Scheduling method and device based on computing network information fusion

Through the computing power routing method based on BGP extension, the resource scheduling and interaction problems in computing network integration computing are solved, and the intelligent scheduling and quality assurance of computing power resources are realized, and the efficiency and service capabilities of data applications are improved.

CN118945096APending Publication Date: 2024-11-12CHINA UNITECHS
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202310513233.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-09
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the existing computing network integrated computing technology, there is a lack of protocol-level interaction and control between data applications and computing power and network, resulting in the deterioration of computing power and network performance or insufficient resources, the use effect of data applications may even be unusable, and the distribution will be Formal computing priority network technology requires hardware upgrades, and there are problems of large investment and slow construction efficiency.

Method used

Using BGP extension-based computing power routing method, through BGP-LS and new address family expansion, the distributed information fusion and centralized management of computing power resources are realized, and the real-time scheduling of computing power resources is carried out through active scheduling and passive scheduling mechanisms are combined to carry out real-time scheduling of computing power resources and Routing decisions ensure the quality and efficiency of data applications.

Benefits of technology

It realizes intelligent scheduling and quality assurance of computing power resources, blocks the differences between computing power access and bearer networks, provides differentiated quality service capabilities for different types of applications and services, and improves the processing efficiency and resource utilization rate of data applications. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945096A_ABST
    Figure CN118945096A_ABST
Patent Text Reader

Abstract

The invention discloses a scheduling method and device based on calculation network information fusion. The method comprises active scheduling and passive scheduling. The active scheduling comprises: a computing power resource request: a user initiates a computing power resource request of a data application service, a corresponding network router receives the computing power resource request, and the network router and a computing network controller perform resource scheduling processing; carrying out computing power routing notification; carrying out computing power routing selection; carrying out computing power routing forwarding; the passive scheduling comprises basic route announcement; and basic routing forwarding: when the computing power resource request service of the user side does not exist, the user side accesses the server side by using a common public network address, and a default routing mechanism in the BGP / IGP network is used in the whole process without being influenced by computing power network scheduling and a quality assurance mechanism. The BGP and the SR of the existing network equipment are fully utilized for expansion, distributed information fusion and centralized management, the method has the advantage of being compatible with an existing network protocol structure, meanwhile, protocol expansion of routing can be defined, and TE + BE forwarding is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of Internet, and in particular to a scheduling method and device based on computing network information fusion. Background Art

[0002] In the digital economy era, data is an important production factor. The integration of data resources with computing power and network resources establishes a new mechanism for data circulation resource scheduling. The computing power information (computing, storage, etc.) messages required by data applications are transmitted to the gateway for centralized processing through the router BGP routing extension. The gateway aggregates computing power (computing, storage) information and network information and combines data application requests to intelligently schedule computing power and network resources in real time, thereby improving data application quality and processing efficiency.

[0003] The centralized scheduling technology of computing network integration integrates computing power, network, and data applications, and realizes effective management, allocation, and scheduling of various computing power, network, and other resources from an overall management perspective, greatly enhancing the efficiency of data applications. The centralized scheduling technology of computing network integration will promote the coordination of computing power, network, and data applications, and promote the technological development in the computing network field.

[0004] The key points of the centralized scheduling technology of computing-network integration are information intercommunication, information transmission, information processing, and resource scheduling. The specific requirements are as follows: 1) The information intercommunication among data applications, computing power, and networks must be timely, accurate, and stable on the basis of intercommunication. 2) The transmission of information by the network needs to guarantee the priority of various data applications and the normal connection and transmission of various data applications. 3) After the information is centralized, a real-time algorithm must be used to process it according to the policy requirements to ensure that the policy requests of data applications, computing power, and networks are implemented. 4) Resource scheduling involves real-time control and scheduling of various types of computing power and network resources.

[0005] There is a lack of interaction and control between data applications, computing power, and networks at the protocol level. When computing power and networks experience performance degradation or insufficient resources, data applications become less useful or even unusable.

[0006] Existing computing-network fusion computing is mainly based on distributed computing-first network (CFN) technology. Distributed computing-first network (CFN) technology publishes the computing power status and network status of service nodes as routing information to the network. The network routes computing task messages to the most suitable computing nodes based on virtual service IDs, achieving optimal user experience, computing resource utilization and network efficiency.

