The increasing availability of high speed Internet access and the decreasing cost of wireless technologies has increased the number of devices in the home that wirelessly connect to the Internet. While home user applications often have different network requirements, the wireless access point (AP) typically gives them all the same treatment. It has been shown that applications that are sensitive to delay, such as VoIP, remote login and online games suffer degraded performance when running concurrently with applications that expand to fill the available capacity, such as file sharing and downloading. Unfortunately, there are few mechanisms available at the AP to mitigate these effects other than for users to explicitly classify traffic based on port numbers or host IP addresses. This work proposes a novel home access point called CHAP that features credit-based queue management designed to eliminate the need for explicit classification and configuration of per-application quality. CHAP is implemented as a Linux queuing discipline and compared with a traditional AP forWeb browsing and online game activities. The comparisons demonstrate the merits of our approach.

Expanded high speed Internet availability and decreased wireless technology costs have increased the number of residential computers wirelessly connected to the Internet. While residential users run applications with a wide range of network requirements, these applications receive identical treatment from most wireless access points (APs). Although delay sensitive applications can suffer increased latency in the presence of throughput intensive applications, wireless APs contain few tools to mitigate these effects beyond explicitly classifying traffic based on port numbers or host IP addresses. We propose a Credit-based Home Access Point (CHAP) that features credit-based queue management designed to eliminate the need for explicit AP configuration of per-application quality. Based on wireless conditions, CHAP dynamically adjusts flow priorities to better satisfy their application requirements. Preliminary comparisons with DropTail and Strict Priority Queuing (SPQ) demonstrate the merits of our CHAP approach.

A new paradigm in video streaming is emerging, that of personal video servers in the home streaming video to remote clients on the Internet. The potential impact of such technologies demands careful study to assess performance and impact. This project studies one such personal video streaming system called Orb in a closed network environment, allowing us to control network bandwidths. Our performance evaluation focuses on Orb's method of bandwidth estimation, video performance and bitrates, and resource usage during transcoding. Analysis shows Orb uses simplistic, but effective, methods of determining available bandwidth, dynamic temporal and spatial scaling, and significant CPU cycles when transcoding. The results should be useful for subsequent comparison with other home streaming technologies and capacity planning for network providers.

Reference picture selection (RPS) is a promising repair technique in lossy networks for delay-sensitive video, whereby the video encoder uses one of several previous frames as a reference frame for predictive encoding. RPS can operate in two different modes: an optimistic policy that uses negative acknowledgements (NACKs) and a more conservative policy that relies upon positive acknowledgements (ACKs). This paper compares RPS NACK and RPS ACK under various network conditions and video contents using two analytical models. The two models characterize RPS NACK and RPS ACK by incorporating the impact of reference distance on video quality, prediction dependency among video frames and Group of Pictures (GOP) length. Given packet-loss rate, round-trip time and capacity constraints, the models predict average video quality for videos with RPS ACK and RPS NACK using the Video Quality Metric (VQM). Using these two models, a series of experiments are conducted to investigate RPS performance under various conditions. The insights derived from our models can help determine appropriate choices for RPS NACK and RPS ACK under various network conditions and video contents.

Most streaming rate selection and buffer optimization algorithms are developed for wired networks and can perform poorly over wireless networks. Wireless MAC layer behavior, such as rate adaptation, retransmissions, and medium sharing, can significantly degrade the effectiveness of current streaming algorithms. This article presents the Buffer and Rate Optimization for Streaming (BROS) algorithm to improve streaming performance. BROS uses a bandwidth estimation tool designed specifically for wireless networks and models the relationship between buffer size, streaming data rate, and available bandwidth distribution. BROS optimizes the streaming data rate and initial buffer size, resulting in a high data rate but with few frame losses and buffer underflow events, while still keeping a small initial buffer delay. BROS is implemented in the Emulated Streaming (EmuS) client-server system and evaluated on an IEEE 802.11 wireless testbed with various wireless conditions. The evaluation shows that BROS can effectively optimize the streaming rate and initial buffer size based on wireless network bandwidth conditions, thus achieving better performance than static rate or buffer selection and jitter removal buffers.

