In this paper, we consider the application of partial buffer sharing to an M/G/1/K queueing system for cognitive radio networks (CRNs). It is assumed that the CRN is subject to Nakagami-?? fading. Secondary users are allowed to utilize the licensed radio spectrum of the primary users through underlay spectrum access. A finite buffer at the secondary transmitter is partitioned into two regions, the first region serves both classes of packets while the second region serves only packets of the highest priority class. Therefore, the examined CRN can be modeled as an M/G/1/K queueing system using partial buffer sharing. An embedded Markov chain is applied to analyze the queueing behavior of the system. Utilizing the balance equations and the normalized equation, the equilibrium state distribution of the system at an arbitrary time instant can be found. This outcome is utilized to investigate the impact of queue length, arrival rates, and fading parameters on queueing performance measures such as blocking probability, throughput, mean packet transmission time, channel utilization, mean number of packets in the system, and mean packet waiting time for each class of packets.

Mobile devices with ever-increasing functionality and the ubiquitous availability of wireless communication networks are driving forces behind innovative mobile applications enriching our daily life. One of the performance measures for a successful application deployment is the ability to support application-data flows by heterogeneous networks within certain delay boundaries. However, the quantitative impact of this measure is unknown and practically infeasible to determine at real time due to the mobile device resource constraints. We research practical methods for measurement-based performance evaluation of heterogeneous data communication networks that support mobile application-data flows. We apply the lightweight Comparative Output-Input Analysis (COIA) method estimating an additional delay based on an observation interval of interest (e.g., 1 second) induced on the flow. An additional delay is the amount of delay that exceeds nonavoidable, minimal end-to-end delay caused by the networks propagation, serialization, and transmission. We propose five COIA methods to estimate additional delay, and we validate their accuracy with measurements obtained from the existing healthcare and multimedia streaming applications. Despite their simplicity, our methods prove to be accurate in relation to an observation interval of interest, and robust under a variety of network conditions. The methods offer novel insights into application-data delays with regards to the performance of heterogeneous data communication networks.

Traffic shapers are used by researchers to emulate the behavior of networks and applications in test environments, typically with user-defined traffic shaping parameters such as throughput and loss. Also, traffic shapers are used for the enforcement of SLA, so they are of interest for Internet Service Providers. However, output given by traffic shapers may not be as accurate as desired. Therefore, it is important to assess the accuracy of the implementation of traffic shapers. In this paper, we evaluate two traffic shapers with regard to the performance of their throughput shaping. For this evaluation, traces were collected. The properties of the resulting throughput at the outlet of the shaper are compared to the properties of the throughput at the inlet in combination with the preset shaper parameters. In this sense, we also compare shapers installed on Advance Micro Devices (AMD) and Intel platforms, and we use different PDU sizes and load levels to test the influence of those parameters on the shaping. We are furthermore able to deduct internal shaper parameters such as packet rate and buffer size from our measurements, and we analyse the statistical properties of the packet departure process. The extensive measurement results in this paper allow for a detailed assessment of the question whether the shaper performance is up to mark for a desired timescale. In general, the performance of both shapers and hardware platforms can be considered satisfactory on the investigated time scales between 1 ms and 1 s, with a slight advantage for NetEm on AMD.

In this work, we present a systematic study of how the traffic of different transport protocols (UDP, TCP and ICMP) is treated, in three operational Swedish 3G networks. This is done by studying the impact that protocol and packet size have on the one-way-delay (OWD) across the networks. We do this using a special method that allows us to calculate the exact OWD, without having to face the usual clock synchronization problems that are normally associated with OWD calculations. From our results we see that all three protocols are treated similarly by all three operators, when we consider packet sizes that are smaller than 250 bytes and larger than 1100 bytes. We also show that larger packet sizes are given preferential treatment, with both smaller median OWD as well as a smaller standard deviation. It is also clear that, ICMP is given a better performance compared to TCP and UDP.

Packet delay variation plays an important role in network performance degradation and affects the user-perceptual quality, especially in case of real-time services such as video streaming, VoIP etc. Lightweight methods for detecting network performance issues are desirable as compared to task-intensive measurement and analysis. On this background, this paper discusses the applicability of the Coefficient of Throughput Variation (CoTV) to quickly and reliably detect bottleneck behavior between two arbitrary points in a network. The CoTV can be used as a Reduced Reference Metric. It is relatively simple to calculate, compare and interpret, yet powerful to provide control feedback when facing changes in network performance. In this paper, we demonstrate above mentioned properties of the CoTV through a formula relating it to the sample interval of the throughput and the variability of the delay. The latter is shown to be detectable on time scales that are significantly larger than that of the variability itself. This observation is a key enabler for reducing the load on the device that performs the analysis due to the possibility to use large sample intervals. We also describe how difference and ratio of CoTV at outlet and inlet can be used to identify network performance issues.