Regression learning assisted efficient energy harvesting method for smart city environment

Abstract

Energy Harvesting in smart cities is a demanding requirement to improve the lifetime of the end-user services. It is achieved by balancing the data transmission, energy consumption, and conservation optimally. In this article, the learning assisted efficient energy harvesting method is proposed for improving the energy efficiency of the Internet of Things (IoT) devices deployed in the smart city environment. The regression learning model used in this proposed method classifies the time and energy-dependent schedules for data queuing and transmission in a view to maximising throughput. Cost-based data transmission and energy harvesting approaches are the concurrent procedures used to identify the linear descent points through the regression method. This identification helps mitigate unnecessary energy dissemination and early energy drain of the IoT devices for their allocated/transmitted data. The performance of the proposed method is evaluated using simulations, and it is verified using the metrics energy consumption, remaining energy ratio, energy harvested, cost factor, and throughput. The proposed method helps to minimise the energy consumption rate and maximise the throughput in an effective manner.