Genetic algorithm-based RBF neural network load forecasting model

Zhangang Yang; Yanbo Che; Ka Wai Eric Cheng

doi:10.1109/PES.2007.385710

Genetic algorithm-based RBF neural network load forecasting model

Zhangang Yang, Yanbo Che, Ka Wai Eric Cheng

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

21 Citations (Scopus)

Abstract

To overcome the limitation of the traditional load forecasting method, a new load forecasting system basing on radial basis Gaussian kernel function (RBF) neural network is proposed in this paper. Genetic algorithm adopting the real coding, crossover probability and mutation probability was applied to optimize the parameters of the neural network, and a faster convergence rate was reached. Theoretical analysis and simulations prove that this load forecasting model is more practical and has more precision than the traditional one.

Original language	English
Title of host publication	2007 IEEE Power Engineering Society General Meeting, PES
DOIs	https://doi.org/10.1109/PES.2007.385710
Publication status	Published - 1 Dec 2007
Event	2007 IEEE Power Engineering Society General Meeting, PES - Tampa, FL, United States Duration: 24 Jun 2007 → 28 Jun 2007

Conference

Conference	2007 IEEE Power Engineering Society General Meeting, PES
Country/Territory	United States
City	Tampa, FL
Period	24/06/07 → 28/06/07

Keywords

Convergence rate
Genetic algorithm
Load forecasting
RBF neural network
Real coding

ASJC Scopus subject areas

General Energy

More information

10.1109/PES.2007.385710

http://hdl.handle.net/10397/1658

Cite this

@inproceedings{b9a9a38e2d9f4e048c6a03b4f88eb827,

title = "Genetic algorithm-based RBF neural network load forecasting model",

abstract = "To overcome the limitation of the traditional load forecasting method, a new load forecasting system basing on radial basis Gaussian kernel function (RBF) neural network is proposed in this paper. Genetic algorithm adopting the real coding, crossover probability and mutation probability was applied to optimize the parameters of the neural network, and a faster convergence rate was reached. Theoretical analysis and simulations prove that this load forecasting model is more practical and has more precision than the traditional one.",

keywords = "Convergence rate, Genetic algorithm, Load forecasting, RBF neural network, Real coding",

author = "Zhangang Yang and Yanbo Che and Cheng, {Ka Wai Eric}",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/PES.2007.385710",

language = "English",

isbn = "1424412986",

booktitle = "2007 IEEE Power Engineering Society General Meeting, PES",

note = "2007 IEEE Power Engineering Society General Meeting, PES ; Conference date: 24-06-2007 Through 28-06-2007",

}

TY - GEN

T1 - Genetic algorithm-based RBF neural network load forecasting model

AU - Yang, Zhangang

AU - Che, Yanbo

AU - Cheng, Ka Wai Eric

PY - 2007/12/1

Y1 - 2007/12/1

N2 - To overcome the limitation of the traditional load forecasting method, a new load forecasting system basing on radial basis Gaussian kernel function (RBF) neural network is proposed in this paper. Genetic algorithm adopting the real coding, crossover probability and mutation probability was applied to optimize the parameters of the neural network, and a faster convergence rate was reached. Theoretical analysis and simulations prove that this load forecasting model is more practical and has more precision than the traditional one.

AB - To overcome the limitation of the traditional load forecasting method, a new load forecasting system basing on radial basis Gaussian kernel function (RBF) neural network is proposed in this paper. Genetic algorithm adopting the real coding, crossover probability and mutation probability was applied to optimize the parameters of the neural network, and a faster convergence rate was reached. Theoretical analysis and simulations prove that this load forecasting model is more practical and has more precision than the traditional one.

KW - Convergence rate

KW - Genetic algorithm

KW - Load forecasting

KW - RBF neural network

KW - Real coding

UR - http://www.scopus.com/inward/record.url?scp=42649098915&partnerID=8YFLogxK

U2 - 10.1109/PES.2007.385710

DO - 10.1109/PES.2007.385710

M3 - Conference article published in proceeding or book

SN - 1424412986

SN - 9781424412983

BT - 2007 IEEE Power Engineering Society General Meeting, PES

T2 - 2007 IEEE Power Engineering Society General Meeting, PES

Y2 - 24 June 2007 through 28 June 2007

ER -

Genetic algorithm-based RBF neural network load forecasting model

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this