[0007] Distributed computing-first network (CFN) technology requires the existing network router equipment to upgrade the hardware version support, which has the problems of large investment and slow effectiveness. At present, CFN technology has formed a comprehensive ecosystem, and it will take time for it to become a common technology. Summary of the invention

[0008] In order to solve the problems existing in the prior art, the present invention provides a scheduling method and device based on computing network information fusion, which fully utilizes the BGP and SR of existing network equipment for expansion, distributed information fusion, centralized management, and computing power routing based on BGP extension. The specific implementation includes BGP-LS extension and new address family extension, which has the advantage of being compatible with the existing network protocol structure, and can define the protocol extension of routing to realize TE+BE forwarding.

[0009] To achieve the above object, the present invention adopts the following technical solutions:

[0010] In one embodiment of the present invention, a scheduling method based on computing network information fusion is proposed, and the method includes: active scheduling and passive scheduling.

[0011] Furthermore, the active scheduling includes:

[0012] S011. Computing resource request: The user initiates a computing resource request for data application services. The corresponding network router receives the computing resource request, and the network router and computing network controller perform resource scheduling and processing.

[0013] S012, computing power routing notification;

[0014] S013, computing power routing selection;

[0015] S014, computing power routing and forwarding.

[0016] Further, the S012 includes:

[0017] S0121, business 1 corresponds to the computing power gateway, and generates computing power routing entries on the BGP routing of the entire network for business 2 through the computing network controller;

[0018] S0122. For data application service 2, computing power gateways notify computing power routing information to the computing power gateway on the user side through the BGP computing power routing address family or through computing power RR (a special route reflector provided for computing power routing).

[0019] S0123. The computing network controller obtains all computing power routing information of the entire network by collecting BGP routing information of the entire network in real time.

[0020] Furthermore, the computing power routing entry in S0121 carries computing power extension information AttributeEncoding including: computing power node identifier (10.0.0.1), computing power service identifier (BB2), Prefix SID (3001:1::1:2), computing power information (CPU, memory, storage, etc.).

[0021] Furthermore, the computing power routing information announced in S0122 includes: business address pools of business 1 and business 2.

[0022] Further, the S014 includes:

[0023] S0141, BE solution: The computing power gateway on the user side selects the route for the destination address corresponding to the NLRI based entirely on the computing power routing received. Service access is affected by the allocation of computing resources (CPU, memory, storage, etc.) by the computing power resource nodes, but is not guaranteed by the SLA.

[0024] S0142, TE solution: BGP routing extension is performed based on the network routing information monitored by the computing network controller. The BGP extension protocol defines NLRI and Community, and builds computing power routing. The computing power routing includes computing power node identification, service identification and other information;

[0025] Collect relevant indicators (delay, jitter, packet loss, bandwidth, etc.) for managed network routers, and calculate and form path strategies based on delay, bandwidth and other requirements, such as delay priority and bandwidth utilization;

[0026] According to the policy requirements, combined with the network latency, bandwidth utilization and other factors, the path that meets the latency and bandwidth utilization is calculated to select the path, and the overall end-to-end guarantee of computing power + network services is provided.

[0027] The functions of computing power routing include: computing power information notification, computing power service selection, and computing power routing decision-making.

[0028] Computing power information notification: Computing power information notification means that the customer resource pool will use the cloud management system to unify the host IP, CPU computing resources, memory resources, storage resources and status (quality, alarm, idle status, etc.) to form a real-time computing power resource identification, and then notify the computing power gateway. The computing power gateway will spread the computing power information through BGP routing and synchronize with other computing power gateway devices, so that the computing power gateway device or management and control system can perceive the computing power (CPU, memory, storage resources, etc.) information of the customer resource pool;

[0029] Computing service selection: The computing service selection is to comprehensively consider the computing service status (resource utilization, quality, fault conditions), network status (latency, jitter, packet loss, bandwidth utilization) and user needs (computing resources, network quality), etc., and select the computing resources (CPU, memory, storage resources, etc.) of a specific customer resource pool to provide the final service; the computing service selection needs to be based on the computing information notification. After obtaining the information and status of the computing nodes, the corresponding computing service selection is made according to the computing resource utilization, network quality and user needs (resource, quality, etc. requirements);

[0030] Computing power routing decision: Computing power routing decision refers to the calculation of traffic forwarding paths based on computing power resources and network quality while selecting computing power gateway nodes.

[0031] Furthermore, the passive scheduling includes:

[0032] S021, basic routing announcement;

[0033] S022. Basic routing forwarding: When there is no computing power resource request service on the user side, the user side accesses the server by using ordinary public network addresses such as 2001::1:1, and uses the default routing mechanism within the network such as BGP / IGP throughout the process, which is not affected by the computing power network scheduling and quality assurance mechanism.

