Sensitivity analysis of similar days parameters for predicting short-term electricity price

Paras Mandal, Tomonobu Senjyu, Atsushi Yona, Jung Wook Park, Anurag K. Srivastava

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

This paper describes an identification of the best similar days parameters for artificial neural network (ANN) based short-term price forecasting. The work presented in this paper is an extended version of our previous works where we proposed the price prediction technique by using ANN, which is based on similar days method. According to similar days method, we select similar price days corresponding to forecast day based on Euclidean norm. The focus of the present paper is mainly on sensitivity analysis of similar days parameter while keeping the parameters same for ANN to forecast hourly electricity prices in the PJM electricity market. We simulated three cases by: (i) selecting two similar days parameters (load at t and price at t); (ii) selecting three similar days parameters (load at t, price at t and price at t - 1), and (iii) selecting five similar days parameters (load at t, load at t - 1, load at t + 1, price at t and price at t - 1). The next-24h price forecasts obtained from ANN based on similar days method confirm that the performance of the ANN model is better when five similar days parameters are selected, i.e., the accuracy of the method is enhanced by the addition of load at t - 1 and t + 1. The factors impacting the electricity price forecasting, including time factors, load factors, and historical price factors are well discussed. Mean absolute percentage error (MAPE) and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination of (R2) of 0.7758 between load and electricity price.

Original languageEnglish
Title of host publication2007 39th North American Power Symposium, NAPS
Pages568-574
Number of pages7
DOIs
Publication statusPublished - 2007 Dec 1
Event2007 39th North American Power Symposium, NAPS - Las Cruces, NM, United States
Duration: 2007 Sep 302007 Oct 2

Publication series

Name2007 39th North American Power Symposium, NAPS

Other

Other2007 39th North American Power Symposium, NAPS
CountryUnited States
CityLas Cruces, NM
Period07/9/3007/10/2

Fingerprint

Sensitivity analysis
Electricity
Neural networks
Mean square error

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

Mandal, P., Senjyu, T., Yona, A., Park, J. W., & Srivastava, A. K. (2007). Sensitivity analysis of similar days parameters for predicting short-term electricity price. In 2007 39th North American Power Symposium, NAPS (pp. 568-574). [4402367] (2007 39th North American Power Symposium, NAPS). https://doi.org/10.1109/NAPS.2007.4402367
Mandal, Paras ; Senjyu, Tomonobu ; Yona, Atsushi ; Park, Jung Wook ; Srivastava, Anurag K. / Sensitivity analysis of similar days parameters for predicting short-term electricity price. 2007 39th North American Power Symposium, NAPS. 2007. pp. 568-574 (2007 39th North American Power Symposium, NAPS).
@inproceedings{faff3012329c434d87fdf7c807d4ca40,
title = "Sensitivity analysis of similar days parameters for predicting short-term electricity price",
abstract = "This paper describes an identification of the best similar days parameters for artificial neural network (ANN) based short-term price forecasting. The work presented in this paper is an extended version of our previous works where we proposed the price prediction technique by using ANN, which is based on similar days method. According to similar days method, we select similar price days corresponding to forecast day based on Euclidean norm. The focus of the present paper is mainly on sensitivity analysis of similar days parameter while keeping the parameters same for ANN to forecast hourly electricity prices in the PJM electricity market. We simulated three cases by: (i) selecting two similar days parameters (load at t and price at t); (ii) selecting three similar days parameters (load at t, price at t and price at t - 1), and (iii) selecting five similar days parameters (load at t, load at t - 1, load at t + 1, price at t and price at t - 1). The next-24h price forecasts obtained from ANN based on similar days method confirm that the performance of the ANN model is better when five similar days parameters are selected, i.e., the accuracy of the method is enhanced by the addition of load at t - 1 and t + 1. The factors impacting the electricity price forecasting, including time factors, load factors, and historical price factors are well discussed. Mean absolute percentage error (MAPE) and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination of (R2) of 0.7758 between load and electricity price.",
author = "Paras Mandal and Tomonobu Senjyu and Atsushi Yona and Park, {Jung Wook} and Srivastava, {Anurag K.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/NAPS.2007.4402367",
language = "English",
isbn = "9781424417261",
series = "2007 39th North American Power Symposium, NAPS",
pages = "568--574",
booktitle = "2007 39th North American Power Symposium, NAPS",

