Peak load forecasting in midsummer based on mechanism analysis of the&#x0FF02;Four Effects&#x0FF02;and time-series large models

Qing LIU; Xingpei JI; Peipei YOU; Xinyang HAN; Yaohua WANG; Baoguo SHAN

doi:10.11930/j.issn.1004-9649.202607100

Electric Power ›› 2026, Vol. 59 ›› Issue (8) : 30-38. DOI: 10.11930/j.issn.1004-9649.202607100

Original article

Peak load forecasting in midsummer based on mechanism analysis of the＂Four Effects＂and time-series large models

Qing LIU ¹^,² ,
Xingpei JI ¹ ,
Peipei YOU ¹ ,
Xinyang HAN ¹ ,
Yaohua WANG ¹ ,
Baoguo SHAN ¹

Author information +

History +

Abstract

In midsummer extreme heat waves occur frequently， and electricity demand surges to its annual peak，posing the greatest pressure and the highest uncertainty for power supply security.To accurately forecast the midsummer peak load and enhance prediction interpretability，this paper proposes a dual- path forecasting method that integrates mechanism analysis of the＂Four Effects＂with time-series large models.In the mech- anism analysis path，based on load composition theory，the total load is decomposed into base load and cooling load，which respectively characterize the economic growth effect，rest-day effect，temperature-rise effect，and accumulation effect.His- torical data of the summer peak load in 2025 are reviewed and decomposed，and then each effect component for midsummer 2026 is extrapolated to obtain the peak load forecast.In the data-driven path，the Chronos-2 time-series large model is adopted，integrating multi-source information including economic，meteorological，and calendar data for daily peak load forecasting.It is compared with patch time series transformer and light gradient boosting machine algorithms to select the best performer，and the mechanistic and data-driven paths are cross-validated against each other.The results show that， considering the latest economic and climatic conditions，the maximum load of a certain regional power grid in midsummer 2026 is 1305 GW，consisting of a base load of 934 GW （economic growth effect 934 GW，rest-day effect 0 GW）and a cooling load of 371 GW（temperature-rise effect 340 GW， accumulation effect 31 GW）.The time-series large model performs best on the test set，with a mean absolute percentage error of only 1.64％，and forecasts a peak load of 1306 GW， which is highly consistent with the conclusion of the＂Four Effects＂，thus verifying the reliability of the proposed method. This work is supported by National Key Research and Development Program of China（No.2024YFF0809200）.

Key words

Four Effects / mechanism analysis / time-series large models / midsummer / peak load forecasting

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Qing LIU , Xingpei JI , Peipei YOU , et al . Peak load forecasting in midsummer based on mechanism analysis of the＂Four Effects＂and time-series large models[J]. Electric Power. 2026, 59(8): 30-38 https://doi.org/10.11930/j.issn.1004-9649.202607100

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis

[1]	袁家海, 张凯, 张健, 等. 极端高温天气下电力系统韧性提升策略[J]. 发电技术, 2025, 46(4):694-704. YUAN Jiahai, ZHANG Kai, ZHANG Jian, et al. Resilience enhancement strategies for power systems under extreme high-temperature weather[J]. Power Generation Technology, 2025, 46(4): 694-704. Cited in this article [1]

[2]	王耀华, 李晓纯, 杨宇, 等. 全球能源转型与地缘环境的交互关系[J]. 中国电力, 2025, 58(12):1-13. WANG Yaohua, LI Xiaochun, YANG Yu, et al. Interactions between global energy transition and geopolitical environment[J]. Electric Power, 2025, 58(12):1-13. Cited in this article [1]

[3]	曹恩惠, 费心懿, 余名伟. 极端高温,＂炙烤＂中欧电网[N]. 21世纪经济报道,2025-07-15(10). Cited in this article [1]

[4]	张献方. 电网度夏向＂新＂向＂智＂转型[N]. 国家电网报,2025-09-15(1). Cited in this article [1]

[5]	李丽旻. 欧洲电力系统再临＂烤＂验[N]. 中国能源报,2025-07-28(5). Cited in this article [1]

[6]	董梓童. 极端高温＂烤＂验欧洲电网[N]. 中国能源报,2026-06-29(5). Cited in this article [1]

[7]

赵子健, 马志远, 陈星, 等. 气候变化下中国跨省互联对电网供需平衡的影响评估[J/OL]. 中国电力,1-11[2026-07-22].

https://link.cnki.net/urlid/11.3265.tm.20260703.1643.003.

