On the self-similar nature of Ethernet traffic
SIGCOMM '93 Conference proceedings on Communications architectures, protocols and applications
Meta-Heuristics: Theory and Applications
Meta-Heuristics: Theory and Applications
Potential Interactions between IP-dial and Voice Traffic on the PSTN
BT Technology Journal
Techniques for the Study of QoS in IP Networks
BT Technology Journal
Capacity Planning for Carrier-scale IP Networks
BT Technology Journal
Statistical properties of MPEG video traffic and their impact on traffic modeling in ATM systems
LCN '95 Proceedings of the 20th Annual IEEE Conference on Local Computer Networks
Techniques for the Study of QoS in IP Networks
BT Technology Journal
Capacity Planning for Carrier-scale IP Networks
BT Technology Journal
Performance — A Retrospective View
BT Technology Journal
BT Technology Journal
Markovian Characterisation of H.264/SVC Scalable Video
ASMTA '08 Proceedings of the 15th international conference on Analytical and Stochastic Modeling Techniques and Applications
Exposing invisible timing-based traffic watermarks with BACKLIT
Proceedings of the 27th Annual Computer Security Applications Conference
A genetic approach to Markovian characterisation of H.264 scalable video
Multimedia Tools and Applications
Hi-index | 0.00 |
New and emerging systems and networks are increasingly rich in functionality. Their usage — that is, the traffic and demands upon them — has become correspondingly more complex and unstable than that of older systems; and the traditional broad-brush descriptions of network behaviour are now far from adequate. Traffic modelling is not an arid statistical description of observed gross volumes, but rather the detailed probabilistic description of the small-scale structure of demand which is essential for the performance assessment of these new systems.This paper is an overview of the field of traffic modelling in its own right, and sets out and discusses some of the techniques that are now an essential part of the armoury of the professional performance engineer when assessing any new network or system. It is devoted principally to the study of traffic itself, as the underlying driver of all performance models; but a number of examples of applications are included for illustrative purposes.