An optical network service orchestration method, electronic equipment and storage medium

Abstract

This invention discloses an optical network service orchestration method, electronic device, and storage medium, relating to the field of optical network technology. The method first acquires user service requirement parameters, converts them into network-recognizable intents, and parses out resource requirements. Based on these resource requirements, cross-domain optical network resource data is collected via network protocols to form a dataset. An optimization algorithm is used to generate a service orchestration scheme based on the dataset. After verifying resource availability and SLA compliance, the scheme is broken down into sub-tasks and executed. The execution metrics of the sub-tasks are tracked and compared with the intents to generate optimization strategies, forming an orchestration closed loop. Based on the closed-loop result, service source and destination parameters are input, inter-domain paths are calculated, and cross-domain services are split into single-domain sub-services. Sub-service parameters are configured domain by domain, and intra-domain and inter-domain configuration information is encapsulated and distributed to complete end-to-end cross-domain service activation. This invention solves the problems of complex cross-domain service activation processes and inaccurate resource allocation, achieving automated cross-domain service orchestration and meeting the unified management and control requirements of optical networks.

Description

Technical Field

[0001] This invention relates to the field of network technology, and in particular to an optical network service orchestration method, electronic device, and storage medium. Background Technology

[0002] With the continuous expansion of optical network management and control scale and the exponential growth of services such as small-granularity services, the demand for intelligent management and control of domestic optical networks is constantly increasing. Currently, optical network management and control mainly rely on control plane protocols and automated management technologies based on software-defined wide area networks (SDN) to provide network management and service capabilities. However, in cross-domain service provisioning scenarios, there are problems such as complex processes and insufficient accuracy in resource allocation. Furthermore, the application of AI large-scale model technology in the field of optical network service configuration has not been fully implemented, making it difficult to meet the needs of flexible management and control and fine-grained resource scheduling for large-scale optical networks.

[0003] To address these technical challenges, this invention proposes an optical network service orchestration method, electronic device, and storage medium. Summary of the Invention

[0004] This invention provides an optical network service orchestration method, electronic device, and storage medium to achieve automatic management of cross-domain optical network resource acquisition, storage, planning, scheduling, and allocation, as well as automatic calculation of cross-domain service paths and automatic generation and distribution of service configurations, thereby meeting the unified orchestration and management requirements of optical network services.

[0005] According to one aspect of the present invention, an optical network service orchestration method is provided, comprising:

[0006] Obtain user service requirement parameters, convert the user service requirement parameters into network-recognizable intents and parse them to obtain resource requirements for services, single-domain networks and inter-domain links;

[0007] Based on the aforementioned resource requirements, the status of cross-domain optical network resources is sensed and resource data is collected through network protocols to form a cross-domain optical network resource dataset.

[0008] Based on the resource data in the cross-domain optical network resource dataset, an optimization algorithm is used to generate a service orchestration scheme. After verifying the resource availability and Service Level Agreement (SLA) compliance rate in the service orchestration scheme, the service orchestration scheme is decomposed into sub-tasks and distributed to each domain controller for execution.

[0009] Track the execution metrics of the subtasks and compare them with the intent to generate an optimization strategy adjustment plan, forming an intent-driven business orchestration closed loop;

[0010] Based on the intent-driven service orchestration closed-loop result, input service source and destination parameters, calculate inter-domain paths and schedule cross-domain resources, and split cross-domain services into single-domain sub-services.

[0011] Configure the parameters of the sub-services in each domain and schedule the resources of each domain, encapsulate the service configuration information within and between domains, and send the parameters of the configuration information to complete the end-to-end cross-domain optical network service activation.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0013] At least one processor;

[0014] and memory that is communicatively connected to at least one processor;

[0015] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that at least one processor can execute the optical network service orchestration method of any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the optical network service orchestration method of any embodiment of the present invention.

[0017] The technical solution of this invention obtains user service requirement parameters and converts them into network-recognizable intents, parsing the resource requirements of services, single-domain networks, and inter-domain links. Based on these resource requirements, the system senses the cross-domain optical network resource status through network protocols and collects resource data to form a cross-domain optical network resource dataset. Combining this dataset, an optimization algorithm is used to generate a service orchestration scheme. After verifying resource availability and Service Level Agreement (SLA) compliance rates, the scheme is broken down into sub-tasks and distributed to each domain controller for execution. Sub-task execution metrics are tracked and compared with intents to generate an optimization strategy adjustment scheme, forming an intent-driven service orchestration closed loop. Based on the closed-loop result, service source and destination parameters are input, inter-domain paths are calculated, and cross-domain resources are scheduled, splitting cross-domain services into single-domain sub-services. Single-domain sub-service parameters are configured for each domain, and single-domain resources are scheduled. Intra-domain and inter-domain service configuration information is encapsulated, and configuration information parameters are distributed to complete end-to-end cross-domain optical network service activation. This solution addresses the technical challenges of complex cross-domain service activation processes, inaccurate cross-domain resource allocation, and difficulties in meeting the unified orchestration and management requirements of optical network services in cross-domain OTN equipment networking scenarios. It enables fully automated and intelligent management of cross-domain optical network services from demand input to activation, effectively simplifying cross-domain service activation steps, improving the accuracy of cross-domain resource allocation, and ensuring that service execution meets user needs through an intent-driven closed-loop mechanism. Ultimately, it meets the core requirements of unified orchestration and management of optical network services and promotes the application of AI large-scale model technology in the field of optical network service configuration.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating an optical network service orchestration method provided in an embodiment of the present invention;

