6G network intelligent collaborative dynamic flow identifier distribution method and system

Abstract

The invention discloses a 6G network intelligent collaborative dynamic flow identifier distribution method and system, belongs to the technical field of mobile communication, and aims to solve the technical problem of how to realize intelligent collaborative dynamic flow identifier distribution. Comprising the following steps: customizing a flow identification feature dimension through a management layer; an identification template and an identification strategy are self-defined through the management layer, an identification template instance is created, and the identification strategy and the identification template instance are issued to the decision-making layer; the method comprises the following steps: collecting network situation data through a decision layer, selecting related data from the network situation data based on a selected flow identifier feature dimension to carry out network overall evaluation to obtain a network evaluation result, reading each part field of an identifier from an identifier template instance based on the network evaluation result and an identifier strategy, dynamically generating a flow unique identifier, and carrying out flow overall evaluation on the flow unique identifier. Issuing the generated flow identifier to an execution layer; the flow identifier is analyzed through the execution layer, mapping from the identifier to the physical resource is realized, and resource configuration is dynamically adjusted.

Description

Technical Field

[0001] The present invention relates to the field of mobile communication technologies, and specifically to a method and system for dynamically allocating flow identifiers for intelligent collaboration in a 6G network. Background Art

[0002] With the rapid development of 6G communication technologies, the ubiquitousness of network computing power has become an inevitable trend. However, how to efficiently manage flows in a complex network environment and achieve dynamic scheduling and optimal allocation of resources has become a major challenge currently faced. Traditional network traffic management methods often lack sufficient flexibility and intelligence, and it is difficult to meet the diverse and dynamic service requirements in the future. Therefore, there is an urgent need for a new type of flow identifier management method to address the challenges brought about by the ubiquitousness of 6G network computing power.

[0003] How to achieve intelligent collaborative dynamic flow identifier allocation is a technical problem that needs to be solved. Summary of the Invention

[0004] The technical task of the present invention is to address the above deficiencies and provide a method and system for dynamically allocating flow identifiers for intelligent collaboration in a 6G network to solve the technical problem of how to achieve intelligent collaborative dynamic flow identifier allocation.

[0005] In a first aspect, a method for dynamically allocating flow identifiers for intelligent collaboration in a 6G network according to the present invention is applied between a management layer, a decision-making layer, and an execution layer, and includes the following steps:

[0006] Customize flow identifier feature dimensions through the management layer, where the flow identifier feature dimensions include delay sensitivity, computing power demand type, and security level to construct an identifier template;

[0007] Customize the identifier template and identifier policy through the management layer, select appropriate fields from the identifier template according to the actual application scenario and the selected flow identifier feature dimensions, and create an identifier template instance by assigning values to the fields, and send the identifier policy and the identifier template instance to the decision-making layer;

[0008] Collect network situation data through the decision-making layer, select relevant data from the network situation data based on the selected flow identifier feature dimensions for overall network evaluation to obtain a network evaluation result, read each part field of the identifier from the identifier template instance based on the network evaluation result and the identifier policy, dynamically generate a flow unique identifier, and send the generated flow identifier to the execution layer, where the network situation data includes node load and link quality;

[0009] Parse the flow identifier through the execution layer and implement the mapping from the identifier to physical resources to dynamically adjust the resource configuration.

[0010] Preferably, the flow identifier includes a fixed part, a mandatory variable-length part, and a custom field part;

[0011] The fixed part has a fixed coding length and is used to explain the basic fields of the flow identifier, including two parts, namely the identifier classification and the template coding;

[0012] The mandatory variable-length part includes two parts, namely the template instance coding and the user capacity. The template instance coding selects an appropriate bit length according to the number of template instances in the actual application scenario, and the user capacity selects an appropriate bit length according to the user capacity in the actual application scenario;

[0013] The custom field part is understood as the field coding of the custom part of the flow identifier template.

[0014] Preferably, the management layer provides an API interface for users to customize the flow identifier template, supporting users to customize the flow identifier through the API interface.

[0015] Preferably, there are multiple routing optimization algorithms based on deep reinforcement learning configured in the decision-making layer. Based on the network evaluation results and the identifier policy, the identifier is read from the identifier template instance through the path optimization algorithm and the identifier is dynamically allocated for the flow.

