Research On Mobile Cloud Task Offloading Mechanism Based On Three-way Decisions

In recent years,with the rapid development of the Internet,the performance of mobile devices has been greatly improved,but due to the limitations of mobile device hardware,problems such as insufficient storage space,poor battery performance,and low computing power often occur.For this reason,many researchers have improved the performance of mobile devices by offloading computationally intensive tasks from mobile devices to more resource-rich servers for execution.There are currently many studies on mobile cloud task offloading,including mobile cloud computing,mobile edge computing,and fog computing.This article focuses on the two offloading methods of mobile cloud computing and mobile edge computing.The main contents are as follows:1.Introduce mobile cloud task-related technologies,uninstallation processes,and uninstallation strategies,including the framework structure of tasks offloaded to cloud servers,the framework structure of tasks offloaded to edge servers,how tasks are offloaded to cloud servers and edge servers,how edge servers and cloud servers Collaborative work.This article summarizes some of the three-way decision existing in cloud task offloading,the three-way decision-making theories used in this paper,and the three-way game-theory that evolved from the three decisions.2.Taking the cloud server as the location where tasks can be offloaded,an energysaving offloading strategy for non-delay-sensitive tasks is proposed.If the pending task is in a situation with a good network connection,you can make a decision immediately.If the pending task is in a situation where the network connection is poor,you can wait for the network to improve within the acceptable delay time range.Combining the three branch decision-making theories,by using the cost value generated when different decisions are made in different states,a pair of threshold values ? and ? are obtained to predict the network state at the next moment,so as to make corresponding decisionmaking methods.3.Carry out research on the perspective of task offloading,and consider both cloud servers and edge servers in task processing scenarios.At this time,the task uninstallation is divided into three places: local uninstallation,edge server uninstallation,and cloud server uninstallation.Because the tasks on different devices can be offloaded to the same edge server and cloud server,the tasks in the devices restrict each other and affect each other.To this end,through three-game game-theory concepts,a pair of thresholds is used to divide the number of tasks that different devices are offloaded to three positions.The game is repeated between devices,and the threshold strategy is continuously adjusted until a balance point is found to minimize the overall cost,and measure the end result of the offload strategy at the cost of task processing time,energy consumption,and communication costs.