[0021] Figure 2 An architecture diagram of an optical network service orchestration system provided in an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of the intent management interface model provided in an embodiment of the present invention;

[0023] Figure 4A flowchart illustrating the intent-driven service orchestration and end-to-end cross-domain service orchestration method provided in this embodiment of the invention;

[0024] Figure 5 A flowchart illustrating the invocation process of the end-to-end cross-domain service orchestration method provided in this embodiment of the invention;

[0025] Figure 6 A schematic diagram of the structure of an electronic device for implementing the optical network service orchestration method of this invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] To further clarify the technical solution of the present invention, the prior art and the technical effects of the present invention are described as follows before introducing specific embodiments:

[0029] With the continuous expansion of optical network management and control, and the exponential growth of services such as small-granularity services, the demand for intelligent management and control of domestic optical networks continues to rise. Currently, optical network management and control primarily utilizes SDN (Software-Defined Networking)-based control plane protocols and automated management technologies to provide network management and service capabilities. To better support flexible management and control of larger-scale networks, future optical network management and control systems will gradually introduce intent-based management capabilities. This will translate user and network intents into service and network configuration and maintenance operations, improving the automation level of service and network management processes. Simultaneously, it will enhance service awareness and network awareness capabilities, enabling dynamic mapping, resource adjustment, and refined management based on user and network services. This will drive the simultaneous upgrade of refined management and control of business models and network resource services. To achieve these goals, optical network service orchestration methods based on network intent awareness and cross-domain resource collaborative orchestration become crucial.

[0030] This invention proposes an optical network service orchestration method. Based on network intent awareness and cross-domain resource collaborative orchestration, this method aims to address the pain points of complex cross-domain service activation processes and inaccurate cross-domain resource allocation in cross-domain optical transport network (OTN) equipment networking scenarios. It also promotes the development and application of AI large-scale model technology in areas such as optical network service configuration. This method, through AI large-scale models and defined northbound interfaces, enables automatic management of cross-domain optical network resource acquisition, storage, planning, scheduling, and allocation; automatic calculation of cross-domain service paths; and automatic generation and distribution of service configurations, meeting the unified orchestration and management requirements of optical network services.

[0031] Figure 1 This is a flowchart illustrating an optical network service orchestration method provided in an embodiment of the present invention. This embodiment is applicable to cross-domain OTN device networking scenarios in optical networks. The method can be executed by an optical network service orchestration system, which can be implemented in hardware and / or software. This system can be configured in an electronic device. Figure 1 As shown, the method specifically includes the following steps:

[0032] S110. Obtain user service requirement parameters, convert the user service requirement parameters into network-recognizable intents and parse them to obtain resource requirements for services, single-domain networks and inter-domain links.

[0033] Among them, user service requirement parameters can be key indicators proposed by users based on service activation, including bandwidth, latency, reliability thresholds, etc.; network-recognizable intent refers to converting user requirement parameters into structured instructions that can be parsed by the optical network system after semantic analysis and matching with policy templates; resource requirements are the resource configuration requirements at the service type, single-domain network, and inter-domain link levels required to support service activation.

[0034] Specifically, user input parameters such as bandwidth and latency can be collected first. Key parameters can be extracted through semantic analysis and matched with a preset structured policy template to convert user requirements into network-recognizable intents. Then, the intents can be decomposed by the business requirement awareness module to obtain resource requirements for services, single-domain networks, and inter-domain links. This ensures that user requirements are accurately converted into network-executable resource configuration criteria and avoids deviations in requirement transmission.

[0035] In some optional embodiments, the step of converting the user service requirement parameters into a network-recognizable intent and parsing it to obtain resource requirements for services, single-domain networks, and inter-domain links may include:

[0036] The system receives service requirement parameters input by the user, wherein the service requirement parameters include at least one of bandwidth, latency, and reliability thresholds; it extracts key parameters from the service requirement parameters through semantic analysis, matches them with a preset structured policy template, and converts the user's service requirement parameters into a network-recognizable intent; based on the service requirement awareness module, it decomposes the intent to obtain service type requirements, single-domain optical transport network (OTN) resource requirements, and inter-domain link bandwidth requirements.

[0037] The service type requirements, single-domain OTN resource requirements, and inter-domain link bandwidth requirements correspond to the resource requirements of the service, single-domain network, and inter-domain link, respectively.

[0038] The service requirement awareness module can be a functional module used to parse network intent and break down resource requirements; the resource requirements of a single-domain optical transport network (OTN) can refer to the resource configuration requirements such as network elements, boards, and time slots required to support service transmission in a single-domain OTN network; the inter-domain link bandwidth requirements refer to the bandwidth capacity requirements that the links connecting different domains need to meet; and the service type requirements refer to the configuration type requirements determined according to service attributes, such as Ethernet leased lines.

