Publication:
Comparison of Electricity Usage Forecasting Model Evaluation Based on Historical Load Dataset Duration Using Long Short-Term Memory Architecture

Simple item page
dc.citedby1
dc.contributor.authorSalleh N.S.M.en_US
dc.contributor.authorSuliman A.en_US
dc.contributor.authorJ�rgensen B.N.en_US
dc.contributor.authorid54946009300en_US
dc.contributor.authorid25825739000en_US
dc.contributor.authorid7202434812en_US
dc.date.accessioned2023-05-29T09:41:13Z
dc.date.available2023-05-29T09:41:13Z
dc.date.issued2022
dc.descriptionBrain; Electric power utilization; Electric utilities; Forecasting; Learning algorithms; Mean square error; Memory architecture; Electric power company; Electrical power; Electricity usage; Error values; Forecasting models; Load data; Mean absolute error; Mean squared error; Model evaluation; Primary sources; Long short-term memoryen_US
dc.description.abstractElectricity prediction helps electric power companies to generate sufficient electrical power to consumers. The primary source used in performing forecasting is historical electricity usage. This research identified the optimum historical load data period in generating the best model for short-term forecasting of a household. The experiment applied Long Short-Term Memory (LSTM) architecture using Adaptive Learning Rate Method (Adadelta) on four categories of dataset: one-year, two-years, three-years, and four-years. The models produced were evaluated using mean squared error (MSE) and mean absolute error (MAE). The model generated from two-years of historical data performed the best among all other models with MSE value of 0.133621 and MAE value of 0.050653. The experiment was enclosed with the application of the model to predict the electricity usage of the following year, shown in two sample categories: one day and one week. Then, the prediction results were compared with the actual load. � 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1007/978-981-16-8515-6_51
dc.identifier.epage686
dc.identifier.scopus2-s2.0-85127698632
dc.identifier.spage675
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85127698632&doi=10.1007%2f978-981-16-8515-6_51&partnerID=40&md5=76e7a9c7d4a13f42d2ebafe4dadcf81a
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/27224
dc.identifier.volume835
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.sourceScopus
dc.sourcetitleLecture Notes in Electrical Engineering
dc.titleComparison of Electricity Usage Forecasting Model Evaluation Based on Historical Load Dataset Duration Using Long Short-Term Memory Architectureen_US
dc.typeConference Paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS