Joint Task Offloading Scheduling And Transmit Power Allocation For Mobile Edge Computing Systems With Multiple-Core Server

Most of the research on traditional mobile edge computing systems does not consider whether the server is a multiple-core server.In view of the fact that there are few researches on multiple-core server mobile edge computing systems,this paper studies the problem of task offloading and power allocation in multiple-core server edge computing systems.Different from the previous research which abstracts the server resources into a whole allocatable resource pool,this article will focus on more fine-grained resource allocation and task scheduling,that is,the process of resource allocation and task scheduling on each core of the server.In the mobile edge computing system with a single cell,single user and multiple-core server,joint task offloading scheduling and transmit power allocation for multiple independent tasks are studied.Firstly,the task offloading scheduling based on the hybrid flow shop scheduling model is modelled to compute the system latency,on which the system energy consumption model is obtained based.Secondly,a hybrid encoding genetic algorithm is proposed to minimize the weighted sum of the system delay and energy consumption.Then the optimal task offloading scheduling strategy and the trade-off relationship between the system latency and energy consumption are determined by this solution.Finally,the simulation provides the optimal gantt chart of task offloading.It is shown that the system latency increases linearly with the number of tasks overall.Besides,compared with a random scheduling algorithm,the system latency can be decreased with the help of the unloading strategy proposed in this paper under the same conditions.In addition,a way to save energy without increasing system latency is found due to the inverse relationship between the system energy consumption and latency.In the mobile edge computing system with single-cell,multiple-user and multiple-core servers,the related issues of task offloading and scheduling are studied when each user has only one computing task.Firstly,it introduces the mobile edge computing system model,computing task model,communication model,four server scheduling algorithms and their evaluation indicators,system delay and energy consumption models of single-cell multiple-user multiple-core servers.Secondly,the simulation shows the relationship of the average turnaround time,the average weighted turnaround time and the system throughput with the increase of the number of users of the four server scheduling algorithms.It can be found that in terms of overall system performance and user satisfaction,the order of performance is the highest response ratio next algorithm,the shortest job first algorithm,the first come first service algorithm,and the random scheduling algorithm.And the order of performance in terms of scheduling strategy efficiency is the highest response ratio next algorithm,the first come first service algorithm,the shortest job first algorithm and the random scheduling algorithm.Finally,the trade-off between system average delay and system average energy consumption is studied,and the inverse relationship between system average delay and system average energy consumption is analyzed,and a way to save energy is found without increasing system delay.