基于样本扩容和数据驱动的台区理论线损计算方法

doi:10.6040/j.issn.1672-3961.0.2024.098

摘要/Abstract

摘要： 针对目前台区理论线损数据驱动研究中面临高质量数据样本规模不足的问题,提出一种基于样本扩容和数据驱动的台区理论线损计算方法。构建生成对抗网络,采用Adam优化器优化确定网络参数;对台区样本进行K-means聚类分析,提出依据轮廓系数和误差平方和优选聚类数目的方法,通过台区合理分类有效降低人工神经网络训练的计算量;基于扩容后的样本集训练各类台区,建立台区理论线损的人工神经网络分析模型。采用山东省聊城市某地的台区实际数据进行仿真分析,结果表明,所提方法可有效扩容样本集,提升人工神经网络模型的训练效果,提高台区理论线损分析的精度。

关键词: 样本扩容, 生成对抗网络, 数据驱动, 人工神经网络, 台区线损

Abstract: Aiming at the problem of insufficient scale of high-quality data samples for data-driven research on theoretical line loss analysis of transformer districts, a calculation method of theoretical line loss in transformer districts based on sample expansion and data-driven was proposed. A generative adversarial network was constructed, and the Adam optimizer was used to optimize the network parameters. The transformer districts samples were analyzed by K-means clustering analysis, while a method for selecting the optimal number of clusters was built based on silhouette coefficient and sum of squared errors. The proper classification of the transformer districts effectively reduced the computational burden of artificial neural network training. The artificial neural network model for theoretical line loss analysis of transformer districts was established through training on each class of transformer districts with the expanded sample set. Simulations were conducted to verify the proposed method by using actual transformer districts data collected from an urban area in Liaocheng City, Shandong Province. The results showed that the sample set was effectively expanded, the training effectiveness of the artificial neural network model was improved, and higher accuracy was achieved in the theoretical line loss analysis of transformer districts.

Key words: sample expansion, generative adversarial network, data-driven, artificial neural network, line loss of transformer districts

中图分类号:

TM744

贾轩,许吉凯,任艺婧,刘德才,许强,张利. 基于样本扩容和数据驱动的台区理论线损计算方法[J]. 山东大学学报 (工学版), 2025, 55(3): 158-164.

JIA Xuan, XU Jikai, REN Yijing, LIU Decai, XU Qiang, ZHANG Li. Calculation method of theoretical line loss in transformer districts based on sample expansion and data-driven[J]. Journal of Shandong University(Engineering Science), 2025, 55(3): 158-164.