[0039] Specifically, it can receive service requirement parameters input by the user; extract key information from these parameters using semantic analysis technology, such as specific bandwidth values ​​and latency limits; then match them with pre-set structured policy templates in the system, such as parameter mapping templates corresponding to different service types, to convert the user's service requirement parameters into an intent that the optical network system can recognize; call the service requirement perception module to decompose the intent into service type requirements, single-domain OTN resource requirements, and inter-domain link bandwidth requirements, and these three requirements correspond one-to-one with the resource requirements of services, single-domain networks, and inter-domain links, respectively, providing a basis for subsequent resource acquisition and orchestration scheme generation, and ensuring that user requirements are accurately converted into network-executable resource configuration requirements.

[0040] S120. Based on the resource requirements, the status of cross-domain optical network resources is sensed and resource data is collected through network protocols to form a cross-domain optical network resource dataset.

[0041] Among them, network protocol refers to the standardized protocol used for network resource query and collection, such as Network Configuration Protocol (NETCONF); cross-domain optical network resource status can be the real-time operating status of topology, network elements, cards, ports, and time slots in a multi-domain optical network; cross-domain optical network resource dataset is a data set formed by aggregating the resource status data of each single domain.

[0042] Specifically, the NETCONF protocol and southbound interface can be enabled to connect to the optical network controllers of each domain. The topology, network element and other resource status of each single domain network can be queried through the interface, the corresponding data can be collected, and after being summarized, the data can be processed in a standardized format to form a cross-domain optical network resource dataset.

[0043] In some optional embodiments, the step of sensing the cross-domain optical network resource status and collecting resource data through network protocols to form a cross-domain optical network resource dataset may include: enabling the network configuration protocol NETCONF and the southbound interface, connecting to the optical network controllers of each domain through the southbound interface; querying the resource status of the topology, network elements, cards, ports, and time slots of each single-domain network through the southbound interface, and collecting the data corresponding to the resource status; summarizing the collected data corresponding to the resource status of each single-domain network to form the cross-domain optical network resource dataset, and storing the cross-domain optical network resource dataset in the knowledge base of the service orchestration system.

[0044] Among them, NETCONF is a standardized protocol for network device configuration and management, supporting data querying and distribution; the southbound interface refers to the communication interface between the optical network controller and the underlying network devices (such as network elements), used to collect resource status and issue configuration commands; each domain optical network controller is a control unit responsible for the management and configuration execution of single-domain optical network resources; the knowledge base of the service orchestration system is a database used to store cross-domain optical network resource datasets, policy templates and other information.

[0045] Specifically, the NETCONF protocol and southbound interface are first enabled, and a communication connection is established with the optical network controllers of each domain through the southbound interface. Then, resource query commands are sent to each domain controller based on the southbound interface to obtain resource status data such as the topology, network element model, board type, port status, and time slot occupancy of each single-domain network.

[0046] Furthermore, the collected single-domain resource status data are summarized and standardized to form a cross-domain optical network resource dataset. This dataset is stored in the knowledge base of the service orchestration system to provide data support for the generation of subsequent orchestration schemes. This achieves unified collection and storage of multi-domain optical network resource status, providing a comprehensive and accurate data foundation for cross-domain resource collaborative scheduling.

[0047] S130. Combining the resource data in the cross-domain optical network resource dataset, an optimization algorithm is used to generate a service orchestration scheme. After verifying the resource availability and service level agreement (SLA) compliance rate in the service orchestration scheme, the service orchestration scheme is decomposed into sub-tasks and distributed to each domain controller for execution.

[0048] Among them, optimization algorithms can be understood as algorithms that can balance latency, cost, and reliability, such as reinforcement learning algorithms; service orchestration schemes refer to resource scheduling and configuration plans that guide service activation; SLA compliance rate refers to the probability that the scheme meets the preset service level requirements; subtasks can be specific execution units that are assigned to each domain controller after the scheme is broken down; each domain controller is a control unit responsible for the resource management and configuration execution of a single domain.

[0049] In this embodiment of the invention, data matching resource requirements can be extracted from a cross-domain optical network resource dataset. An optimization model is constructed using a reinforcement learning algorithm to generate at least one service orchestration scheme. The scheme is then executed in a simulated manner to verify resource availability and SLA compliance. Finally, compliant schemes are selected, broken down into sub-tasks, and distributed to each domain controller. This allows for the generation and execution of the optimal scheme, ensuring both service provisioning quality and resource utilization efficiency.

[0050] In some optional embodiments, the step of generating service orchestration schemes using optimization algorithms and verifying the resource availability and Service Level Agreement (SLA) compliance rate of the service orchestration schemes can be optimized as follows: An optimization model is constructed using a reinforcement learning algorithm with the objectives of lowest latency, optimal cost, and highest reliability; resource data is extracted from the cross-domain optical network resource dataset, and the extracted resource data is input into the optimization model to generate at least one service orchestration scheme; the policy execution effect of each service orchestration scheme is simulated, resource availability is verified by checking the resource occupancy in the service orchestration schemes, and the SLA compliance rate is verified by comparing the indicators of the service orchestration schemes with the SLA requirements; the service orchestration schemes with available resources and SLA compliance are selected as the final executable service orchestration schemes.

