In a multiplayer networked game, actions for players with higher latencies are received and (potentially) acted upon later than players with lower latencies, leading to unfairness, especially important in competitive games. Time delay is a latency compensation technique that can mitigate this unfairness by adding latency to players with lower latency so that all players experience the same latency. Although this provides equal latency to all players, it unnecessarily degrades the responsiveness for the lower-latency players when the players are not interacting. We propose an adaptive time delay technique that only adds latency to low-latency players when they are interacting with players with higher latency. We conducted three separate user studies assessing player performance and experience with network latency and different compensation techniques. Analysis of the results shows adaptive time delay improves average quality of experience compared to fixed time delay while preserving time delay’s fairness.

Computer games - and computer game players - often drive technology improvements, with graphics cards and monitors pushing the limits of display technologies. High frame rates, in particular, promise to provide lower latencies and smoother game visuals to gamers, especially important for competitive first person shooter (FPS) game players. What is not well-known is to what extent gamers benefit from ultra-high frame rates in terms of player performance and quality of experience. This paper studies the effects of frame rates - especially high frame rates - on FPS game players. A custom FPS game was developed to allow for consistent delivery of frame rates from 7 f/s to 500 f/s, while recording objective (performance) and subjective (smoothness) measures. Analysis of data from a 44-person user study shows player performance (e.g., score) improves sharply from 7+ f/s, but levels out after about 90 f/s. However, users perception benefits over the full range of frame rates studied, rising sharply from 7+ f/s, but continuing to improve through the top 500 f/s.

Frametime spikes can disrupt gameplay in first-person shooter (FPS) games, affecting both performance and player experience. This paper examines how spikes during specific game events impact players. We developed a custom FPS game that maintains a steady 500 frames/s while inducing frametime spikes during weapon reloading, fast mouse movement, or targeting. Thirty-eight (38) participants played the game in a user study, providing both performance data and user-reported visual smoothness. Results show that spikes while targeting lowered accuracy and score, while spikes during reloads and mouse movement did not affect performance but still degraded user experience. These results suggest that both the relative timing and size of frametime spikes matter in FPS gameplay. Per-action models better account for average QoE when spikes happen, showing better fit than models that only consider spike size (independent of action).

User studies are a cornerstone of human-computer interaction research, including measures of user performance and quality of experience (QoE) – particularly important for games where frame rates and frame timings can impact performance. Unfortunately, commercial games have limited options for customization and do not log player performance data with sufficient detail for use in such studies. This paper introduces Lead Rush, a first-person shooter game designed for conducting user studies on the effects of frame timing and frame rate. Lead Rush is tuned to run at extremely high frame rates and includes hooks to induce frame time "spikes". Researchers can configure Lead Rush’s gameplay, trigger frame time spikes during specific actions, and log player data per game round and per study session. This paper also introduces a dataset from a user study on the effects of frame time spikes on player performance gathered from Lead Rush, and includes gameplay logs with both performance data and QoE results. Some analysis of the dataset is presented to illustrate its use.

Cloud gaming relies upon smooth delivery of frames and low delay for a good player Quality of Experience (QoE). While playout buffering has long been used in traditional streaming systems – e.g., streaming video and VoIP – to smooth out variations in delay and available bandwidth, algorithms for playout buffering for cloud game streams are under-researched. In particular, QoE models for cloud-based game streams differ from those for traditional media, suggesting algorithms that have been widely used and proposed may need to be adjusted for cloud gaming. This paper investigates playout buffer policies on cloud gaming QoE by employing a trace-driven simulation framework that allows for a head-to-head comparison of policies. By integrating established QoE models, our study quantifies how these technical parameters affect perceived gaming quality. Our results reveal that the effectiveness of a buffer policy is highly dependent on the network conditions, with adaptive strategies showing potential benefits in environments with high jitter, while more conservative policies may suffice under stable network conditions.

Understanding the effects of latency on interaction is important for building applications, such as computer games, that perform well over a range of latencies. For games that require quick reflexes, such as first-person shooter games, reaction times can be a key determinant for player performance. Unfortunately, measuring and reporting reaction times – and analysis thereof – is not done in many user studies, likely because most easy-to-use tools are only available online and do not provide the raw reaction time data of the participants. To address these shortcomings, this paper presents Reflex an open-source tool for measuring human reaction times. Reflex is implemented in JavaScript, allowing it to be run with only a local Web browser and provides the raw data for subsequent analysis. This paper also presents a data set composed of Reflex data gathered from eight previous user studies, with brief analysis comparing their reaction time results to illustrate Reflex’s use.

The initial TCP slow start phase seeks to ramp up data transmission rates quickly to meet available capacity but also to exit the slow start phase before causing undue congestion. Unfortunately, the typical default TCP implementation often exits slow start too early, before capacity has been reached, causing underutilization, particularly detrimental to networks with large capacities and high delays. This study introduces a novel enhancement to TCP slow start - Slow start Exit At Right CHokepoint (SEARCH) - where the link capacity is inferred at the server based on bytes delivered compared to the expected bytes delivered, smoothed to account for link latency variation and normalized to accommodate link capacities. Empirical evaluation over geosynchronous satellite links, low-orbit satellite links, and 4G LTE links shows our approach is a substantial improvement over default TCP implementations by not exiting slow start too early, but better than traditional TCP, too, by exiting slow start before encountering packet loss.

The Slow start Exit At Right CHokepoint (SEARCH) algorithm is designed to exit the TCP slow start phase after the flow has reached the link capacity but before packets have been lost. To do this, SEARCH keeps a history of the bytes delivered over a recent time window, aggregated into bins. Unfortunately, this delivery history must be kept per-flow, adding additional memory load for each TCP connection. We address this per-flow memory load by observing that SEARCH only needs the relative number of bytes delivered and propose a bit-shifting technique that dynamically compresses bin values as needed. Our approach is tunable to the memory-use reduction required compared to the delivery precision needed. Evaluation of our approach over a satellite network shows SEARCH bin memory use can be reduced by 50% or even 75% without any significant sacrifice in SEARCH algorithm accuracy. Our approach is generalizable to other network algorithms, too, reducing memory use for algorithms that use sliding windows and historical data tracking.

TCP’s slow start phase is particularly inefficient over most wireless networks, especially high-latency, high-bandwidth paths such as satellite networks, often exiting too early or too late (after packet loss). To address this, the Slow start Exit At CHokepoint (SEARCH) algorithm is designed to improve exit decisions during slow start by analyzing delivery trends across sliding RTT-based windows. This paper presents a first implementation of SEARCH in the FreeBSD kernel using FreeBSD’s modular congestion control framework. We evaluate our implementation on a testbed with an actual GEO satellite link with ~600 ms RTT and 150 Mb/s capacity. Preliminary results show that SEARCH exits slow start more effectively than HyStart and HyStart++, achieving higher throughput and better utilization.

Computer games have evolved alongside technologies such as personal computers, touchscreens, and virtual reality (VR). The devices have different interaction modes with distinct affordances, including direct physical control with tablets and immersive experiences in VR. Moreover, games are now easily accessible across devices due to cloud-based streaming. Despite this benefit, the challenge of delay persists and continues to affect both performance and quality of experience in games. The negative impact of delay is well-documented, but less is known about how its effect may interplay with a device’s interaction mode. This study applies a cross-platform game with controlled levels of delay, where players use different interaction modes to select moving targets. The findings highlight how the detrimental effect of delay on player performance degradation varies across devices (worst on a PC compared to VR and a tablet, and best on the tablet) even while the interaction mode mediates the effects of delay (quality of experience is fairly stable across all conditions and devices, with VR the most immersive).

Before playing, gamers must wait for the game to load. While the effects of waiting on user quality of experience is well-studied for some domains, the effects of wait times on game players is not known, nor is the impact of computer system components, such as the processor or graphics card, on game loading times. We present results from a user study that evaluates the impact of game loading time on quality of experience using a custom tool that simulates game loading and collects player ratings. Analysis of the results shows game loading time has a pronounced effect on player quality of experience, but differs based on the individual game time and game load content. Results from our subsequent measurement experiment show the potential to reduce game load times through hardware upgrades – type of processor and graphics card have significant effects on game load times, but type of storage device less so.

Latency impacts individual responsiveness and player-versus-player fairness in first-person shooter (FPS) games, degrading the quality of experience (QoE). Time delay applies a fixed latency to players with lower latency to make the game fair, but has the drawback of adding latency regardless of whether players are interacting or not. Adaptive time delay dynamically adds latency only when players interact, improving average responsiveness while preserving fairness. This study assesses QoE for adaptive time delay with latency with a focus on the potential benefits of dynamically adding latency compared to always having a fixed latency for the round. A 38-person user study with a custom FPS game shows degredations to QoE with latency, but less so for adaptive time delay.

In first-person shooter (FPS) games, the peeker’s advantage is the edge the moving peeker gets when battling a stationary defender at a corner due to network latency. However, confirmation of (the size of) this advantage based on network latency and the distance from the corner has not been studied. This paper assesses the peeker’s advantage via two user studies both using an open-source FPS game extended to support two-player networking and a custom map. Users play as both peeker and defender with 3 different corner distances and 3 different network latencies. Analysis of hits, wins, and time-to-damage shows that the advantage for the peeker is impacted more by the defender’s latency than the peeker’s latency and is lowest when the peeker is nearest the corner. The user study with a tournament setting had quicker and more competitive matches resulting in more combat encounters and closer games than did the traditional user study.

QUIC is increasingly being deployed on the Internet as an alternative to TCP. However, QUIC over satellite links faces particular challenges as high and variable round-trip times (RTTs) make it difficult to determine and then reach link capacity. Standard slow start algorithms to detect link capacity can perform poorly over satellite links, often exiting slow start too early and limiting throughput or exiting too late and causing unnecessary packet loss. The Slow start Exit At Right CHokepoint (SEARCH) algorithm aims to exit slow start after reaching link capacity but before incurring packet loss by tracking delivery rates and exiting when rates have not increased by the expected amount. SEARCH has shown benefits over traditional slow start for TCP connections but has yet to be implemented and evaluated in QUIC. This paper presents the design and implementation of SEARCH in an open-source QUIC library, with the code publicly available as a contribution. Evaluation of SEARCH over a geostationary satellite link show SEARCH successfully exits slow start before loss in the majority of cases, Improving goodput compared to the baseline.

Cloud-based game streaming requires low-latency and high-throughput networking to support real-time interactivity and high-quality visuals critical to such platforms. However, the capacity of local networks to meet these demands is challenged by the simultaneous presence of other bandwidth-intensive applications, such as Dynamic Adaptive Streaming over HTTP (DASH) for video content. While some aspects of network congestion for cloud-based game streaming have been studied, missing are comparative performance and congestion responses for cloud-based game streams competing with video flows - a common scenario for users on a home Local Area Network (LAN). This paper presents results from experiments that measure how two commercial cloud-based game streaming systems - NVIDIA GeForce Now and Amazon Luna - respond to DASH flows on a congested network link. Analysis of bitrates, frame rates and round-trip times for the game streaming flows and analysis of media throughput and interrupts for the DASH flows show markedly different responses to the arrival and departure of competing DASH traffic.

