考虑气象敏感性的相似日用电量预测

doi:10.11930/j.issn.1004-9649.202507060

中国电力 ›› 2025, Vol. 58 ›› Issue (12): 155-164.DOI: 10.11930/j.issn.1004-9649.202507060

• 新型电网 • 上一篇

考虑气象敏感性的相似日用电量预测

郑宽昀¹(), 陈一平¹, 单帅杰²^,³(), 刘秀², 于一潇⁴

1. 国电南瑞南京控制系统有限公司，江苏南京　210000
2. 山东大学电气工程学院，山东济南　250061
3. 山东省数字智慧能源创新重点实验室，山东济南　250100
4. 山东大学高等技术研究院，山东济南　250061

收稿日期:2025-07-21 修回日期:2025-09-10 发布日期:2025-12-27 出版日期:2025-12-28
作者简介:
郑宽昀（1982），男，高级工程师，从事电力自动化、电力市场、用电信息采集研究，E-mail：307909019@qq.com
单帅杰（1997），男，通信作者，博士研究生，从事用户侧电力电量预测、电力系统经济运行研究，E-mail：shanshuaijie@126.com
基金资助:
国家自然科学基金资助项目（52177095）。

Similar-Day Electricity Consumption Prediction Considering Meteorological Sensitivity

ZHENG Kuanyun¹(), CHEN Yiping¹, SHAN Shuaijie²^,³(), LIU Xiu², YU Yixiao⁴

1. NARI-TECH Nanjing Control Systems Co., Ltd., Nanjing 210000, China
2. School of Electrical Engineering, Shandong University, Jinan 250061, China
3. Shandong Key Laboratory of Digital Smart Energy, Jinan 250100, China
4. Institute for Advanced Technology, Shandong University, Jinan 250061, China

Received:2025-07-21 Revised:2025-09-10 Online:2025-12-27 Published:2025-12-28
Supported by:
This work is supported by National Natural Science Foundation of China (No.52177095).

摘要/Abstract

摘要：

精准用电量预测能够为电力供应提供技术支撑，为实现高精准预测，提出了一种考虑气象敏感性的相似日用电量预测方法，通过深入挖掘用电量的时序波动特性与气象敏感性，结合关键气象因素，提高相似日匹配度，进而提高预测精度。首先，通过皮尔逊相关系数分析各气象因素与用电量的线性关联程度，再经P值检验，综合二者结果筛选出影响用电量的关键气象因素，并利用K-means聚类算法对与用电量相关系数最高的温度数据进行分类，将历史日划分为高温日、适温日2类，建立相似日类型框架。其次，在相同温度类别内，通过灰色关联分析计算待测日与历史日各气象因素之间的灰色关联度，并结合欧氏距离筛选出与待测日相似的历史日数据，深入挖掘用电量的时序波动与气象敏感性特征。然后，基于相似日数据构建组合预测模型，综合考虑气象因素与时间序列特性，提高预测精度。最后，通过山东某地某小区的用电数据情况进行验证，结果表明：所提方法在解决用电量预测问题方面具有显著优势。

关键词: 用电量预测, K-means聚类, 灰色关联分析, 相似日, 组合预测

Abstract:

Accurate electricity consumption prediction can provide technical support for the precise supply of electricity. To achieve high-precision prediction, a method based on meteorologically similar days for electricity consumption prediction is proposed. By deeply exploring the temporal fluctuation characteristics of electricity consumption and the meteorological sensitivity, and combining key meteorological factors, the matching degree of similar days is improved, thereby enhancing the prediction accuracy. Firstly, the linear correlation degree between each meteorological factor and electricity consumption is analyzed through Pearson correlation coefficient. Then, through P-value test, the key meteorological factors affecting electricity consumption are screened out by integrating the results of both. And the temperature data that exhibits the highest correlation with electricity consumption is classified using the K-means clustering algorithm. Historical days are categorized into two types: high-temperature days and moderate-temperature days, thereby establishing a similar-day typology framework. Secondly, within the same temperature category, the grey relational analysis is used to calculate the grey correlation degree between the meteorological factors of the target day and those of the historical days. By integrating Euclidean distance, the historical days most similar to the target day are screened out to deeply explore the temporal fluctuations and meteorological sensitivity characteristics of electricity consumption. Subsequently, a combined prediction model is constructed based on the similar-day data, comprehensively considering both meteorological factors and time-series characteristics, thereby enhancing prediction accuracy. Finally, the proposed method is validated using the electricity consumption data from a residential district in a certain area of Shandong Province. The results demonstrate that the proposed method has significant advantages in addressing the challenges of electricity consumption prediction.