[0051] Among them, the optimization model can be a mathematical model built based on reinforcement learning algorithms to generate business orchestration schemes that meet multiple objectives; the final executable business orchestration scheme can be understood as a scheme that can be directly decomposed and distributed to each domain controller after resource availability verification and SLA compliance verification.

[0052] Specifically, in this embodiment of the invention, reinforcement learning algorithms can be used to construct a multi-objective optimization model with the goals of reducing latency, optimizing costs, and improving reliability; resource data matching business requirements, such as available time slots and link bandwidth, can be extracted from the cross-domain optical network resource dataset stored in the business orchestration system knowledge base and input into the optimization model.

[0053] Furthermore, an optimization model is run to generate at least one service orchestration scheme that includes resource scheduling paths and configuration parameters. To ensure the optimality of the final scheme, each scheme can be simulated. Resource availability is verified by checking whether resources in the scheme, such as time slots and ports, are occupied. The SLA compliance rate is verified by comparing the latency, reliability, and other indicators of the scheme with the preset SLA requirements. Thus, the scheme with available resources and SLA compliance is selected and determined as the final executable service orchestration scheme, i.e., the optimal service orchestration scheme that meets multiple objectives is generated.

[0054] In some preferred embodiments, before the operation optimization model generates a service orchestration scheme, it may further include: preprocessing the resource data in the cross-domain optical network resource dataset to remove invalid and duplicate data; setting weight coefficients for latency, cost, and reliability targets according to service requirement priorities; inputting the preprocessed resource data and the weight coefficients into the optimization model to initialize the parameters of the optimization model and start the operation of the optimization model.

[0055] Data preprocessing can be the process of cleaning up invalid and duplicate data in cross-domain optical network resource datasets. For example, invalid data could be erroneous port status data. Business requirement priority refers to the degree of importance users place on metrics such as latency, cost, and reliability; for example, high real-time services prioritize latency. Weighting coefficients can be importance coefficients assigned to each optimization objective (latency, cost, reliability) based on business requirement priority. Optimization model parameters refer to parameters that affect the results of the optimization model's calculations, such as learning rate and number of iterations.

[0056] Specifically, before running the optimization model to generate a service orchestration scheme, the resource data in the cross-domain optical network resource dataset can be preprocessed. Invalid data is removed through data verification, and duplicate resource status data is deleted using a deduplication algorithm. Then, based on the priority of user service requirements, weight coefficients are set for latency, cost, and reliability targets. For example, the reliability weight coefficient is set to 0.5, latency to 0.3, and cost to 0.2. The preprocessed resource data and the set weight coefficients are then input into the optimization model. The model's learning rate, iteration count, and other parameters are initialized, and the optimization model's computation process is started. This improves the quality of the input data to the optimization model, ensuring that the model can generate an orchestration scheme that meets the service priorities.

[0057] S140. Track the execution metrics of the sub-tasks and compare them with the intent, generate an optimization strategy adjustment plan, and form an intent-driven business orchestration closed loop.

[0058] Among them, execution metrics can be understood as parameters that reflect the running status of subtasks, such as latency, packet loss rate, and link load; optimization strategy adjustment schemes refer to correcting the execution deviations of subtasks; intent-driven business orchestration closed loop can be understood as a closed loop of perception, decision-making, execution, and verification.

[0059] Specifically, the intelligent analysis and prediction module can track the execution metrics of subtasks in real time, compare these metrics with preset thresholds in the network-recognizable intents obtained in step S110, and generate optimization strategy adjustment plans if the metrics deviate. This updates the service orchestration scheme and synchronizes it to each domain controller, forming a closed loop. This allows for real-time correction of execution deviations, ensuring that services continuously meet user intents.

[0060] In some optional embodiments, the step of tracking the execution metrics of the subtasks and comparing them with the intent to generate an optimization strategy adjustment scheme may include: tracking the execution metrics of each domain controller during the execution of the subtasks in real time through an intelligent analysis and prediction module, wherein the execution metrics include at least one of latency, packet loss rate, and link load metrics; extracting preset bandwidth, latency, and reliability thresholds from the intent, and comparing the tracked execution metrics with the preset bandwidth, latency, and reliability thresholds for compliance; if the execution metrics meet the preset thresholds, maintaining the current service orchestration scheme and recording the execution log of the subtask; if the execution metrics do not meet the preset thresholds, analyzing the reasons for the deviation between the execution metrics and the preset thresholds based on a deep learning model, regenerating the resource scheduling and parameter adjustment optimization strategy according to the reasons for the deviation, updating the service orchestration scheme according to the optimization strategy, and synchronizing the updated service orchestration scheme to each domain controller.

[0061] Among them, the intelligent analysis and prediction module can be a functional module used to collect sub-task execution indicators in real time and analyze the reasons for indicator deviations; the preset threshold is the qualified range of execution indicators set in the network intent; the deviation reason refers to the root cause of the execution indicator exceeding the preset threshold, such as insufficient resources, link congestion, etc.; the optimization strategy is a measure used to adjust the service orchestration scheme, such as rescheduling resources and modifying configuration parameters.

[0062] Specifically, the intelligent analysis and prediction module can collect real-time execution metrics such as latency, packet loss rate, and link load during the execution of subtasks by each domain controller. Preset bandwidth, latency, and reliability thresholds are extracted from network intents, and the real-time collected execution metrics are compared with these preset thresholds to determine if they meet the requirements. If the execution metrics are within the preset threshold range, the current service orchestration scheme remains unchanged, and the execution log of the subtask is recorded, including execution time and metric values.

[0063] If the performance metrics exceed preset thresholds, the cause of the deviation can be analyzed using a deep learning model (e.g., excessive load on a certain domain link). Based on the cause of the deviation, optimization strategies for resource scheduling (e.g., switching to backup links) and parameter adjustment (e.g., adjusting time slot allocation) can be regenerated. The service orchestration scheme can then be updated according to these strategies, and the updated scheme can be synchronized to each domain controller for execution. This forms a closed-loop optimization mechanism for service orchestration, promptly correcting execution deviations and ensuring the continuous and stable operation of services.

[0064] S150. Based on the intent-driven service orchestration closed-loop result, input service source and destination parameters, calculate inter-domain paths and schedule cross-domain resources, and split cross-domain services into single-domain sub-services.

[0065] Among them, the service source and destination parameters can be information such as the network element identifiers of the service initiator and receiver; the inter-domain path is the service transmission path that crosses multiple domains; the cross-domain resource scheduling can be the allocation and locking of resources such as inter-domain links and time slots; and the single-domain sub-service is the service unit that is adapted to single-domain management after the cross-domain service is decomposed.

[0066] Specifically, based on the closed-loop result of step S140, the service source and destination parameters can be input, the path calculation algorithm can be called, and the inter-domain link status of the cross-domain optical network resource dataset can be combined to calculate the end-to-end inter-domain path, schedule and lock the cross-domain resources involved in the path, and split the cross-domain service into single-domain sub-services. This can achieve accurate cross-domain path planning and resource locking, and avoid resource conflicts.

[0067] In some optional embodiments, the calculation of inter-domain paths and scheduling of cross-domain resources may include: extracting source and destination network element information from the service source and destination parameters, combining the inter-domain link resource status in the cross-domain optical network resource dataset, calling a path calculation algorithm to obtain an end-to-end inter-domain path that meets the service requirements; marking and locking the inter-domain links and time slot resources involved in the end-to-end inter-domain path, and generating a cross-domain resource scheduling instruction to synchronize to each domain resource management module.

[0068] Among them, source and destination network element information refers to the unique identifiers (such as network element ID) of the service initiator (source network element) and the receiver (destination network element); inter-domain link resource status refers to the status data such as bandwidth occupancy and fault status of links connecting different domains; path calculation algorithm is an algorithm used to calculate the optimal transmission path from the source network element to the destination network element, such as Dijkstra's algorithm; end-to-end inter-domain path refers to the complete transmission path covering multiple domains from the source network element to the destination network element; cross-domain resource scheduling instruction is an instruction used to notify each domain controller to lock specified resources and avoid resource conflicts; each domain resource management module is a functional module responsible for single-domain resource allocation and conflict avoidance.

[0069] Specifically, the identification information of the source network element and the destination network element can be extracted from the source and destination parameters of the service, and resource data such as bandwidth usage and fault status of inter-domain links can be obtained from the cross-domain optical network resource dataset. The source and destination network element information and the inter-domain link resource status are input into the path calculation algorithm to calculate the end-to-end inter-domain path that meets the service bandwidth and latency requirements.

[0070] Furthermore, the inter-domain links and corresponding time slot resources involved in the path are marked, and locking instructions are sent to each domain controller to prevent these resources from being occupied by other services. Then, a cross-domain resource scheduling instruction containing locked resource information is generated and synchronized to each domain resource management module, which is then responsible for managing the locked resources in its own domain, avoiding resource allocation conflicts. This enables accurate calculation and resource locking of cross-domain paths, ensuring the stability and resource exclusivity of cross-domain service transmission paths.

[0071] S160. Configure the parameters of the single-domain sub-services on a domain-by-domain basis and schedule single-domain resources, encapsulate intra-domain and inter-domain service configuration information, and send the parameters of the configuration information to complete the end-to-end cross-domain optical network service activation.

[0072] Among them, single-domain sub-service parameters include port configuration, time slot allocation, etc.; intra-domain service configuration information is a set of configuration data for each single-domain sub-service; inter-domain service configuration information is a set of configuration data for inter-domain paths and cross-domain resource scheduling; end-to-end cross-domain optical network service activation is the complete process of service from demand to normal transmission.

[0073] Specifically, for the split single-domain sub-services, parameters are configured and single-domain resources are scheduled for each domain. Configuration data from each domain is collected to form intra-domain service configuration information. Inter-domain path and resource scheduling data are aggregated to form inter-domain service configuration information. After encapsulating the two types of information, parameters are sent out to complete the cross-domain service activation.

[0074] In some optional embodiments, the encapsulation and distribution of intra-domain and inter-domain service configuration information may include: collecting the single-domain sub-service configuration completion status reported by each domain, extracting service configuration parameters of each domain to form an intra-domain service configuration set; summarizing the end-to-end inter-domain path calculation results and the cross-domain resource scheduling instructions to form an inter-domain service configuration set; encapsulating the intra-domain and inter-domain service configuration sets into a unified cross-domain service configuration file, and distributing it to each domain controller through the Representation State Transition Configuration Protocol (RESTCONF) and the northbound interface; each domain controller loading the cross-domain service configuration file to execute the configuration, and after completing the end-to-end cross-domain optical network service activation, feeding back the results to the service orchestration system.

