###
计算机系统应用:2020,29(3):161-166
本文二维码信息
码上扫一扫!
基于K-Means和CNN的用户短期电力负荷预测
(国网山东省电力公司 泰安供电公司, 泰安 271000)
Hybrid Method for Short-Term Load Forecasting Based on K-Means and Convolutional Neural Network
(State Grid Tai'an Power Supply Company, Tai'an 271000, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 96次   下载 62
投稿时间:2019-07-27    修订日期:2019-08-23
中文摘要: 随着电力物联网的不断发展,用户级电力负荷预测在电力需求侧管理中呈现出日益重要的作用.为了提高用户级电力负荷预测的性能,本文提出一种基于K-means聚类与卷积神经网络特征提取的短期电力负荷预测模型.首先,利用K-means将用户聚为两类:对于日相关性强的用户,将相邻时刻和日周期的历史负荷作为输入,采用CNN模型提取特征进行预测;对于日相关性弱的用户,仅将相邻时刻的历史负荷输入到CNN模型进行预测.为了验证所提出算法的性能,我们在实际的用户负荷数据上做了实验,并与随机森林、支持向量回归机进行对比,结果表明本文所构建模型的预测平均绝对百分误差降低了20%以上.
Abstract:With the development of smart grid technology, short-term power load forecasting becomes more and more important. To improve the accuracy of short-term electric load forecasting for individual users, this study proposes a load forecasting model, which is based on K-means and Convolutional Neural Network (CNN). Firstly, K-means is applied to group users into two categories. For users with strong daily correlation, the historical loads of adjacent time points and same time points in adjacent days are taken as input to the CNN model to extract abstract features for prediction. For users with weak daily correlation, the historical loads of the adjacent time points are utilized as features. To assess the performance of the proposed method, we conducted comparison experiments on real data with random forest and support vector regression. The experimental results show that the MAPE of the proposed approach is reduced by 20%.
文章编号:     中图分类号:    文献标志码:
基金项目:国网公司科技项目(SGSDTA00YXJS1800585)
引用文本:
吕志星,张虓,王沈征,王一,程思瑾,秦承龙.基于K-Means和CNN的用户短期电力负荷预测.计算机系统应用,2020,29(3):161-166
LYU Zhi-Xing,ZHANG Xiao,WANG Shen-Zheng,WANG Yi,CHENG Si-Jin,QIN Cheng-Long.Hybrid Method for Short-Term Load Forecasting Based on K-Means and Convolutional Neural Network.COMPUTER SYSTEMS APPLICATIONS,2020,29(3):161-166

用微信扫一扫

用微信扫一扫