Cloud side end scheduling collaboration method and system of cloud game

Abstract

The invention discloses a cloud side end scheduling collaboration method and system for a cloud game. The method comprises the steps of cloud game service application, service receiving and task analysis, computing network service arrangement (computing network resource perception and network quality perception data intelligence injection), computing power resource calculation and network path calculation (cloud edge collaborative network path and game user access network channel path), computing network resource planning (computing resource allocation service calling), and computing network resource planning (cloud edge collaborative network path and game user access network channel path calling). And network computing service scheduling and network computing service plug-in execution configuration issuing are carried out to complete network computing resources, and finally, the cloud game service carries out business deployment online application. According to the method and the system, intelligent arrangement and scheduling are realized, a'computing network unified brain 'is constructed, and global intelligent arrangement, scheduling and optimization of cloud, edge, end and network resources are realized.

Description

Technical Field

[0001] The present invention relates to the field of computing network scheduling, and in particular to a cloud-edge-terminal scheduling coordination method and system for cloud gaming. Background Art

[0002] According to data released by the China Audio-Video and Digital Publishing Association Game Working Committee and IDC, the number of Chinese game users reached 640 million in 2019, with revenue reaching RMB 230.88 billion, of which the mobile Internet game market accounted for 68.5%; the client game market accounted for 26.6%; and the web game market accounted for 4.3%. Mobile Internet game revenue occupies a major share of the game market and continues to rise. Mobile Internet games are the result of the integration and development of the mobile Internet and the game industry. On the one hand, the mobile Internet continues to develop.

[0003] Essentially, cloud gaming is like a streaming video service, but interactive (i.e., cloud gaming is similar to an interactive live video service).

[0004] Cloud gaming is composed of a powerful cloud, video streams, and weak terminals. The game runs on a powerful cloud server, which sends high-definition video streams, and the terminal only needs to be able to decode the video and receive input signals. Compared with traditional games, cloud gaming has three major advantages: click-to-play, cross-operating system, and free from hardware limitations.

[0005] Currently, there is no ready-made SDN guarantee method to realize the cloud-edge scheduling coordination of cloud games. It is basically accessed nearby in the CDN way, which only provides guarantee from physical means, and there is no dynamic guarantee from the means of scheduling and control. Summary of the invention

[0006] In response to the above situation, the present invention provides a cloud-edge-terminal scheduling coordination method and system for cloud gaming, which provides cloud gaming providers with optimal deployment of cross-cloud and multi-cloud computing resources at the cloud-edge-terminal, guaranteed scheduling, and high-quality network access services; provides cloud gaming service providers with traffic diversion for cloud gaming services and access to multiple network channels; and provides game users with diverse, low-latency, high-bandwidth, and convenient network access services.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions:

[0008] In one embodiment of the present invention, a cloud-edge-terminal scheduling coordination method for cloud gaming is proposed, and the method includes:

[0009] The computing network brain receives cloud gaming service applications and performs task analysis, converting the tasks into network performance requirements and computing power requirements for cloud gaming services;

[0010] The computing network brain orchestrates cloud gaming services based on the computing power resources of the computing network resource perception module and the network performance information of the network quality perception module according to the network performance requirements and the computing power requirements of the cloud gaming services.

[0011] The computing network brain calculates computing resources and network paths based on the service orchestration results, including cloud-edge collaborative network paths and game user access network channel paths;

[0012] The computing network brain calls the computing network resource allocation service based on the calculation results of computing resources and network paths to implement the computing network resource planning and scheduling solution;

[0013] The computing network brain schedules network paths and computing resources according to the computing network resource planning and scheduling scheme;

[0014] The computing network brain executes the scheduling of network paths and computing resources through the computing network service plug-in;

[0015] After receiving the scheduling instructions executed by the computing network service plug-in, the cloud gaming service schedules and deploys computing power and launches the application.

