基于实时与累积气象因素的广州电力高峰负荷贡献度分析

王凌梓; 赵益帆; 王在文; 陈敏; 周荣卫

doi:10.16516/j.ceec.2026-105

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 >

基于实时与累积气象因素的广州电力高峰负荷贡献度分析

极端气候事件下的能源与交通韧性 | 更新时间：2026-10-14

- 基于实时与累积气象因素的广州电力高峰负荷贡献度分析
- Contribution Analysis of Guangzhou's Peak Electrical Load Based on Real-Time and Cumulative Meteorological Factors
- 南方能源建设 2026年13卷第3期页码：69-81
- 作者机构：
  
  1. 中国南方电力调度控制中心,广东,广州,510663
  2. 北京城市气象研究院,北京,100089
- 作者简介：
  
  王凌梓，ORCID: 0009-0008-6426-292X1991-，女，高级工程师，硕士，主要从事电网气象业务工作（e-mail）wanglz2@csg.cn
  赵益帆，（e-mail）zyf19951103@foxmail.com
- 基金信息：
  
  中国南方电网有限公司项目“能源供需紧张形势下的负荷预测与智能监管关键技术研究”（WT0000330000000412）
- DOI：10.16516/j.ceec.2026-105
  中图分类号： TM7;P49
- 纸质出版：2026
- 稿件说明：
移动端阅览
王凌梓, 赵益帆, 王在文, 等. 基于实时与累积气象因素的广州电力高峰负荷贡献度分析[J]. 南方能源建设, 2026, 13(3): 69-81.

.
王凌梓, 赵益帆, 王在文, 等. 基于实时与累积气象因素的广州电力高峰负荷贡献度分析[J]. 南方能源建设, 2026, 13(3): 69-81. DOI： 10.16516/j.ceec.2026-105.

. DOI： 10.16516/j.ceec.2026-105.

摘要

目的

针对城市电力高峰负荷与气象条件耦合关系日趋复杂的问题，文章旨在厘清负荷对气象要素实时响应与累积响应的内在机制。

方法

基于 2020－2025 年广州市工作日逐小时电力负荷及同期气象观测数据，引入小时尺度热积温效应，结合相关性分析与极端梯度提升（eXtreme Gradient Boosting，XGBoost）算法，量化实时、累积气象因子对电力高峰负荷的协同作用及贡献差异。

结果

研究显示：积温效应、温度、湿度、气压和经向风速是广州高峰负荷的关键气象因子，“高温-高湿-强积温-低气压-弱风速”的气象组合易诱发高峰负荷。气象因素影响具有显著的温度区间依赖性，随温度升高，实时气象因素与高峰负荷的相关性呈“先升后降”特征，而积温效应与高峰负荷的相关性持续增强。基于小时尺度特征因素构建的分季节XGBoost负荷预测模型平均绝对百分比误差（Mean Absolute Percentage Error，MAPE）均低于2.9%，解释方差比例（

）均大于0.92。基于SHAP分析的高峰时段负荷预测特征重要性表明，积温效应与历史负荷是影响春季、夏季和秋季负荷的核心因子，实时湿度在春季、秋季作用突出，冬季负荷则主要受历史负荷惯性调控。

结论

研究结果可为气候相似地区电力负荷预测模型的因子筛选与精细化调度提供依据，为计及气象实时和累积效应的负荷预测技术发展提供参考。

Abstract

Objective

Aiming at the increasingly complex coupling between urban peak power load and meteorological conditions

this paper explores the internal mechanism of peak load responding to real-time and cumulative meteorological factors.

Method

Based on hourly load data and meteorologi

cal observations from workdays in Guangzhou from 2020 to 2025

an hourly-scale accumulated temperature effect was introduced. Correlation analysis and the extreme gradient boosting (XGBoost) modeling method were employed to quantify the complex synergistic effects and contribution differences of real-time and cumulative meteorological factors on peak loads.

Result

The results indicate that the accumulated temperature effect

temperature

humidity

air pressure

and meridional wind speed are the critical meteorological drivers for peak loads in Guangzhou. The meteorological combination of high temperature

high humidity

pronounced heat accumulation effect

low air pressure

and weak wind speed is highly likely to trigger peak power loads. The effects of meteorological factors exhibit a significant temperature-dependent pattern. As temperature rises

the correlation between real-time meteorological factors and peak-hour power load follows a "rising then falling" trend

whereas the correlation between the accumulated temperature effect and peak-hour power load strengthens continuously. Seasonal XGBoost load forecasting models

constructed using hourly-scale features

achieved a mean absolute percentage error (MAPE) of less than 2.9% and an explained variance ratio (

) exceeding 0.92 for all seasons. SHAP-based feature importance analysis for peak-period load forecasting indicates that the accumulated temperature effect and historical load are core factors across spring

summer and autumn. Real-time humidity plays a prominent role during the transitional seasons of spring and autumn

while winter load is primarily regulated by historical load inertia.

Conclusion

This research supports optimized factor selection and dispatch strategies for climatically similar regions

while offering insights into load prediction methodologies that incorporate both the immediate and cumulative influences of weather factors.

关键词

Keywords

references

FENG Y, HONG G P, QIN P C, et al. Climate characteristics of the regional heat processes in Southern China from 1961 to 2024 and their impact on electricity supply and demand [J]. Southern energy construction, 2025, 12(6): 130-141. DOI: 10.16516/j.ceec.2024-400.