Computer games are often rendered with inconsistent frame timing (frame jitter), particularly in cloud-based game streaming where frames traverse network bottlenecks before being rendered. While previous studies have helped understand the Quality of Experience (QoE) with frame jitter, derived models have tended to be limited in their prediction ability for conditions not yet tested. This paper combines results from four different user studies that assess QoE based on frame jitter, the studies differing in games, game systems, and methods of induced frame time variation. Analysis of the results shows the degree to which frame jitter degrades QoE, and that playout interruption sizes matter while interrupt frequencies do not. The rich user study-based data set provides the basis for models for predicting game player QoE with frame jitter - models which should be predictive for both cloud-based game streaming and traditional games, and for a wide range of player actions and game genres.

For gamers, high frame rates are important for a smooth visual display and good quality of experience (QoE). However, high frame rates alone are not enough as variations in the frame display times can degrade QoE even as the average frame rate remains high. While the impact of steady frame rates on player QoE is fairly well-studied, the effects of frame rate variation is not. This paper presents a 33-person user study that evaluates the impact of frame rate variation on users playing three different computer games. Analysis of the results shows average frame rate alone is a poor predictor of QoE, and frame rate variation has a significant impact on player QoE. While the standard deviation of frame times is promising as a general predictor for QoE, frame time standard deviation may not be accurate for all individual games. However, 95% frame rate floor -– the bottom 5% of frame rates the player experiences –- appears to be an effective predictor of both QoE overall and for the individual games tested.

Many young adults do not exercise enough, choosing instead to spend time on electronic media (e.g., smartphone, Internet). Exergames, which gamify physical activity, have been shown to be effective at increasing physical activity in an enjoyable way. For exergames to remain effective, sustained user engagement is key. However, sustaining long-term engagement in games (including exergames) is a challenging research problem – 95% of all new game players stop playing within 3 months, and 85% of new players stop after just one day. We posit that if detected early, waning player exergame enjoyment can be countered by recommending new, more enjoyable games before the player quits playing. In this paper, we investigate machine learning to predict user enjoyment of the Just Dance exergame by analyzing data gathered from the player’s smartphone. Specifically, "ground truth" scores for the players’ enjoyment obtained from the Immersive Experience Questionnaire (IEQ) E-scores are inferred from user behaviors such as increased excitement and gameplay frequency. These, in turn, are predicted by data gathered by the phone’s sensors – accelerometer, gyroscope and game features. Analysis of data from a user study shows the Naive Bayes classification algorithm achieves the best results, achieving 75% accuracy for binary classification (enjoying vs. not enjoying the exergame) of enjoyment E-scores. The most predictive features were the energy in the 0.5 to 3 GHz range, windowed energy in the 0.5 to 3 Hz range and radio spectral peak using a Discrete Cosine Transform (DCT). Our results are preliminary but encouraging and we plan to improve on our results by collecting more data and utilizing state-of-the-art neural networks approaches.

TCP slow start begins at a conservative bitrate but quickly ramps up to the available bandwidth. Unfortunately, current TCP implementations can either: 1) exit from slow start prematurely, which is especially detrimental to utilization on satellite links, or 2) exit from slow start too late, causing unnecessary packet loss. We propose a novel technique to exit slow start while avoiding both premature and belated exits. We evaluate our approach over commercial satellite links - long, fat networks that pose challenges to determining the right slow start exit time. Preliminary results show a high success rate for picking appropriate exit points over satellite links, with potentially being applicable to other types of networks, more generally.

While target selection in a 2D space is fairly well-studied, target selection in a 3D space, such as shooting in first-person shooter (FPS) games, is not, nor are the benefits to players for many latency compensation techniques. This paper presents results from a user study that evaluates the impact of latency and latency compensation techniques on 3D target selection via a bespoke FPS shooter. Analysis of the results shows latency degrades player performance (time to select/shoot a target), with subjective opinions on Quality of Experience (QOE) following suit. Individual latency compensation techniques cannot fully overcome the effects of latency but combined techniques can, letting players perform and feel as if there is no network latency. We derive a basic analytic model for the distribution of the player selection times which can be part of a simulation of a full-range of FPS games.

Understanding how new TCP congestion control algorithms interact with the default TCP Cubic over a wide-range of network conditions is important for moving congestion control research forward. Unfortunately, lacking are studies over actual satellite Internet networks where high latencies pose challenges to TCP performance. This paper presents results from experiments over a commercial satellite Internet link assessing TCP congestion control algorithm performance for Cubic when competing with algorithms using four different approaches: loss-based (Cubic), bandwidth-estimation based (BBR), utility function-based (PCC) and satellite optimized (Hybla). Analysis shows: 1) the default Cubic algorithms are fair to each other; 2) Cubic dominates PCC during steady state; 3) Hybla dominates Cubic during start-up; and 4) BBR dominates Cubic during both start-up and steady state.

Competitive first-person shooter games are played over a network, where latency can degrade player performance. To better understand latency’s impact, a promising approach is to study how latency affects individual game actions, such as moving and shooting. While target selection (aiming and shooting at an opponent) is fairly well studied, navigation (moving an avatar into position) is not. This paper presents results from a 30-person user study that evaluates the impact of latency on first-person navigation using a custom “hide and seek” game that isolates avatar movement in a manner intended to be similar to movement in a first-person shooter game. Analysis of the results shows latency has pronounced effects on player performance (score and seek positioning), with subjective opinions on Quality of Experience following suit.