[0016] Furthermore, the computing network brain includes the following functional modules:

[0017] Intelligent orchestration and scheduling of computing network: Receive and parse the orchestration package designed uniformly by computing network resource services, combine AI services of general capability services and computing resources and network performance data of computing network resource management to perform resource perception, quality perception, path calculation and resource planning, and call the adaptation capability of computing network service plug-ins to dynamically complete product business loading, thus realizing end-to-end orchestration of computing network;

[0018] Computing network service plug-in management: Provide unified collection service and control service management covering all professional computing network resources, forming standardized and reusable capabilities; push the normalized data of the collection service to the computing network resource management, and the computing network intelligent orchestration and scheduling are used to subscribe to the data; the computing network intelligent orchestration and scheduling interact with the control service to realize the control operation of the computing network resources and real-time quality perception;

[0019] General capability service: Provides general capabilities of AI services and security services, and uses API services to provide intelligent orchestration and scheduling for computing networks.

[0020] Computing network resource management: The resource management service receives computing resources and network performance data collected by the collection service in the computing network service plug-in, establishes a unified model for professional data, and aggregates and stores real-time data; based on metadata, a unified data service layer is built, and computing resources and network performance data are opened to the computing network intelligent orchestration and scheduling through data sharing services;

[0021] Unified design of computing network resource services: Provide unified management of computing network products from planning, design to loading, complete the standardization of computing power, network and resources for cloud computing, and conduct integrated design of computing network products and computing network capabilities; establish a fusion PSR model and unified master data and models to achieve one-stop product design and configuration, and full-process online loading; form a product service design template PST, and synchronize it in the form of an orchestration package for intelligent orchestration and scheduling of the computing network.

[0022] Furthermore, the collection service managed by the computing network service plug-in collects and publishes computing resource information, and the service scheduling of the computing network intelligent orchestration and scheduling schedules the computing tasks to the cloud-edge computing nodes that meet user needs according to the computing resource information, thereby ensuring the computing power coordination efficiency of the cloud-edge and edge-edge.

[0023] Furthermore, in the path calculation of intelligent orchestration and scheduling of the computing network, the network factors and computing factors are incorporated into the network path algorithm through SRv6 policy routing and network slicing capabilities, and a network path that meets SLA requirements and has the best computing resource utilization is calculated. Through end-to-end slicing, differentiated service carrying is achieved, ensuring the certainty of computing power transmission.

[0024] In one embodiment of the present invention, a cloud-edge-terminal scheduling coordination system for cloud gaming is also proposed, and the system includes:

[0025] The computing network brain is used to receive cloud game service applications and perform task analysis, and analyze tasks into network performance requirements and computing power requirements of cloud game services; according to the network performance requirements and computing power requirements of cloud game services, it orchestrates cloud game services based on the computing power resources of the computing network resource perception module and the network performance information of the network quality perception module; according to the service orchestration results, it calculates computing power resources and network paths, including cloud-edge collaborative network paths and game user access network channel paths; according to the calculation results of computing power resources and network paths, it calls the computing network resource allocation service to implement the computing network resource planning and scheduling plan; according to the computing network resource planning and scheduling plan, it schedules network paths and computing power resources respectively; and executes the scheduling of network paths and computing power resources through the computing network service plug-in;

[0026] Cloud gaming services are deployed in the central nodes and edge nodes of the cloud resource pool. They are used to schedule and deploy computing power for online applications after receiving scheduling instructions executed by the computing network service plug-in.

[0027] Furthermore, the computing network brain includes the following functional modules:

[0028] Intelligent orchestration and scheduling of computing network: Receive and parse the orchestration package designed uniformly by computing network resource services, combine AI services of general capability services and computing resources and network performance data of computing network resource management to perform resource perception, quality perception, path calculation and resource planning, and call the adaptation capability of computing network service plug-ins to dynamically complete product business loading, thus realizing end-to-end orchestration of computing network;

[0029] Computing network service plug-in management: Provide unified collection service and control service management covering all professional computing network resources, forming standardized and reusable capabilities; push the normalized data of the collection service to the computing network resource management, and the computing network intelligent orchestration and scheduling are used to subscribe to the data; the computing network intelligent orchestration and scheduling interact with the control service to realize the control operation of the computing network resources and real-time quality perception;

[0030] General capability service: Provides general capabilities of AI services and security services, and uses API services to provide intelligent orchestration and scheduling for computing networks.

[0031] Computing network resource management: The resource management service receives computing resources and network performance data collected by the collection service in the computing network service plug-in, establishes a unified model for professional data, and aggregates and stores real-time data; based on metadata, a unified data service layer is built, and computing resources and network performance data are opened to the computing network intelligent orchestration and scheduling through data sharing services;

[0032] Unified design of computing network resource services: Provide unified management of computing network products from planning, design to loading, complete the standardization of computing power, network and resources for cloud computing, and conduct integrated design of computing network products and computing network capabilities; establish a fusion PSR model and unified master data and models to achieve one-stop product design and configuration, and full-process online loading; form a product service design template PST, and synchronize it in the form of an orchestration package for intelligent orchestration and scheduling of the computing network.

[0033] Furthermore, the collection service managed by the computing network service plug-in collects and publishes computing resource information, and the service scheduling of the computing network intelligent orchestration and scheduling schedules the computing tasks to the cloud-edge computing nodes that meet user needs according to the computing resource information, thereby ensuring the computing power coordination efficiency of the cloud-edge and edge-edge.

[0034] Furthermore, in the path calculation of intelligent orchestration and scheduling of the computing network, the network factors and computing factors are incorporated into the network path algorithm through SRv6 policy routing and network slicing capabilities, and a network path that meets SLA requirements and has the best computing resource utilization is calculated. Through end-to-end slicing, differentiated service carrying is achieved, ensuring the certainty of computing power transmission.

[0035] In one embodiment of the present invention, a computer device is also proposed, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the cloud-edge scheduling coordination method of the aforementioned cloud game is designed.

[0036] In one embodiment of the present invention, a computer-readable storage medium is also proposed, which stores a computer program for executing a cloud-edge scheduling collaboration method for cloud gaming.

[0037] Beneficial effects:

[0038] 1. The present invention realizes computing network products with multi-dimensional "resource-based" dimensional capabilities (resource indicators, such as computing power and bandwidth), and the quality can be guaranteed end-to-end.

[0039] 2. The present invention intelligently orchestrates and schedules, builds a "computing network unified brain", and realizes global intelligent orchestration, scheduling and optimization of cloud, edge, terminal and network resources;

[0040] 3. The present invention achieves computing-network symbiosis, where the network supports computing power connection, computing power perception, and computing power routing, thereby achieving more flexible, on-demand, and agile computing power scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of the cloud-edge-terminal scheduling coordination method for cloud gaming of the present invention;

[0042] Figure 2 This is a functional architecture diagram of the computing network brain of the present invention;

[0043] Figure 3 It is a schematic diagram of the structure of the cloud-edge-terminal scheduling collaborative system for cloud gaming of the present invention;

[0044] Figure 4 It is a schematic diagram of the computer device structure of the present invention. DETAILED DESCRIPTION

[0045] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and design the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] Those skilled in the art will appreciate that the embodiments of the present invention may be designed as a system, system, device, method or computer program product. Therefore, the present disclosure may be specifically designed in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0047] According to an implementation manner of the present invention, a cloud-edge-terminal scheduling and coordination method for cloud gaming is proposed, including: cloud gaming service application, receiving service and task analysis, computing network service orchestration (computing network resource perception and network quality perception data injection), computing power resource calculation and network path calculation (cloud-edge collaborative network path, game user access network channel path), computing network resource planning (calling computing resource allocation service), computing network service scheduling, and computing network service plug-in execution configuration and distribution to complete computing network resources, and finally the cloud gaming service deploys the business and launches the application online.

[0048] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0049] like Figure 1 As shown, the cloud-edge-terminal scheduling coordination method of the cloud game of the present invention (cloud game service deployment application activation process) includes:

[0050] 1. Application for cloud gaming services: Apply for cloud gaming services directly on the computing network brain through cooperation with the front-end system (computing service request platform). The application content includes: game type, network requirements, and gaming experience requirements (FPS, resolution, etc.);

[0051] 2. Service reception and task analysis: The computing network brain receives cloud gaming service applications and performs task analysis, converting the tasks into network performance requirements and computing power requirements for cloud gaming services;

[0052] 3. Computing network service orchestration (computing network resource perception and network quality perception data intelligence): The computing network brain orchestrates cloud gaming services based on the computing power resources of the computing network resource perception module and the network performance information of the network quality perception module according to the network performance requirements and the computing power requirements of cloud gaming services;

[0053] 4. Computing power resource calculation and network path calculation: The computing network brain calculates computing power resources and network paths based on the service orchestration results, including cloud-edge collaborative network paths and game user access network channel paths;

[0054] 5. Computing network resource planning: The computing network brain calls the computing network resource allocation service based on the calculation results of computing resources and network paths to implement the computing network resource planning and scheduling solution;

[0055] 6. Computing network service scheduling: The computing network brain schedules network paths and computing resources (cloud game service deployment applications) according to the computing network resource planning and scheduling plan;

[0056] 7. Execution of computing network service plug-in: The computing network brain executes the scheduling of network paths and computing resources through the computing network service plug-in;

[0057] 8. Cloud gaming service deployment application: After receiving the scheduling instructions executed by the computing network service plug-in, the cloud gaming service schedules and deploys computing power to launch the application.

[0058] It should be noted that, although the operations of the method of the present invention are described in a specific order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0059] In order to more clearly explain the cloud-edge scheduling collaboration method of the above-mentioned cloud game, a specific embodiment is used for illustration below. However, it is worth noting that this embodiment is only for better illustrating the present invention and does not constitute an improper limitation of the present invention.

[0060] Example:

[0061] The deployment and application of cloud gaming services are implemented through two major modules: computing network brain and cloud gaming services.

[0062] 1. Computing Network Brain System

[0063] Build a "computing network unified brain" to achieve global intelligent orchestration, scheduling and optimization of cloud, edge, terminal and network resources, real-time quality perception, intelligent computing network simulation design and flexible and fast orchestration and scheduling services. Figure 2 As shown, the functions implemented include the following aspects:

[0064] (1) Intelligent Scheduling of Computing Networks

[0065] The intelligent scheduling of computing network first analyzes the task-based intent, describes the requirements for computing network through the intent interface, and converts the user's intent into a specific scheduling plan for computing resources and network paths, including computing power, network power, location, energy consumption, security and other requirements, and requests computing network scheduling. The computing network scheduling will allocate appropriate computing network resources based on the constraints and solution optimization requirements for the computing network in the scheduling request, combined with computing power resources and network performance information, and call the computing network service plug-in to create and connect computing network service instances to complete the computing network associated scheduling.

[0066] Responsible for the orchestration of cross-professional and cross-domain end-to-end networks, slices, computing resources and services. By receiving and parsing the orchestration package designed uniformly by the computing network resource service, combined with the AI ​​service of the general capability service and the computing resources and network quality data of the computing network resource management, resource perception, quality perception, path calculation and resource planning are performed, and the adaptation capability of the computing network service plug-in is called to dynamically complete product business loading, so as to realize the end-to-end orchestration of the computing network.

[0067] (2) Computing network service plug-in management

[0068] Provide unified collection service and control service management covering all professional computing network resources, forming standardized and reusable capabilities. The normalized data of the collection service is pushed to the computing network resource management, and the computing network intelligent orchestration and scheduling are used to subscribe to the data. The computing network intelligent orchestration and scheduling interact with the control service to realize the control operation and real-time quality perception of the computing network resources.

[0069] By completing the network service and opening up network capabilities, we build the foundation for the integration of computing and network, and realize the atomic capabilities of network perception and network control in various disciplines through computing network service plug-ins. The computing network service atomic capabilities are assembled and designed to build a unified standard multi-professional atomic capability library, realizing the capability topology, assembly rules, and parameter conversion mapping functions of atomic capabilities based on product + network element role + operation as the dimensions, and choreographing and connecting based on the atomic capabilities of various disciplines, flexibly building professional intra-network services for business, and quickly adapting to business scenario requirements.

[0070] (3) General capability services

[0071] Provides general capabilities for AI services and security services, and provides intelligent orchestration and scheduling for applications through API services.

[0072] (4) Network resource management

[0073] The resource management service receives the computing resources and network performance data collected by the collection service of the computing network service plug-in, establishes a unified model for various professional data, aggregates and stores real-time data, builds a unified data service layer based on metadata, and opens the computing resources and network performance data to the computing network intelligent orchestration and scheduling through the data sharing service.

[0074] (5) Computing power collaboration

[0075] This solution is verified based on a test network. In the test network, the CFN (computing power network) router can support the ability to collect and publish computing power resource information and status, and schedule computing tasks to cloud-edge computing power nodes that meet user needs based on the computing power resource information, thereby ensuring the collaborative efficiency of cloud-edge and edge-edge and the end-user experience.

[0076] (6) Computing and Network Collaboration

[0077] Through SRv6 policy routing and network slicing capabilities, network factors such as latency and bandwidth are incorporated into the network path algorithm as are computing factors such as cost and computing power. A network path that meets SLA requirements and has optimal computing resource utilization is calculated. End-to-end slicing is used to achieve differentiated service carrying and ensure the certainty of computing power transmission.

[0078] (7) Unified design of computing network resource services

[0079] Provide unified management of computing network products (cloud games) from planning, design, to loading, complete the standardized capabilities of computing power, network, resources, etc. to dissolve the cloud, and conduct integrated design of computing network products and computing network capabilities; establish a fusion PSR model and unified master data and models to achieve product one-point design (realize unified orchestration design in the computing network brain, from network to computing power to unified design of cloud game service requirements) and configuration, and load the entire process online; form a product service design template PST, and synchronize it to the computing network intelligent orchestration and scheduling in the form of an orchestration package.

[0080] (8) Computing Network Resource Perception

[0081] Through BGP-LS, IGP or SNMP scanning, the whole network equipment information is obtained, and the equipment configuration information is collected one by one, SR-Sid, SRv6Sid information and logical network topology are collected, and the physical topology is obtained in combination with the LLDP protocol, so as to finally ensure the integrity of the whole network equipment and network topology. Links can be automatically discovered through IGP or interconnected IP addresses, and BGP-LS / ISIS / OSPF protocols are used to receive and parse changes in LSDB messages in real time to obtain change update information of equipment, links and routes.

[0082] By distributing computing power resource information through CFN (computing power network) technology, intelligent management and real-time scheduling of computing power resources will be achieved through "cloud-edge collaboration" and "edge-edge collaboration".

[0083] (9) Network Quality Perception

[0084] TWAMP bidirectional active measurement is a performance measurement technology for IP links. TWAMP can perform bidirectional performance statistics in both the forward and reverse directions. TWAMP uses UDP packets as measurement probe frames to count bidirectional network delay and jitter. Through the cooperation between network devices that have deployed the TWAMP protocol, IP performance statistics between devices can be effectively obtained. Use Telemetry to regularly push device-collected performance data to the computing network service plug-in to achieve real-time perception of network quality (performance).

[0085] (10) End-to-end path calculation

[0086] SRv6 is used to calculate the cloud-edge and edge-edge interconnection paths. The optimal path can be selected by combining the real-time perceived network quality information to effectively avoid congested network nodes. SRv6 is SR (Segment Routing) + IPv6, which is an IPv6 forwarding technology. Through the flexible IPv6 extension header, network programmability is achieved. SRv6 simplifies the network protocol type, has good scalability and programmability, can meet the diverse needs of cloud gaming business assurance and cloud-edge collaborative scheduling, and provide a high-reliability network.

[0087] The cross-network professional end-to-end path design is based on the game users' needs for high-bandwidth, low-latency access as well as the characteristics of mobility, on-demand, and immediacy. It is necessary to quickly provide game users with 5G private network end-to-end slicing and PON / PTN access cross-network professional path calculation based on the game users' actual location, computing resources, and network resource availability.

[0088] 2. Cloud gaming services

[0089] Deploy high-end cloud games, cloud e-sports, etc. on the central nodes and edge nodes of the cloud resource pool.

[0090] (1) Hardware construction plan

[0091] GPU Servers:

[0092] 1 GPU server, used to deploy the cloud gaming service of the central node.

[0093] PC Farm Server:

[0094] 2 PC farm servers for deploying cloud gaming services for central nodes and edge nodes.

[0095] Monitor and host:

[0096] 1 monitor and host for terminal access.

[0097] GE electrical access switch:

[0098] Two GE electrical access switches are used to connect the above-mentioned GPU servers, PC farm servers, etc.

[0099] (2) Network construction plan

[0100] Cloud gaming services are deployed at the central node and edge node of the cloud resource pool, and cloud-edge computing resources will be interconnected and synchronized through cloud private networks and optical networks. Game users can use PCs, PADs, mobile phones and other terminal types to flexibly access the 5G private network, access cloud gaming services deployed at the edge of the cloud, and use the computing network brain for intelligent scheduling to create the ultimate cloud gaming experience.

[0101] (3) Network scheduling process:

[0102] Cloud gaming services are deployed on central nodes (Shuitu) and edge nodes (Renhe).

[0103] Simulated user access point: Renhe, accessing cloud games through dedicated lines;

[0104] In normal mode: the computing network brain is dispatched by the computing network, and users access the cloud gaming service of the central node (Shuitu). The delay is expected to be 50ms and the jitter is 2ms.

[0105] In premium mode: the computing network brain dispatches the computing network, and the user accesses the cloud gaming service of the edge node 2 (Renhe) closest to the user. The delay is expected to be 12ms and the jitter is 1ms.

[0106] The difference between normal mode and premium mode is actually the difference in network performance requirements, such as latency and jitter. According to different network performance requirements, the computing network brain combines network quality perception and computing resource perception to calculate the network path, that is, how to plan the path of the network tunnel to achieve performance. After planning, tunnels are issued for the service to ensure the service.

[0107] The network follows the calculation: no matter which server is called, the network brain will dispatch the server to access the game acceleration platform.

[0108] Based on the same inventive concept, the present invention also proposes a cloud-edge scheduling collaboration system for cloud games. The implementation of the system can refer to the implementation of the above method, and the repetitions will not be repeated. The term "module" used below can be a combination of software and / or hardware designed for a predetermined function. Although the system described in the following embodiments is preferably designed in software, the design of hardware, or a combination of software and hardware, is also possible and conceived.

[0109] Figure 3 Schematic diagram of the cloud-edge-end scheduling coordination system of the cloud game of the present invention. Figure 3 As shown, the system includes:

[0110] The computing network brain 101 is used to receive cloud game service applications and perform task analysis, and analyze the tasks into network performance requirements and computing power requirements of cloud game services; according to the network performance requirements and computing power requirements of cloud game services, it orchestrates cloud game services based on the computing power resources of the computing network resource perception module and the network performance information of the network quality perception module; according to the service orchestration results, it calculates computing power resources and network paths, including cloud-edge collaborative network paths and game user access network channel paths; according to the calculation results of computing power resources and network paths, it calls the computing network resource allocation service to implement the computing network resource planning and scheduling plan; according to the computing network resource planning and scheduling plan, it schedules network paths and computing power resources respectively; and executes the scheduling of network paths and computing power resources through the computing network service plug-in.

[0111] The computing network brain 101 includes the following functional modules:

[0112] Intelligent orchestration and scheduling of computing network: Receive and parse the orchestration package designed uniformly by computing network resource services, combine AI services of general capability services and computing resources and network performance data of computing network resource management to perform resource perception, quality perception, path calculation and resource planning, and call the adaptation capability of computing network service plug-ins to dynamically complete product business loading, thus realizing end-to-end orchestration of computing network;

[0113] Computing network service plug-in management: Provide unified collection service and control service management covering all professional computing network resources, forming standardized and reusable capabilities; push the normalized data of the collection service to the computing network resource management, and the computing network intelligent orchestration and scheduling are used to subscribe to the data; the computing network intelligent orchestration and scheduling interact with the control service to realize the control operation of the computing network resources and real-time quality perception;

[0114] General capability service: Provides general capabilities of AI services and security services, and uses API services to provide intelligent orchestration and scheduling for computing networks.

[0115] Computing network resource management: The resource management service receives computing resources and network performance data collected by the collection service in the computing network service plug-in, establishes a unified model for professional data, and aggregates and stores real-time data; based on metadata, a unified data service layer is built, and computing resources and network performance data are opened to the computing network intelligent orchestration and scheduling through data sharing services;

[0116] Unified design of computing network resource services: Provide unified management of computing network products from planning, design to loading, complete the standardization of computing power, network and resources for cloud computing, and conduct integrated design of computing network products and computing network capabilities; establish a fusion PSR model and unified master data and models to achieve one-stop product design and configuration, and full-process online loading; form a product service design template PST, and synchronize it in the form of an orchestration package for intelligent orchestration and scheduling of the computing network.

[0117] The cloud gaming service 102 is deployed in the central node and edge node of the cloud resource pool, and is used to schedule and deploy computing power for online applications after receiving scheduling instructions executed by the computing network service plug-in.

[0118] It should be noted that although several modules of the cloud-edge scheduling collaborative system of cloud gaming are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules described above can be concretized in one module. Conversely, the features and functions of a module described above can be further divided into multiple modules for concretization.

