All Issue

2021 Vol.41, Issue 5 Preview Page

Research Article

Forecast of Long-term Trend of System Marginal Price with Amounts of Machine Learning Train Data

기계학습 기간에 따른 장기간 전력계통한계가격의 추세 예측

Kyeong-Rok Mun1
,
Keon-Woo Lee2
,
Kyung-Nam Ko3*
문 경록1
,
이 건우2
,
고 경남3*
1Master Course Student, Faculty of Wind Energy Engineering, Graduate School, Jeju National University
2Ph. D. Candidate, Multidisciplinary Graduate School Program for Wind Energy, Graduate School, Jeju National University
3Professor, Faculty of Wind Energy Engineering, Graduate School, Jeju National University
1제주대학교 대학원 풍력공학부, 석사과정
2제주대학교 대학원 풍력특성화협동과정, 박사과정
3제주대학교 대학원 풍력공학부, 교수
*Corresponding Author
30 October 2021. pp. 13-24
PDF XML Citation
Abstract

The yearly system marginal prices (SMPs) in mainland Korea, from 2020 to 2030, were predicted using significant amounts of machine learning training data. The factors for deciding SMP were collected from public data portal sites. The factors included supply capacity, maximum power, supply reserve, liquefied natural gas (LNG), West Texas intermediate crude oil (WTI), and FOB Kalimatan. The best two factors for forecasting SMP, LNG, and WTI were selected through correlation analysis. The training data were divided into cases, A for 10 years and B for 5 years. The models, K-nearest neighbor (KNN), light gradient boost machine (LGBM), random forest (RF), and support vector regression (SVR) models were used for machine learning, and their accuracy was evaluated. Finally, long-term mainland SMPs were forecasted using Japanese LNG and WTI prices. The resultant model for the most accurate machine learning was LGBM which was used to forecast long-term SMPs. The mainland SMP was predicted to decrease from 2020 to 2022 and then maintain 72 KRW/kWh for Case A and 69 KRW/kWh for Case B until 2030.