Cloud-based game streaming is emerging as a convenient way to play games when clients have a good network connection. However, high-quality game streams need high bitrates and low latencies, a challenge when competing for network capacity with other flows. While some network aspects of cloud-based game streaming have been studied, missing are comparative performance and congestion responses to competing TCP flows. This paper presents results from experiments that measure how three popular commercial cloud-based game streaming systems - Google Stadia, NVidia GeForce Now, and Amazon Luna - respond and then recover to TCP Cubic and TCP BBR flows on a congested network link. Analysis of bitrates, loss rates and round-trip times show the three systems have markedly different responses to the arrival and departure of competing network traffic.

Satellite networks often use Performance Enhancing Proxies (PEPs) in order to overcome the inherent high latencies that are detrimental to TCP throughputs. Measurements of TCP performance over Satellite PEPs are lacking, both for actual PEP benefits and for interactions between PEPs and TCP congestion control algorithms. This paper presents results from experiments that assess the benefits of a PEP for a commercial satellite network, considering four TCP congestion control algorithms: Cubic, BBR, Hybla and PCC. Without the PEP, the four algorithms have similar steady state throughputs (about 70 Mb/s), but significant differences in start-up throughputs. In particular, the PEP dramatically improves (3x) start-up throughputs for TCP Cubic – the default congestion control algorithm used by most Internet servers. Overall, the PEP equalizes performance irrespective of the TCP congestion control algorithm chosen.

Cloud-based game streaming has emerged as a viable way to play games anywhere with a good network connection. While previous research has studied the network turbulence of game streaming traffic, there is as of yet no work exploring how cloud-based game streaming responds to rival connections on a congested network. This paper presents experiments measuring and comparing the network response for three popular commercial streaming services - Google Stadia, NVidia GeForce Now, and Amazon Luna - competing with TCP flows on a congested network. Analysis of the bitrates, loss and latency show that the three systems have different adaptations to network congestion and vary in their fairness to competing TCP flows sharing a bottleneck link.

Cloud-based game streaming has the disadvantage of added latency from the thin client to the cloud-based server and back, decreasing player performance and degrading their experience. Attribute scaling can make the game eas-ier, potentially exactly counteracting the difficulty added by the latency. We incorporate attribute scaling models into two different games, deploy them on a commercial cloud-based game streaming system and evaluate their efficacy by measuring impact on player performance and Quality of Experience (QoE). Analysis through a user study shows that our compensation methods improve player performance and may improve QoE compared to no latency compensation.

Players of first-person shooter (FPS) games, such as Counter-strike: Global Offensive (CS: GO), seek low latencies in order to play well and have fun. Even network latencies as small as 10 milliseconds may decrease accuracy, score, and Quality of Experience (QoE), degredations that may be exacerbated for some weapons. This paper presents results from 40+ person user study that measures the impact of network latencies on players for the FPS game CS: GO. We setup a testbed where participants played 20+ rounds of CS: GO with controlled amounts of network latency with either a mid-range, rapid fire, high-precision weapon (an AK-47 assault rifle) or a close-range, slow fire, lower-precision weapon (a Nova shotgun). Analysis of the results shows even network latencies under 100 milliseconds degrade player performance (accuracy and score), avatar movements, and QoE, with the impact on player performance more pronounced for the assault rifle compared to the shotgun.

Technological advancement has decreased network latencies while simultaneously increasing local latencies. This may impact exergames—video games that incorporate exercise—the most since exergames tend to have complicated platforms to capture player actions. This article presents a study using a custom desktop-based exergame that controls for local latency and measures player performance and quality of experience (QoE). Analysis of the results from a 37-person user study shows that while player performance and QoE degrade with latency, exergame actions are fairly tolerant of even hundreds of milliseconds of latency. Our data point toward a crucial tipping point at latency values of approximately 400 ms.

Satellite connections are critical for continuous network connectivity when disasters strike and for remote hosts that cannot use traditional network connections. While satellite Internet bitrates have increased, satellite latencies can still degrade TCP performance. Assessment of TCP over satellite networks is lacking, typically done only by simulation or emulation only, if at all. This paper presents experiments over a commercial satellite network comparing two popular TCP congestion control algorithms: Cubic (the default for most Internet servers) and BBR (recently deployed by Google servers). Analysis of the results shows similar steady-state bitrates for both BBR and Cubic, but with BBR having significantly higher bitrates (and, subsequently, higher round-trip times) than Cubic during start-up.

Video game play is among the most popular forms of entertainment in the world and eSports is a multi-billion dollar industry. Esports gamers, and competitive gamers more broadly, want fast game systems to maximize their chances of winning. In general, the faster the game system, the lower the latency between a player’s action and the intended outcome. But how much small reductions in local latencies benefit competitive players is not known. This paper presents results from a 43-person user study that evaluates the impact of system latencies for high-end gaming systems (below 125 ms) on experienced Counter-strike: Global Offensive (CS:GO) players. Analysis of the results show pronounced benefits to CS:GO player performance (accuracy and score) for even small reductions in latency, with subjective opinions on Quality of Experience following suit.

Understanding the effects of latency on interaction is important for building software, such as computer games, that perform well over a range of system configurations. Unfortunately, user studies evaluating latency must each write their own code to add latency to user input and, even worse, must limit themselves to open source applications. To address these shortcomings, this paper presents EvLag, a tool for adding latency to user input devices in Linux. EvLag provides a custom amount of latency for each device regardless of the application being run, enabling user studies for systems and software that cannot be modified (e.g., commercial games). Evaluation shows EvLag has low overhead and accurately adds the expected amount of latency to user input. In addition, EvLag can log user input events for post study analysis with several utilities provided to facilitate output event parsing.

