In this paper, we propose a Packet Cache-Forward(PCF) method based on improved Bayesian outlier detection to eliminate out-of-order packets caused by transmission path drastically degradation during handover events in...In this paper, we propose a Packet Cache-Forward(PCF) method based on improved Bayesian outlier detection to eliminate out-of-order packets caused by transmission path drastically degradation during handover events in the moving satellite networks, for improving the performance of TCP. The proposed method uses an access node satellite to cache all received packets in a short time when handover occurs and forward them out in order. To calculate the cache time accurately, this paper establishes the Bayesian based mixture model for detecting delay outliers of the entire handover scheme. In view of the outliers' misjudgment, an updated classification threshold and the sliding window has been suggested to correct category collections and model parameters for the purpose of quickly identifying exact compensation delay in the varied network load statuses. Simulation shows that, comparing to average processing delay detection method, the average accuracy rate was scaled up by about 4.0%, and there is about 5.5% cut in error rate in the meantime. It also behaves well even though testing with big dataset. Benefiting from the advantage of the proposed scheme in terms of performance, comparing to conventional independent handover and network controlled synchronizedhandover in simulated LEO satellite networks, the proposed independent handover with PCF eliminates packet out-of-order issue to get better improvement on congestion window. Eventually the average delay decreases more than 70% and TCP performance has improved more than 300%.展开更多
Recent researches show that inter-session network coding could decrease the number of packets transmission and achieve higher throughput in wireless network compared with traditional forwarding mechanism. In most exis...Recent researches show that inter-session network coding could decrease the number of packets transmission and achieve higher throughput in wireless network compared with traditional forwarding mechanism. In most existing relay mechanisms based on inter-session network such as COPE, relay node demands to collect the messages from its neighbor nodes to get notice of which packets already overheard by them so as to determine whether there exists coding opportunity between or among forwarding packets. However, transmission overhead of this message collection and computing cost of opportunity determination will degrade the performance of these mechanisms. It is observed that coding opportunity at relay node is much more related with the local topology, and the opportunity of encoding three or more packets together is far less than that of encoding two packets together in wireless network with general density. Based on this, a new coding-aware routing mechanism, named TCAR, is proposed. TCAR ignores the oppommity of encoding three or more than three packets together. Each relay node maintains an encoding mapping table being established according to the result of its local topology detection, which can be used to calculate the path cost during routing setup phase, and determine that which two packets can be encoded together during the packets forwarding phase. In TCAR, instead of periodic messages collection, each relay nodes just need once local topology detection, and the encoding determination is much simpler than that of the former mechanisms. Simulation results show that compared with typical inter-session network coding mechanisms COPE and COPE-based routing, TCAR achieves 12% and 7% throughput gains, and keeps the minimum end to end delay.展开更多
基金supported by National High Technology Research and Development Program of China(863 Program,No.2014AA7011005)National Nature Science Foundation of China(No.91438120)
文摘In this paper, we propose a Packet Cache-Forward(PCF) method based on improved Bayesian outlier detection to eliminate out-of-order packets caused by transmission path drastically degradation during handover events in the moving satellite networks, for improving the performance of TCP. The proposed method uses an access node satellite to cache all received packets in a short time when handover occurs and forward them out in order. To calculate the cache time accurately, this paper establishes the Bayesian based mixture model for detecting delay outliers of the entire handover scheme. In view of the outliers' misjudgment, an updated classification threshold and the sliding window has been suggested to correct category collections and model parameters for the purpose of quickly identifying exact compensation delay in the varied network load statuses. Simulation shows that, comparing to average processing delay detection method, the average accuracy rate was scaled up by about 4.0%, and there is about 5.5% cut in error rate in the meantime. It also behaves well even though testing with big dataset. Benefiting from the advantage of the proposed scheme in terms of performance, comparing to conventional independent handover and network controlled synchronizedhandover in simulated LEO satellite networks, the proposed independent handover with PCF eliminates packet out-of-order issue to get better improvement on congestion window. Eventually the average delay decreases more than 70% and TCP performance has improved more than 300%.
基金Projects(61173169,61106036)supported by the National Natural Science Foundation of ChinaProject(NCET-10-0798)Program for New Century Excellent Talents in University,China
文摘Recent researches show that inter-session network coding could decrease the number of packets transmission and achieve higher throughput in wireless network compared with traditional forwarding mechanism. In most existing relay mechanisms based on inter-session network such as COPE, relay node demands to collect the messages from its neighbor nodes to get notice of which packets already overheard by them so as to determine whether there exists coding opportunity between or among forwarding packets. However, transmission overhead of this message collection and computing cost of opportunity determination will degrade the performance of these mechanisms. It is observed that coding opportunity at relay node is much more related with the local topology, and the opportunity of encoding three or more packets together is far less than that of encoding two packets together in wireless network with general density. Based on this, a new coding-aware routing mechanism, named TCAR, is proposed. TCAR ignores the oppommity of encoding three or more than three packets together. Each relay node maintains an encoding mapping table being established according to the result of its local topology detection, which can be used to calculate the path cost during routing setup phase, and determine that which two packets can be encoded together during the packets forwarding phase. In TCAR, instead of periodic messages collection, each relay nodes just need once local topology detection, and the encoding determination is much simpler than that of the former mechanisms. Simulation results show that compared with typical inter-session network coding mechanisms COPE and COPE-based routing, TCAR achieves 12% and 7% throughput gains, and keeps the minimum end to end delay.
