6g network management computing power session method and system based on 6g network sensing and computing integration

Abstract

The application discloses a 6G all-in-one network management computing power session method and system, and belongs to the technical field of mobile communication.The technical problem to be solved by the application is how to realize flexible scheduling and on-demand allocation of computing power and network fusion resources in a 6G all-in-one network environment without changing network devices, and to build a mobile network environment supporting the computing power as a service mode for users.The technical scheme adopted is that the method is to deploy an algorithm network fusion perception network element, an algorithm network fusion control scheduling network element and an algorithm network fusion service arrangement network element on the core network side, so that the improved core network has the functions of communication, perception and computing power integration;and the computing power application request index is analyzed and identified, the computing power service arrangement is performed, the computing power and network Qos configuration mapping is performed, the algorithm network fusion resources are decided and scheduled, and the distributed collaborative computing task is issued, so that the computing power session creation is completed, so as to meet the different computing power requirements of mobile terminals.

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, specifically to a method and system for managing computing power sessions based on a 6G integrated network of communication, sensing, and computing. Background Technology

[0002] Currently, 5G network session management primarily focuses on ensuring network service quality, guaranteeing reliable, low-latency, and high-bandwidth data transmission. However, when facing emerging AI computing power applications, 5G network session management suffers from limitations such as its inability to directly perceive the computing power needs of the terminal side and its inability to simultaneously allocate computing power and network resources to the terminal side. This is mainly because the initial design and core functions of 5G networks focus more on enhancing communication capabilities than directly supporting the allocation and management of computing resources.

[0003] In 6G networks, the deep integration of communication, sensing, and computing capabilities to form an integrated communication, sensing, and computing network is one of the important directions for 6G development. However, in the design and development of 6G networks, although the deep integration of communication, sensing, and computing capabilities is emphasized, there is a lack of specific protocols, standards, and mature technical solutions for the specific implementation of session and computing power application task binding strategies, as well as session management computing power and network integration indicators.

[0004] Therefore, in a 6G integrated network environment, without changing the network equipment, how to achieve flexible scheduling and on-demand allocation of computing power and network resources, and build a mobile network environment that supports the computing power as a service model for users, is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The technical objective of this invention is to provide a method and system for managing computing power sessions based on a 6G integrated network of communication, sensing, and computing, in order to solve the problem of how to achieve flexible scheduling and on-demand allocation of computing power and network resources in a 6G integrated network environment without changing network equipment, and to build a mobile network environment that supports the computing power as a service model for users.

[0006] The technical objective of this invention is achieved as follows: a method for managing computing power sessions based on a 6G integrated network of communication, sensing, and computing. This method involves deploying integrated computing and network sensing network elements, integrated computing and network control and scheduling network elements, and integrated computing and network service orchestration network elements on the core network side, enabling the improved core network to possess integrated communication, sensing, and computing power functions. Furthermore, it completes the creation of computing power sessions by parsing and identifying computing power application request indicators, computing power service orchestration, computing power and network QoS configuration mapping, and making decisions and scheduling integrated computing and network resources, and issuing distributed collaborative computing tasks, thereby meeting the different computing power needs of mobile terminals.

[0007] As a preferred option, the computing-network fusion sensing network element detects and collects information on the quality status and computing resources of the surrounding network in real time, and constructs a computing power sensing model and a network sensing model.

[0008] The network element for service orchestration in the computing-network convergence is used to identify service requests and execute service orchestration strategies;

[0009] The computing-network convergence control and scheduling network element is used to convert policies into specific parameters and execute resource scheduling.

[0010] More ideally, after the network-computer convergence sensing element is activated, it collects network quality status information and computing power resource information of surrounding devices in real time, and constructs corresponding network sensing models and computing power sensing models based on network quality sensing information and computing power resource information respectively, forming a dynamic computing power and network resource pool; among them, network quality status information includes bandwidth, latency, jitter, packet loss rate and load information; computing power resource information includes computing power device type, computing power value, computing power storage performance and size information.

[0011] Ideally, the decision-making and scheduling computing network should integrate resources as follows:

[0012] After the mobile terminal accesses the improved core network, it initiates a computing power session creation request to the service interface of the computing network convergence service orchestration network element via the HTTP2 protocol, carrying the computing service type and the required network quality requirements and inference computing power requirements fields.

[0013] More specifically, the parsing and identification of computing power application request metrics and the mapping of computing power and network QoS configurations are as follows:

[0014] The network elements for computing-network convergence services parse and identify the service metrics of computing power session requests;

[0015] The total network demand metric for business computing power is calculated from the parsed and identified results using data modeling, as shown in the following formula:

[0016]

[0017] Where E represents the total network demand metric for business computing power; f c This indicates the computing power requirements of the business; f n This represents the computing power requirements of the business in terms of the network; α and β are the weight ratio coefficients corresponding to computing and network respectively;

[0018] By using a table lookup matching method, the QoS (Quality of Service) model index with the highest similarity to the total business computing power network demand metric is retrieved from the local configuration, thereby transforming the business demand indicators into a computing power QoS configuration list and a network QoS configuration list. The computing power QoS configuration list includes computing collaboration methods, number of resource nodes, computing priority, and load scheduling; the network QoS configuration list includes network service categories, maximum uplink and downlink rates, minimum guaranteed rates, and preemption and reservation mechanisms.

