A novel application classification and its impact on network performance

Abstract

Network traffic is believed to have a significant impact on network performance and is the result of the application operation on networks. Majority of current network performance analysis are based on the premise that the traffic transmission is through the shortest path, which is too simple to reflect a real traffic process. The real traffic process is related to the network application process characteristics, involving the realistic user behavior. In this paper, first, an application can be divided into the following three categories according to realistic application process characteristics: random application, customized application and routine application. Then, numerical simulations are carried out to analyze the effect of different applications on the network performance. The main results show that (i) network efficiency for the BA scale-free network is less than the ER random network when similar single application is loaded on the network; (ii) customized application has the greatest effect on the network efficiency when mixed multiple applications are loaded on BA network.

A Service Deployment Method Considering Application Reliability of Networks

“…Ning Huang et al [1], [28] concentrated on network applications research for a long time and yielded some positive results. A three-layer architecture of network systems is established, including infrastructure layer, control layer and application layer, as shown in Fig.…”

End user–oriented node resource allocation: An application‐based method

“…An application is requested by users and can achieve some functions under given requirements . On the basis of the process characteristics, Zhang classified applications into three types: random application, customized application, and routine application. Random application: New packets of applications are generated with random source and sink nodes, and the packets transmit based on given routing protocol. Customized application: New packets of applications are generated with random source and sink nodes, and the packets must be delivered to sink nodes through given critical nodes.…”

“…Some researchers use topology characteristics to evaluate node importance (the probability of packets going through each node), which can provide guidance for resource allocation. The topology characteristics include betweenness, degree, and node usage probability, and the researchers use these characteristics to properly represent the node importance under random applications; ie, new packets are generated at each time step, which have random source and sink nodes . The betweenness of a node can be perceived as the probability of packets passing through the node under a given routing protocol, and considering that the nodes with high betweenness are prone to congestion, the buffer size is allocated proportional to betweenness to maximize network capacity .…”

“…Previous studies have considered some application impacts on resource allocation, such as evaluating node importance (traffic load on nodes) under random applications . However, traffic load is controlled by application demands of users, and applications can affect traffic load from many more concrete aspects, such as quantity of applications, application processes, and mixing ratio of different applications, which shows that the network reliability may not be same under different application demands . In existing methods, resources are allocated indirectly with applications, and this further makes it difficult to optimize resource with given application demands.…”