Cloud Gaming Research Articles

Analysis of 5G technology for games and communication

Thanks to the joint work of industry companies, new devices are already entering the market and 5G networks and infrastructure are being actively deployed. And very soon real 5G gadgets will go on sale! In this article I want to talk about the new opportunities that the 5G era can give people. And these features, including those we have already talked about, are getting closer to users. Let’s talk today about what the advent of the 5G era means for games and communications. The key to the success of 5G cloud gaming is a good strategy that brings the right gaming games to an affordable market with the right infrastructure and coverage and provides a business case that delivers growth and expected ROI. 5G allows developers to deal with the problem of delays and gives them and users completely new features. We believe that with fifth-generation network technology, the very concept of "lag" in games will soon be forgotten, and the combination of 5G and augmented reality in multiplayer mobile AR-games will help bring mobile gaming to a whole new level. Using only smartphones, you and your friends will be able to play augmented reality paintball to combine the real world with the elements of the virtual. As in today’s paintball battle, when you need to run around the field and shoot balls of paint at your friends, you will catch them in the "sight" of your smartphone and tap the screen to fire digital paintball shells. In addition to reducing latency, 5G technology and artificial intelligence will help to ensure complete immersion in the game with quality graphics and new effects. For example, when one such virtual projectile hits the clothes, the ball will not just bounce off it, as in 4G games, it will make the fabric bend at the point of impact, and then in real time it will fill it with a bright.

Forecasting Video QoE With Deep Learning From Multivariate Time-Series

The end users’ satisfactory Quality of Experience (QoE) is a fundamental criterion for networked video service providers such as video-on-demand providers (Netflix, YouTube, etc.), cloud gaming providers (Google Stadia, PlayStation Now, etc.) and videoconferencing providers (Zoom, Microsoft Teams, etc.). To know the QoE, providers today typically predict it from the Quality of Service (QoS) parameters or the client-side's actual QoE metrics measured at the current time-step. But the former does not precisely reflect the users' experience, and the latter has a delay between QoE measurements at the client-side and the user's current experience. Mitigating this delay can provide a noticeable improvement in the delivery system's performance. For example, accurate forecasting of QoE for the near future allows the service management system to take a proactive approach and fix delivery issues before they become a noticeable problem at the end user, or at least reduce overall QoE degradation. QoE forecasting can also be used in rate adaptation in DASH or resource allocation in wireless networks. In this paper, we propose a method to prognosticate QoE metrics. Using data collected from an industry video streaming testbed for three different classes, we define a multivariate time series forecasting problem. We then model a hybrid state-of-the-art deep learning method, BiLSTM-CNN, to forecast the QoE metrics in advance. Evaluation of our proposed method compared to four other well-known ML models of Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), Long short-term memory (LSTM), and Bidirectional LSTM (BiLSTM) demonstrates the superior performance of our proposed method.

Penggunaan Virtual Machine untuk Mengoptimalkan Server pada Cloud Gaming dengan GamingAnywhere

The development of the game industry is increasingly advanced until the emergence of cloud gaming network technology. Cloud gaming allows low-spec clients to play high-spec games. An open-source cloud gaming platform is GamingAnywhere. In this study, we will implement a cloud gaming server using GamingAnywhere and combine it with a virtual machine. The virtual machines that will be used are VirtualBox and VMware. This research is aimed at providing information about resource usage on servers and clients as well as Quality of Service (QoS) and Frames Per Second (FPS) from GamingAnywhere running on virtual machines. From the results of server measurements it only takes 12-21% CPU usage, 5-7% GPU usage, and 75-77% memory usage for VirtualBox and 17-26% CPU usage, 26-35% GPU usage, and 64-65% memory usage for VMware. From the FPS measurement results obtained on the client, it has an average of more than 59 fps for the three test games when GamingAnywhere is running on VirtualBox, VMware, and without using a virtual machine. From the measurement results, to get optimal QoS in accessing games with GamingAnywhere, a minimum bandwidth of 5 Mbps is needed and the distance between the client and the router is a maximum of 7 meters. If the bandwidth is less than 5 Mbps, the system experiences a delay of ± 0.003 seconds and the packet loss is more than 10%.