Bandwidth estimation techniques seek to provide an accurate estimation of available bandwidth such that network applications can adjust their behavior accordingly. However, most current techniques were designed for wired networks and produce relatively inaccurate results and long convergence times on wireless networks where capacity can vary dramatically. This paper presents a new Wireless Bandwidth estimation tool, WBest, designed for fast, non-intrusive, accurate estimation of available bandwidth in IEEE 802.11 networks. WBest is a two-stage algorithm: 1) a packet pair technique estimates the effective capacity over a flow path where the last hop is a wireless LAN (WLAN); and 2) a packet train technique estimates achievable throughput to infer the available bandwidth. WBest parameters are optimized given the tradeoffs of accuracy, intrusiveness and convergence time. The advantage of WBest stems from avoiding a search algorithm to detect the available bandwidth by statistically detecting the available fraction of the effective capacity to mitigate estimation delay and the impact of random wireless channel errors. WBest is implemented and evaluated on an 802.11 wireless testbed. Comparisons with other available bandwidth estimation tools shows WBest to have higher accuracy, lower intrusiveness and faster convergence times. Thus, WBest demonstrates the potential for improving the performance of applications that need bandwidth estimation, such as multimedia streaming, on wireless networks.

While queue capacities have a direct impact on loss and latency during congestion, and wireless networks continue to spread in university, corporate and home networks, little is publicly known about the queue capacities of wireless access points (APs). This paper presents and deploys the Access Point Queue (APQ) methodology for externally estimating the queue capacity for a wireless AP. APQ determines the AP saturation point, measures the baseline delay, induces the saturation rate to measure the delay with a full AP queue and computes the queue capacity. APQ is deployed to determine the queue capacities of three commercial class and four residential class APs. The wireless AP queue capacities are shown to be packet-based and to range from 50 packets to over 350 packets. The fact that queue capacities vary so much among devices targeted for the same network configuration suggests future work to determine the most appropriate queue capacity.

As use of non-TCP applications such as streaming media and network games increases, the potential for unfair, misbehaving flows and the threat of congestion collapse also increases. This paper introduces a statistical traffic filtering technique, stochastic fairness guardian (SFG), that effectively regulates misbehaving flows with minimal traffic state information. SFG can be used in conjunction with an active queue management (AQM) mechanism to improve both network protection and efficiency. Simulations are used to evaluated SFG and the integration of SFG with a proportional-integral (PI) controller in comparison with other similar statistical flow management mechanisms including RED-PD, SFB and CHOKe. The SFG-PI combination outperforms other mechanisms in terms of fairness, queuing delay, stability and TCP performance over a wide range of realistic traffic loads and conditions.

Packet dispersion techniques have been commonly used to estimate bandwidth in wired networks. However, current packet dispersion techniques were developed for wired network environments and can provide inaccurate results in wireless networks due to wireless capacity variability over short time scales. This paper develops an analytical model to investigate packet dispersion behavior in wireless networks. The packet dispersion model is validated using both an extended ns-2 simulator that includes 802.11 MAC layer rate adaptation and wireless 802.11b testbed measurements. Utilizing the model, this study shows that packet dispersion measures effective capacity and achievable throughput of wireless networks instead of the maximum capacity as in wired networks. Additionally, mean and variance of packet dispersion in IEEE 802.11 wireless networks is analyzed while considering the impact of channel conditions such as packet size, link rate, bit error rate and RTS/CTS