[0034] Further, the S021 includes:

[0035] S0211. The computing resource node egress announces the addresses of the two planes of IPv6 and SRv6 (2001:: / 112, 3001:*:: / 64) to the network in the form of ordinary BGP IPv6 routing;

[0036] S0212. The addresses announced within the network are propagated among the backbone routers of the operator through BGP and IGP.

[0037] S0213. After propagation through BGP routing, the user side and computing resource nodes configure the routing address to the BGP routing through the computing network controller, and the public network BGP learns the IPv6 routing of each computing resource pool exit through broadcast.

[0038] In one embodiment of the present invention, a scheduling method and device based on computing network information fusion is also proposed, and the device includes:

[0039] An active scheduling module 110 and a passive scheduling module 120 .

[0040] Furthermore, the active scheduling module 110 includes:

[0041] Computing resource request module: Users initiate computing resource requests for data application services. The corresponding network router receives the computing resource request, and the network router and computing network controller perform resource scheduling and processing.

[0042] Computing power routing notification module;

[0043] Computing power routing selection module;

[0044] Computing power routing and forwarding module.

[0045] Furthermore, the computing power routing notification module includes:

[0046] The computing power routing entry generation module and the computing power gateway corresponding to business 1 generate computing power routing entries on the BGP routing of the entire network for business 2 through the computing network controller;

[0047] The computing power routing information notification module, for data application service 2, the computing power gateways notify the computing power routing information to the computing power gateway on the user side through the BGP computing power routing address family or through the computing power RR.

[0048] The computing power routing information acquisition module and computing network controller collect BGP routing information of the entire network in real time to obtain all computing power routing information of the entire network.

[0049] Furthermore, the computing power routing entry in the computing power routing entry generation module carries computing power extension information Attribute Encoding including: computing power node identifier (10.0.0.1), computing power service identifier (BB2), Prefix SID (3001:1::1:2), computing power information (CPU, memory, storage, etc.).

[0050] Furthermore, the computing power routing information notified in the computing power routing information notification module includes: business address pools of business 1 and business 2.

[0051] Furthermore, the computing power routing forwarding module includes:

[0052] BE solution module: The user-side computing power gateway selects the route for the destination address corresponding to NLRI based entirely on the received computing power routing. Service access is affected by the allocation of computing power resources (CPU, memory, storage, etc.) by the computing power resource node, but is not guaranteed by SLA.

[0053] TE solution module: BGP routing extension is performed based on the network routing information monitored by the computing network controller. The BGP extension protocol defines NLRI and Community, and builds computing power routing. The computing power routing includes computing power node identification, service identification and other information.

[0054] Collect relevant indicators (delay, jitter, packet loss, bandwidth, etc.) for managed network routers, and calculate and form path strategies based on delay, bandwidth and other requirements, such as delay priority and bandwidth utilization;

[0055] According to the policy requirements, combined with the network latency, bandwidth utilization and other factors, the path that meets the latency and bandwidth utilization is calculated to select the path, and the overall end-to-end guarantee of computing power + network services is provided.

[0056] Furthermore, the passive scheduling module 120 includes:

[0057] Basic routing announcement module;

[0058] Basic routing and forwarding module: When there is no user-side computing power resource request service, the user side accesses the server by using ordinary public network addresses such as 2001::1:1, and uses the default routing mechanism within the network such as BGP / IGP throughout the process, which is not affected by the computing power network scheduling and quality assurance mechanism.

[0059] Furthermore, the basic routing advertisement module includes:

[0060] The network notification module and computing resource node egress announce the addresses of the two planes of IPv6 and SRv6 (2001:: / 112, 3001:*:: / 64) to the network in the form of ordinary BGP IPv6 routing;

[0061] The address propagation module and the addresses announced within the network are propagated among the backbone routers of the operator through BGP and IGP;

[0062] After the address configuration module is propagated through BGP routing, the user side and computing resource nodes configure the routing address to the BGP routing through the computing network controller. The public network BGP learns the IPv6 routing of each computing resource pool exit through broadcast.

[0063] 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 aforementioned scheduling method based on computing network information fusion is implemented.

[0064] In one embodiment of the present invention, a computer-readable storage medium is also proposed, which stores a computer program for executing a scheduling method based on computing network information fusion.

