Mid-term electricity demand forecasting using improved variational mode decomposition and extreme learning machine optimized by sparrow search algorithm

Tian Gao, Dongxiao Niu, Zhengsen Ji and Lijie Sun

Energy, 2022, vol. 261, issue PB

Abstract: Mid-term electricity demand forecasting plays an important role in ensuring the operational safety of the power system and the economic efficiency of grid companies. Most studies have focused on deterministic forecasting of electricity demand, while ignoring uncertainty analysis of electricity demand. To bridge this research gap, a point-interval mid-term electricity demand forecasting model is proposed. Firstly, based on Pearson correlation coefficient, feature dimensionality reduction is carried out to filter out key features that greatly affect electricity demand, such as socio-economic factors and meteorological factors, to enhance forecasting efficiency. Secondly, improved variational mode decomposition (IVMD) optimized by sparrow search algorithm (SSA) is proposed to decompose electricity demand series into several subsequences. By combining SSA, extreme learning machine (ELM) and adaptive boosting algorithm (Adaboost), IELM-Adaboost is constructed to forecast each subsequence, and the point forecasting results are obtained by superimposing each subsequence forecasting result. Finally, electricity demand forecasting intervals will be obtained by the application of the kernel density estimation (KDE) of point forecasting error. Three Chinese provinces are applied for empirical analysis in this paper. Compared with ELM, the MAPE of the proposed model in the three datasets are reduced by 87.90%, 66.05% and 75.97% respectively, showing promising point forecasting performance. The empirical results prove that IVMD-IELM-Adaboost performs well in both point forecasting and interval forecasting.

Keywords: Mid-term electricity demand forecasting; Extreme learning machine; Improved variational mode decomposition; Adaptive boosting; Interval forecast (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222022125
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:261:y:2022:i:pb:s0360544222022125

DOI: 10.1016/j.energy.2022.125328

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 ().