy Weight Method-Taking Toyota's Open-source Patent as an Example[J]. Journal of Intelligence, 2020, 39(5): 59-63.
11	李峰, 孙波, 王轩, 等. 层次分析法结合熵权法评估农村屋顶光伏系统电能质量[J]. 农业工程学报, 2019, 35(11): 159-166.
	Li Feng, Sun Bo, Wang Xuan, et al. Power Quality Assessment for Rural Rooftop Photovoltaic Access System Based on Analytic Hierarchy Process and Entropy Weight Method[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(11): 159-166.
12	吴昊, 朱自伟. 基于熵权-层次分析法综合指标的电网关键线路辨识[J]. 中国电力, 2020, 53(5): 39-47, 55.
	Wu Hao, Zhu Ziwei. Design and Application of Full-Time Dimension Dispatching Schedule Safety Check[J]. Electric Power, 2020, 53(5): 39-47, 55.
13	李亚, 刘丽平, 李柏青, 等. 基于改进K-Means聚类和BP神经网络的台区线损率计算方法[J]. 中国电机工程学报, 2016, 36(17): 4543-4552.
	Li Ya, Liu Liping, Li Baiqing, et al. Calculation of Line Loss Rate in Transformer District Based on Improved K-Means Clustering Algorithm and BP Neural Network[J]. Proceedings of the CSEE, 2016, 36(17): 4543-4552.
14	刘澄, 王辉, 李天慧, 等. 分布式新能源发电对配电网电压影响研究[J]. 可再生能源, 2019, 37(10): 1465-1471.
	Liu Cheng, Wang Hui, Li Tianhui, et al. Study on Influence of Distributed New Energy Generation on Distribution Network Voltage[J]. Renewable Energy Resources, 2019, 37(10): 1465-1471.
15	史景坚, 周文涛, 张宁, 等. 含储能系统的配电网电压调节深度强化学习算法[J]. 电力建设, 2020, 41(3): 71-78.
	Shi Jingjian, Zhou Wentao, Zhang Ning, et al. Deep Reinforcement Learning Algorithm of Voltage Regulation in Distribution Network with Energy Storage System[J]. Electric Power Construction, 2020, 41(3): 71-78.
16	宫一玉, 吴浩, 宋卓然. 发电机无功储备的定义和评估[J]. 电网技术, 2013, 37(7): 1902-1908.
	Gong Yiyu, Wu Hao, Song Zhuoran. Definition and Assessment of Generator Reactive Power Reserve[J]. Power System Technology, 2013, 37(7): 1902-1908.
17	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.
18	王文彬, 伍小生, 朱傲, 等. 基于层次分析法的配电网"低电压"智能规划与综合治理评估技术研究及应用[J]. 电工技术学报, 2018, 33(增2): 596-607.
	Wang Wenbin, Wu Xiaosheng, Zhu Ao, et al. Research and Application of Low-Voltage Intelligent Planning and Comprehensive Treatment Evaluation Technology for Distribution Network Based on Analytic Hierarchy Process[J]. Transactions of China Electrotechnical Society, 2018, 33(S2): 596-607.
19	江文超, 张兴, 谢东, 等. 基于小波变换与BP神经网络的光伏电站孤岛检测研究[J]. 电力建设, 2019, 40(12): 113-119.
	Jiang Wenchao, Zhang Xing, Xie Dong, et al. Research on Photovoltaic Power Station Islanding Detection Based on Wavelet Transform and BP Neural Network[J]. Electric Power Construction, 2019, 40(12): 113-119.

输出	评级
1.00~0.85	优
(0.85~0.70]	良
(0.70~0.60]	中
0.60以下	差

接入母线编号	类型	装机容量/MW
4、11、16、21	光伏	300、170、30、30
5、8、9、29、30	风力	140、700、80、30、30

	U₁	U₂	U₃	U₄
U₁	1	1/5	1/3	1/2
U₂	5	1	2	3
U₃	1/3	1/2	1	2
U₄	2	1/3	1/2	1

第一层权重ω_ui		第二层权重ω_ui		权重ω_ui
电压N₁	0.5	电压合格率U₁	0.094 0	0.094 0
电压N₁	0.5	电压波动U₂	0.512 2	0.512 2
无功N₂	0.5	功率因数合格率U₃	0.224 6	0.224 6
无功N₂	0.5	无功储备U₄	0.169 1	0.169 1

日期	组合评价	EWM-AHP	日期	组合评价	EWM-AHP
1	0.748 9	0.776 7	16	0.799 8	0.793 7
2	0.741 4	0.758 2	17	0.739 2	0.793 0
3	0.683 2	0.738 8	18	0.767 5	0.759 7
4	0.898 6	0.720 8	19	0.777 4	0.744 1
5	0.760 0	0.790 6	20	0.783 2	0.744 3
6	0.744 6	0.733 8	21	0.810 8	0.770 5
7	0.736 0	0.761 7	22	0.738 7	0.723 1
8	0.734 1	0.754 8	23	0.746 9	0.743 8
9	0.864 1	0.807 3	24	0.755 6	0.779 1
10	0.735 9	0.731 4	25	0.736 2	0.765 9
11	0.736 1	0.731 2	26	0.735 0	0.752 1
12	0.500 8	0.663 4	27	0.743 2	0.696 8
13	0.778 2	0.734 8	28	0.734 8	0.767 7
14	0.725 0	0.679 6	29	0.736 0	0.790 4
15	0.701 5	0.744 0	30	0.773 4	0.757 4