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 (c), momentum (a) 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, c=0.8, a=0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); c (0.6, 0.8, 1.0, 1.2), a (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 c and a, 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, c= 0.8, a=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 (c), momentum (a) 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, c=0.8, a=0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); c (0.6, 0.8, 1.0, 1.2), a (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 c and a, 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, c= 0.8, a=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.
[1]
C. Cañizares,et al.
Application of Public-Domain Market Information to Forecast Ontario's Wholesale Electricity Prices
,
2006,
IEEE Transactions on Power Systems.
[2]
J. R. Trapero,et al.
Electricity prices forecasting by automatic dynamic harmonic regression models
,
2007
.
[3]
Y.-y. Hong,et al.
Locational marginal price forecasting in deregulated electricity markets using artificial intelligence
,
2002
.
[4]
J. Contreras,et al.
ARIMA models to predict next-day electricity prices
,
2002
.
[5]
Chen-Ching Liu,et al.
Day-Ahead Electricity Price Forecasting in a Grid Environment
,
2007,
IEEE Transactions on Power Systems.
[6]
Jinxiang Zhu,et al.
Forecasting energy prices in a competitive market
,
1999
.
[7]
T. Senjyu,et al.
A Novel Approach to Forecast Electricity Price for PJM Using Neural Network and Similar Days Method
,
2007,
IEEE Transactions on Power Systems.
[8]
Alberto Gómez,et al.
Forecasting next-day price of electricity in the Spanish energy market using artificial neural networks
,
2008,
Eng. Appl. Artif. Intell..
[9]
Alvaro I. Arciniegas,et al.
Forecasting short-term power prices in the Ontario Electricity Market (OEM) with a fuzzy logic based inference system
,
2008
.
[10]
T. Senjyu,et al.
Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market
,
2006
.
[11]
J. Contreras,et al.
Forecasting next-day electricity prices by time series models
,
2002
.
[12]
T. Funabashi,et al.
Next day load curve forecasting using hybrid correction method
,
2005,
IEEE Transactions on Power Systems.
[13]
A.M. Gonzalez,et al.
Modeling and forecasting electricity prices with input/output hidden Markov models
,
2005,
IEEE Transactions on Power Systems.
[14]
T. Dillon,et al.
Electricity price short-term forecasting using artificial neural networks
,
1999
.
[15]
M. Negnevitsky,et al.
Very short-term wind forecasting for Tasmanian power generation
,
2006,
2006 IEEE Power Engineering Society General Meeting.
[16]
Marco van Akkeren,et al.
A GARCH forecasting model to predict day-ahead electricity prices
,
2005,
IEEE Transactions on Power Systems.
[17]
C. Rodriguez,et al.
Energy price forecasting in the Ontario competitive power system market
,
2004,
IEEE Transactions on Power Systems.