Workload distribution method under task delay and reliability constraint

Abstract

The invention discloses a workload distribution method under task delay and reliability constraint. The method comprises the following steps: 1) constructing a system model; 2) establishing a reliability model, (3) establishing a transmission model, (4) establishing a calculation model, (5) performing problem formulation and (6) solving the question.The method has the advantages that task completion time delay is minimized under the condition that the task reliability requirement is met, reliability is high, and task allocation is clear.

Description

technical field [0001] The invention relates to the application field of mobile edge computing systems, in particular to a workload distribution method under task delay and reliability constraints. Background technique [0002] With the popularization of smart mobile devices and the development of mobile applications, users have higher and higher requirements for network service quality and request delay. Although the processing unit (CPU) of the new generation of mobile devices is increasingly powerful, it is still unable to process huge applications (such as virtual reality, autonomous driving, etc.) in a short period of time. In addition, when a mobile device handles some tasks with a large amount of calculation, the mobile device is affected by its small size and rapid battery consumption, which greatly reduces the user experience and operating efficiency. For the development of mobile platforms in the future, how to solve the problem of limited resources of mobile devi...

AI Technical Summary

Problems solved by technology

The above literature solves the computational reliability problem that a single MEC server cannot meet the task under the constraint of task completion delay through the cooperation among multi-regional MEC servers.

However, this literature only considers how the calculation reliability of the MEC server meets the reliability requirements of the task. In the real scene, each channel has interference, so the reliability of each channel cannot reach 100%. If the channel interference is too large, then The reliability of the channel will be very low, and in 5G remote surgery, intelligent transportation and other applications, the reliability requirements of these applications are all 99.99% or above. A single channel transmission cannot meet the reliability requirements of these applications, resulting in task transmission. Unreliable, which will lead to serious consequences

Secondly, each solution in the task assignment problem has a very large number of neighbor solutions. Although the tabu search method proposed in this paper can jump out of the local optimal solution to search for the global optimal solution, the method is essentially in the field of the current solution. Searching for the optimal solution in , which leads to low search efficiency of the method, and the size of the tabu table is also set according to human experience, which will also lead to low search efficiency for the optimal solution of the problem

Images