Research On Multi-core Task Offloading Scheduling For Mobile Edge Computing

In recent years,cloud computing has become a key supporting technology in the information industry,and various industries have used cloud computing to improve the operating efficiency of their own enterprises.At the same time,with the advent of the5 G network,people are entering a smart era where everything is connected through the Internet.More and more mobile terminal devices need to handle computationally intensive tasks.The processing of tasks in mobile terminals will inevitably lead to excessive delay and energy consumption,and cloud processing has the defect of excessive transmission delay caused by too long transmission distance.Neither of these two offloading methods can meet the requirements of the low latency in some applications.At the same time,the contradiction between mobile terminals with limited resources and the resource requirements of computationally intensive tasks has become increasingly prominent.In this context,researchers have proposed an offloading method that uploads user tasks to an edge server close to the user side for processing,namely mobile edge computing.The application of mobile edge computing can not only greatly reduce the task transmission time and task processing time,but also can effectively reduce the data transmission pressure of the core network.In mobile edge computing research,the quality of task offloading and scheduling directly affects user experience,so how to design a reasonable task offloading and scheduling scheme is a very important research content.This paper mainly studies the task offloading and scheduling method between mobile terminal and edge server in the mobile edge computing scenario.In the multicore and multi-user task offloading scenario,the task upload time and the task offload time in the edge cloud are comprehensively considered.The multi-core server adopts a hybrid flow shop scheduling processing method.In order to obtain a reasonable task offloading scheme and reduce the delay of system,a simulated annealing algorithm is proposed to solve the optimization problem.The simulation results show that the algorithm proposed in this article can significantly reduce system delay and improve user experience.At the same time,this paper explores the optimization bottleneck of system delay and the task offloading scenario with priority.By setting different priorities in the model,the algorithm is used to solve the optimization problem.This scheduling method satisfies the requirements of higher priority tasks for lower delay.The simulation result proves the applicability and effectiveness of the scheduling model and the algorithm.Secondly,in the multi-core and multi-user task offloading and scheduling scenario,the system delay and energy consumption are comprehensively considered.At the same time,the traditional simulated annealing algorithm has been improved,which has the defect of missing the current optimal solution.In order to improve the performance of the algorithm,a memory module is added in the algorithm search to retain the better solution in the search process.In order to reduce the system delay,a dynamic power allocation scheme is proposed.The simulation results show that,compared with the traditional simulated annealing algorithm,the dynamic power allocation scheme and the improved simulated annealing algorithm can further reduce the fitness and obtain a better task scheduling scheme.At the same time,the relationship between energy consumption and time delay is obtained.A reasonable energy saving method is found and the task offloading scheduling Gantt chart is given.