Multistep interval prediction model with adjustable horizon for uncertain power load forecasting

Shouping Guan, Chongyang Xu and Tianyi Guan

Energy, 2025, vol. 335, issue C

Abstract: In order to use the prediction interval (PI) method to forecast multistep uncertain power load, this paper proposes a multistep interval prediction model (MIPM) using neural network-based PIs. An iterative lower and upper bounds estimation (ILUBE) neural network with interval input and interval output is constructed, and a new set of PI performance indices with adjustable prediction horizon for ILUBE is proposed to satisfy the needs of high-quality multistep PIs. A knee selection criteria-based multi-objective particle swarm optimization (KMOPSO) algorithm specifically designed for PI is presented to optimize the ILUEB parameters. The power load forecasting of two actual regions is taken as an example, and the proposed MIPM is applied to carry out multistep interval prediction, respectively. The prediction results and the effect of adjusting prediction horizon demonstrate that the proposed model can realize higher quality PIs, even in the situation of arbitrarily adjusting the prediction horizon.

Keywords: Multistep power load forecasting; Prediction interval (PI); Multi-objective particle swarm optimization (MOPSO); Adjustable prediction horizon; Iterative PI network (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225034103
Full text for ScienceDirect subscribers only

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:eee:energy:v:335:y:2025:i:c:s0360544225034103

DOI: 10.1016/j.energy.2025.137768

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().