JP-7856267-B2 - A method for achieving intelligent intent setting in heterogeneous networks based on a network programming language.

Inventors

• 董 黎剛
• 蒋 献
• 鐘 ▲韋▼軒
• 厳 嘉輝

Assignees

• 浙江工商大学

Dates

Publication Date

20260511

Application Date

20241226

Priority Date

20231226

Claims (3)

1. A method for realizing intelligent configuration of intents in heterogeneous networks based on the network programming language, which combines intent realization, network programming language and policy translation technology, The global SDN controller acquires information on the resources of the heterogeneous network and the status of those resources . The steps include: the user describing network service requirements in voice or text format, The intent analysis engine analyzes the network service requirements and extracts intent keywords. The service orchestrator receives information about the resources and resource status of the heterogeneous network from the global SDN controller , combines the information about the resources and resource status of the heterogeneous network based on the intent keyword, and generates a network policy that conforms to the Frenetic network programming language specification. The steps include : the global SDN controller selecting a corresponding domain controller according to the network service requirements and distributing the network policy; The OpenFlow domain controller, which supports the OpenFlow protocol, compiles the network policy as an OpenFlow flow table, and the NETCONF domain controller, which supports the NETCONF protocol, converts the network policy to a YANG data model using a policy translator. The process includes the steps of: the OpenFlow domain controller distributing the OpenFlow flow table to lower network element devices that support the OpenFlow protocol; and the NETCONF domain controller distributing the YANG data model to lower network element devices that support the NETCONF protocol , thereby enabling service placement and initiating closed-loop control . The closed-loop control includes the transmission of information about the resources of the heterogeneous network and the status of those resources from the OpenFlow domain controller and the NETCONF domain controller to the global SDN controller, and the transmission of information about the resources of the heterogeneous network and the status of those resources from the global SDN controller to the service orchestrator. A method for realizing intelligent intent setting in heterogeneous networks based on a network programming language, characterized by the above.
2. 1) Each of the OpenFlow domain controller and the NETCONF domain controller delivers an inquiry command or request to the lower network element device, analyzes the response data returned by the lower network element device, extracts necessary information including device topology information, port status information, fault and alarm information, network function information and device configuration, and then the global SDN controller of the heterogeneous network integrates the data from the OpenFlow domain controller and the NETCONF domain controller. 2) A step in which the user inputs the intent in the form of text or voice, wherein the intent includes the network service requirements and a high-level description of the network, and represents the network service objectives that the user wants to achieve across the entire heterogeneous network , 3) The intent analysis engine extracts important service information based on the intent entered by the user in natural language, converts the intent data into a format that can be processed by the model, extracts intent keywords from the intent data in a format that conforms to the specifications using a tokenizer , and obtains the service scope, network functions included in the service, and service lifecycle information desired by the user. 4) Inputting the acquired intent keyword, the current resources of the heterogeneous network, and the status of the resources into the service orchestrator; the service orchestrator generating a network policy conforming to the Frenetic network programming language specification using large-scale language model code generation technology; and distributing the network policy by selecting an appropriate domain for the scope of user services; 5) For domain controllers with different protocols, the network policy is further processed in different ways; in an OpenFlow domain consisting of lower network element devices that support the OpenFlow protocol, the OpenFlow domain controller compiles the network policy as an OpenFlow flow table; in a NETCONF domain consisting of lower network element devices that support the NETCONF protocol, the NETCONF domain controller extracts and transforms the network policy using a policy translator, and further combines it with information from the lower network element devices to generate a YANG model file corresponding to the network element device; 6) The global SDN controller performs the final deployment to the user network service after it has been implemented, in accordance with the service lifecycle described in the user intent. The method according to claim 1 , characterized by including the steps of: starting a closed-loop control module simultaneously with the start of production operation; the global SDN controller monitoring service QoS with data on the resources and resource status information of the heterogeneous networks returned by each domain controller; and, once the service is unable to satisfy the user intent, the global SDN controller initiating a request to the service orchestrator, which then regenerates and deploys the service based on the current information on the resources and resource status of the heterogeneous networks .
3. In step 5) above , the step of converting the network policy in the NETCONF domain to the YANG model file corresponding to a specific network element device using the policy translator is: 5-1) The extractor extracts functions that describe network functions in the network policy and the objects to be processed, based on the data of the deterministic finite state automaton. 5-2) A step of comparing network function functions with a database containing lower-level network element functions, and mapping the functions and their processing targets in the network policy to information necessary for the functions and configuration services of a specific network element device, 5-3) A step in which a policy generator built on context-free grammar generates a "content generation formula" and a "structure generation formula" based on the data after data transformation and specific network element configuration information, wherein the content generation formula is used to include the data in accurate XML tags, and the structure generation formula is responsible for organizing the overall XML structure and ensuring the correct relationships between each part, 5-4) The method according to claim 2 , characterized by comprising the step of outputting lower network element configuration information, i.e. , the YANG model file.