Temporal Scaling and Quality Scaling are both widely-used techniques to reduce the bitrate of streaming video. However, combinations and comparisons of Temporal and Quality Scaling have not been systematically studied. This research extends previous work to provide a model for combining Temporal and Quality Scaling, and uses an optimization algorithm to provide a systematic analysis of their combination over a range of network conditions and video content. Analytic experiments show: 1) Quality Scaling typically performs better than Temporal Scaling, with performance differences correlated with the motion characteristics of the video. In fact, when the network capacity is moderate and the loss rate is low, Quality Scaling performs nearly as well as the optimal combination of Quality and Temporal Scaling; 2) when the network capacity is low and the packet loss rate is high, Quality Scaling alone is ineffective, but a combination of Quality and Temporal Scaling can provide reasonable video quality; 3) adjusting the amount of Forward Error Correction (FEC) provides significantly better performance than video streaming without FEC or video streaming with a fixed amount of FEC.

Delay sensitive applications, such as voice over IP and network games, often sacrifice throughput for lower delay to obtain better quality. Unfortunately, the Internet does not allow an application to choose the amount of delay or throughput it receives and instead packets from all applications receive the same best-effort service. This paper presents a new QoS mechanism called the traffic sensitive quality of service controller (TSQ) that provides better delay performance for delay sensitive applications and higher throughput for throughput sensitive applications. Also contributed are quality metrics for some typical Internet applications that can be used by an application to adapt its delay hints and evaluate QoS based on current Internet traffic conditions. Experiments suggest TSQ's benefits to performance along with retention of the current best-effort Internet environment without complicated traffic monitoring or policing.

The growth of wireless LANs has brought the expectation for high-bitrate streaming video to wireless PCs. However, it remains unclear how wireless channel characteristics impact the quality of streaming video sent over wireless LANs. This paper presents results from experiments that stream commercial video over a wireless campus network. By analyzing the streaming video quality and capturing wireless LAN characteristics across network and wireless link layers, "weather forecasts" are created such that selected wireless LAN performance indicators might be used to predict the streaming video quality. Furthermore, a quantified measurement of accuracy is presented to evaluate the effectiveness of individual weather forecasts. The paper evaluates six distinct weather forecasts four different streaming configurations including TCP and UDP streaming, and single and multiple-level encoded videos. The results show that the wireless Received Signal Strength Indicator (RSSI) and average wireless link capacity are the most accurate indicators to predict the performance of streaming video over wireless LANs. The weather forecast philosophy can be beneficial for adapting video streaming in wireless LAN environments.

Packet loss can severely impact streaming video quality. Repair techniques protect streaming video from packet loss but at the price of a reduced effective transmission rate when streaming a flow in a capacity constrained situation. This paper proposes an algorithm that optimizes the choice of Forward Error Correction (FEC) to repair packet loss for streaming MPEG videos under a capacity constraint with quality scaling. An analytic model is developed to estimate the video quality of streaming MPEG given a quality scaling level and a specific FEC strength. Given network conditions in terms of packet loss rate, the model searches the total variable space to find the combination of FEC and scaling that yields the optimal quality under the capacity constraint. Analysis over a range of network conditions indicates that adjusting FEC with quality scaling provides significant performance improvement.

Despite the growth in multimedia, there have been few studies that focus on characterizing streaming audio and video stored on the Web. This investigation used a customized Web crawler to traverse 17 million Web pages from diverse geographic locations and identify nearly 30,000 streaming audio and video clips available for analysis. Using custom-built extraction tools, these streaming media objects were analyzed to determine attributes such as media type, encoding format, playout duration, bitrate, resolution, and codec. The streaming media content encountered is dominated by proprietary audio and video formats with the top four commercial products being RealPlayer, Windows Media Player, MP3 and QuickTime. The distribution of the stored playout durations of streaming audio and video clips are long-tailed. More than half of the streaming media clips encountered are video, encoded primarily for broadband connections and at resolutions considerably smaller than the resolutions of typical monitors.

