Advanced Optimal System for Electricity Price Forecasting Based on Hybrid Techniques

Hua Luo and Yuanyuan Shao ()
Additional contact information
Hua Luo: School of Economics and Finance, Shanghai International Studies University, Shanghai 201620, China
Yuanyuan Shao: School of Statistics, Dongbei University of Finance and Economics, Dalian 116025, China

Energies, 2024, vol. 17, issue 19, 1-24

Abstract: In the context of the electricity sector’s liberalization and deregulation, the accurate forecasting of electricity prices has emerged as a crucial strategy for market participants and operators to minimize costs and maximize profits. However, their effectiveness is hampered by the variable temporal characteristics of real-time electricity prices and a wide array of influencing factors. These challenges hinder a single model’s ability to discern the regularity, thereby compromising forecast precision. This study introduces a novel hybrid system to enhance forecast accuracy. Firstly, by employing an advanced decomposition technique, this methodology identifies different variation features within the electricity price series, thus bolstering feature extraction efficiency. Secondly, the incorporation of a novel multi-objective intelligent optimization algorithm, which utilizes two objective functions to constrain estimation errors, facilitates the optimal integration of multiple deep learning models. The case study uses electricity market data from Australia and Singapore to validate the effectiveness of the algorithm. The forecast results indicate that the hybrid short-term electricity price forecasting system proposed in this paper exhibits higher prediction accuracy compared to traditional single-model predictions, with MAE values of 7.3363 and 4.2784, respectively.

Keywords: electricity price forecasting; hybrid model; improved decomposition technique; novel multi-objective optimization algorithm; artificial intelligence (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/1996-1073/17/19/4833/pdf (application/pdf)
https://www.mdpi.com/1996-1073/17/19/4833/ (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:4833-:d:1486714

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 ().