ZHAO

Zijian

, MA

Zhiyuan

, CHEN

Xing

, et al. Evaluating the Role of China Inter-Provincial Grid Interconnection in Power System Supply-demand Match Considering Climate Change Impacts[J/OL]. Electric Power,1-11[2026-07-22].

https://link.cnki.net/urlid/11.3265.tm.20260703.1643.003.

Cited in this article [1]

[8]

韦于思, 周颖, 商永朋, 等. 能源气候韧性下用电敏感行业识别与负荷预测[J]. 煤炭经济研究, 2025, 45(11):15-23.

WEI

Yusi

, ZHOU

Ying

, SHANG

Yongpeng

, et al. Identification and peak load forecasting of sensitive electricity-consuming industries under energy-climate challenges[J]. Coal Economic Research, 2025, 45(11):15-23.

Cited in this article [1]

[9]	PAULOS J P, AZEVEDO F, FIDALGO J N. Feature-engineered long-term hourly load forecasting with climatic uncertainty integration[J]. Electric Power Systems Research, 2026, 260: 113375. Cited in this article [1]

[10]	汲国强, 段金辉, 吴姗姗, 等. 2026 年及＂十五五＂全国电力供需形势分析展望[J]. 中国电力,2026, 59(2):13-23. JI Guoqiang, DUAN Jinhui, WU Shanshan, et al. Analysis and outlook on national power supply-demand situation for 2026 and the 15th Five-Year Plan period[J]. Electric Power, 2026, 59(2):13-23. Cited in this article [1]

[11]

白婕, 秦晓辉, 许彦平, 等. 基于气候因素和社会经济指标的长期电力负荷时序预测方法[J/OL]. 电网技术,1-15[2026-07-23].https://doi.org/10.13335/j.1000-3673.pst.2025.1765.

BAI

Jie

, QIN

Xiaohui

, XU

Yanping

, et al Long-term power load time series forecasting method based on climate factors and socioeconomic indicators[J/OL]. Power System Technology,1-15 [2026-07-23].https://doi.org/10.13335/j.1000-3673.pst.2025.1765.

Cited in this article [1]

[12]	刘添, 张士宁, 翁宇威, 等. 中国电力消费不均衡性变化及时空演化机理分析[J]. 中国电力, 2026, 59(6):13-23. LIU Tian, ZHANG Shining, WENG Yuwei, et al. Analysis on the spatiotemporal evolution mechanism of electricity consumption inequality in China[J]. Electric Power, 2026, 59(6):13-23. Cited in this article [1]

[13]	HASSANPOURI BAESMAT K, SHOKOOHI F, FARROKHI Z. SP-RF-ARIMA:a sparse random forest and ARIMA hybrid model for electric load forecasting[J]. Global Energy Interconnection, 2025, 8(3):486-496. Cited in this article [1]

[14]	于军琪, 聂己开, 赵安军, 等. 基于特征挖掘的 ARIMA-GRU 短期电力负荷预测[J]. 电力系统及其自动化学报, 2022,34(3): 91-99. YU Junqi,NIE Jikai,ZHAO Anjun,et al. ARIMA-GRU short-term power load forecasting based on feature mining[J]. Proceedings of the CSU-EPSA,2022, 34(3):91-99. Cited in this article [1]

[15]

姜山, 周秋鹏, 董弘川, 等. 考虑数据周期性及趋势性特征的长期电力负荷组合预测方法[J]. 电测与仪表, 2022, 59(6):98-104.

