Publication: Short term power load forecasting using a modified generalized regression neural network
No Thumbnail Available
Date
2008
Authors
Yap K.S.
Lim C.P.
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Short Term Load Forecasting is very important from the power systems grid operation point of view. The short term time frame may consist of half hourly prediction up to monthly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the short term load forecasting using a Modified Generalized Regression Neural Network (MGRNN). The experiments are based on the power load data from Jan 1997 to Jan 1999 of East Slovakian Electricity Corporation. Simulation results show that MGRNN has comparable prediction accuracy compared to benchmark result archived by Support Vector Regression.
Description
Keywords
?-Insensitive loss function , Generalized regression neural network , Load forecasting , Time series prediction , Competition , Neural networks , Regression analysis , Time series , Financial performance , Generalized regression neural network , Grid operations , Load demands , Load forecasting , Power load forecasting , Power loads , Power systems , Prediction accuracies , Reliability and stabilities , Short term load forecasting , Short terms , Simulation results , Support vector regressions , Time frames , Time series prediction , Utility companies , Electric load forecasting