Research Of AQM Algorithm Based On Data-driven And Supported By Database

As the application of Internet is more and more common, the complexity of the networksystem is becoming higher and higher. And it could cause the network congestion. It is animportant bottleneck problem that the phenomenon is increasingly serious in networkdevelopment and application. In order to solve the problem of network congestion, the activequeue management algorithm is put forward. The algorithm randomly discarded packetswhen the network congestion occurs, so as to reduce the queuing delay and packet loss rate,stabilize queue length, improve data throughput, and optimize the network performance.In order to solve network congestion, it is an urgent problem that designs a simple andeffective active queue management algorithm. Network congestion control can beconsidered as a feedback control system, so we can get better control performance from theperspective of control theory. The method of data-driven control is characterized by goodoffline timesaving and integrated control effect. It only needs the inputs and outputs data tocontrol the controlled object. This paper researches the use of data-driven way to achieveactive queue management algorithm. It provides a new solution for the more complex activequeue management algorithm.The innovative works of this paper are as follows:1. This paper introduces the research status of active queue management algorithms, thecontrol theory that used in terms of solving network congestion and the research status ofdata-driven control. This paper provides a new active queue management algorithm forms:data-driven to achieve RED and PID algorithms.2. This paper researches and implements the interface between MySQL database and NS2while establishing a interface with the simulation software NS2. It is an important part of thisstudy in control methods to load RED algorithm based on data-driven mode into NS2andexperiment. Finally, the active queue management algorithms that based on data-drive can berealized.3. This paper uses a PID control algorithm as an another example that based on data-drive andsupported by MySQL database. It verifies the correctness of the control method in this paperstudies.