Keywords
System Marginal Price, SMP
Machine Learning
Public Data
Economic Analysis
LGBM
Long-term Trend Forecasting
키워드
계통한계가격
기계학습
공공데이터
경제성 분석
Light Gradient Boost Machine
장기 추세 예측
References
1
Ministry of Trade, Industry and Energy, The 9th Basic Plan for Long-term Electricity Supply and Demand, Sejong: MOTIE, 2019.
2
Kim, H., Ko, K., and Huh, J., Reassessment of Economic Feasibility for a Wind Farm on Jeju Island Considering, Journal of the Korean Solar Energy Society, Variable Jeju SMP, Vol. 33, No. 5, pp. 41-50, 2013. 10.7836/kses.2013.33.5.041
3
Lee, K. and Ko, K., Analysis of LCOE for Korean Onshore Wind Farm Considering Social Discount Rate, Journal of the Korean Solar Energy Society, Vol. 40, No. 1, pp. 1-13, 2020. 10.7836/kses.2020.40.1.001
4
Jung, S. and Won, D., Relation between Oil Price and Electricity Prices, Korean Energy Economic Review Vol. 19, No. 1, pp. 153-176, 2020.
5
Park, M., Moon, Y., and Park, J., An Analysis on the Causal Relation Among SMP, Base-Load Share, LNG Import Price, and Exchange Rate, Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, Vol. 28, No. 7, pp. 97-105, 2014. 10.5207/JIEIE.2014.28.7.097
6
Kim, D., Lee, C., Jeong, Y., Park, J., and Shin, J., Development of System Marginal Price Forecasting Method Using ARIMA Model, The Transactions of the Korean Institute of Electrical Engineers, Vol. 55, No. 2, pp. 85-93, 2006.
7
Kim, Y., Jeong, M., and Son, N., Forecasting of Short-term Wind Power Generation Based on SVR Using Characteristics of Wind Direction and Wind Speed, The Journal of Korean Institute of Communications and Information Sciences, Vol. 42, No. 5, pp. 1085-1092, 2017. 10.7840/kics.2017.42.5.1085
8
Lee, J., Park, J., Shin, J., and Lee, K., A System Marginal Price Forecasting Method Based On An Artificial Neural Network Using Time and Day Information, International Federation of Automatic Control, Prague, Czech Republic, pp. 122-127, 2005 10.3182/20050703-6-CZ-1902.02256
9
Jufri, F., Oh, S., and Jung, J., Day‑Ahead System Marginal Price Forecasting Using Artificial Neural Network and Similar‑Days Information, Journal of Electrical Engineering & Technology, Vol. 14, pp. 561-568, 2019. 10.1007/s42835-018-00058-w
10
Noh, J. and Cho, H., Forecasting System Marginal Price Using Multilayer Perceptron and Nonlinear Autoregressive exogenous model, Jounal of The Korean Society of Mineral and Energy Resources Engineers, Vol. 57, No. 6, pp. 585-592, 2020. 10.32390/ksmer.2020.57.6.585
11
Shin, D., Baek, S., Lee, Y., and Kang, S., System Marginal Price Time Series Data Forecasting Model Development, The Korean Society of Mechanical Engineers, Gangwon Land Convention Center, Jeongseon-gun, Gangwon-do, pp. 3172-3176, 2018.
12
Kim, J., Kwon, O., Oh, B., Kwak, H., Lee, S., Jang, J., Yang, S., Kim, S., and Lee, D., LSTM Based Intelligent Forecasting Power Load and SMP, The Korea Institute of Electrical Engineers (KIEE) Autumn Conference 2019, pp. 115-117, 2019.
13
Lee, S., Forecasting Volatility of Weekday System Marginal Prices : A Multi-frequency Approach, Korean Energy Economic Review, Vol. 15, No. 2, pp. 89-119, 2016.
14
World Bank, Commodity Markets Outlook, World Bank, October 2019.
15
Shin, D. and Kim, J The Identification of Structural Shocks and Analysis of System Marginal Price Volatility in Korean Electricity Power Market, Korean, Association of Applied Economics, Vol. 17, No. 2, pp. 121-166, 2015.
16
Public Data Portal, https://www.data.go.kr, Accessed on 30.May.2021.
17
Benesty, J., Chen, J., Huang, Y., and Cohen, I., Pearson Correlation Coefficient, Noise Reduction in Speech Processing, Springer, p. 14, 2009. 10.1007/978-3-642-00296-0_5
18
Lee, K., Prediction of Hourly Horizontal Solar Irradiation Using Fuzzy Algorithm, Journal of the Korean Solar Energy Society, Vol. 33, No. 1, pp. 268-273, 2013.
19
Oh, W., Kang, S., and Chan, S., Performance Analysis of Photovoltaic Power System in Saudi Arabia, Journal of the Korean Solar Energy Society, Vol. 37, No. 1, pp. 81-90, 2017. 10.7836/kses.2017.37.1.081
20
Kim, T., Ko, T., Park, Y., Kim, T., and Lee, D., Prediction of Uniaxial Compressive Strength of Rock using Shield TBM Machine Data and Machine Learning Technique, Tunnel & Underground Space, Vol. 30, No. 3, pp. 1225-1275, 2020.
21
Korea Energy Economics Institute, Development and Application of Forecasting Method for Renewable Energy Certificate Price, Ulsan: KEEI, 2015.
Information
  • Publisher :Korean Solar Energy Society
  • Publisher(Ko) :한국태양에너지학회
  • Journal Title :Journal of the Korean Solar Energy Society
  • Journal Title(Ko) :한국태양에너지학회 논문집
  • Volume : 41
  • No :5
  • Pages :13-24
  • Received Date : 2021-08-02
  • Revised Date : 2021-09-01
  • Accepted Date : 2021-09-02
  • DOI :https://doi.org/10.7836/kses.2021.41.5.013
Journal Informaiton Journal of the Korean Solar Energy Society Journal of the Korean Solar Energy Society
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close