[0019] More optimally, the specific orchestration of computing power services is as follows:

[0020] When a mobile terminal accesses the improved core network, the mobile terminal initiates a computing power session based on AI computing power applications. The computing network convergence service orchestration network element selects a service orchestration strategy based on the network quality requirements and computing power requirements requested by the computing power application, and in combination with the results of information collected by the computing network convergence sensing network element. Using data modeling methods, it comprehensively considers network status, computing power node load, and service priority to achieve full utilization and optimized configuration of computing power resources.

[0021] Distributed collaborative computing tasks are generated according to the business orchestration strategy, and dedicated computing channels are created for the session. Specific task information is sent to the selected computing power nodes, thereby completing the allocation of computing resources and opening up data transmission paths, enabling end-user applications to obtain good computing network convergence services through computing power sessions.

[0022] More optimally, the establishment of computing power sessions for distributing distributed collaborative computing tasks is as follows:

[0023] After receiving the network QoS configuration, the computing network convergence control and scheduling network element converts the QoS configuration list into network parameters and sends them to the policy control network element through the existing N5 interface of the core network. This creates a computing bearer data channel designed specifically for computing power sessions between the terminal and the base station, and between the base station and the core network.

[0024] After receiving the computing power QoS configuration list, the computing power QoS configuration network element converts the configuration in the list into computing power parameters, establishes computing tasks for the computing power session, selects the computing collaboration mode, computing nodes, candidate computing nodes, and computing path information, and then sends the specific task information to the selected computing nodes to pre-allocate computing power and network resources and establish computing data plane transmission tunnels; among them, computing nodes include master control nodes and slave node clusters.

[0025] More preferably, after the mobile terminal receives the response from the network element of the computing network convergence service orchestration and successfully creates the session, it obtains the master control node (usually the terminal itself) from the response information. The master control node starts the computing task and notifies the slave nodes to start the task collaborative computing.

[0026] A 6G integrated network management computing power session system based on communication, sensing and computing is provided. The system deploys integrated computing and network sensing network elements, integrated computing and network control and scheduling network elements, and integrated computing and network service orchestration network elements on the core network side, so that the improved core network has integrated communication, sensing and computing power functions.

[0027] Among them, the computing-network fusion sensing network element is used to detect and collect information on the quality status and computing resources of the surrounding network in real time, and to build a computing power sensing model and a network sensing model.

[0028] The network element for service orchestration in the computing-network convergence is used to identify service requests and execute service orchestration strategies;

[0029] The computing-network convergence control and scheduling network element is used to convert policies into specific parameters and execute resource scheduling.

[0030] Preferably, the system also includes a main control node, a wireless base station, and a computing server; the specific working process of the system is as follows:

[0031] (0) The main control node, wireless base station and computing power server respectively register computing power with the computing network fusion sensing network element;

[0032] (1) The master control node initiates a computing power session creation request to the computing network convergence service orchestration network element;

[0033] (2) The network element of the computing and network convergence service orchestration classifies the service request indicators and maps the indicators to the computing power QoS configuration list and the network QoS configuration list.

[0034] (3) The computing network convergence service orchestration network element sends the service orchestration results to the computing network convergence control and scheduling network element;

[0035] (4) The network-computing convergence control and scheduling network element converts the network QoS configuration into network parameters and creates computing bearer channels for sessions on the core network side;

[0036] (5) The computing network integration control and scheduling network element distributes specific tasks to the computing server, wireless base station and main control node; among which, the specific task information includes task type, coordination method, node information and transmission tunnel information;

[0037] (6) The network element responds to the successful creation of the computing power session, obtains the main control node in the response information, starts the computing task, and notifies the wireless base station and computing power server to start the task collaborative computing.

[0038] The 6G integrated network management computing power session method and system based on sensing and computing in this invention have the following advantages:

[0039] (I) This invention is applied to computing task type session requests initiated by mobile terminals based on 6G networks. It solves the problem that in the 6G integrated network environment, when faced with computing task session requests initiated by the terminal side, the flexible scheduling and on-demand allocation of computing power and network resources can be achieved by adding self-developed software and protocols without changing the network equipment, thereby building a mobile network environment that supports the "Computing as a Service" (CaaS) mode for users.

[0040] (ii) This invention solves the problem of allocating and scheduling computing power and network resources for mobile sessions to computing services in a 6G interconnected computing network environment. It fully utilizes the effective computing power resources of edge-end-cloud three-level devices to form collaborative distributed computing. It not only provides a stable network transmission environment with high bandwidth, reliability, and low latency, but also greatly reduces the computing time of services through the optimized configuration of computing power resources.