[0075] Among them, the single-domain sub-service configuration completion status refers to the status information of whether the single-domain sub-service parameter configuration is successful, as reported by each domain controller; the intra-domain service configuration set is a summary set of single-domain sub-service configuration parameters (such as port configuration and time slot allocation) of each domain; the inter-domain service configuration set is a summary set of end-to-end inter-domain path calculation results and cross-domain resource scheduling instructions; the cross-domain service configuration file is a unified configuration document formed by integrating the intra-domain and inter-domain service configuration sets; RESTCONF is a protocol used for network device configuration management; the northbound interface refers to the communication interface between the service orchestration system and the optical network controller, used to issue configuration files and receive feedback results.

[0076] Specifically, we can first collect the configuration completion status of single-domain sub-services from each domain controller, including but not limited to success and failure. For single-domain sub-services that have been successfully configured, we can extract their service configuration parameters such as port configuration and time slot allocation, and summarize them to form an intra-domain service configuration set. From the path calculation and resource scheduling results, we can extract the specific routing information of the end-to-end inter-domain path and the cross-domain resource scheduling instructions, and summarize them to form an inter-domain service configuration set.

[0077] Furthermore, the intra-domain service configuration set and the inter-domain service configuration set are integrated according to a preset format and encapsulated into a unified cross-domain service configuration file. This configuration file is then distributed to each domain controller via the RESTCONF protocol and the northbound interface. After receiving the configuration file, each domain controller loads and executes the corresponding configuration operations. Once all domain configurations are completed and services are transmitted normally, the controller reports the successful service activation result to the service orchestration system. This achieves unified encapsulation and distribution of cross-domain service configuration information, ensuring that configurations in each domain are executed synchronously and improving the efficiency of cross-domain service activation.

[0078] The technical solution of this invention obtains user service requirement parameters and converts them into network-recognizable intents, parsing the resource requirements of services, single-domain networks, and inter-domain links. Based on these resource requirements, the system senses the cross-domain optical network resource status through network protocols and collects resource data to form a cross-domain optical network resource dataset. Combining this dataset, an optimization algorithm is used to generate a service orchestration scheme. After verifying resource availability and Service Level Agreement (SLA) compliance rates, the scheme is broken down into sub-tasks and distributed to each domain controller for execution. Sub-task execution metrics are tracked and compared with intents to generate an optimization strategy adjustment scheme, forming an intent-driven service orchestration closed loop. Based on the closed-loop result, service source and destination parameters are input, inter-domain paths are calculated, and cross-domain resources are scheduled, splitting cross-domain services into single-domain sub-services. Single-domain sub-service parameters are configured for each domain, and single-domain resources are scheduled. Intra-domain and inter-domain service configuration information is encapsulated, and configuration information parameters are distributed to complete end-to-end cross-domain optical network service activation. This solution addresses the technical challenges of complex cross-domain service activation processes, inaccurate cross-domain resource allocation, and difficulties in meeting the unified orchestration and management requirements of optical network services in cross-domain OTN equipment networking scenarios. It enables fully automated and intelligent management of cross-domain optical network services from demand input to activation, effectively simplifying cross-domain service activation steps, improving the accuracy of cross-domain resource allocation, and ensuring that service execution meets user needs through an intent-driven closed-loop mechanism. Ultimately, it meets the core requirements of unified orchestration and management of optical network services and promotes the application of AI large-scale model technology in the field of optical network service configuration.

[0079] Figure 2 This is an architecture diagram of an optical network service orchestration system provided by an embodiment of the present invention. This system can implement the optical network service orchestration method of any of the foregoing embodiments. For example... Figure 2 As shown, the system specifically includes:

[0080] Application layer: Employing intelligent agent and knowledge base technologies, an independent intelligent processing module is built through an intent management interface to realize data collection and interaction, cross-domain resource collaborative management, and result feedback of the unified business orchestration process.

[0081] Orchestration Layer: Responsible for cross-domain collaborative orchestration based on optical network industry applications. Through functions such as network change perception, northbound interface for network and service management, and service configuration parameter management, it realizes network data collection and processing, network and service resource query and configuration distribution, and recommendation and confirmation of service configuration parameters.

[0082] Control layer: Responsible for deploying optical network controllers, providing a unified northbound interface based on RESTCONF to enable end-to-end service configuration distribution; it also provides a southbound interface based on NETCONF / YANG to enable the collection and management of single-domain network topology resources;

[0083] Forwarding layer: responsible for deploying ultra-high-speed optical transmission networks involving multiple vendors and domains.

[0084] Based on the above embodiments, the technical solution of the present invention includes not only an optical network service orchestration architecture, but also an intent management interface model, an optical network controller northbound interface, intent-driven service orchestration, and an end-to-end cross-domain service orchestration process.

[0085] The intent management interface addresses the implementation of intent management functions for optical transport network services, and includes an intent model interface, an intent translation interface, and an intent processing interface. For example... Figure 3 The diagram shown is a schematic of the intent management interface model provided in an embodiment of the present invention.

