摘要
随着电力需求增长，精准负荷预测至关重要。利用大数据技术，整合海量电力数据，涵盖历史负荷、气象、经济等信息。经数据预处理、特征提取，构建多元预测模型，融合机器学习与深度学习算法。模型有效提升预测精度，助力电力系统稳定运行、优化调度，为电力行业科学决策提供有力支撑。
关键词： 电力负荷；大数据；预测模型；机器学习；深度学习
Abstract
As electricity demand grows, precise load forecasting becomes crucial. Leveraging big data technology to integrate vast amounts of power data, including historical loads, weather, and economic information, is essential. After preprocessing the data and extracting features, a multi-faceted prediction model is constructed, integrating machine learning and deep learning algorithms. This model effectively enhances prediction accuracy, supporting the stable operation and optimized scheduling of power systems, providing robust support for scientific decision-making in the power industry.
Key words： Power load; Big data; Prediction model; Machine learning; Deep learning
参考文献 References
[1] 俞健心.基于大数据分析的电力负荷模型构建[J].信息记录材料,2024,25(07):147-149.
[2] 臧柏棋,张浩.考虑新兴负荷的城市电力负荷分析与预测[J].科技与创新,2025,(06):117-120.
[3] 高捷,董杰,俞金云,等.基于GIS数据的中长期负荷预测与区域调控技术[J].信息技术,2025,(03):192-196.
[4] 杨晓明.基于电力负荷预测的工业园区“双碳”体系建设研究[J].电气技术与经济,2025,(03):248-250.
[5] 方雨兴,李梅.区域综合能源系统短期电力负荷预测[J].延边大学学报(自然科学版),2025,51(01):111-114.
[6] 朱俊澎,李子钰,李虎军,等.基于负荷分解与辨识的短期电力负荷预测[J].电力需求侧管理,2025,27(02):55-61.
[7] 凌荣光,许巍,严若婧,等.面向电力需求分析的多源数据处理算法设计[J].电子设计工程,2025,33(05):147-151.
[8] 曹华珍,韦斌,高超,等.基于深度信念网络的电力负荷短期预测方法[J].新型电力系统,2025,3(01):111-124.