设为首页 联系我们 加入收藏

当前位置: 网站首页 期刊分类目录 2024年第3期 正文

基于k-shape_STL的用户短期用电负荷预测模型

作者:时间:2024-06-28点击数:

全文下载:  20240318.pdf


文章编号: 1672-6987202403-0132-09 DOI 10.16351/j.1672-6987.2024.03.018


刘红菊1 班浩然2 刘红艳3, 梁宏涛1*(1.青岛科技大学 信息科学技术学院,山东 青岛 266061 2. 浪潮集团有限公司,山东 济南 2500003.山东女子学院, 山东 济南 250002


摘要: 为挖掘复杂环境因素对电力负荷预测效果的影响,提高电力负荷预测精确度,提出了一种基于k-shape时间序列聚类与STL季节趋势分解算法相结合的负荷曲线聚类预测模型(k-shape-seasonal and trend decomposition using loess-gradient boosting decision treek-shape-STL-GBDT)。首先分析用户用电时序特征,利用k-shape时间序列聚类算法根据负荷曲线划分用户聚类,其次,使用STL算法将不同簇的负荷数据划分为季节项、趋势项与随机项。然后,结合温度、湿度等影响因素搭建预测模型,以麻省大学smart*可再生能源项目的公开数据集为例进行分析,并与多种主流聚类分解预测模型进行对比。结果表明新提出的模型框架MAPE减少了4%以上,针对短期负荷预测表现出了较好的性能与预测精度。


关键词: 负荷预测; k-shape STL 趋势项; 气象因素


中图分类号: TP 399文献标志码: A

引用格式: 刘红菊, 班浩然, 刘红艳, . 基于k-shape_STL的用户短期用电负荷预测模型[J. 青岛科技大学学报(自然科学版), 2024, 45(3): 132-140.

LIU Hongju BAN Haoran LIU Hongyan, et al. User short-term power load forecasting model based on k-shape_STLJ. Journal of Qingdao University of Science and TechnologyNatural Science Edition), 2024 453): 132-140.


User Short-Term Power Load Forecasting Model Based on k-shape_STL


LIU Hongju1 BAN Haoran2 LIU Hongyan3, LIANG Hongtao1

(1 College of Information Science and Technology, Qingdao University of Science and Technology Qingdao 266061 China;

2 Inspur Group Co., Ltd. Jinan 250000 China; 3 Shandong Women′s University, Jinan 250002 China)


Abstract: To excavate the influence of complex environmental factors on power load forecasting, improve the accuracy of power load forecasting, a load curve clustering forecasting model based on time series clustering and seasonal trend decomposition algorithm (k-shape-STL-GBDT) is proposed. Firstly, the time series characteristics of users′ electricity consumption are analyzed, and the k-shape algorithm is used to divide the user clusters according to the load curve. Secondly, the STL algorithm is used to divide the load data of different clusters into seasonal items, trend items and resid items. Then, we build a prediction model combining the influencing factors such as temperature and humidity and take the public data set of the UMass smart* renewable energy project as an example, and compare it with a variety of mainstream clustering decomposition prediction models. The results show that the newly proposed model framework MAPE reduces by more than 4%, and shows better performance and prediction accuracy for short-term load forecasting.


Key words: load forecasting k-shape STL trend meteorological factor


收稿日期: 2023-07-11

基金项目: 国家自然科学基金项目(61973180);山东省产教融合研究生联合培养示范基地项目(2020-19).

作者简介: 刘红菊(1997—),,硕士研究生.*通信联系人.


Copyright © 2011-2017 青岛科技大学学报 (自然科学版)