作者：卜飞飞, 白宏坤, 王圆圆, 韩丁

作者单位：国网河南省电力公司经济技术研究院，河南 郑州 450000

关键词：人体气象舒适度指数;气象因子;灰色关联度;灰色RBF神经网络

摘要：

针对气象状况、季节等因素对居民用电负荷有不同影响，为深入分析不同因素与居民用电的相关性，提出人体气象舒适度指数，建立适用于用电负荷的人体气象舒适度指数模型。采用灰色关联度方法分析各气象因子以及人体舒适度指数与居民用电的相关性。基于郑州气象大数据和居民用户用电数据，得到人体气象舒适度指数相比于其他单个气象因子具有更强的关联性。基于灰度预测模型和RBF神经网络，结合人体舒适度指数对用电的影响，提出灰色RBF神经网络预测算法。用郑州某小区近年的负荷数据作为预测样本数据，分别采用灰色预测模型、RBF神经网络预测模型以及灰色RBF神经网络预测模型对用户负荷进行预测分析。测试结果表明：灰色RBF神经网络模型预测精度最高，可为后续居民用电负荷的精确预测奠定理论基础。

Research on resident electricity consumption based on human comfort index and power load forecasting
BU Feifei, BAI Hongkun, WANG Yuanyuan, HAN Ding
State Grid Henan Economic Research Institute, Zhengzhou 450000, China
Abstract: In view of the fact that meteorological conditions, seasons and other influencing factors have different effects on residential electricity load, in order to deeply analyze the correlation between different factors and residential electricity consumption, the human meteorological comfort index is proposed. And a human meteorological comfort index model suitable for electricity load is established. The grey correlation degree method is used to analyze the correlation between meteorological factors, human comfort index and residential electricity consumption. Based on the electricity consumption data of Zhengzhou meteorological big data and residential users, it is found that the human meteorological comfort index has a stronger correlation with other single meteorological factors. Based on RBF neural network, making full use of human comfort index and grey prediction, a grey RBF neural network prediction algorithm is proposed. The load data of a residential district in Zhengzhou in recent years are used as the forecasting sample data, and the grey forecasting model, RBF neural network forecasting model and grey RBF neural network forecasting model are used to forecast and analyze the user load. The test results show that the grey RBF neural network model has the highest prediction accuracy, which lays a theoretical foundation for the accurate prediction of residential power load.
Keywords: human meteorological comfort index;meteorological factors;grey correlation degree;grey RBF neural network
2023, 49(4):85-91  收稿日期: 2021-08-16;收到修改稿日期: 2021-09-29
基金项目: 国家自然科学基金(51807149)
作者简介: 卜飞飞(1985-),男,河南新乡市人,高级工程师,硕士,研究方向为大数据、能源经济
参考文献
[1] 杜忠明, 王雪松. “十三五”中国电力需求水平预测[J]. 中国电力, 2017, 50(9): 11-17
[2] 李永毅, 石蓉, 郎锐, 等. 基于大数据分析的陕西省居民用电行为及影响因素研究[J]. 电网与清洁能源, 2019, 35(4): 43-48
[3] 徐亮亮, 徐艳琴, 温建伟, 等. 基于Apriori算法的城乡居民用电负荷与气象因子关系分析[J]. 内蒙古气象, 2019(2): 39-42
[4] 王芷璇, 周连科. 河北东南沿海地区人体舒适度指数变化特征研究[J]. 农村实用技术, 2020(5): 162
[5] 冯凯. 基于大数据的居民用电行为分析与负荷预测[D]. 保定: 华北电力大学, 2017.
[6] 陈芬, 刘何清, 朱凯颖, 等. 以有效温度为基础的人体舒适度评价模型的发展概述[J]. 采矿技术, 2019, 19(5): 106-111
[7] 李颖玥, 王勋, 康琛, 等. 基于指数加权移动平均多维组合模型的电力负荷预测[J]. 华东交通大学学报, 2019, 36(5): 102-108
[8] SUN W, ZHANG C. Analysis and forecasting of the carbon price using multi-resolution singular value decomposition and extreme learning machine optimized by adaptive whale optimization algorithm[J]. Applied Energy, 2018, 231: 1354-1371
[9] LIU C, SUN B, ZHANG C, et al. A hybrid prediction model for residential electricity consumption using holt-winters and extreme learning machine[J]. Applied Energy, 2020, 275: 115383
[10] 杨德昌, 赵肖余, 何绍文, 等. 面向海量用户用电数据的集成负荷预测[J]. 电网技术, 2018, 42(9): 2923-2929
[11] 田杨阳, 张小斐, 耿俊成, 等. 基于改进聚类和LSTM的居民小区中长期负荷预测[J]. 河南电力, 2020(2): 58-63
[12] 赵冬梅, 马泰屹, 王闯. 基于相空间重构和长短期记忆算法的电力系统无功负荷预测模型[J]. 现代电力, 2020, 37(5): 470-477
[13] 董莉娜, 张志劲, 王茂政. 基于历史天气的区域电网负荷预测的研究[J/OL]. 中国测试:1-7[2023-04-07]. http://kns.cnki.net/kcms/detail/51.1714.TB.20210722.0952.002.html.
[14] 李玉志, 刘晓亮, 邢方方, 等. 基于Bi-LSTM和特征关联性分析的日尖峰负荷预测[J]. 电网技术, 2021, 45(7): 2719-2730
[15] 严勤, 邓高峰, 胡涛, 等. 基于深度循环神经网络的异常用电检测方法[J]. 中国测试, 2021, 47(7): 99-104