Research And Application Of Communication Queue Scheduling Algorithm

With the rapid development of the industrial Internet of Things,in the process of the construction of the IoT system,it is often necessary to face huge perceptual devices and deal with a large amount of perceptual information.On the one hand,there are many kinds of perceptual information which needs to be treated differently.On the other hand,due to the limitation of computing power,perceptual devices will send data centrally at certain time points,resulting in a sudden increase in traffic.In view of these situations,using queue to communicate becomes a feasible solution.This paper studies queue scheduling in the industrial Internet of Things.Based on the analysis of the research status of queue scheduling problem at home and abroad,this paper deeply analyzed the problems of existing scheduling algorithms.Aiming at the business requirements of Shanghai Analog Electronic Technology Co.,Ltd.a threetier architecture of ALG-IoT system is designed,and describes in detail the generation process of queue scheduling problem between middleware and application platform.Following this,it discusses the problems of wasting resource and inadequacy to guarantee message priority that exist in ALG-IoT system.In order to solve above problems,a queue scheduling algorithm——Urgency-based proportional fairness scheduling(UPWRR)is proposed.Based on the proportional differentiated service model,the scheduling algorithm uses Weighted Round Robin(WRR)to dynamically adjust the weights of each queue,so as to achieve the goal of dynamically adjusting the QoS of different queues and guarantee the proportional fairness for queue messages in QoS.And the simulation experiments are carried out to verify the feasibility of the algorithm.This algorithm is also compared with other similar algorithms to test its effectiveness.Finally,the UPWRR algorithm is applied to the ALG-IoT system,the ability to precisely push data and the effectiveness of control to the queue length of the algorithm is verified respectively from the user perspective and Redis memory.