Research On Optimization Methods Of Task Collaborative Scheduling In The Edge Computing Environment

With the rapid development of the Internet of Things,mobile terminal equipment and 5G communication technology,the era of the Internet of Everything has arrived.When the traditional cloud computing mode processes the explosive growth of massive data in the Internet of Everything scenario,it not only increases the computing burden of the cloud computing center,but also increases the load of network transmission bandwidth,an d resuls in high network latency for task scheduling and processing.The pure cloud computing model has been unable to deal with the the explosive growth of data in real time,unable to meet the requirements of low power consumption and low delay of application tasks.can no longer process Edge computing pushes the computing power and storage capacity of cloud computing to the edge of the network.Instead of centralized processing of tasks,tasks are allocated to the edge nearby for processing,which reduces the task transmission delay and relieves the data processing pressure of cloud computing center.At the same time,edge computing and cloud computing can complement each other.Reasonable use of computing resources in the cloud computing center and edge can speed up the processing speed of request tasks,reduce delay and energy consumption,and meet the requirements of different applications.The key issue to be solved in edge computing task scheduling is how to reasonably schedule computing tasks to edge servers or cloud computing centers according to different application characteristics,so as to realize collaborative scheduling between different edge ends and cloud centers,and meet the requirements of different applications for different computing resources.This paper mainly studies the collaborative scheduling of tasks in edge computing environment from two aspects.On the one hand,aiming at the task scheduling problem under the application scenarios of single and different edge computing resources,the collaborative task scheduling method between different edge servers under single edge computing resources is designed and implemented by combining the artificial fish swarm search algorithm,so as to make full use of the computing resources of different edge servers to improve the computing performance of computing tasks.On the other hand,aiming at the computing task scheduling problem in the collaborative application scenario of edge end and cloud,the cloud-edge collaborative computing task scheduling method is designed and implemented based on Lyapunov optimization theory.Through reasonable utilization of different computing resources of cloud and edge,the quality of application service is improved.The main work of this article is as follows:(1)Aiming at the task scheduling problem under the condition of single edge computing resources,an edge computing task scheduling method based on artificial fish group search is proposed.By establishing a reasonable task scheduling model and a mathematical model,combining the artificial fish swarm search algorithm with the edge computing task scheduling model,based on the artificial fish swarm search mechanism,using the Gaussian distribution function to dynamically improve the visual field parameters and step parameters,combined with the tabu search algorithm,a reasonable task scheduling scheme between different edge servers is obtained.The experimental results in the cloudsim 3.0 simulation environment show that the proposed edge computing task scheduling method can make full use of different edge server computing resources,improve the computing performance of computing tasks,and effectively solve the problems of high delay and unbalanced load caused by uneven task scheduling in edge computing.(2)Aiming at the task scheduling problem under the condition of cloud-edge computing resource collaborative processing,a cloud-edge collaborative scheduling algorithm based on Lyapunov optimization is proposed.The Liapunov drift plus punishment mechanism is used to determine the optimal task scheduling and allocation decision,and the task allocation is carried out reasonably.The optimization objective is to minimize the drift plus punishment,and the reasonable cloud-edge collaborative task scheduling is achieved under the condition of ensuring the minimum delay,so as to minimize the system energy consumption.Matlab simulation test results show that the cloud-edge collaborative scheduling algorithm proposed in this paper based on Lyapunov optimization can realize reasonable task scheduling and allocation,make reasonable use of the computing resources of the edge end and the cloud center,and meet the service requests of different applications,and effectively solve the problems of request task service delay and system energy consumption caused by unreasonable task scheduling in cloudedge collaborative task scheduling scenarios.