eCite Digital Repository

Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting

Citation

Mandal, P and Srivastava, AK and Negnevitsky, M and Park, JW, Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting, International Journal of Energy Research, 33, (1) pp. 38-51. ISSN 0363-907X (2009) [Refereed Article]

DOI: doi:10.1002/er.1469

Abstract

This paper presents a sensitivity analysis of neural network (NN) parameters to improve the performance of electricity price forecasting. The presented work is an extended version of previous works done by authors to integrate NN and similar days (SD) method for predicting electricity prices. Focus here is on sensitivity analysis of NN parameters while keeping the parameters same for SD to forecast day-ahead electricity prices in the PJM market. Sensitivity analysis of NN parameters include back-propagation learning set (BP-set), learning rate (), momentum () and NN learning days (dN N). The SD parameters, i.e. time framework of SD (d = 45 days) and number of selected similar price days (N=5) are kept constant for all the simulated cases. Forecasting performance is carried out by choosing two different days from each season of the year 2006 and for which, the NN parameters for the base case are considered as BP-set=500, =0.8, =0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); (0.6, 0.8, 1.0, 1.2), (0.1, 0.2, 0.3) and dNN (15, 30, 45 and 60 days). The most favorable value of BP-set is first found out from the sensitivity analysis followed by that of and , and based on which the best value of dNN is determined. Sensitivity analysis results demonstrate that the best value of mean absolute percentage error (MAPE) is obtained when BP-set = 500, = 0.8, =0.1 and dNN = 60 days for winter season. For spring, summer and autumn, these values are 500, 0.6, 0.1 and 45 days, respectively. MAPE, forecast mean square error and mean absolute error of reasonably small value are obtained for the PJM data, which has correlation coefficient of determination (R2) of 0.7758 between load and electricity price. Numerical results show that forecasts generated by developed NN model based on the most favorable case are accurate and efficient. This paper presents a sensitivity analysis of neural network (NN) parameters to improve the performance of electricity price forecasting. The presented work is an extended version of previous works done by authors to integrate NN and similar days (SD) method for predicting electricity prices. Focus here is on sensitivity analysis of NN parameters while keeping the parameters same for SD to forecast day-ahead electricity prices in the PJM market. Sensitivity analysis of NN parameters include back-propagation learning set (BP-set), learning rate (), momentum () and NN learning days (dN N). The SD parameters, i.e. time framework of SD (d = 45 days) and number of selected similar price days (N=5) are kept constant for all the simulated cases. Forecasting performance is carried out by choosing two different days from each season of the year 2006 and for which, the NN parameters for the base case are considered as BP-set=500, =0.8, =0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); (0.6, 0.8, 1.0, 1.2), (0.1, 0.2, 0.3) and dNN (15, 30, 45 and 60 days). The most favorable value of BP-set is first found out from the sensitivity analysis followed by that of and , and based on which the best value of dNN is determined. Sensitivity analysis results demonstrate that the best value of mean absolute percentage error (MAPE) is obtained when BP-set = 500, = 0.8, =0.1 and dNN = 60 days for winter season. For spring, summer and autumn, these values are 500, 0.6, 0.1 and 45 days, respectively. MAPE, forecast mean square error and mean absolute error of reasonably small value are obtained for the PJM data, which has correlation coefficient of determination (R2) of 0.7758 between load and electricity price. Numerical results show that forecasts generated by developed NN model based on the most favorable case are accurate and efficient.

Item Details

Item Type:Refereed Article
Research Division:Engineering
Research Group:Other Engineering
Research Field:Engineering not elsewhere classified
Objective Division:Energy
Objective Group:Other Energy
Objective Field:Energy not elsewhere classified
Author:Mandal, P (Dr Paras Mandal)
Author:Negnevitsky, M (Professor Michael Negnevitsky)
ID Code:61047
Year Published:2009
Web of Science® Times Cited:4
Deposited By:Engineering
Deposited On:2010-02-24
Last Modified:2010-05-03
Downloads:0

Repository Staff Only: item control page