The Library
High-resolution load forecasting on multiple time scales using Long Short-Term Memory and Support Vector Machine
Tools
Zhang, Sizhe, Liu, Jinqi and Wang, Jihong (2023) High-resolution load forecasting on multiple time scales using Long Short-Term Memory and Support Vector Machine. Energies, 16 (4). 1806. doi:10.3390/en16041806 ISSN 1996-1073.
|
PDF
WRAP-High-resolution-load-forecasting-on-multiple-time-scales-Wang-2023.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (1629Kb) | Preview |
Official URL: https://doi.org/10.3390/en16041806
Abstract
Electricity load prediction is an essential tool for power system planning, operation and manage-ment. The critical information it provides can be used by energy providers to maximise power system operation efficiency and minimise system operation costs. Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) are two suitable methods that have been successfully used for analysing time series problems. In this paper, the two algorithms are explored further for load prediction; two load prediction algorithms are developed and verified by using the half-hourly load data from the University of Warwick campus energy centre with four different prediction time horizons. The novelty lies in comparing and analysing the prediction accuracy of two intelligent algorithms with multiple time scales and in exploring better scenarios for their prediction applica-tions. High-resolution load forecasting over a long range of time is also conducted in this paper. The MAPE values for the LSTM are 2.501%, 3.577%, 25.073% and 69.947% for four prediction time horizons delineated. For the SVM, the MAPE values are 2.531%, 5.039%, 7.819% and 10.841%, respectively. It is found that both methods are suitable for shorter time horizon predictions. The results show that LSTM is more capable of ultra-short and short-term forecasting, while SVM has a higher prediction accuracy in medium-term and long-term forecasts. Further investigation is per-formed via blind tests and the test results are consistent.
Item Type: | Journal Article | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > Q Science (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > Engineering | ||||||
Library of Congress Subject Headings (LCSH): | Support vector machines, Electric power production, Algorithms, Neural networks (Computer science), Time-series analysis, Forecasting | ||||||
Journal or Publication Title: | Energies | ||||||
Publisher: | M.D.P.I.A.G. | ||||||
ISSN: | 1996-1073 | ||||||
Official Date: | 11 February 2023 | ||||||
Dates: |
|
||||||
Volume: | 16 | ||||||
Number: | 4 | ||||||
Article Number: | 1806 | ||||||
DOI: | 10.3390/en16041806 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||
Date of first compliant deposit: | 13 February 2023 | ||||||
Date of first compliant Open Access: | 13 February 2023 | ||||||
RIOXX Funder/Project Grant: |
|
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year