Key words: electricity consumption prediction, k-means clustering, grey relational analysis, similar day, combinatorial forecasting

郑宽昀, 陈一平, 单帅杰, 刘秀, 于一潇. 考虑气象敏感性的相似日用电量预测[J]. 中国电力, 2025, 58(12): 155-164.

ZHENG Kuanyun, CHEN Yiping, SHAN Shuaijie, LIU Xiu, YU Yixiao. Similar-Day Electricity Consumption Prediction Considering Meteorological Sensitivity[J]. Electric Power, 2025, 58(12): 155-164.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202507060

https://www.electricpower.com.cn/CN/Y2025/V58/I12/155

图/表 11

图 1 BiLSTM模型结构

Fig.1 BiLSTM model structure

图 2 整体预测框架

Fig.2 Overall prediction framework

表 1 各气象因素与用电量的相关性及显著性分析

Table 1 Correlation and significance analysis of various meteorological factors and electricity consumption

气象因素	与用电量相关系数	相关程度	P值	显著程度
降雨量	0.2219	弱相关	0.0298	显著
湿度	–0.3722	中度相关	0.0018	显著
风速	0.3193	中度相关	0.0015	显著
温度	0.5578	中度相关	0.0001	显著
风向	0.1320	弱相关	0.1998	不显著
气压	–0.0844	不相关	0.4136	不显著
云量	–0.0610	不相关	0.5549	不显著

图 3 聚类数目

Fig.3 Number of clusters

图 4 聚类结果

Fig.4 Clustering results

表 2 4月19日与3月30日的7个最低综合得分

Table 2 The seven lowest comprehensive scores on April 19 th and March 30 th

序号	4月19日	3月30日
1	28.56700	11.94775
2	31.84896	18.39012
3	38.91220	19.83654
4	48.25884	25.82930
5	49.57415	26.27111
6	51.31181	36.42080
7	53.55670	36.56495

表 3 4月19日与3月30日的7个相似日

Table 3 Seven similar days on April 19 th and March 30 th

序号	4月19日	3月30日
1	3月22日	3月23日
2	2月16日	2月17日
3	4月8日	2月6日
4	3月4日	2月7日
5	3月11日	2月20日
6	3月16日	2月14日
7	3月5日	3月28日

