Study on Enhancing the Efficiency of Work Scheduling Methods in Cloud Environments

Abstract

Mobile cloud computing, the offspring of cloud computing and mobile computing, is mostly dependent on loading computation. Since these sorts of demanding programs are not intended for mobile devices, the process of shifting them from a mobile device to a public cloud is called quotcomputation offloading.quot To efficiently offload the demanding applications, a number of algorithms were developed, including the Deep newlineReinforcement Learning Computation Offloading Algorithm and the Artificial Bee Colony Optimization Algorithm. The Reinforcement technique is used to determine which host the application may switch to without overwhelming it and creating deadlocks. A machine learning technique called Deep Reinforcement Learning Computation Offloading chooses which virtual machine the application should be offloaded to in order to guarantee that it runs. It uses a reward-based strategy to do this. The Artificial Bee Colony Algorithm is an efficient way to move big apps from mobile devices to the cloud, where they are cross-validated all the way up to the final application, using a convolution neural network. Similar to neural networks, convolution neural networks have a specific kind of layer. Each layer of a convolution neural network translates a three-dimensional input volume into a three-dimensional output volume of neuron activations. Every task that has been offloaded is crossverified using a convolution neural network. The Convolution Neural Network uses the confusion matrix to get accurate results. Several parameters, including Efficiency, Computational Intensity, Resource Utilization, and Computation Overhead, are developed in order to assess the accuracy of Computation Offloading using Deep Reinforcement Learning Computation Offloading Algorithm, Artificial Bee Colony Algorithm, and Convolution Neural Network. Computation offloading factors include things like resource context awareness, performance context, and user context.