极端气温事件对多类型电力负荷的影响研究进展

靳双龙; 成丹; 任永建

doi:10.16516/j.ceec.2025-270

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

极端气温事件对多类型电力负荷的影响研究进展

极端气候事件下的能源与交通韧性 | 更新时间：2026-10-14

- 极端气温事件对多类型电力负荷的影响研究进展
- Research Progress on the Impact of Extreme Temperature Events on Multiple Types of Electric Loads
- 南方能源建设 2026年13卷第3期页码：20-31
- 作者机构：
  
  1. 可再生能源并网全国重点实验室（中国电力科学研究院有限公司）,北京,100192
  2. 湖北省气象服务中心,湖北,武汉,430205
- 作者简介：
- 基金信息：
  
  中国电力科学研究院长线攻关项目“融合气象的输电通道气象环境灾害预测预警技术研究”（NY83-24-001）
- DOI：10.16516/j.ceec.2025-270
  中图分类号： TM7;TM714
- 纸质出版：2026
- 稿件说明：
移动端阅览
靳双龙, 成丹, 任永建. 极端气温事件对多类型电力负荷的影响研究进展[J]. 南方能源建设, 2026, 13(3): 20-31.

.
靳双龙, 成丹, 任永建. 极端气温事件对多类型电力负荷的影响研究进展[J]. 南方能源建设, 2026, 13(3): 20-31. DOI： 10.16516/j.ceec.2025-270.

. DOI： 10.16516/j.ceec.2025-270.

摘要

目的

针对极端气温事件对电力负荷影响研究中机制碎片化、区域局限及预测调控针对性不足的问题，文章梳理了高温热浪与低温寒潮对多类型电力负荷的影响规律、预测方法及调控策略，为构建韧性电力系统、保障能源安全提供支撑。

方法

文章采用文献综述与系统分析的方法，界定高温热浪（日最高气温≥35 ℃且持续≥3 d）、低温寒潮（24 h降温≥8 ℃且最低气温≤4 ℃）及居民、工业、商业3类负荷概念，整合2022年川渝高温、2021年美国得州寒潮等典型案例，按传统统计、机器学习、深度学习分类综述预测模型，结合负荷特征提出调控策略并分析研究缺口。

结果

研究发现，极端气温事件对电力负荷的影响本质是“气象因子-用户用电行为-负荷响应”的链式过程，且差异显著：高温热浪下居民与商业空调负荷协同激增，负荷曲线呈“单峰高平台”，温度每升高1 ℃总负荷增2%～5%；低温寒潮下居民采暖负荷主导突变，负荷曲线呈“高谷值、短平峰”，温度每降低1 ℃总负荷增3%～6%；实证显示极端气温下负荷峰值较常态提升15%～40%，且低纬度地区高温敏感性、高纬度地区低温敏感性更突出；预测模型中Transformer等深度学习模型精度最优，传统统计模型可解释性强但难应对负荷非线性变化；高温需通过“错峰电价+智能温控”抑制空调负荷，低温需依托“蓄热式采暖+跨区域协同”保障采暖需求，且需政策机制支撑调控落地。

结论

极端气温事件对多类型电力负荷的影响具有显著差异化与区域特征，深度学习模型是负荷预测的优选方向，差异化调控与政策保障可有效平抑负荷波动；未来需重点突破微观负荷异质性分析、小样本突变预测及跨区域协同调控等研究缺口，进一步提升极端气温事件下电力负荷管理能力，为韧性电力系统构建提供支撑。

Abstract

Objective

Aiming at the problems of fragmented mechanisms

regional limitations and insufficient targeting of prediction and regulation in the research on the impact of extreme temperature events on el

ectric loads

this paper systematically sorts out the impact laws

prediction methods and regulation strategies of heatwaves and cold waves on multiple types of electric loads

so as to provide support for constructing a resilient power system and ensuring energy security.

