An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development

Jin Yang (), Guangxin Jiang (), Yinan Wang () and Ying Chen ()
Additional contact information
Jin Yang: School of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
Guangxin Jiang: School of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
Yinan Wang: Department of Industrial and Systems Engineering, Rensselaer Polytechnic Institute, Troy, New York 12180
Ying Chen: School of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China

INFORMS Journal on Computing, 2025, vol. 37, issue 2, 480-501

Abstract: Recent years have witnessed exponential growth in developing deep learning models for time series electricity forecasting in power systems. However, most of the proposed models are designed based on the designers’ inherent knowledge and experience without elaborating on the suitability of the proposed neural architectures. Moreover, these models cannot be self-adjusted to dynamically changed data patterns due to the inflexible design of their structures. Although several recent studies have considered the application of the neural architecture search (NAS) technique for obtaining a network with an optimized structure in the electricity forecasting sector, their training process is computationally expensive and their search strategies are not flexible, indicating that the NAS application in this area is still at an infancy stage. In this study, we propose an intelligent automated architecture search (IAAS) framework for the development of time series electricity forecasting models. The proposed framework contains three primary components, that is, network function–preserving transformation operation, reinforcement learning–based network transformation control, and heuristic network screening, which aim to improve the search quality of a network structure. After conducting comprehensive experiments on two publicly available electricity load data sets and two wind power data sets, we demonstrate that the proposed IAAS framework significantly outperforms the 10 existing models or methods in terms of forecasting accuracy and stability. Finally, we perform an ablation experiment to showcase the importance of critical components in the proposed IAAS framework in improving forecasting accuracy.

Keywords: neural architecture search; electricity forecasting; recurrent neural network; reinforcement learning; network transformation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/ijoc.2023.0034 (application/pdf)

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:inm:orijoc:v:37:y:2025:i:2:p:480-501

Access Statistics for this article

More articles in INFORMS Journal on Computing from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().