Search

When diagnosing network problems, it is desirable to have a view of the traffic inside the network. This can be achieved by profiling the traffic. A fully profiled traffic can contain significant information of the network's current state, and can be further used to detect anomalous traffic and manage the network better. Many has addressed problems of profiling network traffic, but unfortunately there are no specific profiles could lasts forever for one particular network, since network traffic characteristic always changes over and over based on the sum of nodes, software that being used, type of access, etc. This paper introduces an online adaptive system using Evolving Connectionist Systems to profile network traffic in continuous manner while at the same time try to detect anomalous activity inside the network in real-time and adapt with changes if necessary. Different from an offline approach, which usually profile network traffic using previously captured data for a certain period of time, an online and adaptive approach can use a shorter period of data capturing and evolve its profile if the characteristic of the network traffic has changed. [ABSTRACT FROM AUTHOR]

The Multi-Protocol Encapsulation (MPE) is a standard method for encapsulating IP packets into MPEG-2 TS frames. However MPE has some disadvantages in simplicity and efficiency to support next generation network. The Unidirectional Lightweight Encapsulation (ULE) is a new solution to overcome limitations of MPE. In ULE, packets are layered directly into the payload field of MPEG-2 TS frames. This is a new encapsulation method for the transport of IPv4 and other network protocol packets directly over MPEG-2 TS. In this paper, we describe the principles and the benefits of ULE and we also proposed Robust Header Compression Scheme to work with ULE in order to enhance the performance of existing ULE. This paper also provides a simulation analysis to show that the new proposed method can offer a better performance in delay, throughput and overhead especially when the packet size is small. [ABSTRACT FROM AUTHOR]

This paper presents an application of a new type of fuzzy inference system, denoted as evolvable-neural-based fuzzy inference system (EFIS), for adaptive network anomaly detection in the presence of a concept drift problem. This problem cannot be avoided to happen in every network. It is a problem of modeling the behavior of normal traffic while it keeps changing over time in continuous manner. EFIS can solve the concept drift problem by having dynamic network traffic profile creation and adaptation. The profile is then being further used to detect anomaly. An enhanced evolving clustering method (ECMm), which is employed by EFIS for online network traffic clustering, is also presented. It is demonstrated, through experiments, that EFIS can evolve in a growing network and also successfully detect network traffic anomalies. [ABSTRACT FROM AUTHOR]

Recently, multimedia and group-oriented computing become increasingly popular for the users of ad hoc networks. The study of QoS issues in MANETs is vital for supporting multimedia and real-time applications. MANETs can provide multimedia users with mobility they demand, if efficient QoS multicasting strategies were developed. In this paper, we study QoS requirements, illustrate advantages and limitations of existing QoS routing protocol and propose a QoS Multicast Routing protocol (QMR) with a flexible hybrid scheme for QoS multicast routing. The hybrid scheme contains some mechanisms that provide fix-reservation and shared-reservation bandwidth to guarantee QoS multicast routing. The proposed protocol uses forward nodes to apply QoS multicast routing from source(s) to a group of destinations and support load balancing. Analysis results show the ability of QMR to exploit residual bandwidth efficiently without effect on the reserved bandwidth and provide a balance between performance gains and design complexity. [ABSTRACT FROM AUTHOR]