A Novel Method of Line Loss Rate Prediction for Substation Areas Based on Maximum Information Coefficient and BO-LSTNet

doi:10.3969/j.issn.1008-0198.2025.05.012

Abstract

Abstract: Aiming at the shortcomings of traditional methods for predicting line loss in substation areas, such as inability to adjust flexibly, lack of real-time performance, and accuracy affected by meteorological conditions, a new method for predicting line loss rate in substation areas based on maximum information coefficient and BO-LSTNet is proposed. The maximum information coefficient method is used to screen meteorological information in the substation area, and input variables are filtered and cleaned, and finally the line loss data is put into the LSTNet model after Bayesian optimization. The reliability is verified through simulation experiments, and the results show that compared with previous prediction methods, this model has higher adaptability to the new type of substation line loss rate prediction, and solves the problem of low accuracy in line loss prediction in practical engineering.

Key words: maximum information coefficient, LSTNet (long-and short-term time-series network), selection of correlation features, new type of substation line loss, Bayesian optimization, feature selection algorithm

CLC Number:

TM714

CUI Xianyi, DENG Hanjun, YU Minqi, XU Gang, REN Jiahao. A Novel Method of Line Loss Rate Prediction for Substation Areas Based on Maximum Information Coefficient and BO-LSTNet[J]. Hunan Electric Power, 2025, 45(5): 85-94.

References

[1] 刘康,李彬,薛阳,等. 基于传递熵密度聚类的用户窃电识别方法[J]. 中国电机工程学报,2022,42(20):7535-7546.
[2] 王佳仁,谢宁,王承民,等. 提升现代配电系统效率和效益的研究与实践[J]. 电网技术,2018,42(11):3543-3549.
[3] 吴向明,宋楠,李晓军,等.基于二次模态分解和卷积双向长短期记忆神经网络的高比例光伏配电网线损预测[J/OL].电网技术,1-11.(2024-07-15)[2025-07-15]. https://doi.org/10.13335/j.1000-3673.pst.2024.0577.
[4] 李傲,王京景,谢颖,等. 基于合环潮流计算分析的电网测控调度运行辅助决策模型研究[J/OL]. 自动化技术与应用,1-5.(2024-12-23)[2025-07-15]. http://kns.cnki.net/kcms/detail/23.1474.TP.20241223.1206.030.html.
[5] 徐茹枝,王宇飞. 粒子群优化的支持向量回归机计算配电网理论线损方法[J]. 电力自动化设备,2012,32(5):86-89,93.
[6] 熊军华,牛珂,张春歌,等. 基于小波变异果蝇优化支持向量机短期负荷预测方法研究[J]. 电力系统保护与控制,2017,45(13):71-77.
[7] 李植鹏,侯惠勇,蒋嗣凡,等. 基于人工神经网络的线损计算及窃电分析[J]. 南方电网技术,2019,13(2):7-12,50.
[8] 张勇军,石辉,翟伟芳,等. 基于层次分析法-灰色综合关联及多灰色模型组合建模的线损率预测[J]. 电网技术,2011,35(6):71-76.
[9] JEONG D,PARK C,KO Y M.Short-term electric load forecasting for buildings using logistic mix-ture vector autoregressive model with curve registration[J]. Applied Energy,2021,282:116249.
[10] SHARMA SHALINI,MAJUMDAR ANGSHUL,ELVIRA VICTOR,et al.Blind kalman filtering for short-term load forecasting[J]. IEEE Transactions on Power Systems,2020,35(6):4916-4919.
[11] 杨周义,邢海军,江伟建,等. 基于低碳需求响应的含煤制氢与碳捕集电厂的综合能源系统优化调度[J]. 电力自动化设备,2024,44(4):25-32.
[12] 王训洪,郝同铮,马聪. 基于PSO-BP神经网络的新能源汽车销量预测模型[J]. 科学技术与工程,2024,24(31):13467-13474.
[13] 谢林,李红伟,袁岳,等. 基于K-means聚类和改进多分类相关向量机的台区线损计算方法[J]. 电气工程学报,2021,16(1):62-69.
[14] WEI Y,GAO X L.Transmission line galloping prediction based on GA-BP-SVM combined method[J]. IEEE Access,2021,9:107680-107687.
[15] 徐岩,向益锋,马天祥. 基于EMD-CNN-LSTM混合模型的短期电力负荷预测[J]. 华北电力大学学报(自然科学版),2022,49(2):81-89.
[16] THANH P N,CHO M Y,CHANG C L,et al.Short-term three-phase load prediction with advanced metering infrastructure data in smart solar microgrid based convolution neural network bidirectional gated recurrent unit[J]. IEEE Access,2022,10:68686-68699.
[17] 刘伟,蔡东升,冯付勇,等. 基于DCT-CNN-GRU的短期电力负荷预测研究[J/OL]. 电测与仪表,1-11.(2024-03-22)[2025-07-15]. http://kns.cnki.net/kcms/detail/23.1202.th.20240321.1323.002.html.
[18] 王晓霞,俞敏,霍泽健,等. 基于近邻传播聚类与LSTNet的分布式光伏电站群短期功率预测[J]. 电力系统自动化,2023,47(6):133-141.
[19] HUANG B,LIANG Y,QIU X L.Wind power forecasting using attention-based recurrent neural networks:a comparative study[J]. IEEE Access,2021,9:40432-40444.
[20] 黄璜,张安安.基于分解算法与元学习结合的综合能源系统负荷预测[J]. 电力系统自动化,2024,48(10):151-160.
[21] 康佳宇,张沈习,张庆平,等. 基于ANOVA和BO-SVM的变压器故障诊断方法[J]. 高电压技术,2023,49(5):1882-1891.
[22] 杨秀,傅骞,汤波,等. 基于动态时空适应图神经网络的电网线路参数辨识方法[J/OL]. 中国电机工程学报,1-16.(2024-10-08)[2024-07-15].http://kns.cnki.net/kcms/detail/11.2107.tm.20240930.1550.011.html.