An investigation of documents from the World Wide Web
Proceedings of the fifth international World Wide Web conference on Computer networks and ISDN systems
A practical guide to heavy tails: statistical techniques and applications
A practical guide to heavy tails: statistical techniques and applications
Heavy-tailed probability distributions in the World Wide Web
A practical guide to heavy tails
Self-similarity and heavy tails: structural modeling of network traffic
A practical guide to heavy tails
Bro: a system for detecting network intruders in real-time
Computer Networks: The International Journal of Computer and Telecommunications Networking
Time Series Analysis, Forecasting and Control
Time Series Analysis, Forecasting and Control
| Hi-index | 0.00 |
In optimizing information flows in networks, it would be useful to predict aspects of the network traffic. Yet, the notion of predicting network traffic does not appear in the relevant literature reporting analysis of network traffic. This literature is both well developed and skeptical about the value of traditional time series analysis on network data. It has consistently reported three "traffic invariants" in the analysis of network and Internet traffic. This study uses such time series analysis on a day's worth of Internet log data and finds poor support for one of the invariants. In the preliminary analysis, evidence of nonlinearity was discovered in these data and the analysis presented here examines this question further. This study posits that nonlinear events may be a traffic invariant although this hypothesis would have to be investigated further. The appearance of nonlinear structures is important to the question of predicting network traffic because there are currently no methods to predict time series with nonlinear structures. The discovery of non-linear structures, then, may mean that developing a predictive model is impossible with current techniques. On the other hand, these nonlinearities may result from interactions from other OSI Layers than the one studied.