Short Term Electric Load Forecast with Artificial Neural Networks

TL;DR

This paper explores short-term electric load forecasting using various neural network structures, highlighting the importance of accurate predictions for energy management in open markets.

Contribution

It compares multiple neural network architectures for load forecasting and identifies the most effective structures through extensive training.

Findings

Different neural network structures were evaluated for accuracy.

Best neural network configurations were identified for load prediction.

The study emphasizes the importance of neural networks in energy management.

Abstract

This paper presents issues regarding short term electric load forecasting using feedforward and Elman recurrent neural networks. The study cases were developed using measured data representing electrical energy consume from Banat area. There were considered 35 different types of structure for both feedforward and recurrent network cases. For each type of neural network structure were performed many trainings and best solution was selected. The issue of forecasting the load on short term is essential in the effective energetic consume management in an open market environment.