Description

This invention belongs to the technical field of communication networks, and more specifically, relates to a method for realizing intelligent user intent settings in heterogeneous network environments based on a network programming language. With the rapid development of information technology, networks have become one of the essential infrastructures of modern society. Currently, networks are not only tools for connecting people and information, but also a crucial driving force for promoting industrial innovation and improving work efficiency. As networks expand and diversify rapidly, the complexity and heterogeneity of network structures are increasing daily, and user requirements for network services are becoming more diverse and dynamic. Thanks to the introduction of new network technologies such as Software-Defined Networking (SDN) and ForCES (Forwarding and Control Element Separation), traditional network architectures offer greater flexibility and stability compared to conventional architectures. However, the maintenance and management of lower-level network devices still heavily rely on manual configuration by network developers. As network scales, manual configuration becomes more difficult and inefficient, limiting the overall stability and accuracy of the network due to the inherent risk of human error, and leading to slow service delivery and response times. The OpenFlow and NETCONF protocols are two of the most common controller-device communication protocols in current network architectures. While both protocols offer powerful tools for automated and centralized network management, they focus on different aspects and strengths. For example, the OpenFlow protocol allows controllers to directly control the flow tables of network devices, enabling flexible control and management of network traffic, making it more suitable for specific scenarios such as data centers or research environments. The NETCONF protocol, on the other hand, allows network administrators to securely access various functions for remotely configuring network devices, supporting features such as configuration verification and transaction management, resulting in superior performance in traditional enterprise networks. A heterogeneous network built by combining the OpenFlow and NETCONF protocols fully leverages the strengths of each protocol, providing flexible network management and control capabilities to meet diverse service requirements. However, because the deployment and maintenance of heterogeneous networks are relatively complex, there is a demand for integrated management and intelligent organization of services in heterogeneous network environments. With the rapid pace of digital transformation, user requirements for network services are becoming more diverse and dynamic. Traditional network configuration and management methods struggle to capture and understand user service requirements, and are unable to customize network services to meet the diverse needs of individual network users. Intent-based networking (IBN) is an emerging technological concept as a brand-new network management and control pattern. It aims to apply a more intelligent and predictable approach to network configuration, replacing the manual process of setting up the network. By utilizing artificial intelligence and machine learning methods, the network administrator only needs to define the desired outcome or service objective, and the network software can intelligently determine how to achieve that objective. By introducing the concept of "intent" into traditional network architectures, translating such high-level service objectives into specific settings for lower-level network element devices significantly improves the flexibility and adaptability of traditional network architectures, better meeting the diverse service requirements of users. Network programming languages (DSLs) are domain-specific languages dedicated to network programming and are used to configure and manage network devices. Frenetic is one of the most mature representatives in this field, enabling the description of network behavior and policies in a manner approaching natural language. By leveraging Frenetic's characteristics of flexibly describing service capabilities and describing network policies using Python code, combined with the code generation capabilities of a Large Language Model (LLM), the programming and configuration process for network devices can be significantly simplified and accelerated. However, until now, the Frenetic network programming language has only provided support for OpenFlow network devices, which means that the Frenetic network programming language is less effective as an efficient and flexible network management tool in heterogeneous network environments. In summary, while conventional network architectures offer a dramatic improvement in scale and performance compared to traditional network architectures, they still face challenges such as