}

Mandal, P, Senjyu, T, Yona, A, Park, JW & Srivastava, AK 2007, Sensitivity analysis of similar days parameters for predicting short-term electricity price. in 2007 39th North American Power Symposium, NAPS., 4402367, 2007 39th North American Power Symposium, NAPS, pp. 568-574, 2007 39th North American Power Symposium, NAPS, Las Cruces, NM, United States, 07/9/30. https://doi.org/10.1109/NAPS.2007.4402367

Sensitivity analysis of similar days parameters for predicting short-term electricity price. / Mandal, Paras; Senjyu, Tomonobu; Yona, Atsushi; Park, Jung Wook; Srivastava, Anurag K.

2007 39th North American Power Symposium, NAPS. 2007. p. 568-574 4402367 (2007 39th North American Power Symposium, NAPS).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Sensitivity analysis of similar days parameters for predicting short-term electricity price

AU - Mandal, Paras

AU - Senjyu, Tomonobu

AU - Yona, Atsushi

AU - Park, Jung Wook

AU - Srivastava, Anurag K.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper describes an identification of the best similar days parameters for artificial neural network (ANN) based short-term price forecasting. The work presented in this paper is an extended version of our previous works where we proposed the price prediction technique by using ANN, which is based on similar days method. According to similar days method, we select similar price days corresponding to forecast day based on Euclidean norm. The focus of the present paper is mainly on sensitivity analysis of similar days parameter while keeping the parameters same for ANN to forecast hourly electricity prices in the PJM electricity market. We simulated three cases by: (i) selecting two similar days parameters (load at t and price at t); (ii) selecting three similar days parameters (load at t, price at t and price at t - 1), and (iii) selecting five similar days parameters (load at t, load at t - 1, load at t + 1, price at t and price at t - 1). The next-24h price forecasts obtained from ANN based on similar days method confirm that the performance of the ANN model is better when five similar days parameters are selected, i.e., the accuracy of the method is enhanced by the addition of load at t - 1 and t + 1. The factors impacting the electricity price forecasting, including time factors, load factors, and historical price factors are well discussed. Mean absolute percentage error (MAPE) and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination of (R2) of 0.7758 between load and electricity price.

AB - This paper describes an identification of the best similar days parameters for artificial neural network (ANN) based short-term price forecasting. The work presented in this paper is an extended version of our previous works where we proposed the price prediction technique by using ANN, which is based on similar days method. According to similar days method, we select similar price days corresponding to forecast day based on Euclidean norm. The focus of the present paper is mainly on sensitivity analysis of similar days parameter while keeping the parameters same for ANN to forecast hourly electricity prices in the PJM electricity market. We simulated three cases by: (i) selecting two similar days parameters (load at t and price at t); (ii) selecting three similar days parameters (load at t, price at t and price at t - 1), and (iii) selecting five similar days parameters (load at t, load at t - 1, load at t + 1, price at t and price at t - 1). The next-24h price forecasts obtained from ANN based on similar days method confirm that the performance of the ANN model is better when five similar days parameters are selected, i.e., the accuracy of the method is enhanced by the addition of load at t - 1 and t + 1. The factors impacting the electricity price forecasting, including time factors, load factors, and historical price factors are well discussed. Mean absolute percentage error (MAPE) and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination of (R2) of 0.7758 between load and electricity price.

UR - http://www.scopus.com/inward/record.url?scp=50249112159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249112159&partnerID=8YFLogxK

U2 - 10.1109/NAPS.2007.4402367

DO - 10.1109/NAPS.2007.4402367

M3 - Conference contribution

SN - 9781424417261

T3 - 2007 39th North American Power Symposium, NAPS

SP - 568

EP - 574

BT - 2007 39th North American Power Symposium, NAPS

ER -

Mandal P, Senjyu T, Yona A, Park JW, Srivastava AK. Sensitivity analysis of similar days parameters for predicting short-term electricity price. In 2007 39th North American Power Symposium, NAPS. 2007. p. 568-574. 4402367. (2007 39th North American Power Symposium, NAPS). https://doi.org/10.1109/NAPS.2007.4402367