Prasad Calyam

Performance Measurement and Analysis of H.323 Traffic

The popularity of H.323 applications has been demonstrated by the billions of minutes of audio and video traffic seen on the Internet every month. Our objective in this paper is to obtain Good, Acceptable and Poor performance bounds for network metrics such as delay, jitter and loss for H.323 applications based on objective and subjective quality assessment of various audio and video streams. To obtain the necessary data for our analysis we utilize the H.323 Beacon tool we have developed and a set of Videoconferencing tasks performed in a LAN and also with end-points located across multiple continents, connected via disparate network paths on the Internet.

Modeling and Detection of Camouflaging Worm

Active worms pose major security threats to the Internet. This is due to the ability of active worms to propagate in an automated fashion as they continuously compromise computers on the Internet. Active worms evolve during their propagation, and thus, pose great challenges to defend against them. In this paper, we investigate a new class of active worms, referred to as Camouflaging Worm (C-Worm in short). The C-Worm is different from traditional worms because of its ability to intelligently manipulate its scan traffic volume over time. Thereby, the C-Worm camouflages its propagation from existing worm detection systems based on analyzing the propagation traffic generated by worms. We analyze characteristics of the C-Worm and conduct a comprehensive comparison between its traffic and nonworm traffic (background traffic). We observe that these two types of traffic are barely distinguishable in the time domain. However, their distinction is clear in the frequency domain, due to the recurring manipulative nature of the C-Worm. Motivated by our observations, we design a novel spectrum-based scheme to detect the C-Worm. Our scheme uses the Power Spectral Density (PSD) distribution of the scan traffic volume and its corresponding Spectral Flatness Measure (SFM) to distinguish the C-Worm traffic from background traffic. Using a comprehensive set of detection metrics and real-world traces as background traffic, we conduct extensive performance evaluations on our proposed spectrum-based detection scheme. The performance data clearly demonstrates that our scheme can effectively detect the C-Worm propagation. Furthermore, we show the generality of our spectrum-based scheme in effectively detecting not only the C-Worm, but traditional worms as well.

Assessing readiness of IP networks to support desktop videoconferencing using OPNET

OPNET is a powerful network design and simulation tool that has gained popularity in industry and academia. However, there exists no known simulation approach on how to deploy a popular real-time network service such as videoconferencing. This paper demonstrates how OPNET can be leveraged to assess the readiness of existing IP networks to support desktop videoconference. To date, OPNET does not have built-in features to support videoconferencing or its deployment. The paper offers remarkable details on how to model and configure OPNET for such a purpose. The paper considers two types of video traffic (viz. fixed and empirical video packet sizes). Empirical video packet sizes are collected from well-known Internet traffic traces. The paper presents in-depth analysis and interpretation of simulation results and shows how to draw proper engineering conclusions.

Multi-Resolution Multimedia QoE Models for IPTV Applications

Internet television (IPTV) is rapidly gaining popularity and is being widely deployed in content delivery networks on the Internet. In order to proactively deliver optimum user quality of experience (QoE) for IPTV, service providers need to identify network bottlenecks in real time. In this paper, we develop psycho-acoustic-visual models that can predict user QoE of multimedia applications in real time based on online network status measurements. Our models are neural network based and cater to multi-resolution IPTV applications that include QCIF, QVGA, SD, and HD resolutions encoded using popular audio and video codec combinations. On the network side, our models account for jitter and loss levels, as well as router queuing disciplines: packet-ordered and time-ordered FIFO. We evaluate the performance of our multi-resolution multimedia QoE models in terms of prediction characteristics, accuracy, speed, and consistency. Our evaluation results demonstrate that the models are pertinent for real-time QoE monitoring and resource adaptation in IPTV content delivery networks.

On Detecting Camouflaging Worm

Active worms pose major security threats to the Internet. In this paper, we investigate a new class of active worms, i.e., camouflaging worm (C-Worm in short). The C-Worm has the capability to intelligently manipulate its scan traffic volume over time, thereby camouflaging its propagation from existing worm detection systems. We analyze characteristics of the C-Worm and conduct a comprehensive comparison between its traffic and non-worm traffic. We observe that these two types of traffic are barely distinguishable in the time domain, however, their distinction is clear in the frequency domain, due to the recurring manipulative nature of the C-Worm. Motivated by our observations, we design a novel spectrum-based scheme to detect the C-Worm. Our scheme uses the power spectral density (PSD) distribution of the scan traffic volume and its corresponding spectral flatness measure (SFM) to distinguish the C-Worm traffic from non-worm traffic. We conduct extensive performance evaluations on our proposed detection scheme against the C-Worm. The performance data clearly demonstrates that our proposed scheme can effectively detect the C-Worm propagation

VDC-Analyst: Design and verification of virtual desktop cloud resource allocations ☆

