Bandwidth control method and device for software-defined packet transport network

Abstract

A bandwidth control method and device for a software-defined packet transport network, wherein the method includes: a first DT system of the management plane of SPTN, receiving a first state parameter sent by a digital twin router of an inter-domain controller and a digital twin bandwidth scheduler of an intra-domain controller of the control plane of SPTN, performing offline simulation on the inter-domain controller and the intra-domain controller, generating a policy and configuring it to the digital twin router and the digital twin bandwidth scheduler; a first AI system of the management plane of SPTN, receiving a second state parameter sent by a second AI system of an inter-domain controller and a third AI system of an intra-domain controller of the control plane of SPTN, training an AI model for the second AI system and the third AI system, and configuring and scheduling the second AI system and the third AI system. The present invention can realize intelligent control of the transmission network according to transmission requirements, thereby realizing data transmission with high service quality.

Description

Technical Field

[0001] The present invention relates to the technical field of packet transport network (PTN), and in particular to a bandwidth control method and device for a software-defined packet transport network. Background Art

[0002] Packet Transport Network (PTN) is a multi-service transport technology based on packet switching and using Multi-Protocol Label Switching Transport Profile (MPLS-TP) protocol. The introduction of Software-defined Packet Transport Network (SPTN) technology has promoted the introduction of Software Defined Network (SDN) technology in PTN networks. Through centralized network programmable control and open network capabilities, it can better meet the network-centric business operation needs in the era of deep integration of Information, Communication, and Data Technology (ICDT).

[0003] like Figure 1As shown in the figure, the SPTN system architecture consists of a forwarding plane, a control plane, a management plane, and an application plane. The control plane adopts a hierarchical control architecture. The multi-level controllers at the network element level support the flexible expansion of the network. It is divided into a domain controller (Domain Controller, D-Controller) and an inter-domain controller (Super Controller, S-Controller). The D-Controller is responsible for the control of intra-domain services and controls the forwarding plane equipment through the southbound interface. The S-Controller is responsible for the control of inter-domain services. By calling the northbound interface provided by the D-Controller, it completes the resource coordination and service scheduling of the entire network and realizes cross-domain collaborative control of network resources. The S-Controller is the core of the SPTN architecture and is used for the control and coordination of inter-domain services. It has the functions of inter-domain topology management, path calculation, and service orchestration. The S-Controller can be nested in multiple levels to expand the scale of network control. The S-Controller calculates the end-to-end service forwarding path through the collaboration with the D-Controller through the north-south interface. First, according to the upper-layer topology, the inter-domain forwarding path is calculated, and the path request of the intra-domain service is sent to the D-Controller. After the D-Controller completes the path calculation within the domain, it feeds the calculation result upward, and the S-Controller optimizes the path to form an end-to-end cross-domain forwarding path.

[0004] The management plane will still exist for a long time and will continue to be responsible for resource and version management, alarm and performance monitoring of the forwarding plane and controller to meet the network operation and maintenance needs.

[0005] The artificial intelligence (AI) in the fourth-generation / fifth-generation mobile communication (4G / 5G) network is an external AI, that is, various information required by AI is reported to the AI ​​function node through the network side (base station, core network) and the terminal side, and AI-related processing is performed outside the network element. The AI ​​function node collects and processes data, trains AI models, and sends the results of AI operation or the generated policy to the network.

[0006] At present, AI in 4G / 5G networks is external AI, and only focuses on the control of the core network and base stations, and the measurement and reporting of terminals. It does not take into account the intelligent drive of the transmission network between the core network and base stations and between the base station centralized unit (CU) and distributed unit (DU). As part of end-to-end endogenous AI, AI drive of the transmission network is the key path to realize end-to-end AI network. No matter how intelligent the core network and base stations are, if the transmission network becomes a bottleneck, end-to-end intelligent control cannot be achieved. Summary of the invention

[0007] At least one embodiment of the present invention provides a bandwidth control method and device for a software-defined packet transport network, which can realize intelligent control of the transmission network according to transmission requirements, thereby achieving data transmission with high Quality of Service (QoS).

[0008] According to one aspect of the present invention, at least one embodiment provides a management plane of a software-defined packet transport network SPTN, including a first artificial intelligence AI system and / or a first digital twin DT system;

[0009] The first DT system is used to receive the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of the SPTN, perform offline simulation on the inter-domain controller and the intra-domain controller, generate a policy and configure it to the digital twin router and the digital twin bandwidth scheduler;

[0010] The first AI system is used to receive second state parameters sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN, train AI models for the second AI system and the third AI system, and configure and schedule the second AI system and the third AI system.

[0011] In addition, according to at least one embodiment of the present invention, the first AI system is a part of a distributed AI function running on the management plane, and the distributed AI function also includes the second AI system running on the inter-domain controller, the third AI system running on the intra-domain controller, a fourth AI system running on a core network, a fifth AI system running on a transmission network, and a sixth AI system running on an OAM system of a base station and a terminal, and the first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system, and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

[0012] In addition, according to at least one embodiment of the present invention, the first DT system is also used to simulate the scale change trend, load change trend, server quality change trend, fault prediction, and control collaboration between the intra-domain controller and the inter-domain controller of the transmission network when performing offline simulation of the inter-domain controller and the intra-domain controller, and generate strategies and configure them to the digital twin router and digital twin bandwidth scheduler.

[0013] According to another aspect of the present invention, at least one embodiment provides a control plane of an SPTN, including an inter-domain controller and an intra-domain controller, wherein the inter-domain controller includes a digital twin router and / or a second AI system; the intra-domain controller includes a digital twin bandwidth scheduler and / or a third AI system;

[0014] The digital twin router is used to synchronously obtain the first data information and the first control state carried by the inter-domain controller, and send the first control state to the first DT system of the management plane of the SPTN; receive the first policy sent by the first DT system of the management plane of the SPTN, and perform online simulation of the function of the inter-domain controller according to the first policy, and provide functional support for AI algorithm operation, policy execution, and command verification for the second AI system;

[0015] The second AI system is used to receive the configuration and scheduling of the first AI system of the management plane of the SPTN, and operate under the configuration and scheduling, and generate predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN;

[0016] The digital twin bandwidth scheduler is used to synchronously obtain the second data information and the second control state carried by the intra-domain controller, and send the second control state to the first DT system of the management plane of the SPTN; receive the second strategy sent by the first DT system of the management plane of the SPTN, and perform online simulation of the function of the intra-domain controller according to the second strategy, and provide functional support for AI algorithm operation, strategy execution, and command verification for the third AI system;

[0017] The third AI system is used to receive the configuration and scheduling of the first AI system of the management plane of the SPTN, and run under the configuration and scheduling to generate a QoS guarantee solution for bandwidth or QoS requirements.

[0018] In addition, according to at least one embodiment of the present invention, the second AI system is the part of the distributed AI function running on the inter-domain controller, the third AI system is the part of the distributed AI function running on the intra-domain controller, the first AI system is the part of the distributed AI function running on the management plane, the distributed AI function also includes a fourth AI system running on the core network, a fifth AI system running on the transmission network, and a sixth AI system running on the OAM system of the base station and the terminal, and the first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

[0019] Furthermore, according to at least one embodiment of the present invention, the inter-domain controller further comprises: a bandwidth management function for performing dynamic inter-domain bandwidth management according to characteristics or requirements of data carried by the transmission network;

[0020] The intra-domain controller further comprises: a bandwidth allocation function, which is used to execute the bandwidth allocation function within the domain under the control of the bandwidth management function.