LI Y F, ZHANG Y, LIN F, et al. Medium-and long-term power generation forecast based on climate characterisation and an improved XGBoost algorithm for photovoltaic power plants [J]. Power system protection and control, 2024, 52(11): 84-92. DOI: 10.19783/j.cnki.pspc.231605.

WU R J, WANG D X, XIE C H, et al. Distributed control method for air-conditioning load participating in voltage management of distribution network [J]. Automation of electric power systems, 2021, 45(6): 215-222. DOI: 10.7500/AEPS20200512006.

LI B J, FU X B, SHI K P, et al. Research on ultra short term combination prediction of wind power based on adversarial neural network [J]. Power electronics, 2025, 59(10): 89-95. DOI: 10.20222/j.cnki.cn61-1124/tm.20250704.008.

LIU J, CONG L M, XIA Y Y, et al. Short-term power load prediction based on DBO-VMD and an IWOA-BILSTM neural network combination model [J]. Power system protection and control, 2024, 52(8): 123-133. DOI: 10.19783/j.cnki.pspc.231402.

ZHANG Q Q, WANG B, WANG H S, et al. Meteorological load forecasting based on growth curve and temperature accumulation effect [J]. Modern electric power, 2021, 38(2): 171-177. DOI: 10.19725/j.cnki.1007-2322.2020.0234.

LIAO C H, LUO X, XIE R H, et al. Comparative study on the forecast of the maximum daily electric load in Changsha City based on meteorological factors [J]. Journal of natural disasters, 2023, 32(1): 183-190. DOI: 10.13577/j.jnd.2023.0120.

SU Y J, GU W, ZHAO Y, et al. Load forecasting of regional power grid during the plum rains considering meteorological factors [J]. Zhejiang electric power, 2019, 38(12): 1-7. DOI: 10.19585/j.zjdl.201912001.

SU S, ZHOU L D, WAN X Z, et al. Time-sharing and classified prediction model for short-term load considering meteorological factors [J]. Electric power construction, 2017, 38(10): 76-83. DOI: 10.3969/j.issn.1000-7229.2017.10.011.

LI B, LU M Z. Short-term load forecasting modeling of regional power grid considering real-time meteorological coupling effect [J]. Automation of electric power systems, 2020, 44(17): 60-68. DOI: 10.7500/AEPS20200216001.

CHENG Z Y, YU G X, DING B H. Summer short-term load forecasting method based on improved temperature and humidity variable strategy [J]. Power system protection and control, 2020, 48(1): 48-54. DOI: 10.19783/j.cnki.pspc.190205.

LI X D, ZHANG Y, CAO Y, et al. Power and energy balance method for power system based on refined simulation [J]. Smart power, 2024, 52(10): 70-78. DOI: 10.20204/j.sp.2024.10010.

HAO Y, GUAN L, ZHANG X, et al. Establishment of prediction model of relationship between daily maximum power load rate and meteorological factors in Xi'an [J]. Journal of the meteorological sciences, 2020, 40(3): 421-426. DOI: 10.3969/2019jms.0017.

LIU D X, CHE Q, HUANG W B, et al. Research on the measurement of correlation between load and meteorological factors based on Copula-POME [J]. Water resources and power, 2020, 38(11): 23-26, 39. DOI: 10.20040/j.cnki.1000-7709.2020.11.049.

HE L W, REN Y J. Effect of meteorological factors on electric power load forecasting at different time scales [J]. Water resources and power, 2020, 38(9): 206-210. DOI: 10.20040/j.cnki.1000-7709.2020.09.051.

LIU W J, SHEN C M, GUO J H, et al. Correction method of correlation analysis model between meteorology and electric power load in summer: a case study of Beijing [J]. Journal of electric power science and technology, 2024, 39(2): 112-123. DOI: 10.19781/j.issn.1673-9140.2024.02.013.

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.

REN Y J, XIONG S Q, HONG G P, et al. Sensitivity analysis of meteorological factors to summer maximum power load [J]. Meteorological monthly, 2020, 46(9): 1245-1253. DOI: 10.7519/j.issn.1000-0526.2020.09.011.

DUONG N H, NGUYEN M T, NGUYEN T H, et al. Application of seasonal trend decomposition using loess and long short-term memory in peak load forecasting model in Tien Giang [J]. Engineering, technology applied science research, 2023, 13(5): 11628-11634. DOI: 10.48084/etasr.6181.

LUNDBERG S M, ERION G, CHEN H, et al. From local explanations to global understanding with explainable AI for trees [J]. Nature machine intelligence, 2020, 2(1): 56-67. DOI: 10.1038/s42256-019-0138-9.

CHENG D, LIU J, GUO C W, et al. Prediction of electric loads over central China based on accumulated temperature effect [J]. Meteorological science and technology, 2018, 46(4): 814-821. DOI: 10.19517/j.1671-6345.20170184.

LU S, HAO Y, WANG B P, et al. Forecasting model of meteorological power load in Xi'an in summer based on accumulated temperature effect [J]. Meteorological science and technology, 2017, 45(6): 1090-1094. DOI: 10.19517/j.1671-6345.20160597.

FU G Q, YOU F C, CAO X, et al. Application and verification of accumulated temperature effects on daily peak load and daily valley load of power [J]. Journal of applied meteorological science, 2015, 26(4): 492-499. DOI: 10.11898/1001-7313.20150411.

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

混合型超级电容器在火电调频场景中的应用技术

锂电池储能电站安全风险预警技术及工程应用综述

吸附式液态二氧化碳储能系统热经济性分析

储能技术在发电侧的综合应用与进展

循环多轨斜坡重力储能技术方案研究与模块化设计