Novel Custom Loss Functions and Metrics for Reinforced Forecasting of High and Low Day-Ahead Electricity Prices Using Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) and Ensemble Learning

Ziyang Wang (), Masahiro Mae, Takeshi Yamane, Masato Ajisaka, Tatsuya Nakata and Ryuji Matsuhashi
Additional contact information
Ziyang Wang: Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo 113-8656, Japan
Masahiro Mae: Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo 113-8656, Japan
Takeshi Yamane: Department of Energy Systems Research and Development, KYOCERA Corporation, Yokohama 220-0012, Japan
Masato Ajisaka: Department of Energy Systems Research and Development, KYOCERA Corporation, Yokohama 220-0012, Japan
Tatsuya Nakata: Department of Energy Systems Research and Development, KYOCERA Corporation, Yokohama 220-0012, Japan
Ryuji Matsuhashi: Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo 113-8656, Japan

Energies, 2024, vol. 17, issue 19, 1-15

Abstract: Day-ahead electricity price forecasting (DAEPF) is vital for participants in energy markets, particularly in regions with high integration of renewable energy sources (RESs), where price volatility poses significant challenges. The accurate forecasting of high and low electricity prices is particularly essential, as market participants seek to optimize their strategies by selling electricity when prices are high and purchasing when prices are low to maximize profits and minimize costs. In Japan, the increasing integration of RES has caused day-ahead electricity prices to frequently fall to almost zero JPY/kWh during periods of high RES output, creating significant profitability challenges for electricity retailers. This paper introduces novel custom loss functions and metrics specifically designed to improve the forecasting accuracy of extreme prices (high and low prices) in DAEPF, with a focus on the Japanese wholesale electricity market, addressing the unique challenges posed by the volatility of RES. To implement this, we integrate these custom loss functions into a Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model, augmented by an ensemble learning approach and multimodal features. The proposed custom loss functions and metrics were rigorously validated, demonstrating their effectiveness in accurately predicting high and low electricity prices, thereby indicating their practical application in enhancing the economic strategies of market participants.

Keywords: day-ahead electricity price forecasting (DAEPF); custom loss function; weighted mean absolute error (WMAE); CNN-LSTM; ensemble learning (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/17/19/4885/pdf (application/pdf)
https://www.mdpi.com/1996-1073/17/19/4885/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:17:y:2024:i:19:p:4885-:d:1488606

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().