[0016] In a second aspect, a dynamic flow identifier allocation system for 6G network intelligent collaboration of the present invention includes a management layer, a decision-making layer, and an execution layer, and is used to implement dynamic flow identifier allocation through a dynamic flow identifier allocation method according to any one of the first aspect;

[0017] The management layer is used to support users to customize the flow identifier feature dimensions. The flow identifier feature dimensions include delay sensitivity, computing power demand type, and security level to construct an identifier template, which is used to support users to customize the identifier template and the identifier policy. According to the actual application scenario and the selected flow identifier feature dimensions, the appropriate fields are selected from the identifier template, and the fields are assigned values to create an identifier template instance, and the identifier policy and the identifier template instance are sent to the decision-making layer;

[0018] The decision-making layer is used to collect network situation data, select relevant data from the network situation data based on the selected flow identifier feature dimensions for overall network evaluation to obtain network evaluation results, read each part of the identifier fields from the identifier template instance based on the network evaluation results and the identifier policy, dynamically generate a unique flow identifier, and send the generated flow identifier to the execution layer, where the network situation data includes node load and link quality;

[0019] The execution layer is used to parse the flow identifier and implement the mapping from the identifier to physical resources, and dynamically adjust the resource configuration.

[0020] Preferably, the flow identifier includes a fixed part, a mandatory variable-length part, and a custom field part;

[0021] The fixed part has a fixed coding length and is used to interpret the basic fields of the flow identifier, including two parts, namely the identifier classification and the template coding;

[0022] The mandatory variable-length part includes two parts, namely the template instance coding and the user capacity. The template instance coding selects an appropriate bit length according to the number of template instances in the actual application scenario, and the user capacity selects an appropriate bit length according to the user capacity in the actual application scenario;

[0023] The custom field part is understood as the field coding of the custom part of the flow identifier template.

[0024] Preferably, the management layer provides an API interface for users to customize the flow identifier template, supporting users to customize the flow identifier through the API interface.

[0025] Preferably, there are multiple routing optimization algorithms based on deep reinforcement learning configured in the decision-making layer. Based on the network evaluation results and the identification strategy, the identifier is read from the identifier template instance through the path optimization algorithm and dynamically assigned to the flow.

[0026] The method and system for dynamically allocating flow identifiers for 6G network intelligent collaboration of the present invention have the following advantages: By implementing intelligent management among different levels (execution layer, decision-making layer, and management layer) of the network, allowing users to customize the flow identifier template, and flexibly configuring the identifiers and transmission paths of different data flows according to these templates, thereby improving the network resource utilization efficiency and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] The present invention will be further described below with reference to the drawings.

[0029] Figure 1 It is a flowchart of a method for dynamically allocating flow identifiers for 6G network intelligent collaboration in Embodiment 1;

[0030] Figure 2 It is a schematic diagram of the flow identifier coding structure in a method for dynamically allocating flow identifiers for 6G network intelligent collaboration in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and be able to implement it. However, the illustrated embodiments are not intended to limit the present invention. Without conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0032] The embodiment of the present invention provides a method and system for dynamically allocating flow identifiers for 6G network intelligent collaboration, which is used to solve the technical problem of how to achieve dynamic allocation of flow identifiers for intelligent collaboration.

[0033] Embodiment 1:

[0034] A method for dynamically allocating flow identifiers for 6G network intelligent collaboration according to the present invention is applied between the management layer, the decision-making layer, and the execution layer, and includes the following four steps.

[0035] Step S100: Customize the flow identifier feature dimensions through the management layer. The flow identifier feature dimensions include delay sensitivity, computing power demand type, and security level to construct an identifier template;

[0036] Step S200: Customize the identifier template and identifier policy through the management layer. According to the actual application scenario and the selected flow identifier feature dimensions, select the appropriate fields from the identifier template, and assign values to the fields to create an identifier template instance. Send the identifier policy and the identifier template instance to the decision-making layer;

[0037] Step S300: Collect network situation data through the decision-making layer. Based on the selected flow identifier feature dimensions, select relevant data from the network situation data for overall network evaluation to obtain a network evaluation result. Based on the network evaluation result and the identifier policy, read each part of the fields from the identifier template instance, dynamically generate a unique flow identifier, and send the generated flow identifier to the execution layer, where the network situation data includes node load and link quality;

[0038] Step S400: Parse the flow identifier through the execution layer, and implement the mapping from the identifier to physical resources, and dynamically adjust the resource configuration.

[0039] As Figure 2 shown, in this embodiment, the flow identifier includes a fixed part, a mandatory variable-length part, and a custom field part. The fixed part has a fixed coding length and is used to interpret the basic fields of the flow identifier, including two parts, namely, identifier classification (such as industry classification, 0x1 = communication industry, 0x2 = industrial control) and template coding; the mandatory variable-length part includes two parts, namely, template instance coding and user capacity. The template instance coding selects an appropriate bit length according to the number of template instances in the actual application scenario, and the user capacity selects an appropriate bit length according to the user capacity in the actual application scenario; the custom field part is understood as the field coding of the custom part of the flow identifier template.

[0040] In this embodiment, the management layer provides an API interface for users to customize the flow identifier template, supporting users to customize the flow identifier through the API interface.

[0041] In this embodiment, multiple routing optimization algorithms based on deep reinforcement learning are configured in the decision-making layer. Based on the network evaluation results and identification policies, the identifiers are read from the identifier template instances through the path optimization algorithm and dynamically assigned to the flows.

[0042] The method of this embodiment dynamically generates flow identifiers through user-defined flow templates and template instances, combines network situation data, and distributes them to the execution layer for resource configuration adjustment.

[0043] Embodiment 2:

[0044] A dynamic flow identifier allocation system for intelligent collaboration in a 6G network according to the present invention includes a management layer, a decision-making layer, and an execution layer, and realizes dynamic flow identifier allocation through the method disclosed in Embodiment 1.

[0045] The management layer is used to support users to customize the flow identifier feature dimensions. The flow identifier feature dimensions include delay sensitivity, computing power demand type, and security level to construct an identifier template, support users to customize the identifier template and identification policies, select appropriate fields from the identifier template according to the actual application scenario and the selected flow identifier feature dimensions, and assign values to the fields to create an identifier template instance, and send the identification policy and the identifier template instance to the decision-making layer.

[0046] The decision-making layer is used to collect network situation data, select relevant data from the network situation data based on the selected flow identifier feature dimensions for overall network evaluation to obtain network evaluation results, read each part of the identifier fields from the identifier template instance based on the network evaluation results and identification policies, dynamically generate a flow unique identifier, and send the generated flow identifier to the execution layer, where the network situation data includes node load and link quality.

[0047] The execution layer is used to parse the flow identifier and implement the mapping from the identifier to physical resources, and dynamically adjust the resource configuration.

[0048] The flow identifier includes a fixed part, a mandatory variable-length part, and a custom field part. The fixed part has a fixed coding length and is used to interpret the basic fields of the flow identifier, including two parts, namely identifier classification and template coding; the mandatory variable-length part includes two parts, namely template instance coding and user capacity. The template instance coding selects an appropriate bit length according to the number of template instances in the actual application scenario, and the user capacity selects an appropriate bit length according to the user capacity in the actual application scenario; the custom field part is understood as the field coding of the custom part of the flow identifier template.

[0049] In this embodiment, the management layer provides an API interface for users to customize the flow identification template, supporting users to customize the flow identification through the API interface.

[0050] In this embodiment, multiple routing optimization algorithms based on deep reinforcement learning are configured in the decision-making layer. Based on the network evaluation results and identification policies, the identification is read from the identification template instance through the path optimization algorithm and dynamically assigned to the flow.

[0051] The system of this embodiment is applicable to the dynamic scheduling of multi-modal computing power resources in the network slicing scenario, integrating network function virtualization (NFV), mobile edge computing (MEC) and artificial intelligence network control technology, aiming to improve the resource utilization efficiency and intelligent management level of the 6G network.

