Predictive Analysis of Energy Consumption for Energy Management in Smart Homes

The pace of energy use has significantly grown during the previous several years. In order to reduce energy consumption and demand, energy management systems (EMS) are required in households, workplaces, structures, industries, etc. Newly developing technologies like artificial intelligence (AI), the Internet of Things (IoT), big data, machine learning (ML), deep learning (DL), etc., may assist with this. This helps the users to achieve a very new, sustainable, and advanced life experiences in their homes. This paper aims to discuss smart home energy consumption and weather conditions which affects the demand and consumption of energy in any particular environment. In this research work, a smart home dataset which has different parameters of energy consumption and weather conditions is taken from the online repositories. This dataset is preprocessed using different machine learning techniques. After the preprocessing, the best suited model for the predictive modeling of the energy consumption in smart homes is obtained. A comparative analysis is carried out to find the best techniques among the existing techniques with the batter results and less error rate. This paper aims to perform the predictive modeling of the energy consumption dataset and find out the best suited technique with less error rate.