Deterministic network service orchestration tool and method based on artificial intelligence large model

Abstract

The invention belongs to the field of deterministic network service orchestration, and provides a deterministic network service orchestration tool and method based on an artificial intelligence large model. The deterministic network service orchestration tool based on the artificial intelligence large model comprises a resource management database, a model database, a portal system and a network service orchestrator, the portal system is used for receiving a deterministic network service demand and calling a deterministic network service large model from the model database; the large deterministic network service model is used for analyzing a deterministic network service demand, generating a model matched with the deterministic network service demand, and transmitting the model to the network service orchestrator; and the network service orchestrator is used for dynamically adjusting or pre-occupying the whole network resources in the resource management database according to a model matched with the deterministic network service requirements, generating a network service orchestration result and issuing the network service orchestration result to the deterministic network controller.

Description

Technical Field

[0001] The present invention belongs to the field of deterministic network service orchestration, and in particular, relates to a deterministic network service orchestration tool and method based on an artificial intelligence big model. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The current deterministic network controller integrates a network orchestrator, which can visualize the planning process of network services, visualize service generation, and automate the deployment process for network service orchestration. It also uses SDN and NFV technologies to decouple the network layer from the service layer, and the network layer is compatible with multi-vendor equipment. Although the existing deterministic network controller can realize the orchestration, configuration distribution, and service activation of network services, the network parameters such as equipment, ports, bandwidth, routing, SLA policies, etc. required for network orchestration need to be manually filled in or manually selected, and operated according to predefined steps and configuration interfaces, which cannot fully achieve intelligent and automated activation.

[0004] The existing optimization solution is that the deterministic network controller connects to the external orchestration system through the northbound API interface, solidifies or pre-fills the network parameters involved in the network orchestration process, especially some common parameters, to reduce the number of parameters to be filled in, thereby reducing configuration time and improving configuration efficiency. However, the parameters required for network service orchestration still need to be filled in step by step according to the configuration interface. At the same time, the optimization solution still fails to achieve intelligent management of network resources and automated orchestration and activation of network services. Moreover, if the activated services need to be adjusted, manual editing operations, adjustment of parameters and network models are still required.

[0005] In summary, the current deterministic network service orchestration technology still has the following problems: (1) Network service orchestration still needs to be filled in step by step according to the configuration interface, which fails to solve the intelligent management of network resources; (2) The service model that has been launched is fixed and cannot be dynamically adjusted according to the business situation. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a deterministic network service orchestration tool and method based on an artificial intelligence big model, which can realize intelligent management of network resources and automatic orchestration of network services as well as intelligent dynamic adjustment of network services, thereby improving network operation and maintenance efficiency.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A first aspect of the present invention provides a deterministic network service orchestration tool based on an artificial intelligence big model.

[0009] In one or more embodiments, a deterministic network service orchestration tool based on an artificial intelligence big model is provided, comprising: a resource management database, a model database, a portal system, and a network service orchestrator;

[0010] The resource management database dynamically stores the network resources of the entire network;

[0011] The model database stores a large deterministic network service model;

[0012] The portal system is used to receive deterministic network service requirements and retrieve the deterministic network service large model from the model database;

[0013] The deterministic network service large model is used to analyze the deterministic network service demand, generate a model matching the deterministic network service demand, and transmit it to the network service orchestrator;

[0014] The network service orchestrator is used to orchestrate network services according to a model that matches the deterministic network service requirements and generate corresponding configuration templates to be sent to the deterministic network controller.

[0015] As an implementation mode, when the deterministic network service demand is to activate a deterministic network service, the matching model is: a deterministic network service activation model; and the generated template is a configuration template.

[0016] As an implementation mode, the process of the network service orchestrator generating a configuration template according to the deterministic network service provisioning model is as follows:

[0017] Design networking, routing and transmission paths based on deterministic network service provisioning models and pre-occupied network resources;

[0018] Then configure VPN / network slicing, SLA policy, resource reservation policy, and traffic scheduling policy to generate a configuration template.

[0019] As an implementation mode, when the deterministic network service requirement is to optimize the deterministic network service, the matching model is: a deterministic network service optimization model; and the generated template is a tuning template.

[0020] As an implementation mode, the process of the network service orchestrator generating a tuning template according to the deterministic network service optimization model is as follows:

[0021] The deterministic network service optimization model is used to compare and analyze the optimized deterministic network service requirements with the network resources of the entire network in the resource management database;

[0022] Determine whether the current network resources of the entire network in the resource management database meet the requirements of optimizing deterministic network services. If so, adjust the current network resources of the entire network in the resource management database accordingly and generate an optimization template.

