CMAC-based short-term electricity price forecasting

Hao Zhou; Jianhua Chen; Hao Wu; Siu Lau Ho

CMAC-based short-term electricity price forecasting

Hao Zhou, Jianhua Chen, Hao Wu, Siu Lau Ho

The Hong Kong Polytechnic University

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

3 Citations (Scopus)

Abstract

Electricity price forecasting is, naturally, the basis of decision-making in electricity markets. This paper proposes the day-ahead short-term electricity price forecasting models using a Cerebella Model Articulation Controller (CMAC) neural network, and then constructs the respective models at different trading intervals. The data of California electricity market is employed to predict the short-term electricity price using the proposed CMAC and a BP (back-propagation) neural network. The performance comparison shows that the proposed CMAC neural network can work more steadily and speedily in short-term electricity price forecasting when compared with a BP network.

Original language	English
Title of host publication	Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings
Pages	348-353
Number of pages	6
Volume	1
Publication status	Published - 1 Dec 2003
Event	Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings - Hong Kong, Hong Kong Duration: 11 Nov 2003 → 14 Nov 2003

Conference

Conference	Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings
Country/Territory	Hong Kong
City	Hong Kong
Period	11/11/03 → 14/11/03

ASJC Scopus subject areas

General Engineering

Cite this

@inproceedings{6f3ecf50f8c84d41bfaf3d0c7563e7af,

title = "CMAC-based short-term electricity price forecasting",

abstract = "Electricity price forecasting is, naturally, the basis of decision-making in electricity markets. This paper proposes the day-ahead short-term electricity price forecasting models using a Cerebella Model Articulation Controller (CMAC) neural network, and then constructs the respective models at different trading intervals. The data of California electricity market is employed to predict the short-term electricity price using the proposed CMAC and a BP (back-propagation) neural network. The performance comparison shows that the proposed CMAC neural network can work more steadily and speedily in short-term electricity price forecasting when compared with a BP network.",

author = "Hao Zhou and Jianhua Chen and Hao Wu and Ho, \{Siu Lau\}",

year = "2003",

month = dec,

day = "1",

language = "English",

isbn = "0863413285",

volume = "1",

pages = "348--353",

booktitle = "Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings",

note = "Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings ; Conference date: 11-11-2003 Through 14-11-2003",

}

CMAC-based short-term electricity price forecasting. / Zhou, Hao; Chen, Jianhua; Wu, Hao et al.
Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings. Vol. 1 2003. p. 348-353.

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

TY - GEN

T1 - CMAC-based short-term electricity price forecasting

AU - Zhou, Hao

AU - Chen, Jianhua

AU - Wu, Hao

AU - Ho, Siu Lau

PY - 2003/12/1

Y1 - 2003/12/1

N2 - Electricity price forecasting is, naturally, the basis of decision-making in electricity markets. This paper proposes the day-ahead short-term electricity price forecasting models using a Cerebella Model Articulation Controller (CMAC) neural network, and then constructs the respective models at different trading intervals. The data of California electricity market is employed to predict the short-term electricity price using the proposed CMAC and a BP (back-propagation) neural network. The performance comparison shows that the proposed CMAC neural network can work more steadily and speedily in short-term electricity price forecasting when compared with a BP network.

AB - Electricity price forecasting is, naturally, the basis of decision-making in electricity markets. This paper proposes the day-ahead short-term electricity price forecasting models using a Cerebella Model Articulation Controller (CMAC) neural network, and then constructs the respective models at different trading intervals. The data of California electricity market is employed to predict the short-term electricity price using the proposed CMAC and a BP (back-propagation) neural network. The performance comparison shows that the proposed CMAC neural network can work more steadily and speedily in short-term electricity price forecasting when compared with a BP network.

UR - https://www.scopus.com/pages/publications/4344692477

M3 - Conference article published in proceeding or book

SN - 0863413285

SN - 9780863413285

VL - 1

SP - 348

EP - 353

BT - Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings

T2 - Sixth International Conference on Advances in Power System Control, Operation and Management - Proceedings

Y2 - 11 November 2003 through 14 November 2003

ER -

CMAC-based short-term electricity price forecasting

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this