A Comparative Study of Machine Learning and Deep Learning for Time Series Forecasting: A Case Study of Choosing the Best Prediction Model for Turkey Electricity Production

Abstract

Over the last decades, Turkey pays special attention to electricity production to afford its needs. Researchers applied different methodologies including statisticalbased and artificial intelligence-based to correctly predict the future amount of electricity production, consumption, and demand. However,limited researchers focused on Turkey's electricity production prediction problem as a time series analysis. For this reason, we tackle this problem by considering it as a time series analysis in this study. We have used different methods including traditional machine learning algorithms Support Vector Regression (SVR) and Multilayer Perceptrons (MLP) and a deep learning algorithm Long Short-Term Memory (LSTM) to create a better model for Turkey monthly electricity production dataset. Based on our findings LSTM outperforms SVR and MLP approaches in terms of commonly used statistical error evaluation metrics

The Time-Series Production Simulation in Cost Management of New Energy Grid Connection Under the Internet of Things

“…Hamdoun et al comprehensively analyzed and evaluated various traditional, machine learning, and DL methods for time series forecasting problems related to various energy sources [17]. Ramazan employed different approaches, including traditional machine learning algorithms such as Support Vector Regression (SVR) and Multilayer Perceptrons (MLP), and DL algorithm Long Short-Term Memory (LSTM), to create a better model for handling Turkey's monthly electricity production dataset [18]. The research results demonstrated that LSTM outperformed SVR and MLP methods in commonly used statistical error evaluation indicators.…”