Hours ahead automed long short-term memory (LSTM) electricity load forecasting at substation level: Newcastle substation

Nowadays, electrical energy is of vital importance in our lives, every country needs this resource to develop its economy, factories, businesses, and homes are the basis economic structure a country. In city Newcastle as other cities constant development growing day by terms industries, these elements ones that consume all electricity produced Newcastle. Although Australia has strategically located substations serve function supplying existing loads with quality power, from time load will exceed capacity not be able supply arise future grows. To find solution problem, we use deep learning model improve accuracy. paper, Long Short-Term Memory recurrent neural network (LSTM) tested on publicly available 30-minute dataset containing measured real power data for individual zone Ausgrid area data. The performance comprehensively compared 4 different configurations LSTM. proposed LSTM approach 2 hidden layers 50 neurons outperforms mean absolute error (MAE) 0.0050 short-term forecasting task substations.