[0086] In addition, the northbound interface of the optical network controller is used for optical transport network resource management and service configuration distribution. The northbound interface includes topology management, resource query, port configuration, path calculation, route query, Ethernet leased line service configuration, query, modification, alarm subscription and reporting, querying current and historical alarms, performance monitoring configuration, and performance data acquisition. Resource objects of the northbound interface include network elements, cards, ports, time slots, routing policies, path constraints, service connections, alarms, and performance data. The northbound interface of the optical network controller is shown in Table 1.

[0087] Table 1

[0088]

[0089] Based on the above embodiments, such as Figure 4 The diagram shown is a flowchart of an intent-driven service orchestration and end-to-end cross-domain service orchestration method provided by an embodiment of the present invention. The method flow is as follows:

[0090] Step 1): Intent input: The user inputs their requirements, and key parameters (bandwidth, latency, reliability threshold, etc.) are extracted through semantic analysis. The requirements are then converted into a structured policy template that the network can recognize.

[0091] Step 2): Requirement analysis: Based on the business requirement perception module, the intent is broken down into resource requirements such as business, single-domain network, and inter-domain links (e.g., business type, single-domain OTN network, link bandwidth).

[0092] Step 3): Resource awareness: Utilize protocols such as NETCONF and southbound interfaces to perceive and collect network resources;

[0093] Step 4): Solution generation: Using methods such as reinforcement learning, balance indicators such as latency, cost, and reliability, simulate the effect of strategy execution, and verify resource availability and SLA compliance rate;

[0094] Step 5): Policy execution: The multi-domain collaborative orchestration module decomposes the policy into sub-tasks and distributes them to each domain controller through standardized interfaces (such as RESTCONF, NETCONF);

[0095] Step 6): Closed-loop verification: Track indicators such as latency, packet loss rate, and link load through the intelligent analysis and prediction module, compare the compliance with user intent, regenerate optimization strategies based on deep learning models, and realize the "perception-decision-execution-verification" closed loop.

[0096] Based on the above embodiments, such as Figure 5 As shown, this is an end-to-end cross-domain service orchestration method provided by an embodiment of the present invention. The specific calling process is as follows:

[0097] Step 1): Input parameters such as service source and destination, and begin end-to-end service orchestration;

[0098] Step 2): Based on the source and destination network element information, perform inter-domain path calculation and inter-domain resource scheduling;

[0099] Step 3): Based on the cross-domain business information, perform cross-domain business splitting;

[0100] Step 4): Based on the cross-domain business information, repeatedly execute the intra-domain business configuration and intra-domain resource scheduling on a domain-by-domain basis;

[0101] Step 5): Perform cross-domain business collaborative orchestration, encapsulate intra-domain business configurations on a domain-by-domain basis, and encapsulate inter-domain business configurations.

[0102] Step 6): Issue business configuration parameters to enable cross-domain business activation.

[0103] Step 7): The process ends.

[0104] The technical solution of this invention proposes an optical network service orchestration architecture based on network intent awareness and cross-domain resource collaborative orchestration, an intent management interface model, an optical network controller northbound interface, intent-driven service orchestration, and an end-to-end cross-domain service orchestration method. First, by unifying the standard optical network service intent management interface, it can solve the problems of intelligence and complex service scenarios in next-generation optical transport networks, simplifying service identification, translation, and processing, and improving the intelligence capability of service processing. Second, the automatic unified orchestration of cross-domain optical network services can fundamentally reduce dependence on single equipment vendors when purchasing existing network equipment, reduce equipment procurement costs, promote flexible and open equipment, enhance the activity of the next-generation optical transport network intelligence industry, and increase the willingness of hardware equipment vendors and software suppliers in the industry chain to participate.

[0105] The optical network service orchestration system provided in this embodiment of the invention can execute the optical network service orchestration method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0106] Figure 6 This is a schematic diagram of the structure of an electronic device for implementing the optical network service orchestration method of this invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0107] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0108] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0109] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as optical network service orchestration methods.

[0110] In some embodiments, the optical network service orchestration method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the optical network service orchestration method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the optical network service orchestration method by any other suitable means (e.g., by means of firmware).

[0111] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0115] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0116] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0117] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0118] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for orchestrating optical network services, characterized in that, include: Obtain user service requirement parameters, convert the user service requirement parameters into network-recognizable intents and parse them to obtain resource requirements for services, single-domain networks and inter-domain links; Based on the aforementioned resource requirements, the status of cross-domain optical network resources is sensed and resource data is collected through network protocols to form a cross-domain optical network resource dataset. Based on the resource data in the cross-domain optical network resource dataset, an optimization algorithm is used to generate a service orchestration scheme. After verifying the resource availability and service level agreement (SLA) compliance rate in the service orchestration scheme, the service orchestration scheme is decomposed into sub-tasks and distributed to each domain controller for execution. Track the execution metrics of the sub-tasks and compare them with the intent to generate an optimization strategy adjustment plan, forming an intent-driven business orchestration closed loop; Based on the intent-driven service orchestration closed-loop result, input service source and destination parameters, calculate inter-domain paths and schedule cross-domain resources, and split cross-domain services into single-domain sub-services. Configure the parameters of the sub-services in each domain and schedule the resources of each domain, encapsulate the service configuration information within and between domains, and send the parameters of the configuration information to complete the end-to-end cross-domain optical network service activation.

2. The optical network service orchestration method of claim 1, wherein, The step of converting the user service requirement parameters into a network-recognizable intent and parsing them to obtain the resource requirements for services, single-domain networks, and inter-domain links includes: The system receives the service requirement parameters input by the user, wherein the service requirement parameters include at least one of bandwidth, latency, and reliability threshold. Key parameters in the business requirement parameters are extracted through semantic analysis, matched with a preset structured strategy template, and the user business requirement parameters are converted into network-recognizable intents. Based on the business demand perception module, the intent is broken down to obtain the business type demand, single-domain optical transport network (OTN) resource demand, and inter-domain link bandwidth demand. The service type requirements, single-domain OTN resource requirements, and inter-domain link bandwidth requirements correspond to the resource requirements of the service, single-domain network, and inter-domain link, respectively.

3. The optical network service orchestration method according to claim 1, characterized in that, The process of sensing the status of cross-domain optical network resources and collecting resource data through network protocols to form a cross-domain optical network resource dataset includes: Enable the NETCONF network configuration protocol and the southbound interface, and connect to the optical network controllers of each domain through the southbound interface; The resource status of each single-domain network, including topology, network elements, cards, ports, and time slots, is queried through the southbound interface, and the data corresponding to the resource status is collected. The collected resource status data of each single-domain network are aggregated to form the cross-domain optical network resource dataset, which is then stored in the knowledge base of the service orchestration system.

4. The optical network service orchestration method of claim 1, wherein, The process of generating a service orchestration scheme using an optimization algorithm and verifying the resource availability and Service Level Agreement (SLA) compliance rate of the service orchestration scheme includes: An optimization model is constructed using reinforcement learning algorithms with the goals of minimum latency, optimal cost, and highest reliability. Resource data is extracted from the cross-domain optical network resource dataset, the extracted resource data is input into the optimization model, and the optimization model is run to generate at least one service orchestration scheme; Simulate the strategy execution effect of each of the aforementioned service orchestration schemes, verify resource availability by checking the resource usage in the service orchestration schemes, and verify the SLA compliance rate by comparing the indicators of the service orchestration schemes with the SLA requirements. Select the service orchestration schemes that have available resources and meet the SLA, and use them as the final executable service orchestration schemes.

5. The optical network service orchestration method of claim 4, wherein, Before the operation optimization model generates the service orchestration scheme, the following is also included: The resource data in the cross-domain optical network resource dataset is preprocessed to remove invalid and duplicate data. Based on the priority of business needs, weight coefficients are set for latency, cost, and reliability objectives respectively; The preprocessed resource data and the weight coefficients are input into the optimization model to initialize the parameters of the optimization model and start the operation of the optimization model.

6. The optical network service orchestration method of claim 1, wherein, The process of tracking the execution metrics of the sub-tasks and comparing them with the intent to generate an optimization strategy adjustment plan includes: The intelligent analysis and prediction module tracks the execution metrics of each domain controller in real time during the execution of the sub-tasks. The execution metrics include at least one of latency, packet loss rate, and link load metrics. Extract the preset bandwidth, latency, and reliability thresholds from the intent, and compare the tracked execution metrics with the preset bandwidth, latency, and reliability thresholds for compliance. If the execution metrics meet the preset threshold, maintain the current business orchestration scheme and record the execution log of the subtask; If the performance indicators do not meet the preset threshold, the reasons for the deviation between the performance indicators and the preset threshold are analyzed based on a deep learning model. Based on the reasons for the deviation, an optimization strategy for resource scheduling and parameter adjustment is regenerated. The service orchestration scheme is updated according to the optimization strategy, and the updated service orchestration scheme is synchronized to each domain controller.

7. The optical network service orchestration method of claim 1, wherein, The computation of inter-domain paths and scheduling of cross-domain resources includes: Source and destination network element information is extracted from the service source and destination parameters. Combined with the inter-domain link resource status in the cross-domain optical network resource dataset, the path calculation algorithm is called to obtain the end-to-end inter-domain path that meets the service requirements. The inter-domain links and time slot resources involved in the end-to-end inter-domain path are marked and locked, and cross-domain resource scheduling instructions are generated and synchronized to the resource management modules of each domain.

8. The optical network service orchestration method according to claim 1, characterized in that, The encapsulation and distribution of intra-domain and inter-domain service configuration information includes: Collect the configuration completion status of the single-domain sub-services from each domain, and extract the service configuration parameters of each domain to form a set of service configurations within the domain; The end-to-end inter-domain path calculation results and the cross-domain resource scheduling instructions are combined to form an inter-domain service configuration set. The intra-domain and inter-domain service configuration sets are encapsulated into a unified cross-domain service configuration file, which is then distributed to each domain controller via the RESTCONF representation state transition configuration protocol and the northbound interface. Each domain controller loads the cross-domain service configuration file, executes the configuration, and after completing the end-to-end cross-domain optical network service activation, it sends the results back to the service orchestration system.

9. An electronic device, comprising: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the optical network service orchestration method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the optical network service orchestration method according to any one of claims 1-8.

Images