JIANG

Shan

, ZHOU

Qiupeng

, DONG

Hongchuan

, et al. Long-term load combination forecasting method considering the periodicity and trend of data[J]. Electrical Measurement＆Instrumentation, 2022, 59(6):98-104.

Cited in this article [1]

[16]	AASIM, SINGH S N,MOHAPATRA A.Data driven day-ahead electrical load forecasting through repeated wavelet transform assisted SVM model[J]. Applied Soft Computing, 2021, 111: 107730. Cited in this article [1]

[17]	刘岩, 彭鑫霞, 郑思达. 基于改进 LS-SVM 的短期电力负荷预测方法研究[J]. 电测与仪表, 2021, 58(5):176-181. LIU Yan, PENG Xinxia, ZHENG Sida. Research on short-term power load forecasting method based on improved LS-SVM[J]. Electrical Measurement＆Instrumentation, 2021, 58(5):176-181. Cited in this article [1]

[18]	陈逸枞, 张大海, 李宇欣, 等. 基于 DWT-MOSMA-SVM 的多目标优化短期母线负荷预测[J]. 电力建设, 2023, 44(3):49-55. CHEN Yicong, ZHANG Dahai, LI Yuxin, et al. Multi-objective optimization based on DWT-MOSMA-SVM for short-term bus load forecasting[J]. Electric Power Construction, 2023, 44(3):49-55. Cited in this article [1]

[19]	GONG J Q, QU Z G, ZHU Z L, et al. Ensemble models of TCN-LSTM-LightGBM based on ensemble learning methods for short-term electrical load forecasting[J]. Energy, 2025, 318: 134757. Cited in this article [1]

[20]

李娜, 张湘涵, 刘淇淇, 等. 基于气象要素的 LightGBM 短期电力负荷预测研究[J]. 节能技术, 2026, 44(2):115-119, 154.

, ZHANG

Xianghan

, LIU

Qiqi

, et al. Study on short-term power load forecasting based on meteorological factors with LightGBM[J]. Energy Conservation Technology, 2026, 44(2): 115-119, 154.

Cited in this article [1]

[21]

徐岩, 张晓, 周兴华, 等. 基于 Prophet-LightGBM 的台区短期负荷预测方法[J]. 华北电力大学学报(自然科学版), 2024, 51(6): 13-19.

Yan

, ZHANG

Xiao

, ZHOU

Xinghua

, et al. The short-term load forecasting method of transformer based on Prophet-LightGBM[J]. Journal of North China Electric Power University, 2024, 51(6): 13-19.

Cited in this article [1]

[22]	张未, 余成波, 王士彬, 等. 基于 VMD-LSTM-LightGBM 的多特征短期电力负荷预测[J]. 南方电网技术, 2023, 17(2):74-81. ZHANG Wei, YU Chengbo, WANG Shibin, et al. Multi-featured short-term power load forecasting based on VMD-LSTM-LightGBM[J]. Southern Power System Technology, 2023, 17(2): 74-81. Cited in this article [1]

[23]	SHAWON S M, HAIDER S N, BARUA A, et al. Hybrid CNN-LSTM model for urban energy load forecasting with IGA-XAI for smart grids:Peak and off-peak variability insights[J]. Results in Engineering, 2025, 28: 107245. Cited in this article [1]

[24]

张桂林. 基于多尺度分解和 ICOA-KConvLSTM 的短期电力负荷预测[J/OL]. 中国电力,1-10[2026-07-24.

https://link.cnki.net/urlid/11.3265.TM.20260226.1507.002.

ZHANG

Guilin

. Short-term power load forecasting based on multi-scale decomposition and ICOA-KConvLSTM[J/OL]. Electric Power, 1-10[2026-07-24].

https://link.cnki.net/urlid/11.3265.TM.20260226.1507.002.

