A cross-layer approach to design an Internet Protocol Packet Delay Variation estimator for video streaming services

Abstract

Measurement of Internet Protocol Packet Delay Variation (IPDV) is a relevant issue in application involving real time video streaming. Generally, this quantity is compared with predefined thresholds (whose value depends upon the application requirements) to verify the quality of service to the end user. However, the exceeding of this threshold only for short time intervals and with relatively low repetition rates, generally does not imply a significant decrease of the user perceived quality. Vice-versa, IPDV values not exceeding the admitted threshold but very close to this value for long time intervals and characterized by relatively high repetition rates can significantly affect the user perceived quality. Consequently, a study of the correlation among the measured IPDV values and some performance metrics directly related to the quality perceived by the user has to be accurately investigated. On the other hand, literature concerning with IPDV evaluation does not provide some important information about the measurement procedure, such as measurement rate, how to collect the obtained result in a single estimator, the time interval on which the estimator is evaluated, and so on. Consequently, the absence of these important aspects about the measurement procedure makes very critical the comparison between the evaluated IPDV and the above-mentioned thresholds, thus making even more ambiguous the evaluation of the quality of service to the end user. In this framework, the aim of the paper is to design and fine tune an IPDV estimator able to reliably estimate and detect the objective service degradation from the user perspective.