### Abstract

This paper reports a grid computing approach to parallel-process a neural network time-series model for forecasting electricity market prices. The grid computing of the neural network model not only processes several times faster than a single iterative process but also provides chances of improving forecasting accuracy. A grid-computing environment implemented in a university computing laboratory improves utilization rate of otherwise underused computing resources. Results of numerical tests using the real market data by more than twenty grid-connected PCs are presented.

Original language | English |
---|---|

Pages (from-to) | 273-277 |

Number of pages | 5 |

Journal | Unknown Journal |

Publication status | Published - 2009 |

### Fingerprint

### Keywords

- Electricity market
- Forecasting
- Grid computing
- Neural networks
- Optimization
- Price

### ASJC Scopus subject areas

- Control and Systems Engineering

### Cite this

*Unknown Journal*, 273-277.

**Electricity market forecasting using artificial neural network models optimized by grid computing.** / Mohd Isa, Aishah; Niimura, Takahide; Sakamoto, Noriaki; Ozawa, Kazuhiro; Yokoyama, Ryuichi.

Research output: Contribution to journal › Article

*Unknown Journal*, pp. 273-277.

}

TY - JOUR

T1 - Electricity market forecasting using artificial neural network models optimized by grid computing

AU - Mohd Isa, Aishah

AU - Niimura, Takahide

AU - Sakamoto, Noriaki

AU - Ozawa, Kazuhiro

AU - Yokoyama, Ryuichi

PY - 2009

Y1 - 2009

N2 - This paper reports a grid computing approach to parallel-process a neural network time-series model for forecasting electricity market prices. The grid computing of the neural network model not only processes several times faster than a single iterative process but also provides chances of improving forecasting accuracy. A grid-computing environment implemented in a university computing laboratory improves utilization rate of otherwise underused computing resources. Results of numerical tests using the real market data by more than twenty grid-connected PCs are presented.

AB - This paper reports a grid computing approach to parallel-process a neural network time-series model for forecasting electricity market prices. The grid computing of the neural network model not only processes several times faster than a single iterative process but also provides chances of improving forecasting accuracy. A grid-computing environment implemented in a university computing laboratory improves utilization rate of otherwise underused computing resources. Results of numerical tests using the real market data by more than twenty grid-connected PCs are presented.

KW - Electricity market

KW - Forecasting

KW - Grid computing

KW - Neural networks

KW - Optimization

KW - Price

UR - http://www.scopus.com/inward/record.url?scp=84894585190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894585190&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84894585190

SP - 273

EP - 277

JO - Nuclear Physics A

JF - Nuclear Physics A

SN - 0375-9474

ER -