[0119] Based on the above invention concept, Figure 4As shown, the present invention also proposes a computer device 200, including a memory 210, a processor 220, and a computer program 230 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 230, the cloud-edge scheduling coordination method of the aforementioned cloud game is designed.

[0120] Based on the aforementioned inventive concept, the present invention also proposes a computer-readable storage medium, which stores a computer program for executing the aforementioned cloud-edge scheduling collaboration method for cloud games.

[0121] The cloud-edge-terminal scheduling coordination method and system for cloud gaming proposed in the present invention have the following highlights:

[0122] 1. Realize computing network products with multi-dimensional "resource-based" dimensional capabilities (resource indicators, such as computing power and bandwidth), and ensure end-to-end quality.

[0123] 2. Intelligent orchestration and scheduling, building a "computing network unified brain" to achieve global intelligent orchestration, scheduling and optimization of cloud, edge, terminal and network resources;

[0124] 3. Computing and network symbiosis: the network supports computing power connection, computing power perception, and computing power routing, achieving more flexible, on-demand, and agile computing power scheduling.

[0125] Although the spirit and principle of the present invention have been described with reference to several specific embodiments, it should be understood that the present invention is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present invention is intended to cover various modifications and equivalent arrangements contained in the spirit and scope of the attached claims.

[0126] Regarding the limitation of the protection scope of the present invention, those skilled in the art should understand that, based on the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without creative work are still within the protection scope of the present invention.

Claims

1. A cloud-edge-terminal scheduling coordination method for cloud gaming, characterized in that: The method includes: The computing network brain receives cloud gaming service applications and performs task analysis, converting the tasks into network performance requirements and computing power requirements for cloud gaming services; The computing network brain orchestrates cloud gaming services based on the computing power resources of the computing network resource perception module and the network performance information of the network quality perception module according to the network performance requirements and the computing power requirements of the cloud gaming services. The computing network brain calculates computing resources and network paths based on the service orchestration results, including cloud-edge collaborative network paths and game user access network channel paths; The computing network brain calls the computing network resource allocation service based on the calculation results of computing resources and network paths to implement the computing network resource planning and scheduling solution; The computing network brain schedules network paths and computing resources according to the computing network resource planning and scheduling scheme; The computing network brain executes the scheduling of network paths and computing resources through the computing network service plug-in; After receiving the scheduling instructions executed by the computing network service plug-in, the cloud gaming service schedules and deploys computing power and launches the application.

2. The cloud-edge-terminal scheduling coordination method for cloud gaming according to claim 1, characterized in that: The computing network brain includes the following functional modules: Intelligent orchestration and scheduling of computing network: Receive and parse the orchestration package designed uniformly by computing network resource services, combine AI services of general capability services and computing resources and network performance data of computing network resource management to perform resource perception, quality perception, path calculation and resource planning, and call the adaptation capability of computing network service plug-ins to dynamically complete product business loading, thus realizing end-to-end orchestration of computing network; Computing network service plug-in management: Provide unified collection service and control service management covering all professional computing network resources, forming standardized and reusable capabilities; push the normalized data of the collection service to the computing network resource management, and the computing network intelligently arranges and schedules data subscription; The intelligent scheduling and control services of the computing network interact to achieve control operations and real-time quality perception of computing network resources; General capability service: Provides general capabilities of AI services and security services, and uses API services to provide intelligent orchestration and scheduling for computing networks. Computing network resource management: The resource management service receives computing resources and network performance data collected by the collection service in the computing network service plug-in, establishes a unified model for professional data, and aggregates and stores real-time data; Based on metadata, a unified data service layer is built, and computing resources and network performance data are opened to computing network intelligent orchestration and scheduling through data sharing services; Unified design of computing network resource services: Provide unified management of computing network products from planning, design to loading, complete the standardization of computing power, network and resources for cloud computing, and conduct integrated design of computing network products and computing network capabilities; Establish a fusion PSR model and unified master data and models to achieve one-stop product design and configuration, and full-process online loading; A product service design template PST is formed and synchronized to the computing network intelligent orchestration and scheduling in the form of an orchestration package.