参考文献

[1] 张勇军, 羿应棋, 李立浧, 等. 双碳目标驱动的新型低压配电系统技术展望[J]. 电力系统自动化, 2022, 46(22): 1-12. ZHANG Yongjun, YI Yingqi, LI Licheng, et al. Prospect of new low-voltage distribution system technology driven by carbon emission peak and carbon neutrality targets[J]. Automation of Electric Power Systems, 2022, 46(22): 1-12.
[2] 袁学良, 杨月, 盛雪柔, 等. 碳达峰碳中和政策解析与对策建议[J]. 山东大学学报(工学版), 2023, 53(5): 132-141. YUAN Xueliang, YANG Yue, SHENG Xuerou, et al. Policy analysis and countermeasures for achieving carbon peak and carbon neutrality[J]. Journal of Shandong University(Engineering Science), 2023, 53(5): 132-141.
[3] 田鑫, 牛新生, 朱秀波, 等. 低碳背景下山东电网最优降损策略及评估方法[J]. 电力系统自动化, 2014, 38(17): 67-72. TIAN Xin, NIU Xinsheng, ZHU Xiubo, et al. Optimal strategy and assessment method for minimizing power loss of Shandong power network under low-carbon background[J]. Automation of Electric Power Systems, 2014, 38(17): 67-72.
[4] QUEIROZ L M O, ROSELLI M A, CAVELLUCCI C, et al. Energy losses estimation in power distribution systems[J]. IEEE Transactions on Power Systems, 2012, 27(4): 1879-1887.
[5] 袁旭峰, 鹿振国, 许文强, 等. 基于前推回代三相潮流的低压台区理论线损计算研究[J]. 电测与仪表, 2014, 51(9): 1-5. YUAN Xufeng, LU Zhenguo, XU Wenqiang, et al. Study on the theoretical line loss calculation of low-voltage transformer areas based on forward-back sweep three-phase power flow algorithm[J]. Electrical Measure-ment & Instrumentation, 2014, 51(9): 1-5.
[6] 马喜平, 贾嵘, 梁琛, 等. 高比例新能源接入下电力系统降损研究综述[J]. 电网技术, 2022, 46(11): 4305-4315. MA Xiping, JIA Rong, LIANG Chen, et al. Review of researches on loss reduction in context of high penetration of renewable power generation[J]. Power System Technology, 2022, 46(11): 4305-4315.
[7] 于一潇, 杨佳峻, 杨明, 等. 基于深度强化学习的风电场储能系统预测决策一体化调度[J]. 电力系统自动化, 2021, 45(1): 132-140. YU Yixiao, YANG Jiajun, YANG Ming, et al. Prediction and decision integrated scheduling of energy storage system in wind farm based on deep reinforcement learning[J]. Automation of Electric Power Systems, 2021, 45(1): 132-140.
[8] 赵磊, 栾文鹏, 王倩. 应用AMI数据的低压配电网精确线损分析[J]. 电网技术, 2015, 39(11): 3189-3194. ZHAO Lei, LUAN Wenpeng, WANG Qian. Accurate line loss analysis of LV distribution network using AMI data[J]. Power System Technology, 2015, 39(11): 3189-3194.
[9] 章博, 卢峰, 董寒宇, 等. 基于决策树和数据驱动的零电量用户筛选方法[J]. 山东大学学报(工学版), 2019, 49(5): 29-36. ZHANG Bo, LU Feng, DONG Hanyu, et al. None-consumption users filtering algorithm based on decision tree and data-driven methods[J]. Journal of Shandong University(Engineering Science), 2019, 49(5): 29-36.
[10] 王守相, 周凯, 苏运. 基于随机森林算法的台区合理线损率估计方法[J]. 电力自动化设备, 2017, 37(11): 39-45. WANG Shouxiang, ZHOU Kai, SU Yun. Line loss rate estimation method of transformer district based on random forest algorithm[J]. Electric Power Automation Equipment, 2017, 37(11): 39-45.
[11] YU H L, SUN C Y, YANG X B, et al. Fuzzy support vector machine with relative density information for classifying imbalanced data[J]. IEEE Transactions on Fuzzy Systems, 2019, 27(12): 2353-2367.
[12] 马丽叶, 刘建恒, 卢志刚, 等. 基于深度置信网络的低压台区理论线损计算方法[J]. 电力自动化设备, 2020, 40(8): 140-146. MA Liye, LIU Jianheng, LU Zhigang, et al. Theoretical line loss calculation method of low voltage transform district based on deep belief network[J]. Electric Power Automation Equipment, 2020, 40(8): 140-146.
[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] REN Y J, ZHANG L, WANG H B,et al. Calculation method of the line loss rate in transformer district based on neural network with optimized input variables[C] //2020 IEEE 3rd Student Conference on Electrical Machines and Systems(SCEMS). Jinan, China: IEEE, 2020: 988-994.
[15] 王丽, 于明仟, 刘文鹏, 等. 面向类不平衡数据的K近邻偏标记学习算法[J]. 山东大学学报(工学版), 2022, 52(3): 18-24. WANG Li, YU Mingqian, LIU Wenpeng, et al. K-nearest neighbor based partial label learning algorithm for class imbalanced data[J]. Journal of Shandong Uni-versity(Engineering Science), 2022, 52(3): 18-24.
[16] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357.
[17] KINGMA D P, WELLING M. Auto-encoding variational Bayes[EB/OL].(2022-12-10)[2024-05-08]. https://arxiv.org/abs/1312.6114v11
[18] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C] //Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT, 2014: 2672-2680.
[19] 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.
[20] WANG C G, SHARIFNIA E, GAO Z, et al. Generating multivariate load states using a conditional variational autoencoder[J]. Electric Power Systems Research, 2022, 213: 108603.
[21] 王德文, 杨凯华. 基于生成式对抗网络的窃电检测数据生成方法[J]. 电网技术, 2020, 44(2): 775-782. WANG Dewen, YANG Kaihua. A data generation method for electricity theft detection using generative adversarial network[J]. Power System Technology, 2020, 44(2): 775-782.
[22] UZAIR M, JAMIL N. Effects of hidden layers on the efficiency of neural networks[C] //2020 IEEE 23rd Inter-national Multitopic Conference(INMIC). Bahawalpur, Pakistan: IEEE, 2020: 9318195.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed