Cloud gaming is a new way to deliver high-quality gaming experience to gamers anywhere and anytime. In cloud gaming, sophisticated game software runs on powerful servers in data centers, rendered game scenes are streamed to gamers over the Internet in real time, and the gamers use light-weight software executed on heterogeneous devices to interact with the games. Due to the proliferation of high-speed networks and cloud computing, cloud gaming has attracted tremendous attentions in both the academia and industry since late 2000’s. In this paper, we survey the latest cloud gaming research from different aspects, spanning over cloud gaming platforms, optimization techniques, and commercial cloud gaming services. The readers will gain the overview of cloud gaming research and get familiar with the recent developments in this area.

https://ir.nctu.edu.tw:443/bitstream/11536/145505/1/007df636d72b23b15d610d0c56e730b5.pdf

A Survey on Cloud Gaming: Future of Computer Games

Traffic on future fifth-generation (5G) mobile networks is predicted to be dominated by challenging video applications such as mobile broadcasting, remote surgery and augmented reality, demanding real-time, and ultra-high quality delivery. Two of the main expectations of 5G networks are that they will be able to handle ultra-high-definition (UHD) video streaming and that they will deliver services that meet the requirements of the end user’s perceived quality by adopting quality of experience (QoE) aware network management approaches. This paper proposes a 5G-QoE framework to address the QoE modeling for UHD video flows in 5G networks. Particularly, it focuses on providing a QoE prediction model that is both sufficiently accurate and of low enough complexity to be employed as a continuous real-time indicator of the “health” of video application flows at the scale required in future 5G networks. The model has been developed and implemented as part of the EU 5G PPP SELFNET autonomic management framework, where it provides a primary indicator of the likely perceptual quality of UHD video application flows traversing a realistic multi-tenanted 5G mobile edge network testbed. The proposed 5G-QoE framework has been implemented in the 5G testbed, and the high accuracy of QoE prediction has been validated through comparing the predicted QoE values with not only subjective testing results but also empirical measurements in the testbed. As such, 5G-QoE would enable a holistic video flow self-optimisation system employing the cutting-edge Scalable H.265 video encoding to transmit UHD video applications in a QoE-aware manner.

/pdf/5g-qoe-qoe-modelling-for-ultra-hd-video-streaming-in-5g-o8gl7mmu8p.pdf

5G-QoE: QoE Modelling for Ultra-HD Video Streaming in 5G Networks

/pdf/quality-of-experience-qoe-in-cloud-gaming-models-a-review-3pb8r12o2k.pdf

Quality of experience (QoE) in cloud gaming models: A review

Machine learning models, particularly reinforcement learning (RL), have demonstrated great potential in optimizing video streaming applications. However, the state-of-the-art solutions are limited to an "offline learning" paradigm, i.e., the RL models are trained in simulators and then are operated in real networks. As a result, they inevitably suffer from the simulation-to-reality gap, showing far less satisfactory performance under real conditions compared with simulated environment. In this work, we close the gap by proposing OnRL, an online RL framework for real-time mobile video telephony. OnRL puts many individual RL agents directly into the video telephony system, which make video bitrate decisions in real-time and evolve their models over time. OnRL then aggregates these agents to form a high-level RL model that can help each individual to react to unseen network conditions. Moreover, OnRL incorporates novel mechanisms to handle the adverse impacts of inherent video traffic dynamics, and to eliminate risks of quality degradation caused by the RL model's exploration attempts. We implement OnRL on a mainstream operational video telephony system, Alibaba Taobao-live. In a month-long evaluation with 543 hours of video sessions from 151 real-world mobile users, OnRL outperforms the prior algorithms significantly, reducing video stalling rate by 14.22% while maintaining similar video quality.

OnRL: improving mobile video telephony via online reinforcement learning

Cloud gaming enables playing high-end games, originally designed for PC or game console setups, on low-end devices such as netbooks and smartphones, by offloading graphics rendering to GPU-powered cloud servers. However, transmitting the high-resolution video requires a large amount of network bandwidth, even though it is a compressed video stream. Foveated video encoding (FVE) reduces the bandwidth requirement by taking advantage of the non-uniform acuity of human visual system and by knowing where the user is looking. Based on a consumer-grade real-time eye tracker and an open source cloud gaming platform, we provide a cloud gaming FVE prototype that is game-agnostic and requires no modifications to the underlying game engine. In this article, we describe the prototype and its evaluation through measurements with representative games from different genres to understand the effect of parametrization of the FVE scheme on bandwidth requirements and to understand its feasibility from the latency perspective. We also present results from a user study on first-person shooter games. The results suggest that it is possible to find a “sweet spot” for the encoding parameters so the users hardly notice the presence of foveated encoding but at the same time the scheme yields most of the achievable bandwidth savings.

