An integrated system of energy generation, storages, and appliances consumption based on machine learning techniques and internet of things

Abstract

In the swiftly evolving micro-grid landscape, this paper explores the pivotal role of residential consumers and their active engagement. The primary focus is on revolutionizing customer management through the integration of smart homes, with an emphasis on facilitating demand response and bolstering operational efficiency. Also, the innovative Power Generation, Electricity Storages, and Energy Consumption in Smart Homes (PG–ES–ECSH) approach is introduced, meticulously designed for next-generation technologies, and delve into an smart home load control system. This system, employing Extreme Machine Learning (EML) and an imprecise reasoning framework, aims to enhance computational efficiency in managing diverse electrical energy sources and small-scale power generation appliances. The decision-making process of the framework incorporates real-time monitoring of environmental data, power generation, and battery storage. Our research significantly contributes to the evolution of smart homes and micro-grids by embracing technologies crucial for the future, such as machine learning and the Internet of Things (IoT). In this paper, the application of IoT and EML are used to enhance the connection between users in the microgrid and the learning rate of the proposed system, respectively. Emphasizing the burgeoning significance of energy management in smart homes, our study underscores the profound impact of energy resources on overall quality of life. With the increasing prevalence of smart homes, there is a growing demand for efficient energy utilization and management. Noteworthy is the PG–ES–ECSH method's impressive accuracy ratio of 96 % and a precision rate of 92 %. These findings highlight the imperative need for cost-effective energy management solutions, particularly in the face of escalating electricity consumption and the integration of novel power resources.