论文部分内容阅读
近年来,大量的通信量测量研究表明实际的网络通信量具有自相似或长范围相关特性。为了准确评估军用网络的性能,论文利用叠加多个ON/OFF信源的方法,建立了自相似通信量模型,并对该模型所产生的序列进行检测,验证了其自相似特性;在此基础上,基于自相似通信量,采用离散事件仿真技术对军用网络中的p-坚持CSMA/CD协议建立了排队模型,通过仿真测试了各种负载下p值对冲突次数、平均等待时间、平均队长以及吞吐率等性能指标的影响,仿真结果表明,根据信道负载的轻重,动态调整p的取值可以提高网络的性能。
In recent years, a large number of traffic measurement studies have shown that the actual network traffic has self-similar or long-range correlation characteristics. In order to accurately evaluate the performance of military networks, this paper builds a self-similar traffic model by superposing multiple ON / OFF sources, and verifies its self-similar characteristics by testing the sequence generated by this model On the basis of the self-similar traffic, the discrete event simulation technique is used to establish the queuing model for p-adhering CSMA / CD protocol in military networks. The simulation results show that p-value collisions, average waiting time, average captain And the performance index such as throughput rate. The simulation results show that the dynamic performance of p can be improved according to the severity of channel load.