As one of Qo S(Quality of Service) metrics, delay is critical important to delay sensitive applications, such as interactive video, network game and online surgery. In this paper, we exploit SDN(Software Defined Netwo...As one of Qo S(Quality of Service) metrics, delay is critical important to delay sensitive applications, such as interactive video, network game and online surgery. In this paper, we exploit SDN(Software Defined Networking) advantages to solve delay Qo S problem. Our work mainly focuses on SDN based queuing delay estimation with real traffic and end-to-end delay control. First, we propose a queuing estimation model and extended it for end-to-end delay of the whole path. It is proved to be feasible and accurate with experimental results in SDN environment. Second, in order to demonstrate the use of our proposed model, we also implement an end-to-end delay control application in SDN. It fulfills specific delay Qo S requirements by dynamically switching flows to a suitable queue based on estimation results and delay requirements.展开更多
基金supported by the project of 111 Intelligence Introduction for Innovation at Communication University of ChinaNSFC under grant No.61371191,No.61472389 and No.61201236ETH Zurich for the valuable discussion about H2020 MAMI project related to TCP modeling in this work
文摘As one of Qo S(Quality of Service) metrics, delay is critical important to delay sensitive applications, such as interactive video, network game and online surgery. In this paper, we exploit SDN(Software Defined Networking) advantages to solve delay Qo S problem. Our work mainly focuses on SDN based queuing delay estimation with real traffic and end-to-end delay control. First, we propose a queuing estimation model and extended it for end-to-end delay of the whole path. It is proved to be feasible and accurate with experimental results in SDN environment. Second, in order to demonstrate the use of our proposed model, we also implement an end-to-end delay control application in SDN. It fulfills specific delay Qo S requirements by dynamically switching flows to a suitable queue based on estimation results and delay requirements.
