Open AccessPrediction of Electrical Energy Consumption Using LSTM Algorithm with Teacher Forcing Technique
Author(s) -
Sasmitoh Rahmad Riady,
Tjong Wan Sen
Publication year - 2021
Publication title -
jurnal informatika dan sains/jisa (jurnal informatika dan sains)
Language(s) - English
Resource type - Journals
eISSN - 2776-3234
pISSN - 2614-8404
DOI - 10.31326/jisa.v4i1.904
Subject(s) - forcing (mathematics) , softmax function , mean squared error , computer science , multivariate statistics , algorithm , artificial intelligence , machine learning , energy consumption , time series , series (stratigraphy) , mathematics , statistics , deep learning , engineering , mathematical analysis , paleontology , electrical engineering , biology
Electrical energy is an important foundation in world economic growth, therefore it requires an accurate prediction in predicting energy consumption in the future. The methods that are often used in previous research are the Time Series and Machine Learning methods, but recently there has been a new method that can predict energy consumption using the Deep Learning Method which can process data quickly for training and testing. In this research, the researcher proposes a model and algorithm which contained in Deep Learning, that is Multivariate Time Series Model with LSTM Algorithm and using Teacher Forcing Technique for predicting electrical energy consumption in the future. Because Multivariate Time Series Model and LSTM Algorithm can receive input with various conditions or seasons of electrical energy consumption. Teacher Forcing Technique is able lighten up the computation so that it can training and testing data quickly. The method used in this study is to compare Teacher Forcing LSTM with Non-Teacher Forcing LSTM in Multivariate Time Series model using several activation functions that produce significant differences. TF value of RMSE 0.006, MAE 0.070 and Non-TF has RMSE and MAE values of 0.117 and 0.246. The value of the two models is obtained from Sigmoid Activation and the worst value of the two models is in the Softmax activation function, with TF values is RMSE 0.423, MAE 0.485 and Non-TF RMSE 0.520, MAE 0.519.