[0023] As an implementation method, the deterministic network service large model performs self-update optimization according to periodic deterministic network service demands and corresponding network resource status information of the entire network.

[0024] As an implementation mode, the deterministic network service requirement is described in natural language.

[0025] As an implementation method, the deterministic network service requirements include user access location, user access type, link bandwidth and performance requirements.

[0026] A second aspect of the present invention provides a service orchestration method of a deterministic network service orchestration tool based on an artificial intelligence big model.

[0027] In one or more embodiments, a service orchestration method of a deterministic network service orchestration tool based on an artificial intelligence big model includes:

[0028] Receive deterministic network service requirements and retrieve the deterministic network service large model from the model database;

[0029] Analyzing the deterministic network service requirements using a deterministic network service large model to generate a model that matches the deterministic network service requirements;

[0030] The network services are orchestrated according to the model that matches the deterministic network service requirements and the corresponding configuration templates are generated and sent to the deterministic network controller.

[0031] As an implementation method, deterministic network service requirements and their corresponding network resource status information of the entire network are obtained regularly, and the deterministic network service large model is self-updated and optimized.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] (1) The present invention uses a deterministic network service large model to analyze deterministic network service requirements and generate a matching model. The network service orchestrator then dynamically adjusts or pre-occupies the network resources of the entire network in the resource management database, generates a corresponding template and sends it to the deterministic network controller, thereby realizing intelligent management of network resources, automated orchestration of network services, and intelligent dynamic adjustment of network services, thereby improving network operation and maintenance efficiency.

[0034] (2) The present invention uses a portal system to replace the original network parameter configuration interface. The portal system can receive natural language descriptions, and is thus equally applicable and friendly to non-professional network activation personnel.

[0035] (3) The present invention also trains the deterministic network service big model through regular deterministic network service demands and their corresponding network resource status information of the whole network, thereby realizing the continuous learning and self-improvement of the deterministic network service big model, and enabling the model to continuously adapt to changes in the network environment and changes in service demands. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0037] Figure 1 It is a schematic diagram of the structure of a deterministic network service orchestration tool based on an artificial intelligence big model according to an embodiment of the present invention;

[0038] Figure 2 It is a flow chart of a business orchestration method of a deterministic network business orchestration tool based on an artificial intelligence big model in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0040] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0042] Terminology explanation: A network orchestration system is a software framework for managing and configuring network resources and services. It is usually used to simplify network configuration, optimize resource allocation, improve network performance and reliability, and ensure rapid deployment and flexible adjustment of network services.

[0043] Figure 1 FIG. 1 is a schematic diagram of the structure of a deterministic network service orchestration tool based on an artificial intelligence big model according to an embodiment of the present invention. Figure 1As shown, this embodiment provides a deterministic network service orchestration tool based on an artificial intelligence big model, including: a resource management database, a model database, a portal system, and a network service orchestrator;

[0044] The resource management database dynamically stores the network resources of the entire network (including devices, boards, ports, IP addresses, VLANs, etc.);

[0045] The model database stores a large deterministic network service model;

[0046] The portal system is used to receive deterministic network service requirements and retrieve the deterministic network service large model from the model database;

[0047] The deterministic network service large model is used to analyze the deterministic network service demand, generate a model matching the deterministic network service demand, and transmit it to the network service orchestrator;

[0048] The network service orchestrator is used to orchestrate network services according to a model that matches the deterministic network service requirements and generate corresponding configuration templates to be sent to the deterministic network controller.

[0049] This embodiment uses a deterministic network service large model to parse deterministic network service needs and generate a matching model. The network service orchestrator then dynamically adjusts or pre-occupies network resources across the entire network in the resource management database, generates corresponding templates and sends them to the deterministic network controller, thereby realizing intelligent management of network resources, automated orchestration of network services, and intelligent dynamic adjustment of network services, thereby improving network operation and maintenance efficiency.

[0050] The deterministic network service large model of this embodiment estimates network resources based on the generated network service activation model, and compares and analyzes it with the resource management database, and pre-occupies the required equipment, boards, ports, channel bandwidth, IP addresses, and VLANs required for service activation to ensure that the resources will not be occupied by other services before they are officially allocated to the service.

[0051] In one or more embodiments, when the deterministic network service demand is to open a deterministic network service, the matching model is: a deterministic network service opening model (including SDN dedicated lines, DIP dedicated lines, and corresponding various network architecture models, such as point-to-point, full interconnection, total distribution, etc.); the generated template is a configuration template.

[0052] In the specific implementation process, the combination elements of the deterministic network service provisioning model include networking architecture (point-to-point, point-to-multipoint, total-split), service type (L2VPN, L3VPN), SLA requirements (shortest path, lowest latency, lowest jitter, reliability requirements), bandwidth requirements, etc., and different network service models are generated by combining the above elements. For example, after analyzing user needs, the network service orchestrator maps user needs into a point-to-point, L2VPN layer 2 VPN tunnel, a deterministic private line with minimum jitter requirements and 100Mbps bandwidth slices.

[0053] Specifically, the process of the network service orchestrator generating a configuration template according to the deterministic network service provisioning model is as follows:

[0054] Design networking, routing and transmission paths based on deterministic network service provisioning models and pre-occupied network resources;

[0055] Then configure VPN / network slicing, SLA policy (minimum delay / shortest path / designated path / minimum channel utilization, etc.), resource reservation policy and traffic scheduling policy to generate a configuration template.

[0056] For example, the configuration template is sent to the deterministic network controller through the API interface between the deterministic network controller and the deterministic network controller generates device configuration data according to the configuration template, and sends the configuration data to the network device through the NetConf protocol, thereby realizing the activation of network services.

[0057] In one or more embodiments, when the deterministic network service requirement is to optimize the deterministic network service, the matching model is: a deterministic network service optimization model; and the generated template is a tuning template.

[0058] In a specific implementation process, the process of the network service orchestrator generating a tuning template according to a deterministic network service optimization model includes:

[0059] The deterministic network service optimization model is used to compare and analyze the optimized deterministic network service requirements with the network resources of the entire network in the resource management database;

[0060] Determine whether the current network resources of the entire network in the resource management database meet the requirements of optimizing deterministic network services. If so, adjust the current network resources of the entire network in the resource management database accordingly and generate an optimization template.

[0061] The deterministic network service optimization model here includes bandwidth optimization, link optimization, routing optimization, resource optimization, etc., which can achieve network optimization by analyzing and judging the network service operation data and determining the optimization direction, and calling the network service optimization model. For example, by analyzing the network service operation data and judging that the current link delay does not meet the requirements, it is considered that the routing direction needs to be optimized, and the routing optimization is performed according to the network service optimization model to generate an optimization template.

[0062] Specifically, the tuning template is sent to the deterministic network controller through the API interface between the deterministic network controller and the deterministic network controller generates device configuration change data according to the adjustment template, and sends the changed configuration data to the network device through the NetConf protocol, thereby achieving optimization and adjustment of network services.

[0063] During business operation, this tool periodically communicates with the deterministic network controller through the API interface to obtain business operation data and network monitoring information, and imports it into the large model for data analysis. The large model determines whether the network needs to be optimized and adjusted based on the analysis results. For example, whether the business traffic exceeds the warning threshold, the port bandwidth reservation ratio is dynamically adjusted. At the same time, this tool performs intelligent analysis of historical operation data, and TOP sorts the links with high failure rate, low reliability and high latency. The corresponding analysis information is visualized in this tool portal, providing reference and basis for operation and maintenance personnel to optimize the physical network.

[0064] When it is necessary to adjust the service of an already opened network service, the network operation and maintenance personnel use natural language to make corresponding descriptions in this tool portal, such as adjusting the service bandwidth, adding / deleting / modifying sites, etc. The portal calls the big model to analyze and adjust the network resources, and then executes network service orchestration to realize intelligent adjustment of the service.

[0065] In a specific embodiment, the deterministic network service large model performs self-update optimization according to periodic deterministic network service demands and corresponding network resource status information of the entire network.

[0066] Specifically, after the deterministic network service big model collects network operation data and monitoring data, it selects feature information from the collected data based on business objectives and model requirements, including VPN / slice traffic, link delay, jitter, packet loss rate, bandwidth utilization, SLA policy effect, etc., and uses the above-selected feature information to train the deterministic network service big model, and verify, analyze, and evaluate the performance of the model, while optimizing its performance by adjusting the model parameters. The trained deterministic network service big model is applied to network optimization and adjustment, and configured in the actual network service operation environment. The model is continuously trained and tuned through feedback from new network operation data and monitoring data. This allows the model to continuously adapt to changes in the network environment and changes in business needs, thereby achieving continuous learning and self-improvement.