图 5 4月19日各模型预测结果

Fig.5 The prediction results of various models on April 19 th

图 6 3月30日各模型预测结果

Fig.6 The prediction results of various models on March 30 th

图 7 4月19日各模型评估指标结果

Fig.7 The evaluation index results of various models on April 19 th

图 8 3月30日各模型评估指标结果

Fig.8 The evaluation index results of various models on March 30 th

参考文献 33

1	王文坚, 陈飞雄, 林世琦. 新型电力系统下调频容量需求计算与储-荷调频方法研究综述[J]. 智慧电力, 2025, 53 (12): 1- 12.
	WANG Wenjian, CHEN Feixiong, LIN Shiqi. A review of frequency regulation capacity demand calculation and energy storage-load frequency regulation methods in new-type power systems[J]. Smart Power, 2025, 53 (12): 1- 12.
2	杨胡萍, 余阳, 汪超, 等. 基于VMD-CNN-BIGRU的电力系统短期负荷预测[J]. 中国电力, 2022, 55 (10): 71- 76.
	YANG Huping, YU Yang, WANG Chao, et al. Short-term load forecasting of power system based on VMD-CNN-BIGRU[J]. Electric Power, 2022, 55 (10): 71- 76.
3	孙庆超, 李嘉靓, 江万里, 等. 基于数据驱动时空网络的城市中长期电力负荷预测[J]. 中国电力, 2025, 58 (3): 168- 174. DOI
	SUN Qingchao, LI Jialiang, JIANG Wanli, et al. Mid-long term urban power load forecasting based on data-driven spatio-temporal networks[J]. Electric Power, 2025, 58 (3): 168- 174. DOI
4	李勇, 吴含欣, 李婵虓, 等. 考虑多维气象指标的配电网短期负荷预测[J]. 智慧电力, 2025, 53 (6): 116- 123.
	LI Yong, WU Hanxin, LI Chanxiao, et al. Short-term load forecasting for distribution networks considering multidimensional meteorological indicators[J]. Smart Power, 2025, 53 (6): 116- 123.
5	刘义艳, 李国良, 代杰. 基于VMD-TCN-BiLSTM-Attention的短期电力负荷预测[J]. 智慧电力, 2025, 53 (10): 87- 94.
	LIU Yiyan, LI Guoliang, DAI Jie. Short-term power load forecasting based on VMD-TCN-BiLSTM-attention[J]. Smart Power, 2025, 53 (10): 87- 94.
6	ZHU L, GAO J K, ZHU C Q, et al. Short-term power load forecasting based on spatial-temporal dynamic graph and multi-scale Transformer[J]. Journal of Computational Design and Engineering, 2025, 12 (2): 92- 111. DOI
7	姜东良, 李天昊, 刘文浩. 基于相似日和SAE-DBiLSTM模型的短期电力负荷预测[J]. 电气工程学报, 2022, 17 (4): 240- 249.
	JIANG Dongliang, LI Tianhao, LIU Wenhao. Short-term power load forecasting using similar day and SAE-DBiLSTM model[J]. Journal of Electrical Engineering, 2022, 17 (4): 240- 249.
8	JIANG Q, CHENG Y X, LE H Z, et al. A stacking learning model based on multiple similar days for short-term load forecasting[J]. Mathematics, 2022, 10 (14): 2446. DOI
9	刘明, 尚尚. 基于K_means++聚类与RF_GRU组合模型的电力负荷预测方法研究[J]. 计算机与数字工程, 2024, 52 (6): 1662- 1667, 1702.
	LIU Ming, SHANG Shang. Research on power load forecasting method based on K_means++ clustering and RF_GRU combined model[J]. Computer & Digital Engineering, 2024, 52 (6): 1662- 1667, 1702.
10	祁宇轩, 范俊岩, 吴定会, 等. 基于相似日与BiLSTM组合的短期电力负荷预测[J]. 控制理论与应用, 2024, 41 (12): 2304- 2314.
	QI Yuxuan, FAN Junyan, WU Dinghui, et al. Short term power load forecasting based on the combination of similar days and BiLSTM[J]. Control Theory & Applications, 2024, 41 (12): 2304- 2314.
11	章姝俊, 陆海清, 陈佳玺, 等. 基于多因素相关性分析的气温敏感负荷预测[J]. 浙江电力, 2023, 42 (9): 27- 35. DOI
	ZHANG Shujun, LU Haiqing, CHEN Jiaxi, et al. Research on prediction of temperature-sensitive loads based on multi-factor correlation analysis[J]. Zhejiang Electric Power, 2023, 42 (9): 27- 35. DOI
12	谭诗琪, 范嘉智, 耿欢, 等. 基于LSTM神经网络的多要素用电量动态预测[J]. 农业灾害研究, 2024, 14 (7): 161- 163. DOI
	TAN Shiqi, FAN Jiazhi, GENG Huan, et al. Dynamic prediction of multi-factor electricity consumption based on LSTM neural network[J]. Agricultural Disaster Research, 2024, 14 (7): 161- 163. DOI
13	吴小涛, 袁晓辉, 毛玉鑫, 等. 基于鹈鹕优化CNN-BiLSTM的电力负荷预测[J]. 水电能源科学, 2024, 42 (8): 209- 212, 172.
	WU Xiaotao, YUAN Xiaohui, MAO Yuxin, et al. Power load prediction based on pelican optimized CNN-BiLSTM[J]. Water Resources and Power, 2024, 42 (8): 209- 212, 172.
14	LIU F, LIANG C. Short-term power load forecasting based on AC-BiLSTM model[J]. Energy Reports, 2024, 11, 1570- 1579. DOI
15	任爽, 杨凯, 商继财, 等. 基于CNN-BiGRU-Attention的短期电力负荷预测[J]. 电气工程学报, 2024, 19 (1): 344- 350.
	REN Shuang, YANG Kai, SHANG Jicai, et al. Short-term power load forecasting based on CNN-BiGRU-attention[J]. Journal of Electrical Engineering, 2024, 19 (1): 344- 350.
16	杨汪洋, 魏云冰, 罗程浩. 基于CVMD-TCN-BiLSTM的短期电力负荷预测[J]. 电气工程学报, 2024, 19 (2): 163- 172. DOI
	YANG Wangyang, WEI Yunbing, LUO Chenghao. Short-term electricity load forecasting based on CVMD-TCN-BiLSTM[J]. Journal of Electrical Engineering, 2024, 19 (2): 163- 172. DOI