[0065] Beneficial effects:

[0066] The present invention provides a scheduling method and device based on computing network information fusion, constructs a new computing power gateway, a core business node in the computing power network, shields the access difference between computing power access and bearer network, and the customer resource pool uses the computing power gateway to notify computing power resources. The computing power gateway schedules computing power resources and performs computing network routing forwarding based on computing power resource labels. A network between computing power gateways is constructed to open up resource allocation channels between computing power providers and consumers, and provide service capabilities with differentiated quality for different types of applications and services. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic diagram of the flow of the scheduling method based on computing network information fusion of the present invention;

[0068] Figure 2 It is a flow chart of performing a service penetration test scenario through computing power routing based on a video service scenario in the present invention;

[0069] Figure 3 It is a schematic diagram of the structure of the scheduling method and device based on computing network information fusion of the present invention;

[0070] Figure 4 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] 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 implement 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.

[0072] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0073] The nouns involved in the present invention and their Chinese explanations:

[0074] BGP: Border Gateway Protocol;

[0075] SR: Segment Routing Protocol;

[0076] BGP-LS: Link State Routing Protocol;

[0077] TE: Traffic Engineering, based on segmentation labels, the header node specifies a strict display path;

[0078] BE: Best Effort, shortest path forwarding;

[0079] SLA: Network service level;

[0080] NLRI Encoding: Network layer reachability information encoding;

[0081] Unicast: unicast address;

[0082] Attribute Encoding: attribute encoding;

[0083] Extended Community: extended attributes;

[0084] Prefix SID: prefix label;

[0085] Link-State: Border Gateway Protocol status;

[0086] Descriptor: route description;

[0087] Attribute: routing attribute;

[0088] TLV: Type Length Value;

[0089] Behavior: behavior;

[0090] Overlay: overlay network;

[0091] bsid: Ingress SID.

[0092] According to the implementation mode of the present invention, a scheduling method and device based on computing network information fusion are proposed, which make full use of BGP and SR of existing network equipment for expansion, distributed information fusion, centralized management, and computing power routing based on BGP extension. The specific implementation includes BGP-LS extension and new address family extension, which has the advantage of compatibility with the existing network protocol structure, and can define routing protocol extension to realize TE+BE forwarding.

[0093] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0094] like Figure 1 , Figure 2 As shown, the present invention relates to a scheduling method based on computing network information fusion, the method comprising: active scheduling and passive scheduling.

[0095] The active scheduling includes:

[0096] S011. Computing resource request: The user initiates a computing resource request for data application services. The corresponding network router receives the computing resource request, and the network router and computing network controller perform resource scheduling and processing.

[0097] S012, computing power routing notification;

[0098] The S012 includes:

[0099] S0121, business 1 corresponds to the computing power gateway, and generates computing power routing entries on the BGP routing of the entire network for business 2 through the computing network controller;

[0100] The computing power routing entry carries computing power extension information Attribute Encoding: computing power node identifier (10.0.0.1), computing power service identifier (BB2), Prefix SID (3001:1::1:2), computing power information (CPU, memory, storage, etc.).

[0101] S0122. For data application service 2, computing power gateways notify computing power routing information to the computing power gateway on the user side through the BGP computing power routing address family or through computing power RR (a special route reflector provided for computing power routing).

[0102] The computing power routing information announced in S0122 includes: the business address pools of business 1 and business 2.

[0103] S0123. The computing network controller obtains all computing power routing information of the entire network by collecting BGP routing information of the entire network in real time.

[0104] S013, computing power routing selection;

[0105] S014, computing power routing and forwarding.

[0106] The S014 includes:

[0107] S0141, BE solution: The computing power gateway on the user side selects the route for the destination address corresponding to the NLRI based entirely on the computing power routing received. Service access is affected by the allocation of computing resources (CPU, memory, storage, etc.) by the computing power resource nodes, but is not guaranteed by the SLA.

[0108] S0142, TE solution: BGP routing extension is performed based on the network routing information monitored by the computing network controller. The BGP extension protocol defines NLRI and Community, and builds computing power routing. The computing power routing includes computing power node identification, service identification and other information;

[0109] Collect relevant indicators (delay, jitter, packet loss, bandwidth, etc.) for managed network routers, and calculate and form path strategies based on delay, bandwidth and other requirements, such as delay priority and bandwidth utilization;

[0110] According to the policy requirements, combined with the network latency, bandwidth utilization and other factors, the path that meets the latency and bandwidth utilization is calculated to select the path, and the overall end-to-end guarantee of computing power + network services is provided.