Method

Using literature review and systematic analysis

this paper defined the concepts of heatwaves (daily maximum temperature ≥35 ℃ and duration ≥3 days)

cold waves (24-hour temperature drop ≥8 ℃ and minimum temperature ≤4 ℃) and three types of loads (residential

industrial and commercial). It integrated typical cases such as the 2022 Sichuan-Chongqing heatwave and the 2021 Texas (USA) cold wave

reviews prediction models by categorizing them into traditional statistical models

machine learning models and deep learning models

and proposed regulation strategies combined with load characteristics while analyzing research gaps.

Result

The study finds that the impact of extreme temperature events on electric loads is essentially a chain process of "meteorological factors - user energy consumption behavior - load response" with significant differences: Under heatwaves

residential and commercial air-conditioning loads surge synergistically

the load curve shows a "single-peak high platform" pattern

and the total load increases by 2%～5% for every 1 ℃ rise in temperature; Under cold waves

residential heating loads dominate the sudden change

the load curve shows a "high valley

short flat peak" pattern

and the total load increases by 3%～6% for every 1 ℃ drop in temperature. Empirical evidence shows that the peak load increases by 15%～40% compared with the normal state under extreme temperatures

with higher heat sensitivity in low-latitude regions and higher cold sensitivity in high-latitude regions. Among prediction models

deep learning models such as Transformer have the highest accuracy

while traditional statistical models have strong interpretability but struggle to cope with the nonlinear changes of loads. For

heatwaves

air-conditioning loads need to be suppressed through "time-of-use pricing + intelligent temperature control"; For cold waves

heating demand needs to be guaranteed by "heat storage heating + cross-regional coordination"

and the implementation of regulation requires support from policy mechanisms.

Conclusion

The impact of extreme temperature events on multiple types of electric loads has significant differentiated and regional characteristics. Deep learning models are the preferred direction for load prediction

and differentiated regulation and policy guarantees can effectively stabilize load fluctuations. In the future

it is necessary to focus on breaking through research gaps such as micro load heterogeneity analysis

small-sample sudden change prediction and cross-regional coordinated regulation to further improve the management capacity of electric loads under extreme temperature events and provide support for the construction of a resilient power system.

关键词

Keywords

references

IPCC. Sixth assessment report of the Intergovernmental Panel on Climate Change [R]. Geneva: IPCC, 2023.

National Energy Administration. Work summary of electricity supply guarantee in the Sichuan-Chongqing region in 2022 [R]. Beijing: National Energy Administration, 2022.

ERCOT. 2021 Winter storm Uri preliminary report [R ] . Austin: Electric Reliability Council of Texas, 2021.

ZHANG J, YAN Z H, ZHANG D Q, et al. Design and application research of an interactive fusion system of multi-source data of electric power and meteorology [J]. Power systems and big data, 2025, 28(2): 83-92. DOI: 10.19317/j.cnki.1008-083x.2025.02.010.

YUAN J H, ZHANG K, ZHANG J, et al. Resilience enhancement strategies for power systems under extreme high-temperature weather [J]. Power generation technology, 2025, 46(4): 694-704. DOI: 10.12096/j.2096-4528.pgt.25089.

SCHOOF J T, FORD T W, PRYOR S C. Recent changes in U. S. regional heat wave characteristics in observations and reanalyses [J]. Journal of applied meteorology and climatology, 2017, 56(9): 2621-2636. DOI: 10.1175/jamc-d-16-0393.1.

YU S, HUANG F X, FENG Y L, et al. Neural prophet-based power load forecasting and repair in novel power AMI system [J]. Smart power, 2023, 51(5): 44-50. DOI: 10.3969/j.issn.1673-7598.2023.05.008.

China Meteorological Administration. Regulations on monitoring operations of extreme weather and climate events [R]. Beijing: China Meteorological Administration, 2017.

NOAA. National weather service criteria for heat waves and cold waves [R ] . Washington D. C. : National Oceanic and Atmospheric Administration, 2020.

ZHANG Y X, HUANG X J, ZHENG D Y. Temporal and spatial characteristics of heat waves and assessment of vulnerability in the Yangtze River economic belt [J]. Resources and environment in the Yangtze basin, 2023, 32(2): 440-450. DOI: 10.11870/cjlyzyyhj202302019.

