EXPERIMENTAL INVESTIGATION ON LONG-TERM FORECASTING OF AREA POWER LOAD USING DEEP LEARNING AND MACHINE LEARNING METHODS

Volume 18 No 6 (2020)

Paresh S Chaudhari

DOI: 10.48047/nq.2020.18.6.NQ20193

Abstract

Climate change and smart grid advancements have heightened the need for accurate electricity demand forecasts. This study develops and compares district-level load prediction models using machine learning and deep learning techniques. Results show deep learning outperforms traditional methods with an R-Squared of 0.93–0.96 and MAPE of 4–10%. The model benefits grid management and expansion for municipalities and utility companies, and aids households in adopting renewable energy technologies.

Keywords

neural networks (RNN); random forest; support vector machine (SVM) long short-term memory (LSTM); deep learning; machine learning; non-linear auto-regressive exogenous (NARX)

Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.