When software and hardware processes cause delay between an input and an output, consequences can be both harmful and annoying. In games, this type of delay can cause actions to lag behind a player's inputs. Studies on delayed game actions show negative impact on both player performance and quality of experience. Further research could expand upon this knowledge with more robust data modeling and analysis, as well as a wider range of actions. This paper describes publicly available datasets from four user studies on the effects of delay on the fundamental game action of selecting a moving target with a pointing device. They include performance data, such as time to selection, and demographic data, such as age and gaming experience. Example analysis illustrating the use of the datasets is shown, including comparison of pointing devices, demographic analysis with performance, and analytic modeling.

Esports gamers, and competitive gamers more broadly, want low network latency to maximize their chances of winning - in general, the lower the network latency, the less time between a player's action and the intended outcome. But how much small reductions in network latency benefit competitive players is not known. This paper presents results from a 25person user study that evaluates the impact of network latency on experienced Counter-strike: Global Offensive players. Analysis of the results shows pronounced benefits to player performance (accuracy and score) for even small reductions in network latency, with subjective opinions on Quality of Experience (QoE) following suit. Latency compensation - a software technique to mitigate the effects of latency - significantly improves player performance and QoE.

Streaming video clients use playout buffers to smooth out variations in network bitrates, especially important for mobile devices. The playout buffer sizes trade-off: the time delay before a video starts playing with interrupts when a video stops playing in the middle. The best buffer size a client should choose for the video and network conditions depends upon the relative impacts of buffering delays and interrupts on the user quality of experience (QoE). We design user study experiments that isolate buffering delays and interrupts, allowing for direct, quantitative comparisons of the impact on QoE for buffering delays versus interrupts. In our user study, over thirty users watched and rated 17 videos with a broad range of content, encoded with varying amounts of buffering delays and interrupts. Analysis of the data reveals interrupts more costly to QoE than the corresponding amount of buffering by a factor of about 2 to 1. The data is used to construct an analytic model of QoE which incorporates the impacts of buffering delays and interrupts, a model that can be a tool for assessing and improving how streaming video clients pick buffer sizes to maximize user QoE.

All real-time computer games, particularly networked computer games, have a delay from when a player starts an action (e.g., clicking the mouse) until the game renders the result (e.g., firing a projectile). This delay can degrade both player performance (e.g., reduced game score) and quality of experience (e.g., the game is less fun). While previous work has studied the effects of delay on commercial games and individual game actions, a more detailed understanding is needed of the effects of delay on moving target selection with realistic target motion, a common scenario in many games. This paper presents an in-depth study of the effects of delay on the fundamental game action of selecting a moving target with a mouse while varying two parameters for the target motion – turn frequency and turn angle. We design and implement a custom game where players select moving targets using a mouse, while the game controls both the target motion and input delay. Analysis of data gathered in a 56-person user study shows both target selection time and accuracy degrade with delay. However, both selection time and accuracy increase with the frequency and angle of changes in the target’s movement, because turning slows targets down even while making them less predictable. We set these results in the context of other studies of delay and target selection by comparing our findings to those in seven other previously published papers that investigated the effects of delay on target selection.

All real-time computer games, particularly networked computer games, have a delay from when a player starts an action (e.g., clicking the mouse) until the game renders the result (e.g., firing a projectile). This delay can degrade both player performance (e.g., lower game score) and quality of experience (e.g., less fun). While previous work has studied the effects of delay on commercial games and individual game actions, a more detailed understanding is needed of the effects of delay on moving target selection with realistic target motion. This paper presents an in-depth study of the effects of delay on the fundamental game action of selecting a moving target with a mouse with parameters for the target motion - turn frequency and turn angle. We design and implement a custom game where players select moving targets using a mouse, while the game controls both the target motion and input delay. Analysis of data gathered in a 56-person user study shows both user time and accuracy in selecting the moving target degrade with delay. Target turn frequency and turn angle can make a target easier to select (i.e., selection accuracy increases), but take longer to do so (i.e., selection time increases), because turning slows targets down while making them less predictable.

The increase in radio link capacities has brought significant growth in number and variety of mobile applications. To support these applications, network providers and researchers need an up-to- date, thorough understanding of the composition of 4G LTE traffic. In this paper, we conduct a deep study over a tier-1 U.S. wireless carrier to measure and analyze 4G LTE traffic. We collect data on 2.5+ million flows from 5000+ user devices, analyzing cross-layer characteristics for IPv4/6, HTTP/S and newly emerging Quick UDP Internet Connection (QUIC) traffic, with analysis extracted for the most prolific domains. To the best of our knowledge, our QUIC traffic analysis is the first published from a carrier's perspective. Results show data from multimedia sources (audio, video and images) dominate link capacities, with video, in particular, being the "king of the hill". Detailed analysis suggests methods for identifying encrypted video traffic, potentially leading to improved services that can provide network treatments for video.

Video streaming traffic often dominates mobile wireless networks, forcing Internet Service Providers (ISPs) to deploy video shaping to identify and then manage traffic during congested periods Unfortunately, the increasing use of end-to-end encryption (e.g., TSL/SSL) makes it difficult to identify video flows even with deep packet inspection. As an alternative, this paper presents Silhouette -- a real-time, lightweight video classification method suitable for ISP middle-boxes. Silhouette uses only flow statistics (i.e., "shape") for video identification making it payload-agnostic, effective for identifying video flow even when encrypted. Preliminary results with pre-classified YouTube traffic shows the promise of the Silhouette approach, yielding high identification accuracy over a range of video content and encoding qualities.

