Internet users may not get the service quality promised by theirproviders, and also may not know what service they can receive.When users experience poor Internet connection performance, itis not easy to identify the source of the problem. We developCheesePi, a distributed measurement system that measures theInternet connection experience of home users based on some net-work performance attributes (e.g. latency, packet loss rate, andWiFi signal quality). The CheesePi runs on a Raspberry Pi (acredit card sized computer) connected to the user’s home networkas a measurement agent. It is important to measure the networkperformance from the user’s side since it is difficult to measureeach individual’s link from the operator (provider) side. Eachmeasurement agent conducts measurement periodically withoutdisturbing the user’s Internet quality. Measurements are con-ducted during popular media events from SICS (Swedish Insti-tute of Computer Science) and student accommodations. Themeasurement results show customers with an Ethernet connectionexperienced significantly better latency and packet loss comparedto WiFi users. In most of the measurements users at SICS per-ceived better latency and packet loss compared to the users at thestudent accommodation. We also quantify how customers experi-enced lower performance when streaming from websites which donot use CDN technology compared to the websites which do useCDN, particularly during popular media events. / CheesePi
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-184917 |
Date | January 2015 |
Creators | Guulay, Biniam Gebregergs |
Publisher | KTH, Skolan för elektro- och systemteknik (EES) |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0017 seconds