Enhanced resource allocation in mobile edge computing using reinforcement learning based MOACO algorithm for IIOT

Abstract

The Mobile networks deploy and offers a multiaspective approach for various resource allocation paradigms and the service based options in the computing segments with its implication in the Industrial Internet of Things (IIOT) and the virtual reality. The Mobile edge computing (MEC) paradigm runs the virtual source with the edge communication between data terminals and the execution in the core network with a high pressure load. The demand to meet all the customer requirements is a better way for planning the execution with the support of cognitive agent. The user data with its behavioral approach is clubbed together to fulfill the service type for IIOT. The swarm intelligence based and reinforcement learning techniques provide a neural caching for the memory within the task execution, the prediction provides the caching strategy and cache business that delay the execution. The factors affecting this delay are predicted with mobile edge computing resources and to assess the performance in the neighboring user equipment. The effectiveness builds a cognitive agent model to assess the resource allocation and the communication network is established to enhance the quality of service. The Reinforcement Learning techniques Multi Objective Ant Colony Optimization (MOACO) algorithms has been applied to deal with the accurate resource allocation between the end users in the way of creating the cost mapping tables creations and optimal allocation in MEC.