Comparison of Electricity Load Prediction Errors Between Long Short-Term Memory Architecture and Artificial Neural Network on Smart Meter Consumer

Nur Shakirah Md Salleh*, Azizah Suliman, Bo Nørregaard Jørgensen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Machine learning can perform electricity load prediction on the demand side. This paper compared the electricity prediction errors between two machine learning algorithms: Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) architecture. LSTM can solve the regression problem in time-series. Due to that, this paper applied LSTM. The traditional machine learning approach, ANN, was used to compare the effectiveness of LSTM in performing the time-series prediction. A dataset that consisted of historical electricity consumption data with independent variables was used in this study. The mean squared error (MSE) and mean absolute error (MAE) evaluation metrics were used to evaluate the models. The model generated using LSTM showed the lowest error with MSE value of 0.1238 and MAE value of 0.0388. These results indicated that choosing a suitable machine learning algorithm for the time-series problem could improve the model generated from the training session.

Original languageEnglish
Title of host publicationAdvances in Visual Informatics : 7th International Visual Informatics Conference, IVIC 2021, Kajang, Malaysia, November 23–25, 2021, Proceedings
EditorsHalimah Badioze Zaman, Alan F. Smeaton, Timothy K. Shih, Sergio Velastin, Tada Terutoshi, Bo Nørregaard Jørgensen, Hazleen Aris, Nazrita Ibrahim
PublisherSpringer
Publication date2021
Pages600-609
ISBN (Print)9783030902346
ISBN (Electronic)978-3-030-90235-3
DOIs
Publication statusPublished - 2021
Event7th International Conference on Advances in Visual Informatics, IVIC 2021 - Kajang, Malaysia
Duration: 23. Nov 202125. Nov 2021

Conference

Conference7th International Conference on Advances in Visual Informatics, IVIC 2021
Country/TerritoryMalaysia
CityKajang
Period23/11/202125/11/2021
SeriesLecture Notes in Computer Science
Volume13051
ISSN0302-9743

Keywords

  • ANN
  • Electricity load
  • LSTM
  • Regression
  • Time-series

Fingerprint

Dive into the research topics of 'Comparison of Electricity Load Prediction Errors Between Long Short-Term Memory Architecture and Artificial Neural Network on Smart Meter Consumer'. Together they form a unique fingerprint.

Cite this