Research On QoS Queue Scheduling Algorithms Optimization

With the rapid development of Internet,the requirement for IP network technology and multimedia application technology has been constantly improved.The single data of traditional network can not meet the actual demand.Gradually,an integrated digital network with integrated images,videos and animations has come into being.Multimedia network information with rich contents and functions has replaced traditional IP network information.IP telephony,video conferencing,telemedicine and distance education all belong to the scope of multimedia applications.With the rapid development of the social economy,people's living standards have gradually improved.Therefore,higher requirements are placed on network performance and quality.Therefore,using appropriate scheduling algorithms in the network to ensure the quality of service(QoS)of the network has high research value and practical significance.Different kinds of services have different delay and delay jitter requirements.In order to meet the service quality requirements of various services,it is necessary to apply a most suitable queue scheduling algorithm.This paper first introduces the basic ideas of IntServ model and DiffServ model,and then summarizes the advantages and disadvantages of the two models.DiffServ model machine has research value because of its good scalability.The main content of this paper is to analyze the DiffServ-based queue scheduling algorithm,then improve and optimize the algorithm for the actual situation and needs,and the fairness and delay performance of WFQ and WRR algorithms are studied by the effect of packet length,proposed QZ-WFQ algorithm and the LI-WRR algorithm.Through simulation experiments,it is proved that when there are equal packet lengths,both algorithms have substantially the same latency performance;when having unequal packet lengths,the WRR algorithm cannot guarantee the delay requirement of high priority queues.However,the delay performance of the LI-WRR algorithm is basically the same as the WFQ algorithm.It can better guarantee the delay requirements of high-priority queues,and can greatly reduce the complexity of the algorithm.