QIAO N, YIN Y X, ZHANG P, et al. Trend, driving factors and temperature-humidity relationship of the extreme compound hot and humid events in South China [J]. Theoretical and applied climatology, 2024, 155(5): 4213-4230. DOI: 10.1007/s00704-024-04876-z.

LEEPER R D, HARRINGTON T, PALECKI M A, et al. The influence of drought on heat wave intensity, duration, and exposure [J]. Journal of applied meteorology and climatology, 2025, 64(5): 425-438. DOI: 10.1175/jamc-d-24-0072.1.

TANG D L, SHI J L, XU Z R, et al. Residential air conditioning load regulation methods for power supply guarantee in extreme high temperature conditions [J]. Distribution utilization, 2025, 42(5): 91-99. DOI: 10.19421/j.cnki.1006-6357.2025.05.010.

MAO W Y, LIU J Y, XU L X, et al. Day-ahead load management optimization for an urban power grid in extreme temperature conditions with dual power and energy shortages [J]. Power system protection and control , 2025, 53(6): 15-29. DOI: 10.19783/j.cnki.pspc.240401.

YANG X L, GUO X M, LU Y, et al. Load forecasting algorithm of smart grid considering temperature cumulative effect [J]. Journal of Shenyang University of Technology, 2024, 46(2): 121-126. DOI: 10.7688/j.issn.1000-1646.2024.02.01.

XU J, CHI F J, GE L J, et al. Short-term combined commercial load forecasting method based on SARIMA-GRNN-SVM [J]. Proceedings of the CSU-EPSA, 2020, 32(2): 85-91. DOI: 10.19635/j.cnki.csu-epsa.000353.

LIAO S Y, XIAO Y D, XU J, et al. Economic dispatch model considering production process of energy-intensive industrial load under demand response [J]. Automation of electric power systems, 2025, 49(3): 22-30. DOI: 10.7500/AEPS20240414003.

LI D, HE S, YAN W, et al. Annual daily average load curve prediction considering dynamic time anchors and typical feature constraints [J]. Electric power, 2024, 57(11): 36-47. DOI: 10.11930/j.issn.1004-9649.202308114.

LI Y, YU J W, CAI X N, et al. Characteristics of electric loads in Nanjing and relationship between extreme loads and meteorological conditions in summer [J]. Meteorological science and technology, 2021, 49(4): 637-646. DOI: 10.19517/j.1671-6345.20200259.

WANG N, XIE Z Q, GAO P, et al. Differences in spatiotemporal variation and risk zoning of four types of extreme cold events in Jiangsu province [J]. Acta meteorologica sinica, 2023, 81(1): 110-123. DOI: 10.11676/qxxb2023.20220058.

CHEN Z L, LIU X, LIU J C, et al. Research on regional heating load in Northeast China [J]. Northeast electric power technology, 2025, 46(8): 49-54. DOI: 10.3969/j.issn.1004-7913.2025.08.011.

LIU J, WANG L J, CHENG D, et al. Characteristics of power load in Wuhan and its relationship with meteorological factors [J]. Torrential rain and disasters, 2023, 42(2): 232-240. DOI: 10.12406/byzh.2023-022.

ZHOU D, XU H M, AI W X, et al. The impact of high temperature and drought events in the Sichuan and Chongqing region during summer 2022 on the power supply and demand [J]. Journal of meteorological research and application, 2024, 45(1): 6-11. DOI: 10.19849/j.cnki.CN45-1356/P.2024.1.02.

National Climate Center, China Meteorological Administration. China climate bulletin 2023 [R]. Beijing: China Meteorological Administration, 2024.

CHEN T, LIU J N. High-temperature disaster resilience evaluation and promotion in Guangdong-Hong Kong-Macao Greater Bay Area [J]. Shanghai urban planning review, 2023, 1(1): 9-17. DOI: 10.11982/j.supr.20230102.

European Environment Agency. Heat waves in Europe: impacts on health and the environment [R ] . Copenhagen: European Environment Agency, 2023.

REN21. Renewable energy policy network for the 21st Century annual report 2023 [R ] . Paris: REN21, 2023.

