Title :
An Effort to Optimize Similar Days Parameters for ANN Based Electricity Price Forecasting
Author :
Mandal, Paras ; Srivastava, Anurag K. ; Negnevitsky, Michael ; Park, Jung-Wook
Author_Institution :
Sch. of Eng., Univ. of Tasmania, Hobart, TAS
Abstract :
This paper presents a sensitivity analysis of similar days (SD) parameters to increase the accuracy of artificial neural network (ANN) and SD based short-term price forecasting. Presented work is an extended version of previous works done by authors to integrate ANN and similar days method for predicting electricity price. Focus here is on sensitivity analysis of similar days parameters while keeping the parameters same for ANN to forecast hourly electricity prices in the PJM (regional transmission organization in north-east America) electricity market. Several cases are simulated by choosing: (a) two; (b) three; (c) four; and (d) five similar days parameters to calculate the norm. Additionally, sensitivity analysis has been carried out by changing time framework of similar days (rf=15, 30, 45, 60) and number of selected similar price days (N=5, 10). From sensitivity analysis, it is identified that the optimized mean absolute percentage error (MAPE) is obtained using case-c with rf=30 and iV=10. MAPE of reasonably small value along with forecast mean square error (FMSE) and mean absolute error (MAE) of around 2$/MWh and 1$/MWh 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 ANN model based on the optimized case are accurate and efficient.
Keywords :
economic forecasting; mean square error methods; neural nets; power engineering computing; power markets; power system economics; pricing; artificial neural network; correlation coefficient; electricity market; electricity price forecasting; forecast mean square error; mean absolute error; mean absolute percentage error; north-east America; regional transmission organization; sensitivity analysis; short-term price forecasting; similar days method; similar days parameters; Artificial neural networks; Economic forecasting; Electricity supply industry; Fuel economy; Load forecasting; Neural networks; Power generation economics; Pricing; Sensitivity analysis; Weather forecasting;
Conference_Titel :
Industry Applications Society Annual Meeting, 2008. IAS '08. IEEE
Conference_Location :
Edmonton, Alta.
Print_ISBN :
978-1-4244-2278-4
Electronic_ISBN :
0197-2618
DOI :
10.1109/08IAS.2008.141