Research On Task Offloading Optimization Of Mobile Edge Computing System

With the popularization of mobile devices and the development of wireless communication technology,a large number of low-latency and high-energy-consumption mobile applications continue to emerge.The arrival of the 5th Generation Mobile Communication System(5G)has accelerated the development of such applications.Traditional Mobile Cloud Computing(MCC)has large network delay due to long-distance data offloading and massive data aggregation,which makes it difficult to meet the low-latency requirements of new applications.Mobile Edge Computing(MEC)provides computing services for users at the edge of the network,effectively reducing data transmission and processing delays,and has become a key technology for 5G low-latency communication.How to optimize the design of offloading strategies to ensure low latency,low energy consumption and highly reliable communication is a very challenging task for MEC.Therefore,this paper focuses on the multi-task offloading calculation optimization problem of MEC system,and proposes a low-latency and high-efficiency multi-task offloading calculation scheme.The specific research contents and main results are as follows:(1)The multi-task low-latency offloading computing problem of multi-MEC server system is studied,and the MEC offloading computing scheme and algorithm for joint optimization of task scheduling and delay are proposed.For multi-task MEC scenarios with sequential dependencies,a multi-task offloading calculation optimization problem is established with the goal of minimizing task processing delay and considering energy consumption constraints;the original problem is decomposed into two sub-problems,task scheduling and offloading decision-making.The multitask directed acyclic graph solves the task scheduling scheme with minimum delay,and then designs the earliest offload algorithm based on node replication to solve the minimum delay offload decision scheme of multitask.The simulation results show that the proposed optimization algorithm can significantly reduce the task processing delay,which has obvious advantages compared with other algorithms.(2)The multi-user,multi-task,low-energy-consumption offload computation problem in MEC system is studied,and a multi-user task Non-Orthogonal Multiple Access(NOMA)cooperative relay offload computation scheme that can minimize system energy consumption is proposed.For the multi-user multi-task MEC system scenario with limited spectrum and energy,consider the multiuser cooperative relay scenario and allow multiple tasks to realize parallel offload transmission based on NOMA,and establish a multi-user task offload calculation energy minimization problem under the delay constraint;The problem is solved by Lagrangian dual method,and the optimal task relay offload transmission scheme and user power allocation scheme are obtained.The simulation results show that the proposed scheme can effectively reduce the multi-task offloading computing energy consumption of the MEC system.The work of this paper provides technical solutions and algorithm support for the delay and energy consumption management of the MEC system,and helps to solve the delay and energy consumption constraints of the MEC system.