China Meteorological Administration. Bulletin on national extreme weather events in November 2021 [R]. Beijing: China Meteorological Administration, 2021.

State Grid Corporation of China. Report on electric power supply guarantee during the northern China cold wave in 2021 [R]. Beijing: State Grid Corporation of China, 2021.

U. S. Department of Energy. Review of the February 2021 Texas power outages [R ] . Washington D. C. : U. S. Department of Energy, 2021.

WANG F H, ZHOU H F, ZHANG P, et al. Effects of meteorological factors on electrical load and the forecasting of electrical load [J]. Journal of meteorology and environment, 2020, 36(4): 104-111. DOI: 10.3969/j.issn.1673-503X.2020.04.014.

LIANG R, WANG H T, WU K H, et al. Short-term forecasting of cooling, heating and power loads based on neural network and ARIMA model [J]. Proceedings of the CSU-EPSA, 2020, 32(3): 52-58. DOI: 10.19635/j.cnki.csu-epsa.000260.

GU T T, LUO Y Z, ZHANG Q, et al. Study on gas load forecast in Hangzhou based on meteorological factors [J]. Journal of meteorology and environment, 2017, 33(3): 107-112. DOI: 10.3969/j.issn.1673-503X.2017.03.014.

LI Y, JIA Y J, LI L, et al. Short term power load forecasting based on a stochastic forest algorithm [J]. Power system protection and control, 2020, 48(21): 117-124. DOI: 10.19783/j.cnki.pspc.191594.

CHEN B B, LIN R H, ZOU H. A short term load periodic prediction model based on GBDT [C]//IEEE. 2018 IEEE 18th International Conference on Communication Technology (ICCT), Chongqing, China, October 8-11, 2018. New York: IEEE, 2018: 1402-1406. DOI: 10.1109/ICCT.2018.8600009.

ZHOU S N, WU Y, DOU Y H, et al. Medium- and long-term power load forecasting in Shanxi Province based on RA-LSTM model [J]. Meteorological and environmental sciences, 2025, 48(1): 78-87. DOI: 10.16765/j.cnki.1673-7148.2025.01.009.

ZENG Y J, XIAO X Y, XU F W, et al. A short-term load forecasting method based on CNN-BiGRU-NN model [J]. Electric power, 2021, 54(9): 17-23. DOI: 10.11930/j.issn.1004-9649.202003035.

ZHANG S, LIU W X, TANG H Y, et al. Short-term load forecasting method based on multi-feature fusion using Transformer [J]. Journal of North China Electric Power University, 2025, 52(3): 68-75, 83. DOI: 10.3969/j.ISSN.1007-2691.2025.03.07.

GAO J X, CHEN Y T, HU W B, et al. An adaptive deep-learning load forecasting framework by integrating transformer and domain knowledge [J]. Advances in applied energy, 2023, 10: 100142. DOI: 10.1016/j.adapen.2023.100142.

HUANG W Q, LIANG L Y, WANG X, et al. Mid-long term power load forecasting based variable selection and Transformer model [J]. Journal of Zhejiang University (science edition), 2024, 51(4): 483-491, 500. DOI: 10.3785/j.issn.1008-9497.2024.04.011.

National Development and Reform Commission (NDRC). Notice on further improving the time-of-use electricity pricing mechanism [R ] . Beijing: National Development and Reform Commission (NDRC), 2021.

China Electricity Council (CEC). China electric power industry development report 2023 [R]. Beijing: China Electricity Council (CEC), 2023.

China Meteorological Administration (CMA), National Energy Administration (NEA). Cooperation agreement on information sharing between the meteorological and electric power industries [R]. Beijing: China Meteorological Administration (CMA), National Energy Administration (NEA), 2022.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向火电调频的双电层电容器储能系统设计与特性试验

混合型超级电容器在火电调频场景中的应用技术

碳电市场耦合机制研究综述：模型分类、联动路径与挑战展望

循环多轨斜坡重力储能技术方案研究与模块化设计

深地储气与压缩空气储能数值模拟研究进展