Identifying QoS violations through statistical end‐to‐end analysis

Abstract

SUMMARYMultimedia transmission over the network is susceptible to various runtime impairments such as process failure, network congestion or link error. Existing work usually determines such quality of service (QoS) violations through condition-action rules, which trigger corresponding actions once pre-described conditions are satisfied. However, the results of such rigid rules are often not satisfactory in practice in that there has been little serious study with respect to the relationship between the root cause of a QoS violation and the observed violation phenomenon.In this paper, we introduce a statistical approach to the analysis of QoS violations. We propose and validate through experiments that: (1) a type of QoS violation will present consistent symptoms in terms of the observed application performance and end-to-end traffic pattern. Such a violation can be recognized once the similar symptoms repeat during a QoS session. (2) QoS violations of different nature (e.g. caused by shortage of different resources) will present diverse symptoms. Using a set of end-to-end statistics, we are able to describe and differentiate between QoS violations. We propose a fast orthonormal algorithm for real-time training/classification of QoS violations and prove that this algorithm is universal approximation. We also extend the scope of hidden neurons from kernel functions to additive functions for higher classification accuracy. Our experiments validate our ideas and show the effectiveness of our approach in terms of training overhead and classification accuracy.

Multi‐topology routing based egress selection approach to achieve hybrid intra‐AS and inter‐AS traffic engineering

“…In this paper, the objective we adopted is to minimize the maximum link utilization (MLU).This objective is widely used as performance metric of QoS [19][20][21] and load balancing applications [22].…”

Supporting multimedia applications through network redesign

“…There are also other initiatives in monitoring QoS parameters and ensuring the security of VoIP services [26][27][28][29][30][31]. A secure architecture is proposed in [26] for VoIP services to ensure secured sessions and the authors in [27] proposed a QoS algorithm to reduce the average delay time and jitter for VoIP services.…”

“…Authors in [29] applied the analysis of VoIP over wireless local area network and QoS enhancement mechanisms to provide low-cost wireless voice services. The susceptibility of multimedia networks to various runtime impairments was analyzed in [30] and analysis of various methods for measuring the QoS in VoIP networks was discussed in [31].…”

An OAM function to improve the packet loss in MPLS‐TP domains for prioritized QoS‐aware services

“…In this context, the Gossip-based Local Recovery Policy (GLRP) management is proposed to minimize packet loss for QoS-aware services [14,15]. It is a policy that uses Gossip-based mechanisms in order to distribute the information, standing in contrast to centralized schemes, in which only head ends are responsible for disseminating information about the non-successful reception of packets at the receiver.…”