Markov queueing models are a powerful tool to evaluate the performance of computer networks and have been used in telecommunication studies for over 100 years. To apply them to the evaluation of the modern Internet, we should not only adapt them to the contemporary network structures but also include a description of the complex stochastic patterns (self-similarity and long-range dependance) of transmitted flows. We examine the features of two Markov models of an almost self-similar process, keeping in mind the modeling of Internet traffic. We have found that the obtained results are comparable with those achieved using a well-known generator of self-similar traffic.

中文翻译：

---

自相似马尔可夫源

马尔可夫排队模型是评估计算机网络性能的强大工具，已在电信研究中使用了100多年。为了将它们应用到现代Internet的评估中，我们不仅应该使它们适应当代的网络结构，还应该包括对传输流的复杂随机模式（自相似性和远程依赖性）的描述。考虑到Internet流量的建模，我们研究了几乎自相似过程的两个Markov模型的特征。我们发现，所获得的结果与使用知名的自相似流量生成器所获得的结果相当。