New TCP-friendly constraints require multimedia flows to reduce their data rates under packet loss to that of a conformant TCP flow. To reduce data rates while preserving real-time playout, temporal scaling can be used to discard the encoded multimedia frames that have the least impact on perceived video quality. To limit the impact of lost packets, Forward Error Correction (FEC) can be used to repair frames damaged by packet loss. However, adding FEC requires further reduction of multimedia data, making the decision of how much FEC to use of critical importance. Current approaches use either inflexible FEC patterns or adapt to packet loss on the network without regard to TCP-friendly data rate constraints. In this article, we analytically model the playable frame rate of a TCP-friendly MPEG stream with FEC and temporal scaling, capturing the impact of distributing FEC within MPEG frame types with interframe dependencies. For a given network condition and MPEG video encoding, we use our model to exhaustively search for the optimal combination of FEC and temporal scaling that yields the highest playable frame rate within TCP-friendly constraints. Analytic experiments over a range of network and application conditions indicate that adjustable FEC with temporal scaling can provide a significant performance improvement over current approaches. Extensive simulation experiments based on Internet traces show that our model can be effective as part of a streaming protocol that chooses FEC and temporal scaling patterns that meet dynamically-changing application and network conditions.

The focus in active queue management (AQM) research has been on traffic that is long-lived, insensitive to delay, and often has large TCP congestion windows. However, the majority of the flows on the Internet today are Web flows, which are short-lived, more sensitive to delay, and typically have small TCP congestion windows. In particular, short-lived flows with small congestion windows frequently suffer from timeouts when encountering packet loss. This paper presents and evaluates a new AQM scheme, short-lived flow friendly RED (SHRED), targeted at providing better network performance for short-lived Web traffic. Using an edge hint to indicate the congestion window size in each packet sent by the flow source or by an edge router, SHRED preferentially drops packets from short-lived Web flows less often than packets from long-lived flows. A wide- range of simulation results and analysis demonstrate that SHRED protects short-lived flows from unnecessary timeouts, improving the response time characteristics for Web traffic when the router becomes congested, while not degrading overall network performance.

End-hosts on wireless ad hoc networks typically use TCP as their transport layer protocol. Being designed for wired networks, TCP can perform poorly over wireless networks. Research that has proposed ways to improve TCP performance over wireless networks has concentrated primarily on improving TCP throughput. However, emerging applications, such as interactive multimedia and network games, require reduced delay at least as much as increased throughput. This paper presents LDM/sup 1/, an IP layer queue marking mechanism that uses estimates of the number of hops and flows at each wireless node to approximate the optimal marking probability. Analysis of NS-2 simulation results indicates that LDM greatly reduces the round-trip time of TCP connections while improving throughput under many configurations.

No abstract available.

While previous research has shown that streaming media can respond to network congestion, it is not known to what extent commercial products are responsive. This research characterizes the bitrate response of Windows Streaming Media (WSM) to changes in network capacity and loss rate. A streaming media test bed was built to systematically vary network and content encoding characteristics and measure WSM congestion responsiveness. The results demonstrate that WSM improve response to congestion when content is encoded into several bitrates by the content provider.

The growing requirement of TCP-Friendly bandwidth use by streaming video plus the proven advantages of Forward Error Correction (FEC) to combat packet loss presents the opportunity to optimize the amount of FEC in a TCP-Friendly video stream. In this paper, we derive an analytical model for predicting the playable frame rate in a TCP-Friendly MPEG stream with FEC. Our model characterizes the Group Of Pictures (GOP) and Forward Error Correction (FEC) that are part of the MPEG video transmission. Assuming a network estimate for the packet loss probability, our model incorporates TCP-Friendly throughput constraints to calculate a total playable frame rate. For a given packet loss probability, we use our model to search the variable space to find the MPEG configuration that yields the optimal playable frame rate. Analysis over a range of network conditions indicates that adjusting FEC can provide a significant performance improvement, while adjusting a well-chosen GOP will contribute little improvement. Further analysis shows that a poor choice for a GOP can result in a large degradation of the playable frame rate. Overall, by introducing moderate amounts of FEC overhead, frame rates can be improved 10 to 50 times under network conditions with moderate to high loss rates.