Towards Fog-Assisted Virtual Reality MMOG with Ultra-Low Latency

In this paper, we propose a method to realize a virtual reality MMOG (Massively Multiplayer Online Video Game) with ultra-low latency. The basic idea of the proposed method is to introduce a layer consisting of several fog nodes between clients and cloud server to offload a part of the rendering task which is conducted by the cloud server in conventional cloud games. We examine three techniques to reduce the latency in such a fog-assisted cloud game: 1) To maintain the consistency of the virtual game space, collision detection of virtual objects is conducted by the cloud server in a centralized manner; 2) To reflect subtle changes of the line of sight to the 3D game view, each client is assigned to a fog node and the head motion of the player acquired through HMD (Head-Mounted Display) is directly sent to the corresponding fog node; and 3) To offload a part of the rendering task, we separate the rendering of the background view from that of the foreground view, and migrate the former to other nodes including the cloud server. The performance of the proposed method is evaluated by experiments with an AWS-based prototype system. It is confirmed that the proposed techniques achieve the latency of 32.3 ms, which is 66 % faster than the conventional systems.

A novel cloud game framework in dual Gigabit Network

With the development of 5G, cloud computing, and artificial intelligence (AI) technology, cloud game has become a hotspot about application and innovation of Gigabit bandwidth. This paper, firstly, analyses the present situation and development of cloud game to clarify the key business and key technology of cloud game, then, proposes an operational framework of cloud game, finally, the feasibility of the proposed framework is discussed and several suggestions about the operation of cloud game are given.

Time and Cost Efficient Cloud Resource Allocation for Real-Time Data-Intensive Smart Systems

Cloud computing is the de facto platform for deploying resource- and data-intensive real-time applications due to the collaboration of large scale resources operating in cross-administrative domains. For example, real-time systems are generated by smart devices (e.g., sensors in smart homes that monitor surroundings in real-time, security cameras that produce video streams in real-time, cloud gaming, social media streams, etc.). Such low-end devices form a microgrid which has low computational and storage capacity and hence offload data unto the cloud for processing. Cloud computing still lacks mature time-oriented scheduling and resource allocation strategies which thoroughly deliberate stringent QoS. Traditional approaches are sufficient only when applications have real-time and data constraints, and cloud storage resources are located with computational resources where the data are locally available for task execution. Such approaches mainly focus on resource provision and latency, and are prone to missing deadlines during tasks execution due to the urgency of the tasks and limited user budget constraints. The timing and data requirements exacerbate the efficient task scheduling and resource allocation problems. To cope with the aforementioned gaps, we propose a time- and cost-efficient resource allocation strategy for smart systems that periodically offload computational and data-intensive load to the cloud. The proposed strategy minimizes the data files transfer overhead to computing resources by selecting appropriate pairs of computing and storage resources. The celebrated results show the effectiveness of the proposed technique in terms of resource selection and tasks processing within time and budget constraints when compared with the other counterparts.

글로벌 클라우드 게임 시장에서의 경쟁우위 요소

5세대 통신기술(5G)의 도입은 4세대 통신기술(4G)에서 발생했던 서비스 트래픽 속도와 용량 문제를 크게 감소시켰다. 이러한 통신환경에서 클라우드 게임의 시장 수요는 높아지고 있으며 향후 모바일 게임을 대체하는 분야로 클라우드 게임이 각광받고 있다. 본 연구에서는 통신기술의 발전에 따른 게임 산업의 변화와 클라우드 게임의 특징 및 시장 현황을 설명한다. 다음으로 클라우드 게임의 경쟁우위 요소로서 독창적인 게임콘텐츠, 안정적인 게임 환경, 높은 플랫폼 접근성을 제시한다. 본 연구는 클라우드 게임에 대한 독자의 이해를 높이며, 클라우드 게임 시장 및 산업을 위한 정책적 지원과 관련된 의사결정을 돕기 위한 자료로 활용될 수 있을 것이다.

History of Video Game Distribution

Video games were originally distributed through fixed-function appliances or gaming consoles. As technology improved, various forms of physical media were used to distribute games, such as cartridges and discs. While this provided versatility, it also carried physical design considerations and complexities surrounding backward-compatibility. Today, digital distribution is growing rapidly and beginning to overtake physical media. Cloud gaming is disrupting distribution even further by eliminating local storage, compute, and rendering and shifting all of those tasks to cloud compute resources.

Doris: An Adaptive Soft Real-Time Scheduler in Virtualized Environments

With the development of cloud computing and virtualization technologies, more and more soft real-time applications, such as Voice over Internet Protocol (VoIP) server and cloud gaming, are running in virtualized data centers. Though previous studies optimize CPU schedulers of hypervisors to support these applications in virtualized environments, there are some important challenges in designing an efficient CPU scheduler which is suitable for real-world clouds. On one hand, hypervisors do not know whether an application in a virtual machine (VM) has real-time requirements, so manually setting the scheduling parameters is a common case for CPU schedulers, which probably increases users’ burden, lacks flexibility, and causes misconfigurations. On the other hand, it has been reported that most of existing CPU schedulers designed for soft real-time applications have an obvious propensity to such applications which prevents them from being applied in practical multi-tenant cloud environments. In this paper, we design and implement an adaptive soft real-time scheduler based on Xen, named Doris , to address these challenges. It identifies the VMs running soft real-time applications (RT-VMs) and infers their scheduling parameters according to the communication behaviors of VMs adaptively. Then, it promotes the priorities of VCPUs of the RT-VMs temporarily according to I/O events and the inferred scheduling parameters of RT-VMs to support soft real-time applications adaptively while minimizing the impacts on non-real-time applications. Finally, considering the importance of privileged entities (such as Domain0 in Xen) in I/O processing, Doris sets their types and scheduling parameters dynamically, which enables the adaptive scheduling of them to guarantee the performance of soft real-time applications. Our evaluation shows Doris can support soft real-time applications adaptively and efficiently, and only introduces very slight overhead.

CloudyGame: Enabling cloud gaming on the edge with dynamic asset streaming and shared game instances

Cloud gaming has emerged as a new computer game delivery paradigm that promises gaming anywhere, anytime, on any device, by running the computer game on a cloud server and streaming the rendered frames to users. To fulfill its promises, a cloud gaming provider must face three main challenges: reducing the interaction latency, reducing the cloud infrastructure cost, and reducing the network bandwidth demand. One way to reduce interaction latency is to run the game on the edge instead of the cloud. This introduces two additional challenges due to the limited resources available on the edge servers. First, there is a high initialization cost to install a game on the edge server if the game that a player wishes to play is not already installed. Second, an edge server typically has limited computing resources compared to the servers in the cloud. In this work, we address these two issues by proposing CloudyGame, a new software architecture for developing computer games, in which (i) resources are more efficiently shared and managed between different playing instances, and (ii) game assets are streamed on-demand to reduce the initialization cost. CloudyGame is implemented with a popular game engine, and thus any game built on the engine supports CloudyGame out of the box. Our evaluation shows that a game running on CloudyGame architecture needs 70–80% less RAM, VRAM, and CPU than a game using conventional architecture when running with four players. Furthermore, the game asset streaming system reduces the game’s initial loading time by 70%. Hence, our cloud gaming architecture is highly scalable and economically deployable to the edge. Further, due to a reduction in resource usage, the CloudyGame architecture would benefit games running in the cloud as well.

Mobile cloud game in high performance computing environment

Mobile cloud game is a solution to play high-end games in indigent thin clients with a diversity of end-user devices, and as real-time gaming, mobile cloud game hosting game engines in the cloud. Moreover, frequent change in network quality is another issue that should be limited to run the real fast cloud game. Thus, reliable software components between cloud and user devices as clients, including using artificial intelligence (AI) algorithms such as machine learning, deep learning and so on will enhance the game performance, particularly in multiplayer and real-time conditions. In this paper, we list the mobile cloud game architecture in the high-performance computing (HPC) environment, where a load of the game will be distributed between servers as cloud and clients. The server node as clouds or clients will consist of more than one server with many processors (cores) or sometimes can be recognized as distributed computing. Using HPC for cloud games will boost the game performance where the execution times will be dispersed not only in some node in servers and clients but in many cores of each server or client. The involvement of the internet of things (IoT) and ubiquitous access from heterogeneous devices will give benefit to enjoyment in the game itself.

NDNetGaming - development of a no-reference deep CNN for gaming video quality prediction

Gaming video streaming services are growing rapidly due to new services such as passive video streaming of gaming content, e.g. Twitch.tv, as well as cloud gaming, e.g. Nvidia GeForce NOW and Google Stadia. In contrast to traditional video content, gaming content has special characteristics such as extremely high and special motion patterns, synthetic content and repetitive content, which poses new opportunities for the design of machine learning-based models to outperform the state-of-the-art video and image quality approaches for this special computer generated content. In this paper, we train a Convolutional Neural Network (CNN) based on an objective quality model, VMAF, as ground truth and fine-tuned it based on subjective image quality ratings. In addition, we propose a new temporal pooling method to predict gaming video quality based on frame-level predictions. Finally, the paper also describes how an appropriate CNN architecture can be chosen and how well the model performs on different contents. Our result shows that among four popular network architectures that we investigated, DenseNet performs best for image quality assessment based on the training dataset. By training the last 57 convolutional layers of DenseNet based on VMAF values, we obtained a high performance model to predict VMAF of distorted frames of video games with a Spearman’s Rank correlation (SRCC) of 0.945 and Root Mean Score Error (RMSE) of 7.07 on the image level, while achieving a higher performance on the video level leading to a SRCC of 0.967 and RMSE of 5.47 for the KUGVD dataset. Furthermore, we fine-tuned the model based on subjective quality ratings of images from gaming content which resulted in a SRCC of 0.93 and RMSE of 0.46 using one-hold-out cross validation. Finally, on the video level, using the proposed pooling method, the model achieves a very good performance indicated by a SRCC of 0.968 and RMSE of 0.30 for the used gaming video dataset.

IMPLEMENTASI DAN ANALISIS CLOUD GAMING SKYEGRID PADA PERANGKAT ANDROID

Cloud computing is the transformation of information and communication technology from client or server-based computers. Cloud computing technology benefits users no longer need to invest heavily in software or maintenance software applications. So by developing the Cloud, there is a Cloud gaming which is a process to install a remote interactive game in the cloud and issued in the form of video to the user's device via the internet. In this journal, we need a cloud gaming application called Skyegrid. This study aims to implement cloud-based mobile gaming cloud implementation using an open-source server (Skyegrid) to find out Resources, Service Quality and Experience Quality in this study. In this study Skyegrid is used to discuss some popular games, namely games called Rainbow Six Siege and Monster Hunter World. The result of this study is that Skyegrid's cloud gaming mobile system is able to implement PC games that can be run on Android smartphones and reduce the use of CPU and RAM resources, and use low cost using skyegrid cloud gaming using personal computers that require greater costs.

Cloud-Based Dynamic GI for Shared VR Experiences.

Real-time high-fidelity rendering requires the use of expensive high-end hardware, even when rendering moderately complex scenes. Interactive streaming services and cloud gaming have somewhat mitigated the problem at the cost of response lag. In this article, we present Regular Grid Global Illumination (ReGGI), a distributed rendering pipeline that eliminates response lag and provides cloud-based dynamic GI for low-powered devices such as smartphones and the class of devices typically used in untethered VR headsets. Results show that ReGGI is scalable, has low bandwidth requirements, and produces images of comparable quality to instant radiosity.

Virtual Machine Placement Optimization in Mobile Cloud Gaming Through QoE-Oriented Resource Competition

Cloud gaming is a novel service provisioning paradigm, which hosts video games in the cloud and transmits interactive game streams to game players via the Internet. In such cloud gaming scenarios, the cloud is required to consume tremendous resources for video rendering and streaming, especially when the number of concurrent players reaches a certain level. On the other hand, different game players may have distinct requirements on Quality-of-Experience, such as high video quality, low delay, etc. Under this circumstance, how to satisfy players of different interests by efficiently leveraging cloud resources becomes a major challenge to existing cloud gaming services. In order to meet the overall requirements of players in a cost-effective manner, this article applies game theory to cloud gaming scenarios. It proposes a distributed algorithm to optimize virtual machine (VM) placement in mobile cloud gaming through resource competition. Further, by constructing a potential function, we prove that the resource competition game is a potential game, and the proposed algorithm scales well as the player population increases. We prove theoretically and verify experimentally that, with the proposed distributed VM placement algorithm, players can achieve a mutually satisfying state within a finite number of iterations.

Deployment of real-time systems in the cloud environment

Interest in real-time systems has grown considerably over recent years, primarily due to significant increase in the use of smart technologies and latency-sensitive applications such as cloud gaming, audio/video streaming, and smart homes. Significant work has been done on resource mapping in the cloud environment, and a number of promising results have been established accordingly where the focus is mainly on resource provisioning. However, the applicability of cloud computing services for real-time systems generated from smart systems is still in its infancy and remains unexplored, relatively. To address this gap, we propose a model for the smart systems that periodically offload computational workload to the cloud environment where virtual machines are allocated according to rate-monotonic scheduling policy to ensure requests are processed within the associated deadlines. Deadlines of tasks have been relaxed to improve server utilization as well as maintain a level of confidence in the timing constrains. Experimental results are discussed to highlight the applicability of static priority assignment for the workload in the context of virtual machines allocation.

IJNM Special Issue—International Journal of Network Management: QoE‐centric analysis and management of communication networks

IJNM Special Issue—International Journal of Network Management: QoE‐centric analysis and management of communication networks

A COMPARATIVE STUDY ON THE USER EXPERIENCE OF PC GAMING VS CLOUD GAMING

Cloud gaming is gaining in popularity, but it's still unknown whether the user-experience it provides is sweet enough to enable cloud gaming to exchange with a traditional PC gaming and what are the key expectations of a gamer. The Major goal of our research presented during this paper is to collect objective, experimental data on this subject. We've executed a user study that exposed ourselves to at least one simple and one complex game using cloud gaming and PC gaming approaches. After a timed gaming session on both platforms we analyzed the impact of the sessions and compared our experiences. The results of our study show that for a run of the mill casual gamer there's not much difference between cloud gaming and PC gaming. Whereas, more matured gamers tend to favor PC gaming, especially on high-end PCs. Although, both user groups did select cloud gaming as a far better solution for a low-end hardware. The results of our experiments lead to a conclusion that cloud gaming, in its current form, isn't ready to replace the PC gaming, but it fills a distinct segment that PC gaming has no possibility of reaching and basically allowing people to play their favorite titles without having to take a position in high-end gaming hardware. KEYWORDS: User Experience, Internet, Cloud-based Applications, Computer Games, Virtualized Applications.

An Optimized Meta-heuristic Bees Algorithm for Players’ Frame Rate Allocation Problem in Cloud Gaming Environments

Recently, cloud gaming has attracted much attention from service providers. The majority of cloud users have hardware limitations on their devices, hence why users are termed “thin clients”. A cloud service provider aims to afford the best-required frames of game scenes with each thin client in order to provide the best Quality of Experience (QoE). The importance of this issue is particularly critical with the emergence of 4K game service levels. Since 4K game scenes impose many demands upon the Central Processing Unit, Graphical Processing Unit, memory and bandwidth, cloud service providers tend to use the strategy of satisfying the highest number of gamers with the least amount of resources. Given that the problem of frame rate allocation is NP-hard, it is not possible to solve it with exact mathematical methods. In this paper, we propose a method inspired by the Bees algorithm. The approach presented in this article could significantly increases cloud providers’ profitability and reduce server-side wastage. Given the emergence of a new game-as-a-service paradigm for cloud-based games, cloud service providers must pay close attention to the issues of profitability and optimal resource allocation. The simulation of the proposed algorithm on the CloudSim simulator platform illustrates its robustness in terms of significant criteria such as runtime, number of admitted users, frame quality level, the QoE, etc.

Learned Resolution Scaling Powered Gaming-as-a-Service at Scale

Built on the explosive advancement of cloud and telecommunication technologies, Gaming-as-a-Service (GaaS) or cloud gaming system is expected to revolutionize the traditional multi-billion video game market in the near future. This wave is analogous to the rise of live-video-streaming-based-Netflix to replace conventional DVD rental business for movies and TVs. In practice, a successful GaaS platform need to operate in a transparent mode without requiring substantial efforts from both content providers and end users, and offer the pristine quality of experience (QoE) at an affordable cost. Our analysis suggests that GaaS provisioning cost can be reduced significantly by enforcing the game video rendering and streaming at a lower resolution (so as to increase the user concurrency in the cloud and reduce the streaming bandwidth over the network). However, streaming video at a lower resolution may deteriorate the QoE. To maintain the client QoE at the level using the default-native resolution for streaming or even enhance it, we introduce the learned resolution scaling (LRS), which leverages the computational capabilities at clients/edges to restore/improve the reconstructed image/video quality via stacked deep neural networks (DNN). We integrate this LRS into a commercialized GaaS platform - AnyGame, to study its efficiency and complexity quantitatively. Extensive real-life experiments have shown that LRS-powered AnyGame offers the state-of-the-art performance, and the lower operational cost, paving the road for a potential success of GaaS over the Internet. Additionally, we dive into proposed LRS via ablation studies to further demonstrate its consistent performance, including the discussions on trade-off between efficiency and complexity, alternative training sets, etc.