Forecasting System Marginal Price Using Multilayer Perceptron and Nonlinear Autoregressive exogenous model

Jooman Noh and Hong Chong Cho

doi:10.32390/ksmer.2020.57.6.585

All Issue

2020 Vol.57, Issue 6 Preview Page Next Page

Research Paper

Forecasting System Marginal Price Using Multilayer Perceptron and Nonlinear Autoregressive exogenous model Multilayer Perceptron(MLP), Nonlinear Autoregressive exogenous (NARX) 모형을 이용한 계통한계가격(SMP) 예측

December 2020. pp. 585-592

PDF XML

Abstract

우리나라 전력시장 발전부문에 경쟁을 도입함으로써 각발전사들이 얼마나 발전해야 할지는 중요한 문제가 되었고, 안정적인 계통한계가격(System Marginal Price, SMP)유지는 중요한 문제다. 본 연구에서는 인공신경망 중 MLP(Multi-Layer Perceptron), NARX(Nonlinear Autoregressive exogenous)를 이용하여 서로 비교 분석했고 외부변수로 전력수요를 설정하여 SMP를 예측했으며, ARIMA(Autoregressive Integrated Moving Average)와도 비교를 실시했다. 모두 30일, 40일, 50일을 예측해 봤으며 MLP의 경우 은닉층의 개수가 90개, 85개, 80개 였을 때 최적의 결과를 보여준 반면, NARX의 경우 95개, 80개, 70개 였을 때 최적의 결과를 보여주었다. 전반적으로 모든 예측에서 ARIMA, MLP, NARX 순으로 예측 오차가 작게 나타났다.

키워드

SMP예측

MLP

NARX

우리나라 전력시장

With the introduction of competition in the power generation sector in Korea, determining how much each electricity company should develop and maintain a stable system marginal price (SMP) has become an important issue. In this study, SMP was predicted by comparing the values for each company using a multilayer perceptron (MLP) and nonlinear autoregressive exogenous (NARX) model among artificial neural networks (ANN), and setting electricity demand as an external variable. The Autoregressive Integrated Moving Average (ARIMA) was also compared. Each method predicted 30, 40, and 50 days. In the case of MLP, optimal results were obtained when the number of hidden layer units were 90, 85, and 80, whereas in the case of NARX, optimal results were obtained when the number of hidden layer units were 95, 80, and 70. Overall, the forecast errors were small in the order of ARIMA, MLP, and NARX for all predictions.

Keywords

SMP Forecasting

Multilayer Perceptron (MLP)

Nonliner Autoregressive exogenous (NARX)

Korea’s electricity market

References

Jeong, S.Y., 2006. Day Ahead System Marginal Price Forecasting Using an Artificial Neural Network, MS Thesis, Kon Kuk University, Seoul, Korea, 41p.

Jeong, S.Y., Lee, J.K., Park, J.B., Shin, J.R., and K, S.S., 2005. A hybrid neural network framework for hour-ahead system marginal price forecasting. The Transactions of the Korean Institute of Electrical Engineers (KIEE) Autumn Conference 2005, p.162-164.

Kim, D.W., Kim, K.I., Cho, S.B., and Choi, W.J., 2015. A Study on Improving Capacity Payments in the Korean Electricity Market. Korean Energy Economic Review, 14(3), p.293-318.

Kim, D.Y., Lee, C.J., Jeong, Y.W., Park, J.B., and Shin, J.R., 2006. Development of system marginal price forecasting method using ARIMA model. The Transactions of the Korean Institute of Electrical Engineers,55(2), p.85-93.

Kim, D.Y., Lee, C.J., Lee, M.H., Park, J.B., and Shin, J.R., 2005. A day-ahead system marginal price forecasting using ARIMA model. The Transactions of the Korean Institute of Electrical Engineers (KIEE) Summer Conference 2005,p.819-821.

Kim, N.Y., 2019. A Study on Power Price Prediction Model Based on Artificial Neural Networks, MS Thesis, Korea Polytechnic University, Seoul, Korea, 48p.

Korea Energy Economics Institute, 2003. A Study on the Behavior of Market Participants in the Power Wholesale Market: Game Theoretical Approach, KEEI Report 2003-03, Ulsan, Korea, 91p.

Korea Energy Economics Institute, 2013. A Study on the Stabilization of Power Market Price, KEEI Issue Paper 13-03, Ulsan, Korea, 23p.

Korea Institute Industrial Economics & Trade, 2007. Major Issues and Problems of the Current Power Market Operating System and Direction of Improvement, KIET Industrial Economic Review Report 2007-07, Sejong, Korea, p.53-68.

Lee, J.K., Park, J.B., Shin, J.R., and Lee, K.Y., 2005. A system marginal price forecasting method based on an artificial neural network using time and day information. International Federation of Automatic Control(IFAC) Journal 16th Triennial World Congress, Prague, Czech Republic, p. 122-127. 10.3182/20050703-6-CZ-1902.02256

Lee, S.H., 2016. Forecasting volatility of weekday system marginal prices: a multi-frequency approach. Korean Energy Economic Review, 15(2), p.89-119.

Shin, D., Baek, S., Lee, Y., and Kang, S., 2018. System marginal price time series data forecasting model development. The Korean Society of Mechanical Engineers,Kangwon Land Convention Center, Jeongseon-gun, Gangwon-do, p.3172-3176.

Shin, D.Y. and Kim, J.H., 2015. The identification of structural shocks and analysis of system marginal price volatility in Korean electricity power market. Korean Association of Applied Economics, 17(2), p.121-166.

Software Policy & Research Institute, 2017. Deep Learning Tutorial-Understanding Neural Network & Deep Learning, SPRI Report 2016-007, Gyeonggi-do, Korea, 71p.

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 57
No :6
Pages :585-592
Received Date :2020. 11. 02
Revised Date :2020. 12. 04
Accepted Date : 2020. 12. 22
DOI :https://doi.org/10.32390/ksmer.2020.57.6.585

Journal of the Korean Society of Mineral and Energy Resources Engineers ISSN:2288-0291(Print) 2288-2790(Online) 한국자원공학회지

All Issue