The Internet today carries traffic for applications with a wide range of delay and throughput requirements. Traditional applications such as FTP and e-mail can tolerate high delays due to long router queues in exchange for high throughput. Unfortunately, current Internet routers do not provide a quality of service (QoS) adapted to the current traffic mix. Most active queue management (AQM) techniques are either heavy-weight by requiring significant architectural changes or focus on providing higher throughput at the router without much consideration for queuing delays. DiffServ approaches, such as assured forwarding (AF) and expedited forwarding (EF), provide differentiated service to traffic aggregates. However, they require complicated mechanisms to negotiate service level agreements. Additionally, DiffServ requires traffic monitors, markers, shapers, classifiers and droppers and a framework to enable these components to work together. We propose an extension to ARED called called RED-Worcester to improve overall QoS support at the router by satisfying the average performance requirements of incoming packets in terms of throughput and delay. While not a differential service, RED-Worcester provides a service that better matches the average requirements of all applications without adding much complexity and it requires no additional policing mechanisms, charging mechanisms or usage control.

The performance of currently available streaming media products will play an important role in the network impact of streaming media. However, there are few empirical studies that analyze the network traffic characteristics and lnternet impact of current streaming media products. This paper presents analysis from an empirical study of the two dominant streaming multimedia products, RealNetworks RealPlayer™ and Microsoft MediaPlayer™. Utilizing two custom media player measurement tools, RealTracker and MediaTracker, we are able to gather application layer and network layer information about RcalPlayer and MediaPlayer for the same media under the same network conditions. Our analysis shows that RealPlayer and MediaPlayer have distinctly different behavior characteristics and exposes some of the impact of streaming media on the network and provides valuable information for building more realistic streaming media simulations.

Using ns-2 simulations, this paper evaluates an adaptive explicit congestion notification (AECN) router. By receiving round-trip time (RTT) source hints from each TCP flow, AECN divides flows into flow groups based on RTT ranges. AECN uses distinct flow group drop probabilities and a mark front scheme to provide higher goodput and better fairness than random early detection (RED) and explicit congestion notification (ECN) routers.

This paper describes our experiences with the Webware, Interfaces and Networking Experimental (WINE) Laboratory. The WINE Lab was created to assist in teaching the topics of computer networks, user interfaces and webware. The goal of the lab is to provide students with the opportunity to complete projects, experiment with relevant techniques and make connections between topics with resources not available in a general purpose Unix-based computing environment. The results from offering courses with the lab show success in meeting these goals. 1 Introduction The paper describes our experiences with the Webware, Interfaces and Networking Experimental Laboratory (WINE Lab) here at Worcester Polytechnic Institute (WPI). This lab was developed to assist in teaching the topics of computer networks, user interfaces and webware. The objective in developing the WINE Lab was to improve these three courses by providing students with the opportunity to complete projects, experiment with relevant...

This paper presents results from a series of simulation experiments designed to study network performance when TCP Vegas and the Random Early Detection (RED) algorithm are used together. Using the x-Sim network simulator, simulation tests were conducted with a variety of traffic scenarios using both TCP Reno and TCP Vegas in combination with First-Come-First-Served (FCFS) and RED routers. Analysis of the performance results for three configurations shows that TCP Vegas host-dominated configurations perform better than TCP Reno host-dominated configurations and that the RED algorithm provides better fairness than FCFS. The RED improvement is higher when the configuration includes a mix of Reno and Vegas hosts. Furthermore, when the buffer allocation in a FCFS router is inadequate, the router performance becomes unstable under heavy traffic. When fragile and robust TCP sources send traffic into a congested router, the TCP Vegas/RED router combination provides the highest throughput and best fairness for the fragile hosts.