Vol 5, No 1 (2020)

Neural Network-based Electricity Load Forecasting using Constructive Technique

Authors: Kazi Rafiqul Islam, Md. Shahid Iqbal, Md. Monirul Kabir

Abstract: This paper presents a new electricity load forecasting (ELF) model based on feed-forward neural network (FFNN) using the constructive technique  in course of training. The vital aspect of this model is to determine the FFNN architecture automatically during training in order to forecast the electricity load. Thus, the strength of standard FFNN increases in forecasting the electricity load. Furthermore, the proposed model overcomes efficiently the existing shortcomings of FFNN to predict loads of holidays and fast load changes. We call this model as constructive  approach for electricity load forecasting (CAELF) as per short term basis. In order to evaluate the performance of CAELF, the daily electricity load demand data of Spain has been used. Extensive experimental results and comparisons show that CAELF has a significant capability to forecast the electricity load compared to the other standard FFNN models.

 Keywords: Electricity load forecasting (ELF), CAELF, FFNN models

Full Issue

View or download the full issue PDF 11-30

Table of Contents