Delays are ever-present in interactive tasks, such as controlling a cursor with a mouse. Unfortunately, perceptible delays are likely to affect both quality of experience and task performance, and even imperceptible delays can potentially be harmful to performance. This paper presents a controlled behavioural experiment that explores the impact of delay on interactions with motor inputs and visual outputs. Because system and network delays interact and overlap, we address total interface delay, focusing on the effect rather than the cause. In the experiment, 51 participants played a simple game of chase-and -catch, using the mouse to intercept a bouncing target. The game includes three levels of difficulty, defined by the speed of the target, with controlled interface delay added between the mouse and the corresponding cursor. The delay values ranged from the system's minimum processing time of 40 ms up to a total of 440 ms. We evaluated participants' game performance, as well as perceived game responsiveness. In line with predictions, our analyses show a negative relation between delay and quality of experience, along with deteriorating performance. In contrast, performance does not co-vary with self-reported game skill. Moreover, an individual's experience with other time-dependent activities has no significant effect on neither performance nor experience, with one exception - musical practice appears to benefit performance for this type of interaction.

Hosting interactive video-based services, such as computer games, in the Cloud poses particular challenges given user sensitivity to delay. A better understanding of the impact of delay on player-game interactions can help design cloud systems and games that accommodate delays inherent in cloud systems. Previous top-down studies of delay using full-featured games have helped understand the impact of delay, but often do not generalize or lend themselves to analytic modeling. Bottom-up studies isolating user input and delay can better generalize and be used in models, but have yet to be applied to cloud-hosted computer games. In order to better understand delay impact in cloud-hosted computer games, we conduct a large bottom-up user study centered on a fundamental game interaction—selecting a moving target with user input impeded by delay. Our work builds a custom game that controls both the target speed and input delay and has players select the target using a game controller analog thumbstick. Analysis of data from over 50 users shows target selection time exponentially increases with delay and target speed and is well-fit by an exponential model that includes a delay and target speed interaction term. A comparison with two previous studies, both using a mouse instead of a thumbstick, suggests the model’s relationship between selection time, delay, and target speed holds more broadly, providing a foundation for a potential law explaining moving target selection with delay encountered in cloud-hosted games.

Networks and local systems add delays to user actions in computer games, increasing the time between user input and rendering on the screen. Top-down studies using games have helped understand the impact of delays, but often do not generalize nor lend themselves to analytic modeling. Bottom-up studies isolating user input can better generalize and be used in models, but have yet to be applied to computer games. Our work builds a custom game for studying delay and the fundamental user input of selecting a moving target with a mouse. Analysis of data from a large user study shows target selection time is exponential with delay, and provides for an analytic model based on delay and the interaction between delay and target speed.

The degradation of player performance in network games with latency is well documented. However, quantifying the effects of latency on player individual actions is an unmet challenge. Under constrained bitrate conditions, player actions delayed on the client add additional latency, so network game developers need tools to help prioritize the sending of player actions. This paper presents a taxonomy for player actions with latency in network games, where player actions are defined by their precision, deadline & impact. The effects of latency along each dimension of the taxonomy are analyzed through extensive experiments with a custom 2d game. Efficacy of the taxonomy in game development is illustrated by experiments that show improved player performance when prioritizing player actions based on their expected impact derived from the taxonomy dimensions.

Measuring Internet performance for home users can provide useful information for improving networks. Unfortunately, Internet measurements typically require users to install special software, a major impediment to use. To overcome this impediment, we designed and implemented several scripting techniques to predict Internet performance from within the tightly constrained sandbox environment of a Web browser. Our techniques are integrated into a Web site project called “How's My Network” that provides predictions for common Internet activities, with this paper concentrating on the performance of online news, social networks, and online shopping. The contributions of this work include the design, implementation and evaluation of new approaches for predicting Web browser performance.

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.

The growth in network capacities and availability has been accompanied by a proliferation of online games. While online games perform well under many network conditions, Internet delays can often degrade online game performance. The precise impact that latency has on online gameplay depends upon the game type and the actions within the game. While the effects of latency on specific games has been studied, knowledge about the effects of latency on classes of games and about the effects of latency on different player actions is lacking. This paper presents a broad, perspective-based classification of games based on player control and camera view. The foundation of the game classification are player actions, each of which is defined by its precision and deadline requirements. Experiments with controlled amount of precision, deadline and latency support the classification. This classification of games should prove useful for game designers, network engineers and game players themselves as they build and play on tomorrow's networks.

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.

This work provides detailed measurements of the motion and scene complexity for a wide variety of video games. Novel algorithms to measure motion and scene complexity are presented and then applied to over twenty-five games from a range of game genres. Direct comparisons of motion and scene complexity are made to traditional video, with differences highlighted in order to help thin client systems perform better when streaming video games. Preliminary performance measurements of current thin client systems are presented, evaluating the efficacy of streaming video games in the context of the motion and scene complexity measurements provided.

Hardware and platform limitations restrict the display settings for most computer games, forcing a tradeoff between frame rate and resolution to achieve acceptable performance. Previous work has explored the effects of frame rate and/or resolution on a variety of multimedia applications, but most of these are less interactive than typical computer games. Previous work within the context of computer games has concentrated primarily on user actions for specific environments, such as combat in a first-person shooter game. This paper provides a detailed study of the effects of frame rate and resolution on discrete, canonical actions common to many games, shooting and navigation. The study uses a novel perspective based classification defined by the position of the camera relative to the user and the visual change in object sizes relative to the camera, to further refine the findings across a broad spectrum of game genres. A custom game with levels that combine actions and perspectives and measures user performance with different display settings provides the core for the user study experiments. Analysis for over 25 users shows that frame rate has a much greater impact on user performance than does resolution across all game perspectives and gameplay actions. Both frame rate and resolution impact user opinion on playability and quality. These insights into the effects of frame rates and resolution on user performance and opinions can guide game players in their choice for game settings and new hardware purchases, and inform system designers in their development of new hardware.