[0021] In addition, according to at least one embodiment of the present invention, the bandwidth management function is specifically used to detect the characteristics of data carried by the transmission network under the drive of the second AI system and combine the status information generated during the transmission process to generate the characteristics of the transmitted data, and combine the data processing configured by the management plane or the performance index of the service to generate a bandwidth management command for the data and send it to the bandwidth allocation function;

[0022] The bandwidth allocation function is specifically configured to receive a bandwidth management command for the data sent by the bandwidth management function, and according to the bandwidth management command, call the third AI system to perform bandwidth allocation within the domain to generate a globally optimal or locally optimal bandwidth allocation plan, or call the third AI system to formulate a bandwidth allocation strategy in advance, and report the bandwidth allocation plan or bandwidth allocation strategy to the bandwidth management function;

[0023] The third AI system is further configured to generate a bandwidth allocation plan or a bandwidth allocation strategy according to the calling of the bandwidth allocation function.

[0024] In addition, according to at least one embodiment of the present invention, the inter-domain controller further includes: a QoS management function for performing QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network;

[0025] The intra-domain controller also includes: a QoS control function, which is used to perform QoS control within the domain under the control of the QoS management function.

[0026] In addition, according to at least one embodiment of the present invention, the QoS management function is specifically used to detect the data characteristics carried by the transmission network under the drive of the second AI system and combine the status information generated during the transmission process to generate a QoS feature characterization of the transmitted data, and combine the data or service QoS indicators configured by the management plane to generate a QoS management command for the data and send it to the QoS control function;

[0027] The QoS control function is specifically configured to receive a QoS management command sent by the QoS management function, and according to the QoS management command, call the third AI system to perform intra-domain QoS guarantee control to generate a globally optimal or locally optimal QoS guarantee solution, or call the third AI system to implement an on-demand QoS guarantee solution, and report the status information of the intra-domain QoS guarantee to the QoS management function;

[0028] The third AI system is further used to generate a QoS guarantee solution according to the call of the QoS control function.

[0029] In addition, according to at least one embodiment of the present invention, the characteristics or requirements of the data carried by the transmission network are predicted by the first AI system or configured by the OAM system.

[0030] According to another aspect of the present invention, at least one embodiment provides a bandwidth control method for SPTN, the method comprising:

[0031] The first DT system of the management plane of SPTN receives the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of SPTN, performs offline simulation on the inter-domain controller and the intra-domain controller, generates a policy and configures it to the digital twin router and the digital twin bandwidth scheduler;

[0032] The first AI system of the management plane of the SPTN receives the second state parameter sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN, trains AI models for the second AI system and the third AI system, and configures and schedules the second AI system and the third AI system.

[0033] In addition, according to at least one embodiment of the present invention, the first AI system is a part of a distributed AI function running on the management plane, and the distributed AI function also includes the second AI system running on the inter-domain controller, the third AI system running on the intra-domain controller, a fourth AI system running on a core network, a fifth AI system running on a transmission network, and a sixth AI system running on an OAM system of a base station and a terminal, and the first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system, and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

[0034] In addition, according to at least one embodiment of the present invention, the present invention further comprises:

[0035] When the first DT system performs offline simulation on the inter-domain controller and the intra-domain controller, it simulates the scale change trend, load change trend, server quality change trend, fault prediction, and control collaboration between the intra-domain controller and the inter-domain controller of the transmission network, and generates strategies and configures them to the digital twin router and digital twin bandwidth scheduler.

[0036] According to another aspect of the present invention, at least one embodiment provides a bandwidth control method for SPTN, wherein the control plane of the SPTN includes an inter-domain controller and an intra-domain controller, the inter-domain controller includes a digital twin router and a second AI system; the intra-domain controller includes a digital twin bandwidth scheduler and a third AI system; the method includes:

[0037] The digital twin router synchronously obtains the first data information and the first control state carried by the inter-domain controller, and sends the first control state to the first DT system of the management plane of the SPTN; receives the first policy sent by the first DT system of the management plane of the SPTN, performs online simulation of the function of the inter-domain controller according to the first policy, and provides functional support for AI algorithm operation, policy execution, and command verification for the second AI system;

[0038] The second AI system receives the configuration and scheduling of the first AI system of the management plane of the SPTN, and operates under the configuration and scheduling, and generates predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN;

[0039] The digital twin bandwidth scheduler synchronously obtains the second data information and the second control state carried by the intra-domain controller, and sends the second control state to the first DT system of the management plane of SPTN; receives the second strategy sent by the first DT system of the management plane of SPTN, and performs online simulation of the function of the intra-domain controller according to the second strategy, and provides functional support for AI algorithm operation, strategy execution, and command verification for the third AI system;

[0040] The third AI system receives the configuration and scheduling of the first AI system of the management plane of the SPTN, and operates under the configuration and scheduling to generate a QoS guarantee solution for bandwidth or QoS requirements.

[0041] In addition, according to at least one embodiment of the present invention, the second AI system is the part of the distributed AI function running on the inter-domain controller, the third AI system is the part of the distributed AI function running on the intra-domain controller, the first AI system is the part of the distributed AI function running on the management plane, the distributed AI function also includes a fourth AI system running on the core network, a fifth AI system running on the transmission network, and a sixth AI system running on the OAM system of the base station and the terminal, and the first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

[0042] In addition, according to at least one embodiment of the present invention, the inter-domain controller further includes a bandwidth management function; the intra-domain controller further includes a bandwidth allocation function; and the method further includes:

[0043] The bandwidth management function performs dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network;

[0044] The bandwidth allocation function performs bandwidth allocation function within the domain under the control of the bandwidth management function.

[0045] In addition, according to at least one embodiment of the present invention, the bandwidth management function performs dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network, specifically including: the bandwidth management function, under the drive of the second AI system, detects the characteristics of the data carried by the transmission network and combines the status information generated during the transmission process to generate the characteristics of the transmitted data, and combines the data processing configured by the management plane or the performance index of the service to generate a bandwidth management command for the data and send it to the bandwidth allocation function;

[0046] The bandwidth allocation function executes the bandwidth allocation function within the domain under the control of the bandwidth management function, specifically including: the bandwidth allocation function receives a bandwidth management command for the data sent by the bandwidth management function, and calls the third AI system to perform bandwidth allocation within the domain according to the bandwidth management command to generate a globally optimal or locally optimal bandwidth allocation plan, or calls the third AI system to formulate a bandwidth allocation strategy in advance, and reports the bandwidth allocation plan or bandwidth allocation strategy to the bandwidth management function;

[0047] The third AI system generates a bandwidth allocation plan or a bandwidth allocation strategy according to the calling of the bandwidth allocation function.

[0048] In addition, according to at least one embodiment of the present invention, the inter-domain controller further includes a QoS management function, and the intra-domain controller further includes a QoS control function; and the method further includes:

[0049] The QoS management function performs QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network;

[0050] The QoS control function performs QoS control within the domain under the control of the QoS management function. In addition, according to at least one embodiment of the present invention, the QoS management function performs QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network, specifically including: the QoS management function, driven by the second AI system, detects the characteristics of the data carried by the transmission network and combines the status information generated during the transmission process to generate a QoS feature characterization of the transmitted data, and combines the data or service QoS indicators configured by the management plane to generate a QoS management command for the data and send it to the QoS control function;

[0051] The QoS control function performs QoS control within the domain under the control of the QoS management function, specifically including: the QoS control function receives a QoS management command sent by the QoS management function, and calls the third AI system to perform QoS guarantee control within the domain according to the QoS management command to generate a global optimal or local optimal QoS guarantee solution, or calls the third AI system to implement an on-demand QoS guarantee solution, and reports the status information of the QoS guarantee within the domain to the QoS management function;

[0052] The third AI system is further used to generate a QoS guarantee solution according to the call of the QoS control function.

[0053] In addition, according to at least one embodiment of the present invention, the characteristics or requirements of the data carried by the transmission network are predicted by the first AI system or configured by the OAM system.

[0054] According to another aspect of the present invention, at least one embodiment provides a management plane of SPTN, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program implements the steps of the method described above when executed by the processor.

[0055] According to another aspect of the present invention, at least one embodiment provides a control plane of an SPTN, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program implements the steps of the method described above when executed by the processor.

[0056] According to another aspect of the present invention, at least one embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0057] Compared with the prior art, the bandwidth control method and device of the software-defined packet transport network provided in the embodiment of the present invention provide an SPTN architecture for native AI, realizing the capability of native AI driving. In addition, the endogenous DT function is also realized to realize the driving of the SPTN network by online simulation. In the embodiment of the present invention, the deep combination of Native AI and Native DT in the SPTN network can give full play to the driving force of AI. In addition, the end-to-end uniformly controlled distributed AI system of the embodiment of the present invention makes the transmission network a part of the end-to-end intelligent system. Moreover, the end-to-end uniformly controlled AI and DT realize the softwareization and configurability on the terminal side. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0059] Figure 1 A schematic diagram of a system architecture of SPTN in the prior art;

[0060] Figure 2 A schematic diagram of a network architecture of a SPTN based on digital twins according to an embodiment of the present invention;

[0061] Figure 3 A schematic diagram of the structure of a control plane provided by an embodiment of the present invention;

[0062] Figure 4 A schematic diagram of the structure of a management plane provided in an embodiment of the present invention;

[0063] Figure 5 A flow chart of a bandwidth control method according to an embodiment of the present invention;

[0064] Figure 6 Another flow chart of the bandwidth control method according to an embodiment of the present invention;

[0065] Figure 7 A schematic diagram of another structure of a control plane provided in an embodiment of the present invention;

[0066] Figure 8A schematic diagram of another structure of a management plane provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0068] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. "And / or" in the specification and claims represents at least one of the connected objects.

[0069] The following description provides examples and does not limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the functions and arrangements of the elements discussed without departing from the spirit and scope of the present disclosure. Various examples may appropriately omit, replace, or add various procedures or components. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0070] In the research of 6G network, endogenous intelligence and digital twins have become the core features of 6G network. 6G network is considered to be a network with endogenous intelligence (Native AI). In the 6G network with endogenous intelligence, AI is no longer just the optimization of wireless resources of wireless network, but an intelligent system (AI System) integrated with core network, transmission network and wireless access.

[0071] The 6G digital twin system (DT) provides a basic operating environment for 6G endogenous intelligence, which provides basic support for AI-related processing and computing, and simplifies the operating load and complexity of the physical network. In other words, the 6G digital twin system and the endogenous intelligence system together constitute a series of online operations such as operation, maintenance, and application-oriented control computing for the physical network, becoming the brain of the physical network, commanding each part of the physical network to complete the service capabilities required by the protocol or operator.

[0072] At present, AI in 4G / 5G networks is external AI, and only focuses on the control of the core network and base stations, and the measurement and reporting of terminals, without taking into account the intelligent drive of the transmission network between the core network and base stations and between the base station CU and DU. As part of end-to-end endogenous AI, AI drive of the transmission network is the key path to realize end-to-end AI network. No matter how intelligent the core network and base stations are, if the transmission network becomes a bottleneck, end-to-end intelligent control cannot be achieved.

[0073] In response to the above problems, the embodiment of the present invention proposes an intelligent transmission bandwidth control solution based on digital twins. In this solution, by introducing digital twins and AI functional bodies in the control plane and management plane of the SPTN architecture, intelligent control of the transmission network is realized according to the transmission requirements of the core network and base stations, and high QoS data transmission can be achieved.

[0074] In order to realize an end-to-end intelligent network of core network, transmission network, base station and terminal, the embodiment of the present invention constructs an end-to-end AI control system, and the transmission network controls the transmission bandwidth in a unified AI control system. By introducing AI and DT in the control plane and management plane, intelligent transmission bandwidth control is realized.

[0075] In the embodiment of the present invention, the offline and online in the online DT and offline DT have nothing to do with the traditional high / low real-time, fast / slow speed, etc., and they reflect the synchronization relationship between the corresponding functional bodies. For example, the offline DT can obtain high-real-time data within a period of time by recording and broadcasting, and then process the data to obtain the simulation result.

[0076] Distributed AI refers to the AI ​​algorithms between the Operations and Maintenance (OAM) system, the SPTN management plane and the SPTN control plane being logically different parts of a complete algorithm, or a logical constraint relationship that must be maintained in order to complete a task. Here, the OAM system is the management system that manages the core network, transmission network, base stations and terminals.

[0077] Figure 2 An intelligent SPTN network architecture based on digital twins of an embodiment of the present invention is provided. Among them, distributed AI (Distributed AI) and offline DT (Offline DT) functions are added to the SPTN management plane, which are the first AI system and the first DT system respectively. The distributed AI of the management plane is responsible for configuring and scheduling the AI ​​of the control plane, training the AI ​​model, etc. Among them, the configuration includes the configuration of the AI ​​algorithm or the AI ​​algorithm model, the configuration of the AI ​​algorithm parameters, etc. Scheduling includes functional customization of the management plane AI and the control plane AI, task allocation, or completing different steps of the AI ​​algorithm or collaboration between different AI algorithms according to different control accuracy requirements.

[0078] The distributed AI function of the control plane reports the required status parameters to the distributed AI function of the management plane. The offline DT of the management plane performs offline simulation on the two controllers (S-Controller and D-Controller) of the control plane, simulating the scale change trend, load change trend, service quality change trend, fault prediction, control collaboration between the two controllers, etc. of the transmission network, and forms a policy configuration for the online DT function body. The online DT function body reports the required status parameters to the offline DT function body.

[0079] Add distributed AI function and online DT function to the SPTN control plane, and add new functions of transmission bandwidth control and transmission QoS control.

[0080] In the inter-domain controller (S-Controller), in addition to the existing route selection function (Route Selecting), new bandwidth management functions (Bandwidth Management), QoS management functions (QoS Management), AI accelerators (AI Accelerator) and digital twin routers (DT Router) have been added. Here, the AI ​​accelerator is the functional body of distributed AI (Distributed AI), which is also referred to as the second AI system in this article; the digital twin router is an online simulation functional body (Online DT). The route selection function (Route Selecting) is specifically used to calculate the end-to-end service forwarding path. For example, first, according to the upper-level topology, the inter-domain forwarding path is calculated, and the path request of the intra-domain service is sent to the D-Controller, and finally the path is optimized and spliced ​​to form an end-to-end cross-domain forwarding path.

[0081] In addition, requirements can also be input to the S-Controller through the application (APP).

[0082] In the domain controller (D-Controller), in addition to the existing route control (Route Controlling) function, new bandwidth allocation function (Bandwidth Allocation), QoS control function (QoS Controlling), AI calculator (AI Calculator) and digital twin bandwidth scheduler (DT Bandwidth Scheduler) are added. Here, the AI ​​calculator is a distributed AI function body (Distributed AI), which is also referred to as the third AI system in this article; the digital twin bandwidth scheduler is an online simulation function body (Online DT). The route control (Route Controlling) function is specifically used to complete the path calculation within the D-Controller domain under the control of the S-Controller, and feed the calculation results upward to the S-Controller.

[0083] The following is a detailed description of each functional module in the S-Controller.

[0084] Bandwidth Management function: Dynamic inter-domain bandwidth management is performed according to the characteristics or requirements of the data carried by the transmission network. The characteristics or requirements of the data carried can be obtained in two ways or in combination: 1. Intelligent computing through AI accelerators; 2. Configuration by OAM system. When the OAM system monitors and obtains the characteristics or requirements of the data or services carried by the network, it formulates the data processing or service performance indicators that each network element needs to bear, and then configures them to each network element respectively. For the SPTN network, driven by the AI ​​accelerator, the characteristics of the data carried are automatically detected and combined with various status information generated during the transmission process (such as retransmission information, packet loss information, delay information, jitter information, etc.), the characteristics of the first type of data or service transmitted are generated, and the performance indicators of the data processing or service configured by the management plane are combined to generate bandwidth management commands for the first type of data or service, including the transmission bandwidth that needs to be allocated to each node on the entire routing path, the shortest and maximum delays on the entire routing path, the range of jitter and other indicators. The above bandwidth management command can be sent to the bandwidth allocation function of the domain controller to control the bandwidth allocation function to complete the bandwidth allocation function within the domain.

[0085] QoS management function: According to the characteristics or requirements of the data carried by the transmission network, QoS assurance management of dynamic inter-domain transmission data is performed. The QoS requirements of the carried data are obtained in the following two ways or by combining these two ways: 1) prediction through the AI ​​accelerator; 2) configuration by the OAM system. The OAM system monitors and obtains the QoS indicators of the data or services carried by the network during service establishment or network operation, and decomposes these QoS indicators into each network element. For the SPTN network, driven by the AI ​​accelerator, the characteristics of the carried data are intelligently detected and combined with various status information generated during the transmission process (such as retransmission information, packet loss information, delay information, jitter information, etc.), and the QoS characteristics of the second type of data or service transmitted are characterized, and combined with the data or service QoS indicators configured by the management plane, a QoS management command for the second type of data or service is generated, and sent to the QoS control function of the domain controller to control the QoS control function to complete the QoS control function in the domain to which it belongs.

[0086] AI accelerator: runs under the unified control and configuration of the management plane, and generates prediction information, policies or control commands for data transmission route selection, bandwidth management, QoS management, etc. by monitoring the data characteristics transmitted on each SPTN domain. The above prediction information, policies or control commands are sent to the route selection function (RouteSelecting) of SPTN.

[0087] Digital twin router: By synchronously obtaining the data information and the first control state carried between domains from the S-Controller, online simulation of the routing selection, bandwidth management, QoS management and other functions of the S-Controller is carried out to provide AI accelerators with AI algorithm operation, policy execution, command verification and other functional support. The digital twin router also runs under the unified control and configuration of the management plane. The above-mentioned first control state may specifically include: bandwidth allocation information of routers within the domain, information on related cooperation between routers, etc. The router includes various router entities or devices under the control of the D-Controller. Through the above-mentioned control state, the state of each intra-domain controller under the control of the inter-domain controller can be obtained.

[0088] The following is a detailed description of each functional module in the D-Controller.

[0089] Bandwidth Allocation Function: Under the control of the Bandwidth Management function of the S-Controller, the bandwidth allocation function within the domain is completed. The AI ​​Calculator is used to allocate bandwidth within the domain, and the AI ​​algorithm is called to generate the global optimal or local optimal bandwidth allocation plan. The bandwidth allocation strategy is formulated in advance through the AI ​​algorithm to reduce the calculation load during real-time bandwidth allocation, and to achieve fast, real-time, and flexible bandwidth allocation. At the same time, the allocation results and the bandwidth information within the domain after each allocation are reported to the Bandwidth Management function of the S-Controller.

[0090] QoS Controlling Function: Under the control of the QoS Management function of the S-Controller, complete the QoS control within the domain. Through the AI ​​Calculator, perform QoS guarantee control within the domain, call the AI ​​algorithm, generate the global optimal or local optimal QoS guarantee solution, and use the AI ​​algorithm to achieve on-demand QoS guarantee and maximize the efficiency of transmission bandwidth utilization. At the same time, report the status information of QoS guarantee within the domain (for example: the ratio and reason for failure to complete QoS guarantee, the data type with the best QoS guarantee, the transmission bandwidth utilization rate, the data type with the worst QoS guarantee, and the rationality analysis information of various QoS indicators) to the QoS Management (QoSManagement) function of the S-Controller.

[0091] AI calculator: runs under the unified control and configuration of the management plane. Under the call of bandwidth allocation and QoS control functions, a QoS guarantee scheme is generated for bandwidth or QoS requirements of various types of data. The above QoS guarantee scheme can be configured on the D-Controller, and this type of QoS guarantee scheme can be used when the same type of data is transmitted.

[0092] In an embodiment of the present invention, the digital twin router obtains the data information and the second control state carried in the domain from the D-Controller synchronously, simulates the routing control, bandwidth allocation, QoS control and other functions of the D-Controller online, and provides the AI ​​calculator with AI algorithm operation, policy execution, command verification and other functional support. The digital twin router also runs under the unified control and configuration of the management plane. The second control state here is the control information generated by the D-Controller itself for each characteristic business or data, which is used to draw the router when performing digital twinning.

[0093] In the embodiment of the present invention, the newly added functions of the S-Controller and the D-Controller use the existing north-south interface interaction mechanism. The control command configuration process of the bandwidth management and QoS management in the S-Controller and the bandwidth allocation and QoS control functions in the D-Controller is added to the north-south interface. At the same time, the function of the bandwidth allocation function and the QoS control function in the D-Controller reporting information to the bandwidth management and QoS management function in the S-Controller is added.

[0094] The newly added distributed AI and online DT functions in the S-Controller and D-Controller can interact with the AI ​​and offline DT of the management plane.

[0095] In the embodiment of the present invention, each online simulation function body can have a corresponding distributed AI function body, which has the capability of one or more AI algorithms. These distributed AI algorithms provide AI capability drive to each online function body under the control or management of the distributed AI algorithm of the OAM system. Here, AI capability drive refers to strengthening related functions under the AI ​​algorithm, or realizing one or more online functions based on the AI ​​algorithm.

[0096] based on Figure 2 The embodiment of the present invention further provides a management plane of SPTN, such as Figure 3 As shown, the management plane includes a first DT system 32 and / or a first AI system 31, wherein:

[0097] The first DT system 32 is used to receive the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of the SPTN, perform offline simulation on the inter-domain controller and the intra-domain controller, generate a policy and configure it to the digital twin router and the digital twin bandwidth scheduler;

[0098] The first AI system 31 is used to receive the second state parameter sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN, train AI models for the second AI system and the third AI system, and configure and schedule the second AI system and the third AI system.

[0099] Here, the first AI system is a part of the distributed AI function running on the management plane, and the distributed AI function also includes the second AI system running on the inter-domain controller, the third AI system running on the intra-domain controller, the fourth AI system running on the core network, the fifth AI system running on the transmission network, and the sixth AI system running on the OAM system of the base station and the terminal. The first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

[0100] Optionally, the first DT system is also used to simulate the scale change trend, load change trend, server quality change trend, fault prediction, and control collaboration between the intra-domain controller and the inter-domain controller of the transmission network when performing offline simulation on the inter-domain controller and the intra-domain controller, and generate strategies and configure them to the digital twin router and digital twin bandwidth scheduler.

[0101] based on Figure 2 The embodiment of the present invention further provides a control plane of SPTN, such as Figure 4 As shown, the control plane includes an inter-domain controller 41 and an intra-domain controller 42, and the inter-domain controller includes a digital twin router 411 and / or a second AI system 412; the intra-domain controller 42 includes a digital twin bandwidth scheduler 421 and / or a third AI system 422.

[0102] Here, the digital twin router 411 is used to synchronously obtain the first data information and the first control state carried by the inter-domain controller, and send the first control state to the first DT system of the management plane of the SPTN; receive the first policy sent by the first DT system of the management plane of the SPTN, and perform online simulation of the function of the inter-domain controller according to the first policy, and provide functional support for AI algorithm operation, policy execution, and command verification for the second AI system;

[0103] The second AI system 412 is used to receive the configuration and scheduling of the first AI system of the management plane of the SPTN, and operate under the configuration and scheduling, and generate predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN;

[0104] The digital twin bandwidth scheduler 421 is used to synchronously obtain the second data information and the second control state carried by the intra-domain controller, and send the second control state to the first DT system of the management plane of the SPTN; receive the second strategy sent by the first DT system of the management plane of the SPTN, and perform online simulation of the function of the intra-domain controller according to the second strategy, and provide functional support for AI algorithm operation, strategy execution, and command verification for the third AI system;

[0105] The third AI system 422 is used to receive the configuration and scheduling of the first AI system of the management plane of the SPTN, and operate under the configuration and scheduling to generate a QoS guarantee solution for bandwidth or QoS requirements.

[0106] Here, the second AI system is the part of the distributed AI function running on the inter-domain controller, the third AI system is the part of the distributed AI function running on the intra-domain controller, the first AI system is the part of the distributed AI function running on the management plane, the distributed AI function also includes a fourth AI system running on the core network, a fifth AI system running on the transmission network, and a sixth AI system running on the OAM system of the base station and the terminal. The first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

[0107] Preferably, the inter-domain controller further comprises: a bandwidth management function for performing dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network;

[0108] The intra-domain controller further comprises: a bandwidth allocation function, which is used to execute the bandwidth allocation function within the domain under the control of the bandwidth management function.

[0109] Preferably, the bandwidth management function is specifically used to detect the characteristics of data carried by the transmission network under the drive of the second AI system and combine the status information generated during the transmission process to generate the characteristics of the transmitted data, and combine the data processing configured by the management plane or the performance index of the service to generate a bandwidth management command for the data and send it to the bandwidth allocation function;

[0110] The bandwidth allocation function is specifically configured to receive a bandwidth management command for the data sent by the bandwidth management function, and according to the bandwidth management command, call the third AI system to perform bandwidth allocation within the domain to generate a globally optimal or locally optimal bandwidth allocation plan, or call the third AI system to formulate a bandwidth allocation strategy in advance, and report the bandwidth allocation plan or bandwidth allocation strategy to the bandwidth management function;

[0111] The third AI system is further configured to generate a bandwidth allocation plan or a bandwidth allocation strategy according to the calling of the bandwidth allocation function.

[0112] Preferably, the inter-domain controller further includes: a QoS management function for performing QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network;

[0113] The intra-domain controller also includes: a QoS control function, which is used to perform QoS control within the domain under the control of the QoS management function.

[0114] Preferably, the QoS management function is specifically used to detect the data characteristics carried by the transmission network under the drive of the second AI system and generate a QoS feature characterization of the transmitted data in combination with the status information generated during the transmission process, and generate a QoS management command for the data in combination with the data or service QoS indicators configured by the management plane and send it to the QoS control function;

[0115] The QoS control function is specifically configured to receive a QoS management command sent by the QoS management function, and according to the QoS management command, call the third AI system to perform intra-domain QoS guarantee control to generate a globally optimal or locally optimal QoS guarantee solution, or call the third AI system to implement an on-demand QoS guarantee solution, and report the status information of the intra-domain QoS guarantee to the QoS management function;

[0116] The third AI system is further used to generate a QoS guarantee solution according to the call of the QoS control function.

[0117] Preferably, the characteristics or requirements of the data carried by the transmission network are predicted by the first AI system or configured by the OAM system.

[0118] From the above, it can be seen that the embodiment of the present invention provides an SPTN architecture for endogenous AI (Native AI) to realize the capability of endogenous AI driving. In addition, it also realizes the endogenous DT function to realize the driving of the SPTN network by online simulation. In the embodiment of the present invention, the deep combination of Native AI and Native DT in the SPTN network can give full play to the driving force of AI. In addition, the end-to-end uniformly controlled distributed AI system of the embodiment of the present invention makes the transmission network a part of the end-to-end intelligent system. Moreover, the end-to-end uniformly controlled AI and DT realize the softwareization and configurability on the terminal side.

[0119] based on Figure 2 The embodiment of the present invention further provides a bandwidth control method of SPTN, which is executed by the above management plane, such as Figure 5 As shown, the method specifically includes:

[0120] Step 51, the first DT system of the management plane of SPTN receives the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of SPTN, performs offline simulation on the inter-domain controller and the intra-domain controller, generates a policy and configures it to the digital twin router and the digital twin bandwidth scheduler;

[0121] Step 52: The first AI system of the management plane of the SPTN receives the second state parameter sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN, trains AI models for the second AI system and the third AI system, and configures and schedules the second AI system and the third AI system.

[0122] Optionally, the above method also includes: when the first DT system performs offline simulation on the inter-domain controller and the intra-domain controller, it simulates the scale change trend, load change trend, server quality change trend, fault prediction, and control collaboration between the intra-domain controller and the inter-domain controller of the transmission network, and generates strategies and configures them to the digital twin router and digital twin bandwidth scheduler.