[0067] In the specific implementation process, the deterministic network service requirements are described in natural language, wherein the deterministic network service requirements include user access location, user access type, link bandwidth and performance requirements.

[0068] Figure 2 The embodiment of the present invention is as described above Figure 1 The flowchart of the business orchestration method of the deterministic network business orchestration tool based on the artificial intelligence big model is shown. Figure 2 As shown, the service orchestration method of the deterministic network service orchestration tool based on the artificial intelligence big model includes:

[0069] S201: receiving a deterministic network service demand and retrieving a deterministic network service large model from a model database;

[0070] S202: Analyze the deterministic network service demand using the deterministic network service large model to generate a model matching the deterministic network service demand;

[0071] S203: Orchestrate network services according to a model that matches the deterministic network service requirements and generate corresponding configuration templates that are sent to the deterministic network controller.

[0072] In one or more embodiments, in step S202, the deterministic network service demand and its corresponding network resource status information of the entire network are obtained regularly, and the deterministic network service large model is self-updated and optimized.

[0073] This embodiment can realize intelligent management of network resources and automatic arrangement of network services as well as intelligent dynamic adjustment of network services, thereby improving network operation and maintenance efficiency.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A deterministic network service orchestration tool based on an artificial intelligence big model, characterized in that: include: Resource management database, model database, portal system and network business orchestrator; The resource management database dynamically stores the network resources of the entire network; The model database stores a large deterministic network service model; The portal system is used to receive deterministic network service requirements and retrieve the deterministic network service large model from the model database; The deterministic network service large model is used to analyze the deterministic network service demand, generate a model matching the deterministic network service demand, and transmit it to the network service orchestrator; The network service orchestrator is used to orchestrate network services according to a model that matches the deterministic network service requirements and generate corresponding configuration templates to be sent to the deterministic network controller.

2. The deterministic network service orchestration tool based on artificial intelligence big model according to claim 1, characterized in that: When the deterministic network service demand is to activate a deterministic network service, the matching model is: a deterministic network service activation model; and the generated template is a configuration template.

3. The deterministic network service orchestration tool based on artificial intelligence big model as claimed in claim 2, characterized in that: The process of the network service orchestrator generating a configuration template according to the deterministic network service provisioning model is as follows: Design networking, routing and transmission paths based on deterministic network service provisioning models and pre-occupied network resources; Then configure VPN / network slicing, SLA policy, resource reservation policy, and traffic scheduling policy to generate a configuration template.

4. The deterministic network service orchestration tool based on artificial intelligence big model according to claim 1, characterized in that: When the deterministic network service requirement is to optimize the deterministic network service, the matching model is: the deterministic network service optimization model; the generated template is the tuning template.

5. The deterministic network service orchestration tool based on artificial intelligence big model as claimed in claim 4, characterized in that: The process of the network service orchestrator generating a tuning template according to the deterministic network service optimization model is as follows: The deterministic network service optimization model is used to compare and analyze the optimized deterministic network service requirements with the network resources of the entire network in the resource management database; Determine whether the current network resources of the entire network in the resource management database meet the requirements of optimizing deterministic network services. If so, adjust the current network resources of the entire network in the resource management database accordingly and generate an optimization template.

6. The deterministic network service orchestration tool based on artificial intelligence big model according to claim 1, characterized in that: The deterministic network service large model performs self-update optimization according to regular deterministic network service demands and corresponding network resource status information of the entire network.

7. The deterministic network service orchestration tool based on artificial intelligence big model according to claim 1, characterized in that: The deterministic network service requirements are described in natural language.

8. The deterministic network service orchestration tool based on artificial intelligence big model according to claim 1, characterized in that: The deterministic network service requirements include user access location, user access type, link bandwidth and performance requirements.

9. A service orchestration method of a deterministic network service orchestration tool based on an artificial intelligence big model as claimed in any one of claims 1 to 8, characterized in that: include: Receive deterministic network service requirements and retrieve the deterministic network service large model from the model database; Analyzing the deterministic network service requirements using a deterministic network service large model to generate a model that matches the deterministic network service requirements; The network services are orchestrated according to the model that matches the deterministic network service requirements and the corresponding configuration templates are generated and sent to the deterministic network controller.

10. The service orchestration method of the deterministic network service orchestration tool based on the artificial intelligence big model as claimed in claim 9, characterized in that: Regularly obtain deterministic network service requirements and their corresponding network resource status information for the entire network, and self-update and optimize the deterministic network service model.

Images