Suzhou Electric Appliance Research Institute
期刊号: CN32-1800/TM| ISSN1007-3175

SUBSCRIPTION MANAGEMENT

发行征订

首页 >> 发行征订 >> 征订方式

基于CNN-LSTM-AM模型的短期电力负荷预测研究

来源:电工电气发布时间:2025-05-27 15:27浏览次数:9

基于CNN-LSTM-AM模型的短期电力负荷预测研究

王生1,张和茂1,王晓荣2
(1 山西大同大学 机电工程学院,山西 大同 037000;
2 国网河北省电力有限公司承德供电公司,河北 承德 067000)
 
    摘 要:为应对气象因素变化时电力负荷波动对电力系统稳定性的影响,探究了一种引入注意力机制的 CNN-LSTM 组合模型来预测短期电力负荷的波动。电力负荷受多维度气候因素的复杂耦合影响,为有效表征这些非线性、时变的气候-负荷关联特性,构建了融合温度、降水量、湿度和风速的多特征输入模型。采用卷积神经网络(CNN)捕捉数据中的局部气候模式,通过滑动窗口机制提取关键气象事件的时空特征;将特征向量输入长短期记忆(LSTM)网络,其门控机制可有效建模气候因素与负荷响应的延时效应;引入注意力机制(AM)动态量化各气候要素的时序重要性。仿真实验对比结果表明,CNN-LSTMAM 模型比传统 LSTM 和 CNN-LSTM 模型具有更好的预测精度。
    关键词: 卷积神经网络;长短期记忆;注意力机制;电力负荷预测
    中图分类号:TM715     文献标识码:A     文章编号:1007-3175(2025)05-0057-05
 
Research on Short-Term Power Load Forecasting Based on
CNN-LSTM-AM Model
 
WANG Sheng1, ZHANG He-mao1, WANG Xiao-rong2
(1 College of Mechanical and Electrical Engineering, Shanxi Datong University, Datong 037000, China;
2 Chengde Power Supply Company of State Grid Hebei Electric Power Co., Ltd, Chengde 067000, China)
 
    Abstract: In order to cope with the influence of power load fluctuation on the stability of power system when meteoro logical factors change, a CNN-LSTM combination model with attention mechanism was explored to predict the fluctuation of short-term power load. The power load was affected by the complex coupling of multi-dimensional climate factors, in order to effectively characterize these nonlinear and time-varying climate-load correlation characteristics, a multi-feature input model integrating temperature, precipitation, humidity and wind speed was constructed.This paper used the convolutional neural network(CNN) to capture the local climate patterns in the data, and the time-conditioning characteristics of key meteorological events were extracted through the sliding window mechanism. Then, the feature vectors were fed into the long short-term memory (LSTM) network, and its gating mechanism can effectively model the delay effect of climate factors and load response.Finally, the attention mechanism (AM) was introduced to dynamically quantify the temporal importance of each climate element. Through the comparison of simulation experiments, the results show that the CNN-LSTM-AM model has better prediction accuracy than the traditional LSTM and CNN-LSTM models.
    Key words: convolutional neural network; long short-term memory; attention mechanism; power load forecasting
 
参考文献
[1] 张智刚,康重庆. 碳中和目标下构建新型电力系统的挑战与展望[J] . 中国电机工程学报,2022,42(8) :2806-2818.
[2] 舒印彪,陈国平,贺静波,等. 构建以新能源为主体的新型电力系统框架研究[J] . 中国工程科学, 2021,23(6) :61-69.
[3] WANG Han, ZHANG Ning, DU Ershun, et al.A comprehensive review for wind, solar, and electrical load forecasting methods[J].Global Energy Interconnection,2022,5(1) :9-30.
[4] 魏泓屹,卓振宇,张宁,等. 中国电力系统碳达峰·碳中和转型路径优化与影响因素分析[J]. 电力系统自动化,2022,46(19) :1-12.
[5] 蔡帜,张国芳,王淼,等. 电力市场环境下区域和省级电网协同安全校核及校正[J] . 中国电机工程学报,2023,43(10) :3758-3767.
[6] LINDBERG K B, SELJOM P, MADSEN H, et al.Longterm electricity load forecasting :Current and future trends[J].Utilities Policy,2019,58 :102-119.
[7] 王欢,李鹏,曹敏,等. 基于 CNN_BiLSTM 的长短期电力负荷预测方法[J]. 计算机仿真,2022,39(3) :96-103.
[8] 钱育树,孔钰婷,黄聪. 电力负荷预测研究综述[J] .四川电力技术,2023,46(4) :37-43.
[9] 韩富佳,王晓辉,乔骥,等. 基于人工智能技术的新型电力系统负荷预测研究综述[J] . 中国电机工程学报,2023,43(22) :8569-8591.
[10] 赵东雷,李丹华,库巍,等. 基于神经网络的电力系统短期负荷预测[J] . 华北电力技术,2017(9) :22-27.
[11] 夏超鹏,洪宇,刘新山,等. 基于 LSTM 深度学习网络的中长期电力负荷预测[J] . 自动化与仪器仪表,2024(7) :343-346.
[12] CHEN Xinfang, CHEN Weiran, DINAVAHI Venkata, et al.Short-Term Load Forecasting and Associated Weather Variables Prediction Using ResNet-LSTM Based Deep Learning[J].IEEE Access,2023,11 :5393-5405.
[13] 孟磊. 基于 CNN-LSTM 网络的电力负荷预测[J]. 机电信息,2023(7) :7-10.
[14] 林美. 基于深度学习方法的短期电力负荷预测[D]. 哈尔滨:东北农业大学,2022.
[15] WANG Bin. A Zipf-plot based normalization method for high-throughput RNA-seq data[J].PLoS One,2020,15(4) :e0230594.