[0123] based on Figure 2 The embodiment of the present invention further provides a bandwidth control method of SPTN, which is executed by the above control plane, such as Figure 6 As shown, the method specifically includes:

[0124] Step 61, the digital twin router synchronously obtains the first data information and the first control state carried by the inter-domain controller, and sends the first control state to the first DT system of the management plane of the SPTN; receives the first policy sent by the first DT system of the management plane of the SPTN, and performs online simulation of the function of the inter-domain controller according to the first policy, and provides functional support for AI algorithm operation, policy execution, and command verification for the second AI system;

[0125] Step 62, the second AI system receives the configuration and scheduling of the first AI system of the management plane of the SPTN, and operates under the configuration and scheduling, and generates predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN;

[0126] Step 63, the digital twin bandwidth scheduler synchronously obtains the second data information and the second control state carried by the intra-domain controller, and sends the second control state to the first DT system of the management plane of SPTN; receives the second strategy sent by the first DT system of the management plane of SPTN, and performs online simulation of the function of the intra-domain controller according to the second strategy, and provides functional support for AI algorithm operation, strategy execution, and command verification for the third AI system;

[0127] Step 64: The third AI system receives the configuration and scheduling of the first AI system of the management plane of the SPTN, and operates under the configuration and scheduling to generate a QoS guarantee solution for bandwidth or QoS requirements.

[0128] Optionally, the inter-domain controller also includes a bandwidth management function; the intra-domain controller also includes a bandwidth allocation function; the method also includes: the bandwidth management function performs dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network; the bandwidth allocation function executes the intra-domain bandwidth allocation function under the control of the bandwidth management function.

[0129] Optionally, the bandwidth management function performs dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network, specifically including: the bandwidth management function, under the drive of the second AI system, detects the characteristics of the data carried by the transmission network and combines the status information generated during the transmission process to generate the characteristics of the transmitted data, and combines the data processing configured by the management plane or the performance indicators of the service to generate a bandwidth management command for the data and send it to the bandwidth allocation function;

[0130] The bandwidth allocation function executes the bandwidth allocation function within the domain under the control of the bandwidth management function, specifically including: the bandwidth allocation function receives a bandwidth management command for the data sent by the bandwidth management function, and calls the third AI system to perform bandwidth allocation within the domain according to the bandwidth management command to generate a globally optimal or locally optimal bandwidth allocation plan, or calls the third AI system to formulate a bandwidth allocation strategy in advance, and reports the bandwidth allocation plan or bandwidth allocation strategy to the bandwidth management function;

[0131] The third AI system generates a bandwidth allocation plan or a bandwidth allocation strategy according to the calling of the bandwidth allocation function.

[0132] Optionally, the above method further includes: the inter-domain controller further includes a QoS management function, and the intra-domain controller further includes a QoS control function; the method further includes:

[0133] The QoS management function performs QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network;

[0134] The QoS control function performs QoS control within the domain under the control of the QoS management function.

[0135] Optionally, the QoS management function performs QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network, specifically including: the QoS management function, driven by the second AI system, detects the characteristics of the data carried by the transmission network and combines the status information generated during the transmission process to generate a QoS feature characterization of the transmitted data, and combines the data or service QoS indicators configured by the management plane to generate a QoS management command for the data and send it to the QoS control function;

[0136] The QoS control function performs QoS control within the domain under the control of the QoS management function, specifically including: the QoS control function receives a QoS management command sent by the QoS management function, and calls the third AI system to perform QoS guarantee control within the domain according to the QoS management command to generate a global optimal or local optimal QoS guarantee solution, or calls the third AI system to implement an on-demand QoS guarantee solution, and reports the status information of the QoS guarantee within the domain to the QoS management function;

[0137] The third AI system is further used to generate a QoS guarantee solution according to the call of the QoS control function.

[0138] Optionally, characteristics or requirements of the data carried by the transmission network are predicted by the first AI system or configured by the OAM system.

[0139] Please refer to Figure 7 , a structural diagram of a management plane of an SPTN provided in an embodiment of the present invention, the management plane includes: a processor 701, a transceiver 702, a memory 703, a user interface 704 and a bus interface.

[0140] In the embodiment of the present invention, the management plane further includes: a program stored in the memory 703 and executable on the processor 701 .

[0141] When the processor 701 executes the program, the following steps are implemented:

[0142] Receive, through the first DT system of the management plane of SPTN, the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of SPTN, perform offline simulation on the inter-domain controller and the intra-domain controller, generate a policy and configure it to the digital twin router and the digital twin bandwidth scheduler;

[0143] Through the first AI system of the management plane of the SPTN, the second state parameter sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN is received, AI models are trained for the second AI system and the third AI system, and the second AI system and the third AI system are configured and scheduled.

[0144] exist Figure 7 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 701 and various circuits of memory represented by memory 703 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 702 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different user devices, the user interface 704 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0145] The processor 701 is responsible for managing the bus architecture and general processing, and the memory 703 can store data used by the processor 701 when performing operations.

[0146] It should be noted that the device in this embodiment is the same as the above Figure 5The device corresponding to the method shown, the implementation methods in the above embodiments are all applicable to the embodiments of the device, and can also achieve the same technical effect. In the device, the transceiver 702 and the memory 703, as well as the transceiver 702 and the processor 701 can be connected through the bus interface communication, the function of the processor 701 can also be implemented by the transceiver 702, and the function of the transceiver 702 can also be implemented by the processor 701. It should be noted that the above device provided by the embodiment of the present invention can implement all the method steps implemented by the above method embodiment, and can achieve the same technical effect, and the parts and beneficial effects that are the same as the method embodiment in this embodiment will not be specifically repeated here.

[0147] In some embodiments of the present invention, a computer-readable storage medium is further provided, on which a program is stored, and when the program is executed by a processor, the following steps are implemented:

[0148] Receive, through the first DT system of the management plane of SPTN, the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of SPTN, perform offline simulation on the inter-domain controller and the intra-domain controller, generate a policy and configure it to the digital twin router and the digital twin bandwidth scheduler;

[0149] Through the first AI system of the management plane of the SPTN, the second state parameter sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN is received, AI models are trained for the second AI system and the third AI system, and the second AI system and the third AI system are configured and scheduled.

[0150] When the program is executed by the processor, all implementation methods of the bandwidth control method applied to the management plane side can be implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0151] Please refer to Figure 8 The embodiment of the present invention provides a schematic diagram of the structure of the control plane of SPTN, including: a processor 801, a transceiver 802, a memory 803 and a bus interface, wherein:

[0152] In the embodiment of the present invention, the core network further includes: a program stored in the memory 803 and executable on the processor 801, wherein the program implements the following steps when executed by the processor 801:

[0153] Synchronously obtain the first data information and the first control state carried by the inter-domain controller through the digital twin router, and send the first control state to the first DT system of the management plane of the SPTN; receive the first strategy sent by the first DT system of the management plane of the SPTN, perform online simulation on the function of the inter-domain controller according to the first strategy, and provide functional support for AI algorithm operation, strategy execution, and command verification for the second AI system;

[0154] Receive the configuration and scheduling of the first AI system of the management plane of the SPTN through the second AI system, and operate under the configuration and scheduling, and generate predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN;

[0155] The digital twin bandwidth scheduler synchronously obtains the second data information and the second control state carried by the intra-domain controller, and sends the second control state to the first DT system of the management plane of the SPTN; receives the second strategy sent by the first DT system of the management plane of the SPTN, and performs online simulation of the function of the intra-domain controller according to the second strategy, and provides functional support for AI algorithm operation, strategy execution, and command verification for the third AI system;

[0156] The configuration and scheduling of the first AI system of the management plane of the SPTN is received through the third AI system, and the configuration and scheduling are operated under the third AI system to generate a QoS guarantee solution for bandwidth or QoS requirements.

