Advanced short-term load forecasting in power systems using machine learning technologies

View at publisher Summarise with VIRAT
Authors: Amritjot Kaur, Divia Cheetu, Manjeet Singh, Rishabh Dev Shukla, Anton Pavlovich Pljonkin
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The present paper serves as a comprehensive assessment of Short-term-load-forecasting (STLF) using machine learning methodologies, focusing solely on the Panama case study. The data set used for this exercise consists of multiple data sources, including historical electricity load data, weather variables, and calendar data. Machine learning models include multiple linear regression and neural networks and will be used to predict electricity load demand. The findings also identify the efficacy relevant to the comparison of the model forecasts with official forecasts. The results provide evidence that machine learning models in STLF can be effective, demonstrates the importance of incorporating contextual variables, and illustrates added benefits to the electricity demand prediction of STLF models. The study also considers the limitations of the approach and the potential for future research to increase the technological reliability and scalability of STLF model types. The research advances STLF methodologies that have a natural path for adopting the machine-learning techniques in load forecasting.

Fields of Study & Subjects

Energy Load and Power Forecasting Smart Grid Energy Management Solar Radiation and Photovoltaics

Publication details

Journal / source
CRC Press eBooks
Pages
555–562
Publication date
19 March 2026
Language
EN
Document type
Book chapter