[0111] The functions of computing power routing include: computing power information notification, computing power service selection, and computing power routing decision-making.

[0112] Computing power information notification: Computing power information notification means that the customer resource pool will use the cloud management system to unify the host IP, CPU computing resources, memory resources, storage resources and status (quality, alarm, idle status, etc.) to form a real-time computing power resource identification, and then notify the computing power gateway. The computing power gateway will spread the computing power information through BGP routing and synchronize with other computing power gateway devices, so that the computing power gateway device or management and control system can perceive the computing power (CPU, memory, storage resources, etc.) information of the customer resource pool;

[0113] Computing service selection: The computing service selection is to comprehensively consider the computing service status (resource utilization, quality, fault conditions), network status (latency, jitter, packet loss, bandwidth utilization) and user needs (computing resources, network quality), etc., and select the computing resources (CPU, memory, storage resources, etc.) of a specific customer resource pool to provide the final service; the computing service selection needs to be based on the computing information notification. After obtaining the information and status of the computing nodes, the corresponding computing service selection is made according to the computing resource utilization, network quality and user needs (resource, quality, etc. requirements);

[0114] Computing power routing decision: Computing power routing decision refers to the calculation of traffic forwarding paths based on computing power resources and network quality while selecting computing power gateway nodes.

[0115] Traditional network scenario: Service routing only needs to select a specific network path (such as SR tunnel) for the destination.

[0116] Computing power routing scenario: You need to select specific computing resources and the network path to the computing resources based on the destination address. Note that this is done simultaneously, not in two steps.

[0117] Description of computing power routing technology based on BGP extension:

[0118] Description of BGP computing power routing structure:

[0119] NLRI Encoding

[0120] NLRI uses the IPv6 Unicast address format and carries the unique public network address of the computing service as the path primary key.

[0121] Attribute Encoding

[0122] Use IPv4 Extended Community or IPv6 Extended Community to carry the code of the extended attribute.

[0123] Required parameters: IPv6 Unicast routing with the following parameters is considered as computing power

[0124] Computing power node identifier: IPv4 format, used to mark the computing power node (computing power gateway) to which the computing power service belongs.

[0125] Computing power service identifier: IPv4 format, used to identify the service type of the computing power service. Services with the same service identifier from different computing power gateway nodes are considered equivalent services, and computing power information can be superimposed for differentiated selection.

[0126] Optional parameters

[0127] Prefix SID (prefix label): IPv6 format, 16-byte SRv6 SID + 2 bytes padded with 0. Each NLRI can only carry one of this attribute. It is used to identify the forwarding information of computing power in the SRv6 space and needs to be associated with the local SRv6 routing table of the computing power gateway.

[0128] Computing power information: IPv4 format, 2-byte type + 4-byte IEEE754 (binary floating-point arithmetic standard) floating-point index. Each NLRI of this attribute allows carrying multiple different types, such as CPU, GPU, storage index, etc.

[0129] IPv4 Extended Community format:

[0137] IPv6 Extended Community (Extended Attribute) Format

[0151] Reuse BGP-LS (node ​​and prefix information are encoded using AFI 16388 / SAFI 71 standard) definitions;

[0152] Added NLRI (Network Layer Reachability Information) and Protocol ID (Protocol ID) for computing power identification under Link-State (Border Gateway Protocol state);

[0153] The descriptor of this type of route defines the computing power identifier;

[0154] The attributes of this type of routing can carry multiple extended attributes. Through TLV combination, various information such as computing service type, network performance, computing resources, etc. can be defined;

[0155] The Attribute of this type of route can carry the Prefix SID attribute, reuse the structure of the current Link-State notification SID, and use it for the computing power gateway to notify the forwarding identifier of the computing power.

[0156] The computing power SID needs to define a behavior separately, and there is a dedicated forwarding action on the computing power gateway, that is, forwarding to the computing power gateway or forwarding to the network router.

[0157] The passive scheduling includes:

[0158] S021, basic routing announcement;

[0159] The S021 includes:

[0160] S0211. The computing resource node egress announces the addresses of the two planes of IPv6 and SRv6 (2001:: / 112, 3001:*:: / 64) to the network in the form of ordinary BGP IPv6 routing;

[0161] S0212. The addresses announced within the network are propagated among the backbone routers of the operator through BGP and IGP.

[0162] S0213. After propagation through BGP routing, the user side and computing resource nodes configure the routing address to the BGP routing through the computing network controller, and the public network BGP learns the IPv6 routing of each computing resource pool exit through broadcast.

[0163] S022. Basic routing forwarding: When there is no computing power resource request service on the user side, the user side accesses the server by using ordinary public network addresses such as 2001::1:1, and uses the default routing mechanism within the network such as BGP / IGP throughout the process, which is not affected by the computing power network scheduling and quality assurance mechanism.

[0164] 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.

[0165] In order to explain the above-mentioned scheduling method based on computing network information fusion more clearly, it is described in conjunction with a specific embodiment below. However, it should be noted that this embodiment is only for better illustrating the present invention and does not constitute an improper limitation to the present invention.

[0166] Computing power routing and computing power gateway based on BGP structure. Publish computing power resource information into routing protocol messages, realize information notification between computing power gateways, and route task messages to the optimal path.

[0167] like Figure 3 As shown, the method includes:

[0168] Implement logical networking architecture;

[0169] Physical machine 1 virtualizes two server computing gateways and one client computing gateway, pulls up three ordinary virtual machines to act as two servers and one client, and allocates independent IP addresses accordingly;

[0170] Physical machine 2 deploys a computing network controller to connect to the computing power gateway and router devices;

[0171] Simulate the establishment of BGP neighbors between the server and the computing power gateway, and publish the corresponding computing power information in the computing power gateway (including computing power service identifier, computing power node identifier, and network performance indicators). Server1 and Server2 publish the same computing power information of type A, but carry computing power indicators of different sizes. For example, gateway 1 publishes 50 units of Type 1 computing power indicators, and gateway 2 publishes 100 units of Type 1 computing power indicators.

[0172] The service-side computing power gateway notifies the computing power information to the user computing power gateway and computing network controller;

[0173] The computing power gateway on the user side receives computing power routing information;

[0174] The computing network controller establishes a BGP neighbor relationship with the computing power gateway to obtain the corresponding routing information of all computing power;

[0175] The simulated computing network controller receives the user's BE computing power request for service A, sends the BE request, and the user computing power gateway selects the path based on the difference in the computing power indicators of the two.

[0176] The simulated computing network controller receives the user's TE computing power request for service A, calculates the path based on the computing power and network performance, and sends the TE request. The computing power gateway forwards it according to the sent TE path.

[0177] Based on the same inventive concept, the present invention also proposes a scheduling method device based on computing network information fusion. The implementation of the device can refer to the implementation of the above method, and the repeated parts will not be repeated. The term "module" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0178] Figure 3 Schematic diagram of the scheduling method and device structure based on computing network information fusion of the present invention. Figure 3 As shown, the device comprises:

[0179] An active scheduling module 110 and a passive scheduling module 120 .

[0180] Furthermore, the active scheduling module 110 includes:

[0181] Computing resource request module: Users initiate computing resource requests for data application services. The corresponding network router receives the computing resource request, and the network router and computing network controller perform resource scheduling and processing.

[0182] Computing power routing notification module;

[0183] Computing power routing selection module;

[0184] Computing power routing and forwarding module.

[0185] Furthermore, the computing power routing notification module includes:

[0186] The computing power routing entry generation module and the computing power gateway corresponding to business 1 generate computing power routing entries on the BGP routing of the entire network for business 2 through the computing network controller;

[0187] The computing power routing information notification module, for data application service 2, the computing power gateways notify the computing power routing information to the computing power gateway on the user side through the BGP computing power routing address family or through the computing power RR.

[0188] The computing power routing information acquisition module and computing network controller collect BGP routing information of the entire network in real time to obtain all computing power routing information of the entire network.

[0189] Furthermore, the computing power routing entry in the computing power routing entry generation module carries computing power extension information Attribute Encoding including: computing power node identifier (10.0.0.1), computing power service identifier (BB2), Prefix SID (3001:1::1:2), computing power information (CPU, memory, storage, etc.).

[0190] Furthermore, the computing power routing information notified in the computing power routing information notification module includes: business address pools of business 1 and business 2.

[0191] Furthermore, the computing power routing forwarding module includes:

[0192] BE solution module: The user-side computing power gateway selects the route for the destination address corresponding to NLRI based entirely on the received computing power routing. Service access is affected by the allocation of computing power resources (CPU, memory, storage, etc.) by the computing power resource node, but is not guaranteed by SLA.

[0193] TE solution module: BGP routing extension is performed based on the network routing information monitored by the computing network controller. The BGP extension protocol defines NLRI and Community, and builds computing power routing. The computing power routing includes computing power node identification, service identification and other information.

