At present,most of the current traffic classification technology is adopted by the means of offline classification,unable to realize real-time online classification.A novel approach for network traffic online classifi...
详细信息
At present,most of the current traffic classification technology is adopted by the means of offline classification,unable to realize real-time online classification.A novel approach for network traffic online classification is proposed in this paper.A strategy of converting the C4.5 decision tree data structure to parallel data structure called encoded data structure is *** encoded data structure is very easy for hardware realization,based on FPGA parallel and pipeline *** only needs two clock cycles to complete C4.5 decision tree search process without extra write and read *** results show that the throughput of the classification system can reach to 1Gbit/s on the NetFPGA2.1.3 platform,and we expect that this design can be expanded to the NetFPGA-10G platform and the throughput can reach to 10Gbit/*** classification accuracy can reach to more than 97% if we choose the appropriate evaluation algorithm and search algorithm to obtain the effective features set.
With more and more network coding methods being put forward,the metric of network coding performance becomes a key issue in network coding *** this paper,relative traffic gain(RTG) is proposed to measure the performan...
详细信息
With more and more network coding methods being put forward,the metric of network coding performance becomes a key issue in network coding *** this paper,relative traffic gain(RTG) is proposed to measure the performance of network coding;it is defined as the expected value of the ratio of saved traffic flows to the sum of all traffic *** the diversity of actual network traffic flow,the relationship between relative traffic gain and parameters of different traffic models is analyzed,including normal distribution model,Poisson distribution model,Constant Bit-Rate(CBR) traffic model,exponential distribution model and Pareto distribution *** bidirectional traffic flows and multiple traffic flows are taken as examples to analyze the relative traffic gain of network *** results show that:better relative traffic gain can be obtained under larger mean value and smaller standard deviation for normal distribution,larger expected value for Poisson distribution,and smaller difference between the traffic flows rates for CBR distribution,smaller for exponentional distribution and lager k for Pareto *** results would help in measuring NC performance and give a reference to implementation and optimization of NC.
A semi-joint user scheduling(semi-JUS) scheme is proposed to improve the performance of advanced version of Long Term Evolution,***,*** system is low cost and *** aggregation(CA) based LTEAdvanced systems commonly ado...
详细信息
A semi-joint user scheduling(semi-JUS) scheme is proposed to improve the performance of advanced version of Long Term Evolution,***,*** system is low cost and *** aggregation(CA) based LTEAdvanced systems commonly adopt joint user scheduling(JUS) and separated random user scheduling(SRUS) *** former is optimal in performance but with high complexity and the latter is simple but less *** our proposed scheme,the user equipments(UEs) are limited to receive and transmit from only one of the component carriers(CCs) at any time,which ensures lower complexity compared with ***,the traffic load of each CC could be well balanced by switching the single connected CC for UEs in burst level using different burst dispatching *** leads to the significant performance gain compared with *** classes of load balancing policy are applied in semi-JUS scheme,termed as round robin(RR) and shortest queue(SQ).We prove the superiority of the scheme with Poisson-based multiple flow traffic input by numerical experiments.
暂无评论