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.

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.

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.

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.