[0194] Collect relevant indicators (delay, jitter, packet loss, bandwidth, etc.) for managed network routers, and calculate and form path strategies based on delay, bandwidth and other requirements, such as delay priority and bandwidth utilization;

[0195] According to the policy requirements, combined with the network latency, bandwidth utilization and other factors, the path that meets the latency and bandwidth utilization is calculated to select the path, and the overall end-to-end guarantee of computing power + network services is provided.

[0196] Furthermore, the passive scheduling module 120 includes:

[0197] Basic routing announcement module;

[0198] Basic routing and forwarding module: When there is no user-side computing power resource request service, the user side accesses the server by using ordinary public network addresses such as 2001::1:1, and uses the default routing mechanism within the network such as BGP / IGP throughout the process, which is not affected by the computing power network scheduling and quality assurance mechanism.

[0199] Furthermore, the basic routing advertisement module includes:

[0200] The network notification module and computing resource node egress announce the addresses of the two planes of IPv6 and SRv6 (2001:: / 112, 3001:*:: / 64) to the network in the form of ordinary BGP IPv6 routing;

[0201] The address propagation module and the addresses announced within the network are propagated among the backbone routers of the operator through BGP and IGP;

[0202] After the address configuration module is propagated through BGP routing, the user side and computing resource nodes configure the routing address to the BGP routing through the computing network controller. The public network BGP learns the IPv6 routing of each computing resource pool exit through broadcast.

[0203] It should be noted that although several modules of the scheduling method and device based on computing network information fusion are mentioned in the above detailed description, this division is only 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 one module described above can be further divided into multiple modules for concretization.

[0204] Based on the above invention concept, Figure 4 As 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 aforementioned scheduling method based on computing network information fusion is implemented.

[0205] 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 scheduling method based on computing-network information fusion.

[0206] The core business node in the computing power network is a border portal that opens the computing power business in the form of network services, shields the access differences between computing power access and bearer network, announces and schedules computing power resources, and performs computing network routing forwarding based on computing power resource labels. For computing power providers, the computing power gateway provides a means to convert computing power information into network services and open them to the outside; and for computing power users, the computing power gateway provides the possibility of aggregating computing power in the network and dynamically scheduling it. The channels between computing power gateways are built on the underlying bearer network in the form of overlay, allowing computing power and network to be guaranteed simultaneously through service-oriented network capabilities such as BSIDS.

[0207] The present invention provides a scheduling method and device based on computing network information fusion, constructs a new computing power gateway, a core business node in the computing power network, shields the access difference between computing power access and bearer network, and the customer resource pool uses the computing power gateway to notify computing power resources. The computing power gateway schedules computing power resources and performs computing network routing forwarding based on computing power resource labels. A network between computing power gateways is constructed to open up resource allocation channels between computing power providers and consumers, and provide service capabilities with differentiated quality for different types of applications and services.

[0208] 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.

[0209] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0210] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0211] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0212] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0213] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0214] The computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0215] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0216] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

[0217] 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 scheduling method based on computing network information fusion, characterized in that: The method includes: Active scheduling and passive scheduling.

2. The scheduling method based on computing network information fusion according to claim 1 is characterized in that: The active scheduling includes: S011. Computing resource request: The user initiates a computing resource request for data application services. The corresponding network router receives the computing resource request, and the network router and computing network controller perform resource scheduling and processing. S012, computing power routing notification; S013, computing power routing selection; S014, computing power routing and forwarding.

3. The scheduling method based on computing network information fusion according to claim 2 is characterized in that: The S012 includes: S0121, business 1 corresponds to the computing power gateway, and generates computing power routing entries on the BGP routing of the entire network for business 2 through the computing network controller; S0122. For data application service 2, the computing power gateways notify the computing power routing information to the computing power gateway on the user side through the BGP computing power routing address family or through the computing power RR; S0123. The computing network controller obtains all computing power routing information of the entire network by collecting BGP routing information of the entire network in real time.

4. The scheduling method based on computing network information fusion according to claim 3 is characterized in that: The computing power routing entry in S0121 carries computing power extension information AttributeEncoding including: computing power node identifier, computing power service identifier, PrefixSID, and computing power information.

5. The scheduling method based on computing network information fusion according to claim 3 is characterized in that: The computing power routing information announced in S0122 includes: the business address pools of business 1 and business 2.

