A Framework for End-to-End Latency Measurements in a Satellite Network Environment

Abstract

Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. Abstract-In this work, a precise method for end-to-end (E2E) latency measurement in satellite Internet protocol (SIP) network environment is proposed. Latency is considered a key parameter affecting the quality of service (QoS) and performance of communications. This is more pronounced in IP over Satellite. Metrics such as throughput and bandwidth performance of communications systems are dependent on latency, which also has a direct impact on other QoS metrics such as Internet packet transfer delay and delay variation or jitter. The upper limits of QoS objective performance metrics are defined by E2E latency for different QoS traffic classes in this environment. Therefore, there is a need to develop efficient methods for the accurate measurement of E2E latency in a SIP environment. Two case study scenarios were developed for satellite and hybrid networks to measure the latency in a SIP environment. Two Geostationary Satellite Network Services were used to compare the performance of the different scenarios and networks. The results demonstrate that at least 50% of the E2E latency is due to processing and transmitting IP packets over the satellite in both scenarios. Inconsistent latency behaviour was also observed from daily results at different times of the day, which may degrade performance of jitter sensitive applications.

Experimental Performance Evaluation of TCP Over an Integrated Satellite-Terrestrial Network Environment

“…The actual latency figures measured by experiments with a real GEO satellite and terrestrial network testbed (see Section III-B), summarized in Tables I and II [30], were used to compute numerical results by implementing the TCP and Hybla congestion control algorithms (see (1) to (9)) in a Matlab program. During algorithm implementations, an ideal channel (i.e error free with P ER = 0) was considered and in the absence of congestion for effective evaluation and analysis and better understanding.…”

“…The setup assumes a Bent-Pipe (BP) satellite hop, which doubles the latency due to intermediary gateway stations (GWS). Scenarios were developed and used to derived a framework for the measurement, details of which are published in [30].…”

Telemedicine via Satellite: Improving Access to Healthcare for Remote Rural Communities in Africa

“…The E2E latency measurement used for performance evaluation for different scenarios are described in [28], the setup consisted of real Wi-Fi and Satellite hybrid links connected to a Broadband Global Area Network (BGAN ). The satellite BGAN link has maximum Achievable Throughput (ATP) of 464kbps connecting three Wi-Fi nodes with two of the nodes generating TCP traffic over the link while the other node serve as TCP traffic sink.…”

“…This variable sets limits to the amount of data the sender can transmit into the network path before an acknowledgement is received. The results obtained in this paper using Equation 3 were used to compute and evaluate E2E capacity utilisation with knowledge of the system's available capacity C The E2E latency measurement results obtained experimentally in [28] using real SatComs network environment showed that the E2E latency is much higher than assumed by many studies related to SatCom, particularly geostationary [25]- [27].…”

Performance Evaluation of Power Efficient Mechanisms on Multimedia over LTE-A Networks

“…2) Packet Delay Variation: PDV is described as the variation in packet delay inside a given media at the mobile user station and always measured in msec. Eq.3 describes PDV for multimedia streaming procedure with ideal ranges <50 msec [17]- [19].…”