2001/07/02 by Tony Field, Field, Tony, Uli Harder +4
Business, Management and Accounting · Computer Science · Engineering · #Advanced Optical Network Technologies #Advanced Queuing Theory Analysis #C.2.5 #C.4 #D.2.8 #FOS: Computer and information sciences #G.3 #Network Traffic and Congestion Control #Networking and Internet Architecture (cs.NI) #Performance (cs.PF) #cs.NI #cs.PF
paper · pdf · doi:10.48550/arxiv.cs/0107001
12 pages, 14 figures, using infocom.cls (included) and graphicx (not included); all power spectrum plots replaced with new ones; minor typos in figure captions corrected
openalex publication_date 2001/07/02 · arxiv created 2001/11/06 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A 100 Mbps Ethernet link between a college campus and the outside world was monitored with a dedicated PC and the measured data analysed for its statistical properties. Similar measurements were taken at an internal node of the network. The networks in both cases are a full-duplex switched Ethernet. Inter-event interval histograms and power spectra of the throughput aggregated for 10ms bins were used to analyse the measured traffic. For most investigated cases both methods reveal that the traffic behaves according to a power law. The results will be used in later studies to parameterise models for network traffic.