Open AccessReview on Analysis of Power Supply and Demand in Maharashtra State for Load Forecasting Using ANN
Author(s) -
Suraj G. Patil,
M. S. Ali
Publication year - 2022
Publication title -
international journal of scientific research in science and technology
Language(s) - English
Resource type - Journals
eISSN - 2395-602X
pISSN - 2395-6011
DOI - 10.32628/ijsrst229152
Subject(s) - computer science , electric power system , fuzzy logic , artificial neural network , scheduling (production processes) , electric power , electrical load , support vector machine , artificial intelligence , electric power industry , operations research , industrial engineering , reliability engineering , machine learning , power (physics) , engineering , electricity , operations management , physics , electrical engineering , quantum mechanics
The Electric load forecasting (ELF) is a critical procedure in the electrical industry's planning and plays a critical role in electric capacity scheduling and power system management, hence it has piqued academic attention. As a result, for energy generating capacity scheduling and power system management, the accuracy of electric load forecasting is critical. This document provides an overview of power load forecasting methodologies and models. A total of 40 scholarly publications were included in the comparison, which was based on certain criteria such as time frame, inputs, outcomes, project scale, and value. Despite the relative simplicity of all studied models, the regression analysis is still extensively employed and effective for long-term forecasting, according to the research. Machine learning or artificial intelligence-based models such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Fuzzy logic are preferred for short-term forecasts.