A network traffic analysis tool for the prediction of perceived VoIP call quality

[摘要] ENGLISH ABSTRACT: The perceived quality of Voice over Internet Protocol (IP) (VoIP) communicationrelies on the network which is used to transport voice packets between the endpoints. Variable network characteristics such as bandwidth, delay and loss are criticalfor real-time voice traffic and are not always guaranteed by networks. It isimportant for network service providers to determine the Quality of Service (QoS)it provides to its customers. The solution proposed here is to predict the perceivedquality of a VoIP call, in real-time by using network statistics.The main objective of this thesis is to develop a network analysis tool, whichgathers meaningful statistics from network traffic. These statistics will then beused for predicting the perceived quality of a VoIP call. This study includes theinvestigation and deployment of two main components. Firstly, to determine callquality, it is necessary to extract the voice streams from captured network traffic.The extracted sound files can then be analysed by various VoIP quality models todetermine the perceived quality of a VoIP call.The second component is the analysis of network characteristics. Loss, delayand jitter are all known to influence perceived call quality. These characteristicsare, therefore, determined from the captured network traffic and compared withthe call quality. Using the statistics obtained by the repeated comparison of thecall quality and network characteristics, a network specific algorithm is generated.This Non-Intrusive Quality Prediction Algorithm (NIQPA) uses basic characteristicssuch as time of day, delay, loss and jitter to predict the quality of a real-time VoIP call quickly in a non-intrusive way. The realised algorithm for each networkwill differ, because every network is different.Prediction results can then be used to adapt either the network (more bandwidth,packet prioritising) or the voice stream (error correction, change VoIP codecs)to assure QoS.

[发布机构] Stellenbosch University