ATM QoS prediction using neural-networks

Mohammad, Nazeeruddin; Mohandes, M.; Çam, Hasan

doi:10.1109/iconip.1999.845650

Cited by 1 publication

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…interactive, bulk transfer, streaming and transactional) and classified streaming traffics into one of these four categories using nearest neighbors and linear discriminant analysis algorithms. Similarly, authors of [19] have defined four QoS classes of different performance levels for the ATM network. Neural network (BP algorithm) is employed to sort traffics with different QoS requirements into one of these classes based on parameters such as cell loss rate and cell delay variation.…”

Section: Overview Of Our Approachmentioning

confidence: 99%

“…They validate their models through simulation and show that by correctly assigning each traffic to a proper service class, overall end-to-end performance (such as delay and throughput) can be improved. It should be noted that [18][19][20][21] classify QoS from performance perspective: applications of similar business nature and QoS requirements are grouped into the same category. In contrast, our work focuses on the direct identification of QoS violations through end-to-end observation and classification.…”

Section: Overview Of Our Approachmentioning

confidence: 99%

See 1 more Smart Citation

Identifying QoS violations through statistical end‐to‐end analysis

Zhou

Chen

Pung

et al. 2011

Int J Communication

View full text Add to dashboard Cite

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.

show abstract

Section: Overview Of Our Approachmentioning

confidence: 99%

Section: Overview Of Our Approachmentioning

confidence: 99%