17	PENG D G, LIU Y, WANG D H, et al. Multi-energy load forecasting for integrated energy system based on sequence decomposition fusion and factors correlation analysis[J]. Energy, 2024, 308, 132796. DOI
18	YANG Z H, LI J D, WANG H T, et al. An informer model for very short-term power load forecasting[J]. Energies, 2025, 18 (5): 1150. DOI
19	汪繁荣, 梅涛, 卢璐. 基于相似日聚类和VMD-LTWDBO-BiLSTM的短期光伏功率预测[J]. 智慧电力, 2024, 52 (10): 56- 63, 111.
	WANG Fanrong, MEI Tao, LU Lu. Short-term PV power prediction based on similar day clustering with VMD-LTWDBO-BiLSTM[J]. Smart Power, 2024, 52 (10): 56- 63, 111.
20	陈启凡, 丁云飞, 田锟, 等. 基于K-means聚类的BP-DTR的电动汽车短期充电负荷预测[J]. 上海电机学院学报, 2024, 27 (4): 187- 191. DOI
	CHEN Qifan, DING Yunfei, TIAN Kun, et al. Short-term charging load prediction of electric vehicles based on BP-DTR with K-means clustering[J]. Journal of Shanghai Dianji University, 2024, 27 (4): 187- 191. DOI
21	PANG X F, SUN W, LI H B, et al. Short-term power load forecasting based on gray relational analysis and support vector machine optimized by artificial bee colony algorithm[J]. PeerJ Computer Science, 2022, 8, e1108. DOI
22	金丽丽. 基于GRA-SSA-BP神经网络的电力负荷预测方法[J]. 红水河, 2022, 41 (3): 92- 96. DOI
	JIN Lili. Power load forecasting method based on GRA-SSA-BP neural network[J]. Hongshui River, 2022, 41 (3): 92- 96. DOI
23	梁海维, 王阳光, 邓小亮, 等. 基于分段预测及天气相似日选择的区域电网短期负荷预测方法[J]. 湖南电力, 2024, 44 (5): 109- 116. DOI
	LIANG Haiwei, WANG Yangguang, DENG Xiaoliang, et al. Short-term load forecasting method for regional power grid based on segmented prediction and weather similar day selection[J]. Hunan Electric Power, 2024, 44 (5): 109- 116. DOI
24	王晓东, 李清, 付德义, 等. 基于卷积双向长短期记忆网络的风电机组传动系统疲劳载荷预测[J]. 中国电力, 2025, 58 (4): 90- 97. DOI
	WANG Xiaodong, LI Qing, FU Deyi, et al. Fatigue load prediction of wind turbine drive train based on CNN-BiLSTM[J]. Electric Power, 2025, 58 (4): 90- 97. DOI
25	吴辉, 邹子威, 肖丰明, 等. 基于BiLSTM与自注意力机制生成对抗网络的GSA防护方法[J]. 中国电力, 2024, 57 (9): 61- 70. DOI
	WU Hui, ZOU Ziwei, XIAO Fengming, et al. Defense method for smart grid GPS spoofing attack based on BiLSTM and self-attention mechanism generative adversarial network[J]. Electric Power, 2024, 57 (9): 61- 70. DOI
26	高芷蓉, 杨杉, 喻希, 等. 基于CNN-BiLSTM-Attention的电力系统虚假数据注入攻击检测[J]. 智慧电力, 2025, 53 (4): 103- 111. DOI
	GAO Zhirong, YANG Shan, YU Xi, et al. False data injection attack detection in power systems based on CNN-BiLSTM-attention[J]. Smart Power, 2025, 53 (4): 103- 111. DOI
27	田书欣, 韩雪. 基于正交小波变换的LSTM-ARIMA海上风速组合预测模型[J]. 智慧电力, 2023, 51 (7): 39- 43, 50. DOI
	TIAN Shuxin, HAN Xue. LSTM-ARIMA offshore wind speed combined prediction model based on orthogonal wavelet transform[J]. Smart Power, 2023, 51 (7): 39- 43, 50. DOI
28	ZHOU R Y, ZHANG X C. Short-term power load forecasting based on ARIMA-LSTM[J]. Journal of Physics: Conference Series, 2024, 2803 (1): 012002. DOI
29	王晨, 李又轩, 吴其琦, 等. 基于SVM-STL-LSTM的区域短期电力负荷预测研究[J]. 水电能源科学, 2024, 42 (4): 215- 218. DOI
	WANG Chen, LI Youxuan, WU Qiqi, et al. Research on regional short-term load forecasting based on SVM-STL-LSTM[J]. Water Resources and Power, 2024, 42 (4): 215- 218. DOI
30	WANG Z X, KU Y Y, LIU J. The power load forecasting model of combined SaDE-ELM and FA-CAWOA-SVM based on CSSA[J]. IEEE Access, 2024, 12, 41870- 41882. DOI
31	李鹏, 罗湘淳, 孟庆伟, 等. 基于Spearman相关性阈值寻优和VMD-LSTM的用户级综合能源系统超短期负荷预测[J]. 全球能源互联网, 2024, 7 (4): 406- 420. DOI
	LI Peng, LUO Xiangchun, MENG Qingwei, et al. Ultra short-term load forecasting of user level integrated energy system based on spearman threshold optimization and variational mode decomposition and long short-term memory[J]. Journal of Global Energy Interconnection, 2024, 7 (4): 406- 420. DOI
32	郑巧兰, 林燕薇, 王景周. P值大小不等价于差异或相关性大小[J]. 数理医药学杂志, 2024, 37 (3): 158- 163. DOI
	ZHENG Qiaolan, LIN Yanwei, WANG Jingzhou. The size of P value does not equal to the magnitude of difference or correlation[J]. Journal of Mathematical Medicine, 2024, 37 (3): 158- 163. DOI
33	王宇飞, 杜桐, 边伟国, 等. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57 (6): 121- 130. DOI
	WANG Yufei, DU Tong, BIAN Weiguo, et al. Short-term load forecasting based on DTW K-medoids and VMD multi-branch neural network for multiple users[J]. Electric Power, 2024, 57 (6): 121- 130. DOI

