Improved conservation of energy in fog IoT services using machine learning model

English (OpenAlex)

This Fog Computing is an extension of Cloud Computing technology to the network edge, which enables a newer breed of services and applications. Resource sharing and resource discovery is considered to be critical for the performance of fog computing applications. In general, the methods to reduce are consumption of energy in heterogonous network is very minimal. Considering the higher consumption of energy in heterogeneous networks as a problem statement, this work proposes a machine learning model to reduce the consumption of energy demand in fog computing Internet of Things (IoT) services. Considering the problem, the machine learning model adopts network density, latency and mobility as its energy constraints and designs an objective function to support the lower energy consumption in the network. The simulation of the proposed method is carried out between the proposed and existing methods in terms of various performance metrics. The result shows that the proposed machine learning method in Fog IoT environment is efficient in conserving the energy than the other methods.