A new forecasting approach for short-term load intelligence based on cluster method

Hong Yi Chen; Cun Bin Li; Li Gang Shi

A new forecasting approach for short-term load intelligence based on cluster method

Hong Yi Chen, Cun Bin Li, Li Gang Shi

Mechanical & Industrial Engineering

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

Load forecasting is one of the basic issues of the electric power industry. However, because load has a certain social attributes, the improvement of the accuracy of load forecasting result is a difficult issue. This paper first used k-means cluster method to find similar data from historical date and weather data, and then used support vector machine (SVM) for forecasting. Seen from the result, the proposed method's MAPE is 0.88%, but BP-ANN and ARMA are 1.66% and 3.81% respectively. It is proved that this method has a high accuracy.

Original language	English (US)
Pages (from-to)	94-98
Number of pages	5
Journal	Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences
Volume	41
Issue number	5
State	Published - 2014

Keywords

Clustering
Data mining
Load forecasting
Support vector machine(SVM)
k-means

OpenUrl availability

Full text

Cite this

@article{9e1ce938df9f41b1a8f0025641a44e60,

title = "A new forecasting approach for short-term load intelligence based on cluster method",

abstract = "Load forecasting is one of the basic issues of the electric power industry. However, because load has a certain social attributes, the improvement of the accuracy of load forecasting result is a difficult issue. This paper first used k-means cluster method to find similar data from historical date and weather data, and then used support vector machine (SVM) for forecasting. Seen from the result, the proposed method's MAPE is 0.88%, but BP-ANN and ARMA are 1.66% and 3.81% respectively. It is proved that this method has a high accuracy.",

keywords = "Clustering, Data mining, Load forecasting, Support vector machine(SVM), k-means",

author = "Chen, {Hong Yi} and Li, {Cun Bin} and Shi, {Li Gang}",

year = "2014",

language = "English (US)",

volume = "41",

pages = "94--98",

journal = "Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences",

issn = "1674-2974",

publisher = "Hunan Daxue/Hunan University",

number = "5",

}

TY - JOUR

T1 - A new forecasting approach for short-term load intelligence based on cluster method

AU - Chen, Hong Yi

AU - Li, Cun Bin

AU - Shi, Li Gang

PY - 2014

Y1 - 2014

N2 - Load forecasting is one of the basic issues of the electric power industry. However, because load has a certain social attributes, the improvement of the accuracy of load forecasting result is a difficult issue. This paper first used k-means cluster method to find similar data from historical date and weather data, and then used support vector machine (SVM) for forecasting. Seen from the result, the proposed method's MAPE is 0.88%, but BP-ANN and ARMA are 1.66% and 3.81% respectively. It is proved that this method has a high accuracy.

AB - Load forecasting is one of the basic issues of the electric power industry. However, because load has a certain social attributes, the improvement of the accuracy of load forecasting result is a difficult issue. This paper first used k-means cluster method to find similar data from historical date and weather data, and then used support vector machine (SVM) for forecasting. Seen from the result, the proposed method's MAPE is 0.88%, but BP-ANN and ARMA are 1.66% and 3.81% respectively. It is proved that this method has a high accuracy.

KW - Clustering

KW - Data mining

KW - Load forecasting

KW - Support vector machine(SVM)

KW - k-means

UR - http://www.scopus.com/inward/record.url?scp=84902073748&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902073748&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84902073748

SN - 1674-2974

VL - 41

SP - 94

EP - 98

JO - Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences

JF - Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences

IS - 5

ER -

A new forecasting approach for short-term load intelligence based on cluster method

Abstract

Keywords

OpenUrl availability

Other files and links

Fingerprint

Cite this