[1]	陈庆斌, 杨耿煌, 耿丽清, 苏娟, 孙京生. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
[2]	但扬清, 王蕾, 郑伟民, 武佳卉, 王晨轩, 余高旺. 高比例可再生能源接入背景下电网承载能力鲁棒提升策略[J]. 中国电力, 2023, 56(9): 104-111.
[3]	罗超月岭, 李智威, 徐祯雨, 唐学军, 李黎, 方钊. 配电网设备资产运检成本影响因素评价分析[J]. 中国电力, 2023, 56(7): 216-227.
[4]	徐一伦, 张彬桥, 黄婧, 谢枭, 王若昕, 沈丹青, 何丽娜, 杨凯帆. 考虑天气类型和相似日的IWPA-LSSVM光伏发电功率预测[J]. 中国电力, 2023, 56(2): 143-149.
[5]	王晶, 袁懿, 邵尹池, 张晋奇, 丁然, 巩彦江. 考虑资源储备度的主动配电网多目标集群划分与电压控制方法[J]. 中国电力, 2023, 56(12): 69-79.
[6]	张娜, 任强, 刘广忱, 郭力萍, 李静宇. 基于VMD-GWO-ELMAN的光伏功率短期预测方法[J]. 中国电力, 2022, 55(5): 57-65.
[7]	贾睿, 杨国华, 郑豪丰, 张鸿皓, 柳萱, 郁航. 基于自适应权重的CNN-LSTM&GRU组合风电功率预测方法[J]. 中国电力, 2022, 55(5): 47-56,110.
[8]	王新刚, 朱彬若, 顾臻. 基于综合能源计量大数据的中长期用电量预测[J]. 中国电力, 2021, 54(10): 211-216.
[9]	韩俊, 韩文花, 陈曦, 王娜, 车倩倩, 苏晓燕. 基于熵权-灰色关联分析的降低区域停电损失举措研究[J]. 中国电力, 2020, 53(5): 10-17.
[10]	肖帅, 张岩, 章德, 禹海峰, 李梦骄. 风电群输电规划评价指标体系和方法[J]. 中国电力, 2019, 52(10): 115-122.
[11]	邓博, 徐鸿, 郭鹏, 张乃强, 倪永中. 变负荷下超（超）临界机组过热器壁温预测[J]. 中国电力, 2018, 51(3): 13-20.
[12]	党杰, 张文朝, 王少博, 奚江惠, 徐友平, 陆勇, 顾雪平, 潘艳. 基于灰色关联分析法的电压稳定故障筛选与排序[J]. 中国电力, 2017, 50(4): 71-76.
[13]	龙禹, 王小英, 周琪, 姜楠, 罗欣. 考虑不同发展情境的江苏省中长期电力需求预测[J]. 中国电力, 2016, 49(7): 72-76.
[14]	杨锡运，任杰，肖运启. 基于粗糙集的光伏输出功率组合预测模型[J]. 中国电力, 2016, 49(12): 133-138.
[15]	陈武，肖先勇. 短期母线负荷优性组合预测方法及其在成都电网中的应用[J]. 中国电力, 2015, 48(8): 97-103.

考虑气象敏感性的相似日用电量预测

Similar-Day Electricity Consumption Prediction Considering Meteorological Sensitivity

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 33

相关文章 15

编辑推荐

Metrics

模态框（Modal）标题

考虑气象敏感性的相似日用电量预测

Similar-Day Electricity Consumption Prediction Considering Meteorological Sensitivity

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 33

相关文章 15

编辑推荐

Metrics