3. The cloud-edge-terminal scheduling coordination method for cloud gaming according to claim 2 is characterized in that: The collection service managed by the computing network service plug-in collects and publishes computing resource information. The service scheduling of the computing network intelligent orchestration and scheduling schedules computing tasks to the cloud-edge computing nodes that meet user needs based on the computing resource information, ensuring the computing power coordination efficiency of the cloud-edge and edge-edge.

4. The cloud-edge-terminal scheduling coordination method for cloud gaming according to claim 2, characterized in that: In the path calculation of intelligent orchestration and scheduling of computing networks, network factors and computing factors are incorporated into the network path algorithm through SRv6 policy routing and network slicing capabilities, and a network path that meets SLA requirements and has the best computing resource utilization is calculated. End-to-end slicing is used to achieve differentiated service carrying and ensure the certainty of computing power transmission.

5. A cloud-edge-terminal scheduling coordination system for cloud gaming, characterized in that: The system includes: The computing network brain is used to receive cloud game service applications and perform task analysis, and analyze tasks into network performance requirements and computing power requirements of cloud game services; according to the network performance requirements and computing power requirements of cloud game services, it orchestrates cloud game services based on the computing power resources of the computing network resource perception module and the network performance information of the network quality perception module; according to the service orchestration results, it calculates computing power resources and network paths, including cloud-edge collaborative network paths and game user access network channel paths; according to the calculation results of computing power resources and network paths, it calls the computing network resource allocation service to implement the computing network resource planning and scheduling plan; according to the computing network resource planning and scheduling plan, it schedules network paths and computing power resources respectively; and executes the scheduling of network paths and computing power resources through the computing network service plug-in; Cloud gaming services are deployed in the central nodes and edge nodes of the cloud resource pool. They are used to schedule and deploy computing power for online applications after receiving scheduling instructions executed by the computing network service plug-in.

6. The cloud-edge-terminal scheduling coordination system for cloud gaming according to claim 5, characterized in that: The computing network brain includes the following functional modules: Intelligent orchestration and scheduling of computing network: Receive and parse the orchestration package designed uniformly by computing network resource services, combine AI services of general capability services and computing resources and network performance data of computing network resource management to perform resource perception, quality perception, path calculation and resource planning, and call the adaptation capability of computing network service plug-ins to dynamically complete product business loading, thus realizing end-to-end orchestration of computing network; Computing network service plug-in management: Provide unified collection service and control service management covering all professional computing network resources, forming standardized and reusable capabilities; push the normalized data of the collection service to the computing network resource management, and the computing network intelligently arranges and schedules data subscription; The intelligent scheduling and control services of the computing network interact to achieve control operations and real-time quality perception of computing network resources; General capability service: Provides general capabilities of AI services and security services, and uses API services to provide intelligent orchestration and scheduling for computing networks. Computing network resource management: The resource management service receives computing resources and network performance data collected by the collection service in the computing network service plug-in, establishes a unified model for professional data, and aggregates and stores real-time data; Based on metadata, a unified data service layer is built, and computing resources and network performance data are opened to computing network intelligent orchestration and scheduling through data sharing services; Unified design of computing network resource services: Provide unified management of computing network products from planning, design to loading, complete the standardization of computing power, network and resources for cloud computing, and conduct integrated design of computing network products and computing network capabilities; Establish a fusion PSR model and unified master data and models to achieve one-stop product design and configuration, and full-process online loading; A product service design template PST is formed and synchronized to the computing network intelligent orchestration and scheduling in the form of an orchestration package.

7. The cloud-edge-terminal scheduling coordination system for cloud gaming according to claim 6, characterized in that: The collection service managed by the computing network service plug-in collects and publishes computing resource information. The service scheduling of the computing network intelligent orchestration and scheduling schedules computing tasks to the cloud-edge computing nodes that meet user needs based on the computing resource information, ensuring the computing power coordination efficiency of the cloud-edge and edge-edge.

8. The cloud-edge-terminal scheduling coordination system for cloud gaming according to claim 6, characterized in that: In the path calculation of intelligent orchestration and scheduling of computing networks, network factors and computing factors are incorporated into the network path algorithm through SRv6 policy routing and network slicing capabilities, and a network path that meets SLA requirements and has the best computing resource utilization is calculated. End-to-end slicing is used to achieve differentiated service carrying and ensure the certainty of computing power transmission.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the method according to any one of claims 1 to 4.

Images