As the interactive entertainment industry matures, a better understanding of what makes software entertaining is needed. A natural starting point is the application of traditional Human-Computer Interaction (HCI) tools to interactive entertainment software. HCI tools include cognitive models that researchers have used to model users' thought processes and evaluate interface design. This paper users a simple cognitive model to investigate the relationship between the complexity of an interaction and the entertainment experienced by the user. We design a simple computer game, create a normative model for how a user plays this game, and build several variations of this game such that normative models of these variants differed across two factors: pace and complexity. User studies conducted on these variations allow comparison with these factors to user performance and self-reported user enjoyment. Users ingame enjoyment was found to be related to both the subject's performance and the game complexity.

As part of a project to develop a user-centered network measurement platform that limits impediments to participation, this work focuses on using the execution of a signed Java applet for home network measurement. We have developed a Java applet tool to understand the capabilities of such a tool for measuring characteristics of a user's network environment from the browser. This paper reports on the capabilities of the tool, the measurement methodology employed, and initial results obtained for a set of residential users employing the tool. Despite the sandbox-type restrictions in Java, the results include information about the configuration of the user's testing machine, wireless connectivity of the testing machine, available upload and download throughput, DNS performance and the number and type of devices on the user's network.

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.

New forms for interaction in virtual worlds, such as Second Life, bring dynamic network traffic because the number of online users can vary greatly from region to region and users can add their own content, such as dynamic objects and custom artwork. While there have been numerous studies on network traffic for multimedia applications and even online games, there has been little effort in understanding the traffic profile for virtual worlds. Earlier work suggests bandwidth used by Second Life varies with the avatar actions and amount of streaming content. Our paper complements this work, first by confirming some earlier results, then by strengthening the network analysis by extending the set of avatar actions studied and by varying the number of objects and avatars interacted with in the virtual world. Our results show that the population and number of objects near an avatar in the virtual world have a dramatic effect on the network characteristics, with dense, crowded areas demanding far more bandwidth than sparse, deserted areas. Similarly, avatar actions that require fast motion, such as walking and flying, use more bandwidth than standing, especially when the former is in a dense area and the latter is in a sparse area. The analysis in this paper can help network planning for access links and core networks as well as provide a base for building synthetic models for simulation.

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.

Many projects currently used in Software Engineering curricula lack both the “fun factor ” needed to engage students, as well as the practical realism of engineering projects that include other computer science disciplines such as Software Engineering, Networks, or Human Computer Interaction. This paper reports on our endeavor to enhance interest and retention in an existing Software Engineering curriculum through the use of computer game-based projects. Specifically, a set of game-centric, project-based modules have been developed that enable students to: (1) actively participate in the different phases of the software lifecycle taking a single project from requirement elicitation to testing and maintenance; (2) expose students to real issues in project and team management over the course of a 2-semester project; and at the same time (3) introduce students to the different aspects of computer game design. Preliminary results suggest the merits of our approach, showing improved class participation and performance.

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.

With growth in interactive network games comes increased importance in a better understanding of the effects of latency on game performance. While previous work has measured the effects of latency on first-person shooters and real-time strategy games, there has been no systematic investigation of the effects of latency on sports games. In this work, we study the effects of latency on online Madden NFL football, one of the most popular online sports games, through a series of carefully designed experiments in which we systematically control latency between players. Our experiments illustrate the mechanisms Madden NFL uses to compensate for latency. Our user studies show there is little impact from latency on user performance in Madden NFL over typical low Internet latencies. However, for latencies higher than 500 ms, there is a significant impact on user performance, degrading performance by almost 30%. Our network measurements show periodic data rates during game-play with significant command aggregation at higher latencies.

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.

Network games are becoming increasingly popular, but their traffic patterns have received little attention from the academic research community. A better understanding of network game traffic can lead to more effective network architectures and more realistic network simulations. We gathered traffic traces from live Internet games of Counter-strike and Starcraft, representative games from two different gaming genres. We analyzed the network traffic patterns and bandwidth consumption to better understand how such games impact the network. Both games were found to have very low bandwidth usage and packets significantly smaller than typical Internet applications. Starcraft games showed consistent traffic behavior across games while the traffic patterns for Counter-strike varied widely, especially for the server. In particular, Counter-strike clients and servers often send bursts of very small packets. Since current Internet routers are typically designed for large transfers with large packets, there may be opportunities to improve network architectures to better manage and support game traffic.

Active Queue Management (AQM) is intended to achieve high link utilization with a low queuing delay. Recent studies show that RED, one of the most well-known AQMs, is difficult to configure and does not provide significant performance gains given the complexity required for proper configuration. Recent variants of RED, such as Adaptive-RED are designed to provide more robust RED performance under a wider-range of traffic conditions but have not yet been evaluated. This paper presents a router queue behavior model (a queue law) for TCP-dropping and TCP-marking control systems, and uses the queue law to illustrate the impact of TCP traffic on the load and queue behavior of congested routers. Through queue law analysis and simulation, this paper confirms that RED-like AQM techniques that employ packet dropping do not significantly improve performance over that of drop-tail queue management. However, when AQM techniques use Explicit Congestion Notification (ECN) as a method to notify TCP sources of congestion rather than packet drops, the performance gains of AQM in terms of goodput and delay can be significant over that of drop-tail queue management.

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.