Cited in this article [1]

[25]	张家安, 李凤贤, 王铁成, 等. 一种采用记忆神经网络和曲线形状修正的负荷预测方法[J]. 电力工程技术, 2024, 43(1):117-126. ZHANG Jiaan, LI Fengxian, WANG Tiecheng, et al. A load prediction method using memory neural network and curve shape correction[J]. Electric Power Engineering Technology, 2024, 43(1): 117-126. Cited in this article [1]

[26]

周阔, 张鹏超, 王磊, 等. 基于最大信息系数与优化 VMD 的 DCN-BiLSTM 短期电力负荷预测[J/OL]. 中国电力,1-10[2026-07-28].

https://link.cnki.net/urlid/11.3265.tm.20260616.1932.002.

ZHOU

Kuo

, ZHANG

Pengchao

, WANG

Lei

, et al. Maximum information coefficient-guided DCN-BiLSTM with optimized VMD for short-term power load forecasting[J/OL]. Electric Power,1-10[2026-07-28].

https://link.cnki.net/urlid/11.3265.tm.20260616.1932.002.

Cited in this article [2]

[27]	QU Z J, MENG Y, HOU X X, et al. Integrated energy short-term multivariate load forecasting based on PatchTST secondary decoupling reconstruction for progressive layered extraction multi-task learning network[J]. Expert Systems with Applications, 2025, 269: 126446. Cited in this article [1]

[28]

杨韵, 程永峰, 谢祥中, 等. 含分布式储能系统的主动配电网负荷预测模型构建[J]. 储能科学与技术, 2026, 15(4):1302-1311.

YANG

Yun

, CHENG

Yongfeng

, XIE

Xiangzhong

, et al. Construction of an active distribution network load forecasting model with distributed energy storage system[J]. Energy Storage Science and Technology, 2026, 15(4):1302-1311.

Cited in this article [1]

[29]

章莉, 王吉文, 张炜, 等. 基于 MOP-PatchTST 的分布式电源与负荷资源协同控制研究[J/OL]. 南京信息工程大学学报,1-15[2026-07-28].https://doi.org/10.13878/j.cnki.jnuist.20250428002.

ZHANG

, WANG

Jiwen

, ZHANG

Wei

et al. Research on cooperative control of distributed generation and load resourcesbased on MOP-PatchTST[J/OL]. Journal of Nanjing University of Information Science and Technology,1-15[2026-07-28].

https://doi.org/10.13878/j.cnki.jnuist.20250428002.

Cited in this article [1]

[30]	战泓伊. 基于 QR-PatchTST 的综合能源系统多元负荷概率预测[D]. 吉林: 东北电力大学, 2025. ZHAN Hongyi. Probabilistic load forecasting for integrated energy systems based on quantile regression patch time series transformer[D]. Jilin:Northeast Electric Power University, 2025. Cited in this article [1]

[31]

, ADAM

N A

, SHAKARALIYEVA

, et al. A deep reinforcement learning for joint short term electricity load and price forecasting in China＇s smart grids:Evidence from energy economics, market volatility and financial risk management[J]. Energy Strategy Reviews, 2026, 66: 102322.

Cited in this article [1]

[32]

邱敏, 王阳, 李建锋, 等. 新型电力系统负荷预测技术综述及基于数据空间的架构展望[J]. 全球能源互联网, 2026, 9(3):371-391.

QIU

Min

, WANG

Yang

, LI

Jianfeng

, et al. A review of load forecasting technologies for new power systems and architecture outlook based on data space[J]. Journal of Global Energy Interconnection, 2026, 9(3):371-391.

Cited in this article [1]

[33]	马恒瑞, 袁傲添, 王波, 等. 基于深度学习的负荷预测研究综述与展望[J]. 高电压技术, 2025, 51(3):1233-1250. MA Hengrui, YUAN Aotian, WANG Bo, et al. Review and prospect of load forecasting based on deep learning[J]. High Voltage Engineering, 2025, 51(3):1233-1250. Cited in this article [1]