[0052] The above has introduced in detail the method and system for dynamic flow identification allocation of 6G network intelligent collaboration. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A 6G network intelligent collaborative dynamic flow identifier allocation method, characterized in that: Applied between management, decision-making and execution levels, it includes the following steps: Customize the flow identification feature dimensions at the management level. The flow identification feature dimensions include latency sensitivity, computing power requirement type, and security level to build identification templates. Through the management layer, you can customize the identification template and identification strategy, select the appropriate fields from the identification template according to the actual application scenario and the selected flow identification feature dimension, assign values ​​to the fields, create identification template instances, and send the identification strategy and identification template instances to the decision-making layer; The decision layer collects network situation data, selects relevant data from the network situation data based on the selected flow identification feature dimension to perform overall network evaluation, obtains network evaluation results, reads the identification fields from the identification template instance based on the network evaluation results and identification strategy, dynamically generates a unique flow identification, and sends the generated flow identification to the execution layer, where the network situation data includes node load and link quality; The execution layer parses the flow identifier and implements the mapping from the identifier to the physical resource, thus dynamically adjusting the resource configuration.

2. The method for dynamic flow identification allocation for 6G network intelligent collaboration according to claim 1 is characterized in that: The flow identifier includes a fixed part, a mandatory variable-length part, and a custom field part; The fixed part has a fixed encoding length and is used to interpret the basic fields of the flow identifier. It includes two parts: identifier classification and template encoding. The mandatory variable length part includes two parts, namely, template instance coding and user capacity. The template instance coding selects an appropriate bit length according to the number of template instances in the actual application scenario, and the user capacity selects an appropriate bit length according to the user capacity in the actual application scenario. The custom field part is understood as the field code of the custom part of the flow identification template.

3. The method for dynamic flow identification allocation for 6G network intelligent collaboration according to claim 1 is characterized in that: The management layer provides an API interface for users to customize flow identifier templates, supporting users to customize flow identifiers through the API interface.

4. The method for dynamic flow identification allocation for 6G network intelligent collaboration according to claim 1 is characterized in that: The decision layer is configured with a variety of deep reinforcement learning-based routing optimization algorithms. Based on network evaluation results and identification strategies, the path optimization algorithm reads the identification from the identification template instance and dynamically assigns the identification to the flow.

5. A 6G network intelligent collaborative dynamic flow identification allocation system, characterized in that: It includes a management layer, a decision layer and an execution layer, and is used to implement dynamic flow identifier allocation through a 6G network intelligent collaborative dynamic flow identifier allocation method as described in any one of claims 1 to 4; The management layer is used to support user-defined flow identification feature dimensions. The flow identification feature dimensions include latency sensitivity, computing power requirement type, and security level to build identification templates. It is used to support user-defined identification templates and identification policies. According to the actual application scenario and the selected flow identification feature dimensions, the adapted fields are selected from the identification template, and identification template instances are created for field assignments. The identification policies and identification template instances are sent to the decision-making layer. The decision layer is used to collect network situation data, select relevant data from the network situation data based on the selected flow identification feature dimension to perform overall network evaluation, obtain network evaluation results, read the identification fields from the identification template instance based on the network evaluation results and identification strategy, dynamically generate a unique flow identification, and send the generated flow identification to the execution layer, where the network situation data includes node load and link quality; The execution layer is used to parse the flow identifier, implement the mapping from the identifier to the physical resource, and dynamically adjust the resource configuration.

6. The 6G network intelligent collaborative dynamic flow identification allocation system according to claim 5 is characterized in that: The flow identifier includes a fixed part, a mandatory variable-length part, and a custom field part; The fixed part has a fixed encoding length and is used to interpret the basic fields of the flow identifier. It includes two parts: identifier classification and template encoding. The mandatory variable length part includes two parts, namely, template instance coding and user capacity. The template instance coding selects an appropriate bit length according to the number of template instances in the actual application scenario, and the user capacity selects an appropriate bit length according to the user capacity in the actual application scenario. The custom field part is understood as the field code of the custom part of the flow identification template.

7. The 6G network intelligent collaborative dynamic flow identifier allocation system according to claim 5 is characterized in that: The management layer provides an API interface for users to customize flow identifier templates, supporting users to customize flow identifiers through the API interface.

8. The 6G network intelligent collaborative dynamic flow identification allocation system according to claim 5 is characterized in that: The decision layer is configured with a variety of deep reinforcement learning-based routing optimization algorithms. Based on network evaluation results and identification strategies, the path optimization algorithm reads the identification from the identification template instance and dynamically assigns the identification to the flow.

Images