Cloud Gaming with Foveated Video Encoding

Cloud gaming has been recognized as a promising shift in the online game industry, with the aim being to deliver high-quality graphics games to any type of end user device. The concepts of cloud computing are leveraged to render the game scene as a video stream which is then delivered to players in real-time. Given high bandwidth and strict latency requirements, a key challenge faced by cloud game providers lies in configuring the video encoding parameters so as to maximize player Quality of Experience (QoE) while meeting bandwidth availability constraints. In this paper we address this challenge by conducting a subjective laboratory study involving 52 players and two different games aimed at identifying QoE-driven video encoding adaptation strategies. Empirical results are used to derive analytical QoE estimation models as functions of bitrate and framerate, while also taking into account game type and player skill. Results have shown that under certain identified bandwidth conditions, reductions of framerate lead to QoE improvements due to improved graphics quality. Given that results indicate that different QoE-driven video adaptation policies should likely be applied for different types of games, we further report on objective video metrics that may be used to classify games for the purpose of choosing an appropriate and QoE-driven video codec configuration strategy.

Cloud gaming QoE models for deriving video encoding adaptation strategies

In this paper we analyze the impact of different game types and video adaptation strategies on Quality of Experience (QoE) in cloud gaming. We focus on image quality and frame rate as parameters to be manipulated in the video encoder in different ways in order to meet bandwidth constraints of the network link. Our hypothesis is that under certain bandwidth conditions, maximization of the QoE for players will be achieved with different combinations of video encoding parameters (i.e., frame rate and image quality) in dependence of the game type. We test our hypothesis through a series of subjective tests on the streaming solution of the Steam In-home streaming platform. For subjective tests we focus on players with previous gaming experience. Obtained results may be used to drive effective QoE optimization strategies at the cloud gaming server.

The impact of video encoding parameters and game type on QoE for cloud gaming: A case study using the steam platform

In-home streaming of online game content to a wide range of low-end and thin client devices via wired/wireless local area connections mitigates the effects of network limitations that pose challenges in directly delivering cloud-based games to such devices. In this paper, we study whether (and to what extent) the rendering and streaming of game content to client devices (from an in-home server) imposes a degradation in gaming QoE as compared to the case of playing using a traditional online game client. We report on the results of an empirical study whereby an in-home game streaming scenario is set up using the GamingAnywhere platform, and participants are asked to provides subjective QoE assessments while playing a Massive Multiplayer Online Role Playing game (World of Warcraft). We test the impact of different delay and loss conditions, emulated along the external Internet link from the online game server to the home. Results show that switching from an online client to a in-home streaming client consistently results in perceived game quality degradations. Further, we report on the "willingness to keep playing" under different network condition in both online and in-home game streaming cases.

https://www.fer.unizg.hr/images/50010419/Empirical%20QoE%20Study%20of%20In-Home%20Streaming%20of%20Online%20Games.pdf

Empirical QoE study of in-home streaming of online games

Cloud gaming represents a highly interactive service whereby game logic is rendered in the cloud and streamed as a video to end devices. While benefits include the ability to stream high-quality graphics games to practically any end user device, drawbacks include high bandwidth requirements and very low latency. Consequently, a challenge faced by cloud gaming service providers is the design of algorithms for adapting video streaming parameters to meet the end user system and network resource constraints. In this paper, we conduct an analysis of the commercial NVIDIA GeForce NOW game streaming platform adaptation mechanisms in light of variable network conditions. We further conduct an empirical user study involving the GeForce NOW platform to assess player Quality of Experience when such adaptation mechanisms are employed. The results provide insight into limitations of the currently deployed mechanisms, as well as aim to provide input for the proposal of designing future video encoding adaptation strategies.

Analysis and QoE evaluation of cloud gaming service adaptation under different network conditions: The case of NVIDIA GeForce NOW

Cloud gaming has been recognized as a promising shift in the online game industry, with the aim of implementing the “on demand” service concept that has achieved market success in other areas of digital entertainment such as movies and TV shows. The concepts of cloud computing are leveraged to render the game scene as a video stream that is then delivered to players in real-time. The main advantage of this approach is the capability of delivering high-quality graphics games to any type of end user device; however, at the cost of high bandwidth consumption and strict latency requirements. A key challenge faced by cloud game providers lies in configuring the video encoding parameters so as to maximize player Quality of Experience (QoE) while meeting bandwidth availability constraints. In this article, we tackle one aspect of this problem by addressing the following research question: Is it possible to improve service adaptation based on information about the characteristics of the game being streamed? To answer this question, two main challenges need to be addressed: the need for different QoE-driven video encoding (re-)configuration strategies for different categories of games, and how to determine a relevant game categorization to be used for assigning appropriate configuration strategies. We investigate these problems by conducting two subjective laboratory studies with a total of 80 players and three different games. Results indicate that different strategies should likely be applied for different types of games, and show that existing game classifications are not necessarily suitable for differentiating game types in this context. We thus further analyze objective video metrics of collected game play video traces as well as player actions per minute and use this as input data for clustering of games into two clusters. Subjective results verify that different video encoding configuration strategies may be applied to games belonging to different clusters.

Ivan Slivar

Papers

Cloud gaming QoE models for deriving video encoding adaptation strategies

The impact of video encoding parameters and game type on QoE for cloud gaming: A case study using the steam platform

Empirical QoE study of in-home streaming of online games

Analysis and QoE evaluation of cloud gaming service adaptation under different network conditions: The case of NVIDIA GeForce NOW

Game Categorization for Deriving QoE-Driven Video Encoding Configuration Strategies for Cloud Gaming