6. The scheduling method based on computing network information fusion according to claim 2 is characterized in that: The S014 includes: S0141, BE solution: The user-side computing power gateway selects the route for the destination address corresponding to the NLRI based entirely on the received computing power routing. Service access is affected by the computing power resource allocation of the computing power resource node, but is not guaranteed by the SLA. S0142, TE solution: BGP routing extension is performed based on the network routing information monitored by the computing network controller. The BGP extension protocol defines NLRI and Community, and builds computing power routing. The computing power routing includes computing power node identification and service identification information.

7. The scheduling method based on computing network information fusion according to claim 1 is characterized in that: The passive scheduling includes: S021, basic routing announcement; S022, basic routing forwarding: When there is no user-side computing power resource request service, the user side accesses the server by using a normal public network address, and uses the default routing mechanism within the BGP / IGP network throughout the process, which is not affected by the computing power network scheduling and quality assurance mechanism.

8. The scheduling method based on computing network information fusion according to claim 7 is characterized in that: The S021 includes: S0211. The computing resource node egress announces the addresses of the two planes, IPv6 and SRv6, to the network in the form of ordinary BGPIPv6 routing; S0212. The addresses announced within the network are propagated among the backbone routers of the operator through BGP and IGP. S0213. After propagation through BGP routing, the user side and computing resource nodes configure the routing address to the BGP routing through the computing network controller, and the public network BGP learns the IPv6 routing of each computing resource pool exit through broadcast.

9. A scheduling method and device based on computing network information fusion, characterized in that: The device includes: Active scheduling module and passive scheduling module.

10. The scheduling method and device based on computing network information fusion according to claim 9 is characterized in that: The active scheduling module includes: Computing resource request module: Users initiate computing resource requests for data application services. The corresponding network router receives the computing resource request, and the network router and computing network controller perform resource scheduling and processing. Computing power routing notification module; Computing power routing selection module; Computing power routing and forwarding module.

11. The scheduling method and device based on computing network information fusion according to claim 10, characterized in that: The computing power routing notification module includes: The computing power routing entry generation module and the computing power gateway corresponding to business 1 generate computing power routing entries on the BGP routing of the entire network for business 2 through the computing network controller; The computing power routing information notification module, for data application service 2, the computing power gateways notify the computing power routing information to the computing power gateway on the user side through the BGP computing power routing address family or through the computing power RR; The computing power routing information acquisition module and computing network controller collect BGP routing information of the entire network in real time to obtain all computing power routing information of the entire network.

12. The scheduling method and device based on computing network information fusion according to claim 11, characterized in that: The computing power routing entry in the computing power routing entry generation module carries computing power extension information AttributeEncoding including: computing power node identifier, computing power service identifier, PrefixSID, and computing power information.

13. The scheduling method and device based on computing network information fusion according to claim 11, characterized in that: The computing power routing information announced in the computing power routing information announcement module includes: the business address pools of business 1 and business 2.

14. The scheduling method and device based on computing network information fusion according to claim 10, characterized in that: The computing power routing forwarding module includes: BE solution module: The user-side computing power gateway selects the route for the destination address corresponding to NLRI based entirely on the received computing power routing. Service access is affected by the computing power resource allocation of the computing power resource node, but is not guaranteed by the SLA. TE solution module: BGP routing extension is performed based on the network routing information monitored by the computing network controller. The BGP extension protocol defines NLRI and Community, and builds computing power routing. The computing power routing includes computing power node identification and service identification information.

15. The scheduling method and device based on computing network information fusion according to claim 9, characterized in that: The passive scheduling module includes: Basic routing announcement module; Basic routing and forwarding module: When there is no user-side computing power resource request service, the user side accesses the server by using a common public network address, and uses the default routing mechanism within the BGP / IGP network throughout the process, which is not affected by the computing power network scheduling and quality assurance mechanism.

16. The scheduling method and device based on computing network information fusion according to claim 15, characterized in that: The basic routing advertisement module includes: The network notification module and computing resource node egress announce the addresses of the two planes IPv6 and SRv6 to the network in the form of ordinary BGPIPv6 routing; The address propagation module and the addresses announced within the network are propagated among the backbone routers of the operator through BGP and IGP; After the address configuration module is propagated through BGP routing, the user side and computing resource nodes configure the routing address to the BGP routing through the computing network controller. The public network BGP learns the IPv6 routing of each computing resource pool exit through broadcast.

17. 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 8 is implemented.

18. 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 8.

Citation Information

Cited By

  • Network performance state determination method and device, electronic equipment and storage medium

    CN119814644A