Edge Computing Task Scheduling And Optimization Algorithm Based On Lyapunov Theory

The processing of explosively growing data traffic has increased the computional burden on cloud data centers,resulting in a dramatic increase in network transmission bandwidth load and a long network delay for data processing.The single computing model of the cloud computing model obviously has difficulty in realizing the real-time processing of massive data,ensuring the security of data processing and low energy consumption.In order to solve the foreseeable problems in the future,edge computing came into being.Edge computing uses a distributed computing architecture,whose original intention is to migrate some of the cloud-based tasks from the center to the network edge devices without centralizing the data in the cloud.The purpose is to improve the network transmission performance of data and ensure real-time data processing while reducing the computational load of the cloud computing center.Edge computing and cloud computing complement each other.Therefore,how to make reasonable and effective use of resources in the cloud and edge and dispatch tasks to the cloud or edge to process,so that the task processing speed becomes faster and the delay in the task scheduling process is reduced is of great significance.The main work of this paper is as follows:(1)Based on the task queue priority,queue capacity,task scheduling completion time,and task scheduling energy consumption,designed a cloud-edge-terminal three-tier architecture task scheduling system model and established the objective function under these constraints.The objective function is to minimize the processing time of the task dispatching to the cloud server and the edge server under these constraints and maximize the utility of the task scheduling.(2)Applying Lyapunov theory to the cloud-edge task scheduling algorithm,designed an algorithm based on Lyapunov function,Lyapunov drift and penalty,and Lyapunov optimization to stabilize the vehicle movement model queue and maximize the utility,minimizing the processing time of task scheduling,in order to achieving the task scheduling and optimization between the distributed edges,clouds,and terminals.(3)The designed Lyapunov-based edge computing task scheduling and optimization algorithm is simulated in OMNeT++ simulation software.The simulation results are analyzed from the aspects of vehicle movement model stability,task scheduling queue performance,task scheduling utility,and task scheduling processing delay.The simulation results prove the stability of the task-scheduled vehicle movement model in the joint cloud and edge design.The Lyapunov-based edge computing task scheduling and optimization algorithm designed in this paper can effectively reduce the delay in the task scheduling process.At the same time,the utility of task scheduling is also significantly better than the utility of the task alone in the cloud server or edge server.