[0157] exist Figure 8 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 801 and memory represented by memory 803. The bus architecture may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 802 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium.

[0158] The processor 801 is responsible for managing the bus architecture and general processing, and the memory 803 can store data used by the processor 801 when performing operations.

[0159] It should be noted that the terminal in this embodiment is the same as the above Figure 6The device corresponding to the method shown, the implementation methods in the above embodiments are all applicable to the embodiments of the terminal, and can also achieve the same technical effect. In the device, the transceiver 802 and the memory 803, as well as the transceiver 802 and the processor 801 can be connected through the bus interface communication, the function of the processor 801 can also be implemented by the transceiver 802, and the function of the transceiver 802 can also be implemented by the processor 801. It should be noted that the above device provided by the embodiment of the present invention can implement all the method steps implemented by the above method embodiment, and can achieve the same technical effect, and the parts and beneficial effects that are the same as the method embodiment in this embodiment will not be specifically repeated here.

[0160] In some embodiments of the present invention, a computer-readable storage medium is further provided, on which a program is stored, and when the program is executed by a processor, the following steps are implemented:

[0161] Synchronously obtain the first data information and the first control state carried by the inter-domain controller through the digital twin router, and send the first control state to the first DT system of the management plane of the SPTN; receive the first strategy sent by the first DT system of the management plane of the SPTN, perform online simulation on the function of the inter-domain controller according to the first strategy, and provide functional support for AI algorithm operation, strategy execution, and command verification for the second AI system;

[0162] Receive the configuration and scheduling of the first AI system of the management plane of the SPTN through the second AI system, and operate under the configuration and scheduling, and generate predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN;

[0163] The digital twin bandwidth scheduler synchronously obtains the second data information and the second control state carried by the intra-domain controller, and sends the second control state to the first DT system of the management plane of the SPTN; receives the second strategy sent by the first DT system of the management plane of the SPTN, and performs online simulation of the function of the intra-domain controller according to the second strategy, and provides functional support for AI algorithm operation, strategy execution, and command verification for the third AI system;

[0164] The configuration and scheduling of the first AI system of the management plane of the SPTN is received through the third AI system, and the configuration and scheduling are operated under the third AI system to generate a QoS guarantee solution for bandwidth or QoS requirements.

[0165] When the program is executed by a processor, it can implement all the implementation methods of the bandwidth control method of the software-defined packet transport network applied to the OAM system and achieve the same technical effect. To avoid repetition, it will not be described here.

[0166] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0168] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0170] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0171] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0172] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A management plane system for a software defined packet transport network (SPTN), characterized in that: Including the first artificial intelligence AI system and the first digital twin DT system; The first DT system is used to receive the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of the SPTN, perform offline simulation on the inter-domain controller and the intra-domain controller, generate a policy and configure it to the digital twin router and the digital twin bandwidth scheduler; The first AI system is used to receive second state parameters sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN, train AI models for the second AI system and the third AI system, and configure and schedule the second AI system and the third AI system.

2. The management plane system according to claim 1, characterized in that: The first AI system is a part of the distributed AI function running on the management plane system, and the distributed AI function also includes the second AI system running on the inter-domain controller, the third AI system running on the intra-domain controller, a fourth AI system running on the core network, a fifth AI system running on the transmission network, and a sixth AI system running on the OAM system of the base station and the terminal. The first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

3. The management plane system according to claim 1, characterized in that: The first DT system is also used to simulate the scale change trend, load change trend, server quality change trend, fault prediction, and control collaboration between the intra-domain controller and the inter-domain controller of the transmission network when performing offline simulation on the inter-domain controller and the intra-domain controller, and generate strategies and configure them to the digital twin router and digital twin bandwidth scheduler.

4. A control plane system of an SPTN, comprising an inter-domain controller and an intra-domain controller, characterized in that: The inter-domain controller includes a digital twin router and a second AI system; the intra-domain controller includes a digital twin bandwidth scheduler and a third AI system; The digital twin router is used to synchronously obtain the first data information and the first control state carried by the inter-domain controller, and send the first control state to the first DT system of the management plane system of the SPTN; Receive a first policy sent by a first DT system of the management plane system of the SPTN, perform online simulation on the function of the inter-domain controller according to the first policy, and provide functional support for AI algorithm operation, policy execution, and command verification for the second AI system; The second AI system is used to receive the configuration and scheduling of the first AI system of the management plane system of the SPTN, and operate under the configuration and scheduling, and generate predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN; The digital twin bandwidth scheduler is used to synchronously obtain the second data information and the second control state carried by the intra-domain controller, and send the second control state to the first DT system of the management plane system of the SPTN; Receive a second policy sent by the first DT system of the management plane system of the SPTN, perform online simulation on the function of the controller within the domain according to the second policy, and provide functional support for AI algorithm operation, policy execution, and command verification for the third AI system; The third AI system is used to receive the configuration and scheduling of the first AI system of the management plane system of the SPTN, and operate under the configuration and scheduling to generate a QoS guarantee solution for bandwidth or QoS requirements.

5. The control plane system according to claim 4, characterized in that The second AI system is the part of the distributed AI function running on the inter-domain controller, the third AI system is the part of the distributed AI function running on the intra-domain controller, the first AI system is the part of the distributed AI function running on the management plane system, the distributed AI function also includes a fourth AI system running on the core network, a fifth AI system running on the transmission network, and a sixth AI system running on the OAM system of the base station and the terminal, and the first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

6. The control plane system according to claim 4, characterized in that The inter-domain controller also includes: a bandwidth management function for performing dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network; The intra-domain controller further comprises: a bandwidth allocation function, which is used to execute the bandwidth allocation function within the domain under the control of the bandwidth management function.

7. The control plane system of claim 6, wherein: The bandwidth management function is specifically used to detect the characteristics of data carried by the transmission network under the drive of the second AI system and combine the status information generated during the transmission process to generate the characteristics of the transmitted data, and combine the data processing configured by the management plane system or the performance indicators of the service to generate a bandwidth management command for the data and send it to the bandwidth allocation function; The bandwidth allocation function is specifically configured to receive a bandwidth management command for the data sent by the bandwidth management function, and according to the bandwidth management command, call the third AI system to perform bandwidth allocation within the domain to generate a globally optimal or locally optimal bandwidth allocation plan, or call the third AI system to formulate a bandwidth allocation strategy in advance, and report the bandwidth allocation plan or bandwidth allocation strategy to the bandwidth management function; The third AI system is further configured to generate a bandwidth allocation plan or a bandwidth allocation strategy according to the calling of the bandwidth allocation function.

8. The control plane system of claim 4, wherein: The inter-domain controller also includes: a QoS management function for performing QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network; The intra-domain controller also includes: a QoS control function, which is used to perform QoS control within the domain under the control of the QoS management function.

