Investigation of energy demand correlation during pandemic using self-organizing map algorithm

Abstract

The world faces a significant impact from the coronavirus disease 2019 (Covid-19) pandemic, which also influences energy consumption. This study investigates the substantial connection of the classified data between power consumption, cooling degree days, average temperature, and covid-19 cases information using mathematical and neural network approaches regression analysis, and self-organizing maps. It is well established that various data mining methods have revamped the classification process of data analytics. Specifically, this study investigates the correlation between the collected variables using regression analysis and selecting the best-matching unit under the normalization method using self-organizing maps. The selforganizing maps become better when the datasets have variations; the result denotes that this method produced high mapping quality based on the map size and normalization method. Furthermore, the data crossing connection is indicated using the regression analysis method. Finally, the classified data results during the movement control order are validated in self-organizing maps to achieve the study objective. By performing these methods, this study established that the correlation between the energy demand towards cooling degree days, average temperature, and covid-19 cases is very weak. The verification has been made where the ‘logistic’ normalization method has produced the best classification result.