Task Scheduling Model of Edge Computing for AI Flow Computing in Internet of Things

With the development of intelligent applications of the Internet of things, the sharp increase of data scale and the improvement of computational model complexity in the edge computing environment put forward higher requirements for the performance of edge computing. Reasonably optimizing the scheduling of AI data intensive computing tasks can greatly improve the overall performance of edge computing. Therefore, a novel particle swarm optimization algorithm is proposed to realize task scheduling in edge computing environment by calculating task scheduling to optimize task execution time and scheduling cost. Improve the speed formula of particle swarm optimization algorithm to improve the convergence speed and row performance of the algorithm. Finally, on the Cloudsim simulation platform, the proposed particle group algorithm LK-PSO was compared with the other four benchmark algorithms. The results showed that the method task scheduling cost and execution time were effectively optimized. This method can effectively improve the resource utilization rate of marginal computing and improve the efficiency of marginal computing power.