9. The control plane system of claim 8, wherein: The QoS management function is specifically used to detect the data characteristics carried by the transmission network under the drive of the second AI system and generate a QoS feature characterization of the transmitted data in combination with the status information generated during the transmission process, and generate a QoS management command for the data in combination with the data configured by the management plane system or the service QoS indicator and send it to the QoS control function; The QoS control function is specifically configured to receive a QoS management command sent by the QoS management function, and according to the QoS management command, call the third AI system to perform intra-domain QoS guarantee control to generate a globally optimal or locally optimal QoS guarantee solution, or call the third AI system to implement an on-demand QoS guarantee solution, and report the status information of the intra-domain QoS guarantee to the QoS management function; The third AI system is further used to generate a QoS guarantee solution according to the call of the QoS control function.

10. The control plane system according to claim 6 or 8, characterized in that: The characteristics or requirements of the data carried by the transmission network are predicted by the first AI system or configured by the OAM system.

11. A bandwidth control method for SPTN, characterized in that: The first DT system of the management plane of SPTN receives the first state parameter sent by the digital twin router of the inter-domain controller and the digital twin bandwidth scheduler of the intra-domain controller of the control plane of SPTN, performs offline simulation on the inter-domain controller and the intra-domain controller, generates a policy and configures it to the digital twin router and the digital twin bandwidth scheduler; The first AI system of the management plane of the SPTN receives the second state parameter sent by the second AI system of the inter-domain controller and the third AI system of the intra-domain controller of the control plane of the SPTN, trains AI models for the second AI system and the third AI system, and configures and schedules the second AI system and the third AI system.

12. The method according to claim 11, characterized in that The first AI system is a part of the distributed AI function running on the management plane, and the distributed AI function also includes the second AI system running on the inter-domain controller, the third AI system running on the intra-domain controller, a fourth AI system running on the core network, a fifth AI system running on the transmission network, and a sixth AI system running on the OAM system of the base station and the terminal. The first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

13. The method according to claim 11, characterized in that Also includes: When the first DT system performs offline simulation on the inter-domain controller and the intra-domain controller, it simulates the scale change trend, load change trend, server quality change trend, fault prediction, and control collaboration between the intra-domain controller and the inter-domain controller of the transmission network, and generates strategies and configures them to the digital twin router and digital twin bandwidth scheduler.

14. A bandwidth control method for SPTN, wherein the control plane of the SPTN includes an inter-domain controller and an intra-domain controller, characterized in that: The inter-domain controller includes a digital twin router and a second AI system; the intra-domain controller includes a digital twin bandwidth scheduler and a third AI system; the method includes: The digital twin router synchronously obtains the first data information and the first control state carried by the inter-domain controller, and sends the first control state to the first DT system of the management plane of the SPTN; receives the first policy sent by the first DT system of the management plane of the SPTN, performs online simulation of the function of the inter-domain controller according to the first policy, and provides functional support for AI algorithm operation, policy execution, and command verification for the second AI system; The second AI system receives the configuration and scheduling of the first AI system of the management plane of the SPTN, and operates under the configuration and scheduling, and generates predictions, policies or control commands for routing selection, bandwidth management and QoS management of data transmission by monitoring the characteristics of data transmitted on each domain of the SPTN; The digital twin bandwidth scheduler synchronously obtains the second data information and the second control state carried by the intra-domain controller, and sends the second control state to the first DT system of the management plane of SPTN; receives the second strategy sent by the first DT system of the management plane of SPTN, and performs online simulation of the function of the intra-domain controller according to the second strategy, and provides functional support for AI algorithm operation, strategy execution, and command verification for the third AI system; The third AI system receives the configuration and scheduling of the first AI system of the management plane of the SPTN, and operates under the configuration and scheduling to generate a QoS guarantee solution for bandwidth or QoS requirements.

15. The method according to claim 14, characterized in that The second AI system is the part of the distributed AI function running on the inter-domain controller, the third AI system is the part of the distributed AI function running on the intra-domain controller, the first AI system is the part of the distributed AI function running on the management plane, the distributed AI function also includes a fourth AI system running on the core network, a fifth AI system running on the transmission network, and a sixth AI system running on the OAM system of the base station and the terminal, and the first AI system, the second AI system, the third AI system, the fourth AI system, the fifth AI system and the sixth AI system jointly execute a predetermined AI algorithm or a predetermined task.

16. The method according to claim 14, characterized in that The inter-domain controller further includes a bandwidth management function; the intra-domain controller further includes a bandwidth allocation function; the method further includes: The bandwidth management function performs dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network; The bandwidth allocation function performs bandwidth allocation function within the domain under the control of the bandwidth management function.

17. The method according to claim 16, characterized in that The bandwidth management function performs dynamic inter-domain bandwidth management according to the characteristics or requirements of the data carried by the transmission network, specifically including: the bandwidth management function, driven by the second AI system, detects the characteristics of the data carried by the transmission network and combines the status information generated during the transmission process to generate the characteristics of the transmitted data, and combines the data processing configured by the management plane or the performance indicators of the service to generate a bandwidth management command for the data and send it to the bandwidth allocation function; The bandwidth allocation function executes the bandwidth allocation function within the domain under the control of the bandwidth management function, specifically including: the bandwidth allocation function receives a bandwidth management command for the data sent by the bandwidth management function, and calls the third AI system to perform bandwidth allocation within the domain according to the bandwidth management command to generate a globally optimal or locally optimal bandwidth allocation plan, or calls the third AI system to formulate a bandwidth allocation strategy in advance, and reports the bandwidth allocation plan or bandwidth allocation strategy to the bandwidth management function; The third AI system generates a bandwidth allocation plan or a bandwidth allocation strategy according to the calling of the bandwidth allocation function.

18. The method of claim 14, wherein: Also includes: The inter-domain controller further includes a QoS management function, and the intra-domain controller further includes a QoS control function; the method further includes: The QoS management function performs QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network; The QoS control function performs QoS control within the domain under the control of the QoS management function.

19. The method according to claim 18, characterized in that The QoS management function performs QoS assurance management of dynamic inter-domain transmission data according to the characteristics or requirements of the data carried by the transmission network, specifically including: the QoS management function, driven by the second AI system, detects the characteristics of the data carried by the transmission network and combines the status information generated during the transmission process to generate a QoS feature characterization of the transmitted data, and combines the data or service QoS indicators configured by the management plane to generate a QoS management command for the data and send it to the QoS control function; The QoS control function performs QoS control within the domain under the control of the QoS management function, specifically including: the QoS control function receives a QoS management command sent by the QoS management function, and calls the third AI system to perform QoS guarantee control within the domain according to the QoS management command to generate a global optimal or local optimal QoS guarantee solution, or calls the third AI system to implement an on-demand QoS guarantee solution, and reports the status information of the QoS guarantee within the domain to the QoS management function; The third AI system is further used to generate a QoS guarantee solution according to the call of the QoS control function.

20. The method according to claim 16 or 18, characterized in that The characteristics or requirements of the data carried by the transmission network are predicted by the first AI system or configured by the OAM system.

21. A management plane system of SPTN, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method according to any one of claims 11 to 13 are implemented.

22. A control plane system of SPTN, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method according to any one of claims 14 to 20 are implemented.

23. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 11 to 20 are implemented.

Images