Measuring the Spatial Structure of Traffic Congestion in the Internet

1. Measuring the Spatial Structure of Traffic Congestion in the Internet Gábor Vattay Center for Communication Networks Data Analysis, Collegium Budapest Physics of Complex Systems, Eötvös University ELTE-Ericsson Research Communication Networks Laboratory

2. The Blue Ocean • Telecommunication Services and Computer Hardware Equipment is one of the most R&D intensive sectors (70 B$ R&D spending in 2005) • Research spending traditionally goes into Electrical Engineering and Computer Science, Physics, Complexity is not on thehorizon due to cultural problems • While in biology, economy/finance there is traditional scientific competition, telecommunication is still a competition free Blue Ocean for complexity research • Interdisciplinary research of Engineering and Complex Systems has a great perspective if log-logging is avoided Spatial Structure of Internet Traffic

3. Inspiration from complex system side: What you need? Complex Network Selfsimilar Traffic Nonlinearity and Chaos

4. Topology Spatial Structure of Internet Traffic

5. The Faloutsos Graph 1999 Spatial Structure of Internet Traffic

6. Traffic Spatial Structure of Internet Traffic

7. Typical internet traffic traces W. E. Leland et al. SIGCOMM 93 Spatial Structure of Internet Traffic

8. Chaos Spatial Structure of Internet Traffic

9. Chaos in Computer Networks Spatial Structure of Internet Traffic

10. Periodicity Veres & Boda INFOCOM 2000 Spatial Structure of Internet Traffic

11. Chaos Veres & Boda INFOCOM 2000 Spatial Structure of Internet Traffic

12. Ljapunov properties Veres & Boda INFOCOM 2000 Spatial Structure of Internet Traffic

13. Strange attractor Veres & Boda INFOCOM 2000 Spatial Structure of Internet Traffic

14. Active Internetmeasurements • Internet: highly heterogeneous and decentralized • why are we measuring state variables (e.g. loss-rates, delays, bandwith)? • to predict the quality of various services and applications over the Internet, • to construct more efficient transfer protocols, • to analyze the spatial structure of the traffic, etc. • active probing: • injecting probe packets + analyzing the received probe stream • end-to-end information about the participating nodes • resolved information: only with the cooperation of routers Spatial Structure of Internet Traffic

15. Network Tomography Goal: to resolve delaystatistics on internal network segments too, where we do not have monitoring stations Method: we send back-to-back packet pairs and measure their end-to-end delay at arrival with very high precision Key idea:delay correlation on the common segment for the packets in a pair Spatial Structure of Internet Traffic

16. Definitions: N - number of successful pairs, where none of the probes is lost. and , the end-to-end delay experienced by the probes of the k-th pair Goal: Estimate the distribution of , and from the end-to-end delays. Quantization of the delay into B bins of uniform size q if , Delay estimation for the Y-topology Spatial Structure of Internet Traffic

17. Spatial Structure of Internet Traffic

18. EM-algorithm Spatial Structure of Internet Traffic

19. Spatial Structure of Internet Traffic

20. Real and virtual measurement points Spatial Structure of Internet Traffic

21. The etomic active probing infrastructure

22. History • The European Traffic Observatory Measurement InfrastruCture (etomic) was created in 2004-05 within the Evergrow Integrated Project launched by the Future and Emergent Technologies Programme of the European Union. • Its goals: • to provide an open access, public test bed for researchers investigating the Internet with active measurement methods • to serve as a Virtual Observatory active measurement data on the European part of the Internet Best Testbed Award Spatial Structure of Internet Traffic

23. Founders • Its Central Management System (CMS) has been developed by the Grupo de Redes, Sistemas y Servicios TelemáticosDepartamento de Automática y Computación Universidad Pública de Navarra. • Its hardware infrastructure has been designed and built by the Cooperative Center for Communication Network Data Analysis in Collegium Budapest Institute for Advanced Study. • The measurement stations are hosted by European research groups collaborating in the Evergrow project. Spatial Structure of Internet Traffic

24. Measurement sites Spatial Structure of Internet Traffic

25. Visualization 2005.07.01. 3:30AM Spatial Structure of Internet Traffic

26. Visualization 2005.07.01. 3:30AM Spatial Structure of Internet Traffic

27. etomic stations routers Topology of routers Spatial Structure of Internet Traffic

28. Snapshot of queueing dealys in Europe Spatial Structure of Internet Traffic

29. Daily change of mean queuing delays Spatial Structure of Internet Traffic

30. Distribution of the mean queuing delay (night 3:30) Spatial Structure of Internet Traffic

31. Distribution of the mean queuing delay (afternoon 16:00) Spatial Structure of Internet Traffic

32. Distribution of the mean queuing delay (day 14:00) Spatial Structure of Internet Traffic

33. Variance vs. mean Night Day Afternoon

34. Main results Log-normal distribution of the delay Variance and delay are proportional Spatial Structure of Internet Traffic

35. Future measuremnets

36. Growing number of monitored links Spatial Structure of Internet Traffic

37. The DIMES project Spatial Structure of Internet Traffic

38. DIMES Agents in Europe Spatial Structure of Internet Traffic

39. Measurement sites Properly located Dimes agents (red) Branching routers (blue) Spatial Structure of Internet Traffic

40. Expectations 2. Traceroute between 257 Dimes agents and 15 Etomic nodes Newly discovered internal segments Number of discoveredsegments/branching routers Newly discovered branching routers Number of Dimes agents Spatial Structure of Internet Traffic

41. Thanks! IST Future and Emerging Technologies Spatial Structure of Internet Traffic