Empirical Mode Decomposition with Random Forest Model Based Short Term Load Forecasting

Abstract

This paper presents a hybrid methodology for improving load forecasting in electric power networks by combining the time-frequency data analysis method based on Empirical Mode Decomposition (EMD) with the Random Forest (RF) technique. The performance of the hybrid EMD-RF model is tested on real-time load data of Bengaluru city, Karnataka (India) from 01st January 2019 to 30th June 2019. An ensemble empirical mode decomposition is applied to decompose original load data into various signals known as intrinsic mode functions (IMF). The meteorological variables (MV) such as moisture content, dew point, dry bulb temperature, humidity, and solar irradiance (SR) are also taken into consideration for the day ahead seasonal STLF. The decomposed signals are further analysed using the ensemble learning-based Random Forest (RF) technique. The result obtained from the model is aggregated to obtain the final forecasted result. The superiority of the hybrid EMD-RF model is established through a comparative statistical error analysis with other non-decomposition and decomposition methods based on EMD-Bagging, EMD-ANN, Artificial Neural Network (ANN), Bagging, and Random Forest (RF).

Multi-objective optimization of distributed energy resources based microgrid using random forest model

“…Numerous studies have examined the use of such algorithms to address the battery sizing problem of renewable energy systems producing better outcomes [10], [11]. Recently, due to the advancement in artificial intelligence (AI) tools, machine learning-based optimization techniques are implemented in MG for fast convergence and more accurate results [12], [13].…”