Abstract One of the significant challenges for Cloud Service Providers (CSPs) hosting “virtual desktop cloud” (VDC) infrastructures is to deliver a satisfactory quality of experience (QoE) to the user. In order to maximize the user QoE without expensive resource overprovisioning, there is a need to design and verify resource allocation schemes for a comprehensive set of VDC configurations. In this paper, we present “VDC-Analyst”, a novel tool that can capture critical quality metrics such as Net Utility and Service Response Time, which can be used to quantify VDC platform readiness. This tool allows CSPs, researchers and educators to design and verify various resource allocation schemes using both simulation and emulation in two modes: “Run Simulation” and “Run Experiment”, respectively. The Run Simulation mode allows users to test and visualize resource provisioning and placement schemes on a simulation framework. Run Experiment mode allows testing on a real software-defined network testbed using emulated virtual desktop application traffic to create a realistic environment. Results from using our tool demonstrate that a significant increase in perceived user QoE can be achieved by using a combination of the following techniques incorporated in the tool: (i) optimizing Net Utility through a “Cost-Aware Utility-Maximal Resource Allocation Algorithm”, (ii) estimating values for Service Response Time using a “Multi-stage Queuing Model”, and (iii) appropriate load balancing through software-defined networking adaptations in the VDC testbed.

OnTimeDetect: Dynamic Network Anomaly Notification in perfSONAR Deployments

To monitor and diagnose bottlenecks on network paths used for large-scale data transfers, there is an increasing trend to deploy measurement frameworks such as perfSONAR. These deployments use web-services to expose vast data archives of current and historic measurements, which can be queried across end-to-end multi-domain network paths. Consequently, there has arisen a need to develop automated techniques and intuitive tools that help analyze these measurements for detecting and notifying prominent network anomalies such as plateaus in both real-time and offline manner. In this paper, we present a dynamically adaptive plateau-detection (APD) scheme and its implementation in our “OnTimeDetect” tool to enable consumers of perfSONAR measurements within the data-intensive scientific communities in overcoming their existing limitations of network anomaly detection and notification. We empirically evaluate our APD scheme in terms of accuracy, agility and scalability by using measurement traces collected by OnTimeDetect tool from worldwide perfSONAR deployments in HPC communities.

TBI: end-to-end network performance measurement testbed for empirical bottleneck detection

Recent advances in networking include new bandwidth-intensive applications, sophisticated protocols that enable real-time data and multimedia delivery and aspects of network security that were not conceived in the beginnings of the Internet. Given these advances and the rapid increase in the number of users accessing the Internet, todays networks need to deliver high levels of end-to-end performance in a reliable fashion. In this paper, we present our novel network measurement methodology which employs an application-specific measurement toolkit including a scaleable test scheduler and analysis module to empirically identify end-to-end bottleneck paths in monitored network routes. To show the utility of our proposed methodology, we present case-studies from a network measurement testbed between 3 University campus labs traversing regional and national academic network backbones. Our case-studies address identifying network measurement anomalies in routine ISP operations due to route changes, device misconfigurations and erroneous data from measurement tools. We also present a performance comparison of campus, regional, national-academic and national-commercial network paths based on the measurement data obtained from our testbed. Finally, we illustrate the requirements and potential of federated measurement testbeds to better characterize end-to-end network performance bottlenecks across multiple ISP domains.

Simulation as a service (SMaaS): a cloud-based framework to support the educational use of scientific software

Large manufacturers increasingly leverage modelling and simulation to improve quality and reduce cost. Small manufacturers have not adopted these techniques due to sizable upfront costs for expertise, software and hardware. The software as a service (SaaS) model provides access to applications hosted in a cloud environment, allowing users to try services at low cost and scale as needed. We have extended SaaS to include high-performance computing-hosted applications, thus creating simulation as a service (SMaaS). Polymer portal is a first-generation SMaaS platform designed to integrate access to multiple modelling, simulation and training services. Polymer portal provides a number of features including an e-commerce front end, common AAA service, and support for both cloud-hosted virtual machine (VM) images and high-performance computing (HPC) jobs. It has been deployed for six months and has been used successfully for a number of training and simulation activities. This paper describes the requirements, challenges, design and implementation of the polymer portal.

Incident-Supporting Visual Cloud Computing Utilizing Software-Defined Networking

In the event of natural or man-made disasters, providing rapid situational awareness through video/image data collected at salient incident scenes is often critical to the first responders. However, computer vision techniques that can process the media-rich and data-intensive content obtained from civilian smartphones or surveillance cameras require large amounts of computational resources or ancillary data sources that may not be available at the geographical location of the incident. In this paper, we propose an incident-supporting visual cloud computing solution by defining a collection, computation, and consumption (3C) architecture supporting fog computing at the network edge close to the collection/consumption sites, which is coupled with cloud offloading to a core computation, utilizing software-defined networking (SDN). We evaluate our 3C architecture and algorithms using realistic virtual environment test beds. We also describe our insights in preparing the cloud provisioning and thin-client desktop fogs to handle the elasticity and user mobility demands in a theater-scale application. In addition, we demonstrate the use of SDN for on-demand compute offload with congestion-avoiding traffic steering to enhance remote user quality of experience in a regional-scale application. The optimization between fogs computing at the network edge with core cloud computing for managing visual analytics reduces latency, congestion, and increases throughput.