A Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net Analysis

A short-term load forecasting method based on load characteristics clustering and elastic net analysis is proposed in this paper. By analyzing and clustering the historical load characteristics, the annual days are classified and its clusters are specified, and the lack of pertinence of the types of...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingjie JIN, Yong LIN, Shuxin LUO, Bin WEI, Shucan ZHOU
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2020-09-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201905111
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850227396874076160
author Bingjie JIN
Yong LIN
Shuxin LUO
Bin WEI
Shucan ZHOU
author_facet Bingjie JIN
Yong LIN
Shuxin LUO
Bin WEI
Shucan ZHOU
author_sort Bingjie JIN
collection DOAJ
description A short-term load forecasting method based on load characteristics clustering and elastic net analysis is proposed in this paper. By analyzing and clustering the historical load characteristics, the annual days are classified and its clusters are specified, and the lack of pertinence of the types of the day cluster selection is avoided. At the same time, Elastic net analysis is adopted to identify and select the dominant factors for short-term load forecasting. Furthermore, the neural network forecasting model is established on the basis of input variable optimization. Taking the actual load of a city in Guangdong province as an example, the effectiveness of the proposed method in improving the daily load curve forecasting accuracy is verified by comparing with other methods. Results show that the model established is long-term effective, dispensing with repeated training, which is applicable for short-term load forecasting.
format Article
id doaj-art-fd22a2a57c5d486ea9ac259e6d04df2a
institution OA Journals
issn 1004-9649
language zho
publishDate 2020-09-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-fd22a2a57c5d486ea9ac259e6d04df2a2025-08-20T02:04:51ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492020-09-0153922122810.11930/j.issn.1004-9649.201905111zgdl-53-4-jinbingjieA Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net AnalysisBingjie JIN0Yong LIN1Shuxin LUO2Bin WEI3Shucan ZHOU4Power Grid Planning Center of Guangdong Power Grid Company, Guangzhou 510080, ChinaPower Grid Planning Center of Guangdong Power Grid Company, Guangzhou 510080, ChinaPower Grid Planning Center of Guangdong Power Grid Company, Guangzhou 510080, ChinaPower Grid Planning Center of Guangdong Power Grid Company, Guangzhou 510080, ChinaPower Grid Planning Center of Guangdong Power Grid Company, Guangzhou 510080, ChinaA short-term load forecasting method based on load characteristics clustering and elastic net analysis is proposed in this paper. By analyzing and clustering the historical load characteristics, the annual days are classified and its clusters are specified, and the lack of pertinence of the types of the day cluster selection is avoided. At the same time, Elastic net analysis is adopted to identify and select the dominant factors for short-term load forecasting. Furthermore, the neural network forecasting model is established on the basis of input variable optimization. Taking the actual load of a city in Guangdong province as an example, the effectiveness of the proposed method in improving the daily load curve forecasting accuracy is verified by comparing with other methods. Results show that the model established is long-term effective, dispensing with repeated training, which is applicable for short-term load forecasting.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201905111load characteristicsclusteringelastic netneural networkload forecasting
spellingShingle Bingjie JIN
Yong LIN
Shuxin LUO
Bin WEI
Shucan ZHOU
A Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net Analysis
Zhongguo dianli
load characteristics
clustering
elastic net
neural network
load forecasting
title A Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net Analysis
title_full A Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net Analysis
title_fullStr A Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net Analysis
title_full_unstemmed A Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net Analysis
title_short A Short-Term Load Forecasting Method Based on Load Curve Clustering and Elastic Net Analysis
title_sort short term load forecasting method based on load curve clustering and elastic net analysis
topic load characteristics
clustering
elastic net
neural network
load forecasting
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201905111
work_keys_str_mv AT bingjiejin ashorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT yonglin ashorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT shuxinluo ashorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT binwei ashorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT shucanzhou ashorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT bingjiejin shorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT yonglin shorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT shuxinluo shorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT binwei shorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis
AT shucanzhou shorttermloadforecastingmethodbasedonloadcurveclusteringandelasticnetanalysis