Open AccessHYBRID NEURO-WAVELET MODEL FOR SHORT TERM LOAD FORECASTING
Author(s) -
Ravindra M. Gimonkar,
Deepak Kapgate
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v06i05.041
Subject(s) - wavelet , artificial neural network , computer science , term (time) , electricity , wavelet transform , discrete wavelet transform , levenberg–marquardt algorithm , artificial intelligence , data mining , machine learning , engineering , physics , quantum mechanics , electrical engineering
- Accuracy of the electricity load forecasting iscrucial in providing better cost effective risk managementplans. This paper proposes a Short Term Electricity LoadForecast (STLF) model with a high forecasting accuracy.A cascaded forward BPN neuro-wavelet forecast model isadopted to perform the STLF. The model is composed ofseveral neural networks whose data are processed using awavelet technique. The data to be used in the model iselectricity load historical data. The historical electricityload data is decomposed into several wavelet coefficientusing the Discrete wavelet transform (DWT). The waveletcoefficients are used to train the neural networks (NNs)and later, used as the inputs to the NNs for electricity loadprediction. The Levenberg-Marquardt (LM) algorithm isselected as the training algorithm for the NNs. To obtainthe final forecast, the outputs from the NNs arerecombined using the same wavelet technique.