Video streaming on the Internet often suffers from high frame loss rates due to fragmentation of large frames and inter-frame dependencies needed for high compression. We propose adding lightweight, priority-based queue management to Internet routers to significantly improve performance of video streaming. We extend a Rate-Based RED approach to support three priority classes and apply it to MPEG. The performance of the mechanism on video streams is measured, analyzed and compared with Drop-Tail and RED in terms of transport layer throughput, system fairness, application layer throughput and goodput, and video stream quality. Extensive simulation shows that our approach improves MPEG video stream quality and network system fairness over traditional RED under a variety of workloads.

Typical undergraduate operating systems projects use services provided by an operating system via system calls or develop code in a simulated operating system. With the increasing popularity of operating systems with open source code such as Linux, there are untapped possibilities for operating systems projects to modify real operating system code. We present the hardware and software configuration of an open source laboratory that promises to provide students that use it with a better understanding of operating system internals than is typically gained in a traditional operating systems course. Our preliminary projects and evaluation suggest that thus far the lab has achieved its primary goal in that students that used the lab feel more knowledgeable in operating systems and more confident in their ability to write and modify operating system code.

Recommender systems provide personalized suggestions about items that users will find interesting. Typically, recommender systems require a user interface that can ``intelligently'' determine the interest of a user and use this information to make suggestions. The common solution, ``explicit ratings'', where users tell the system what they think about a piece of information, is well-understood and fairly precise. However, having to stop to enter explicit ratings can alter normal patterns of browsing and reading. A more ``intelligent'' method is to useimplicit ratings, where a rating is obtained by a method other than obtaining it directly from the user. These implicit interest indicators have obvious advantages, including removing the cost of the user rating, and that every user interaction with the system can contribute to an implicit rating.

The explosive increase in the volume and variety of Internet traffic has placed a growing emphasis on congestion control and fairness in Internet routers. Approaches to the problem of congestion, such as active queue management schemes like Random Early Detection (RED) use congestion avoidance techniques and are successful with TCP flows. Approaches to the problem of fairness, such as Fair Random Early Drop (FRED), keep per-flow state and punish misbehaved, non-TCP flows. Unfortunately, these punishment mechanisms also result in a significant performance drop for multimedia flows that use flow control. We extend Class-Based Threshold (CRT) [12], and propose a new active queue management mechanism as an extension to RED called Dynamic Class-Based Threshold (D- CBT) to improve multimedia performance on the Internet. Also, as an effort to reduce multimedia jitter, we propose a lightweight packet scheduling called Cut-In Packet Scheduling (ChIPS) as an alternative to FIFO packet scheduling. The performance of our proposed mechanisms is measured, analyzed and compared with other mechanisms (RED and CBT) in terms of throughput, fairness and multimedia jitter through simulation using NS. The study shows that D-CBT improves fairness among different classes of flows and ChIPS improves multimedia jitter without degrading fairness.

Article The effects of jitter on the peceptual quality of video Share on Authors: Mark Claypool Computer Science Department, Worcester Polytechnic Institute Computer Science Department, Worcester Polytechnic InstituteView Profile , Jonathan Tanner Computer Science Department, Worcester Polytechnic Institute Computer Science Department, Worcester Polytechnic InstituteView Profile Authors Info & Claims MULTIMEDIA '99: Proceedings of the seventh ACM international conference on Multimedia (Part 2)October 1999 Pages 115–118https://doi.org/10.1145/319878.319909Online:01 October 1999Publication History 78citation1,438DownloadsMetricsTotal Citations78Total Downloads1,438Last 12 Months70Last 6 weeks11 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Tomorrow's multimedia applications will stress all parts of a computer system.To determine the computer resources needed to meet application demands we have developed a new capacity planning model that is based on application quality as perceived by the user.We have applied our model to a Distributed Interactive Simulation flight simulator called the Viiual Cockpit.We investigate the quality of the Vkttral Cockpit on existing networks and processors and predict the effects of high-speed networks and high-performance processors on Virtual Cockpit quality.We find processor performance is the current bottleneck in application quality for the Virtual Cockpit, but that higher-speed networks, such as ATM, will be needed to meet network requirements after two to three generations of processor improvement.

In laboratories around the world, neuroscientists from diverse disciplines are exploring various aspects of brain structure. Because of the size of the domain, neuroscientists must specialize, making it difficult to fit results together, causing some research efforts to be duplicated because of lack of sharing of information. The authors have begun a long-term project to build a neuroscience research database for brain structure. One aspect of the database is the ability to visualize high-quality, high-resolution micrographs montaged together into 3-D structures as they were in the living brain. As demonstrated in this paper's analysis, realistic presentation of these visualizations across computer networks will stress current and proposed gigabit networks. Image compression can reduce network loads, but wide-spread use of the visualizations will still require networks capable of sustaining terabits per second of throughput.>

SuiteSound, a programming environment with integrated support for multimedia, is discussed. SuiteSound is built in the Suite object-based system on a conventional UNIX operating system. SuiteSound objects incorporate multimedia by creating flows and filters. Flows are streams of multimedia data moving through a sequence of objects. They bridge the gap between objects representing the state of an entity at a discrete point in time and space and continuous media such as live audio or video. Filters are intermediate objects between the source and destination of a flow. They take flow as input, perform one of several operations such as multiplex-in, multiplex-out, gain control, or silence deletion on it, and send the resulting flow to its destination. In effect, they provide a virtual device interface for the application programmer that is uniform and independent of any physical device. The design and implementation of SuiteSound on the Sun SparcStation are described. Experiments performed to determine the network and CPU load of the sound tool are reviewed.>