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

Paras Mandal, Anurag K. Srivastava, Michael Negnevitsky, Jung Wook Park

Research output: Contribution to journalArticle

9 Citations (Scopus)

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 (η), momentum (α) 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, η=0.8, α=0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); η (0.6, 0.8, 1.0, 1.2), α (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 η and α, 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, η= 0.8, α=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.

Original languageEnglish
Pages (from-to)38-51
Number of pages14
JournalInternational Journal of Energy Research
Volume33
Issue number1
DOIs
Publication statusPublished - 2009 Jun 2

Fingerprint

Sensitivity analysis
Electricity
Backpropagation
Neural networks
Mean square error
Momentum

All Science Journal Classification (ASJC) codes

  • Renewable Energy, Sustainability and the Environment
  • Nuclear Energy and Engineering
  • Fuel Technology
  • Energy Engineering and Power Technology

Cite this

@article{99a498afdcde406eabfd15c83bdb4225,
title = "Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting",
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 (η), momentum (α) 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, η=0.8, α=0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); η (0.6, 0.8, 1.0, 1.2), α (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 η and α, 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, η= 0.8, α=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.",
author = "Paras Mandal and Srivastava, {Anurag K.} and Michael Negnevitsky and Park, {Jung Wook}",
year = "2009",
month = "6",
day = "2",
doi = "10.1002/er.1469",
language = "English",
volume = "33",
pages = "38--51",
journal = "International Journal of Energy Research",
issn = "0363-907X",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting. / Mandal, Paras; Srivastava, Anurag K.; Negnevitsky, Michael; Park, Jung Wook.

In: International Journal of Energy Research, Vol. 33, No. 1, 02.06.2009, p. 38-51.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting

AU - Mandal, Paras

AU - Srivastava, Anurag K.

AU - Negnevitsky, Michael

AU - Park, Jung Wook

PY - 2009/6/2

Y1 - 2009/6/2

N2 - 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 (η), momentum (α) 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, η=0.8, α=0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); η (0.6, 0.8, 1.0, 1.2), α (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 η and α, 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, η= 0.8, α=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.

AB - 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 (η), momentum (α) 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, η=0.8, α=0.1 and dNN = 45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); η (0.6, 0.8, 1.0, 1.2), α (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 η and α, 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, η= 0.8, α=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.

UR - http://www.scopus.com/inward/record.url?scp=66049096482&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66049096482&partnerID=8YFLogxK

U2 - 10.1002/er.1469

DO - 10.1002/er.1469

M3 - Article

AN - SCOPUS:66049096482

VL - 33

SP - 38

EP - 51

JO - International Journal of Energy Research

JF - International Journal of Energy Research

SN - 0363-907X

IS - 1

ER -