[0041] (III) This invention is applied to the 6G integrated network architecture of communication, sensing and computing. While retaining the original network architecture and functions, it adds computing-network converged sensing network elements, computing-network converged control and scheduling network elements, and computing-network converged service orchestration network elements to the core network side. This enables the network to not only be responsible for communication, but also to have the ability to perceive resources and coordinate computing and network in a unified manner. On this basis, the session management function adds processes such as parsing and identifying computing power application request indicators, computing power and network QoS configuration mapping, computing power service orchestration, decision-making and scheduling of computing-network converged resources, and issuing distributed collaborative computing tasks. This transforms ordinary sessions into computing power sessions to meet the different computing power needs of terminals.

[0042] (iv) This invention integrates network quality requirements and computing power requirements into the session request metrics. The QoS configuration mapping also associates computing power and network metrics together. Furthermore, in subsequent orchestration and scheduling, computing power and network resources are used together to enable sessions to obtain computing power resource support. Attached Figure Description

[0043] The invention will be further described below with reference to the accompanying drawings.

[0044] Appendix Figure 1 This is a diagram of the 6G integrated sensing and computing network architecture.

[0045] Appendix Figure 2 This is a flowchart illustrating the process of a 6G-based integrated network management computing power session system.

[0046] Appendix Figure 3 This is a schematic diagram of the QoS model for the convergence of computing and network. Detailed Implementation

[0047] The following detailed description of the 6G integrated network management computing power session method and system based on sensing and computing is provided with reference to the accompanying drawings and specific embodiments.

[0048] Example 1:

[0049] As attached Figure 1 As shown, this embodiment provides a method for managing computing power sessions based on a 6G integrated network of sensing, computing, and computing. This method deploys converged computing and network sensing network elements, converged computing and network control and scheduling network elements, and converged computing and network service orchestration network elements on the core network side, enabling the improved core network to possess integrated communication, sensing, and computing power functions. It completes the creation of computing power sessions by parsing and identifying computing power application request indicators, computing power service orchestration, computing power and network QoS configuration mapping, and making decisions and scheduling converged computing and network resources, and issuing distributed collaborative computing tasks, thereby meeting the different computing power needs of mobile terminals. When a mobile terminal accesses the improved core network, the mobile terminal initiates an AI computing power application... The computing power session creation process involves network elements that orchestrate computing and network convergence services selecting a service orchestration strategy based on the network quality and computing power requirements of the computing application request, combined with the information collected by the network elements that are sensing the computing and network convergence. Using data modeling methods, the system comprehensively considers network status, computing node load, and service priorities to fully utilize and optimize computing resources. Finally, distributed collaborative computing tasks are generated according to the service orchestration strategy, and a dedicated computing channel is created for the session. Specific task information is then distributed to the selected computing nodes, thereby completing the allocation of computing resources and establishing data transmission paths. This enables end-user applications to obtain excellent computing and network convergence services through the computing power session.

[0050] In this embodiment, the computing-network fusion sensing network element detects and collects information on the surrounding network quality and computing resources in real time, and constructs a computing power sensing model and a network sensing model.

[0051] In this embodiment, the computing-network convergence service orchestration network element is used to identify service requests and to orchestrate and execute service strategies.

[0052] In this embodiment, the computing-network convergence control and scheduling network element is used to convert the strategy into specific parameters and execute resource scheduling.

[0053] The specific steps in this embodiment are as follows:

[0054] S1. After the network-computer interface convergence sensing element is activated, it collects network quality status information and computing power resource information of surrounding devices in real time, and constructs corresponding network sensing models and computing power sensing models based on the network quality sensing information and computing power resource information respectively, forming a dynamic computing power and network resource pool. Among them, the network quality status information includes bandwidth, latency, jitter, packet loss rate and load information; the computing power resource information includes computing power device type, computing power value, computing power storage performance and size information.

[0055] S2. After the mobile terminal accesses the improved core network, it initiates a computing power session creation request to the service interface of the computing network convergence service orchestration network element through the HTTP2 protocol, carrying the computing service type and the required network quality requirements and inference computing power requirements fields.

[0056] S3, the network element for converged computing and network services, parses and identifies the service metrics of computing power session requests. The results of this parsing and identification are then used to calculate the total service computing power network demand metric using data modeling, as shown in the following formula:

[0057]

[0058] Where E represents the total network demand metric for business computing power; f c This indicates the computing power requirements of the business; f n This represents the computing power requirements of the business in terms of network; α and β are the weighting coefficients corresponding to computing and network; then, through table lookup matching, the QoS (Quality of Service) model index with the highest similarity to the total business computing power network demand metric is retrieved from the local configuration, as shown in the appendix. Figure 3 As shown, business requirement indicators are transformed into a computing power QoS configuration list and a network QoS configuration list; the computing power QoS configuration list includes computing collaboration methods, number of resource nodes, computing priority and load scheduling; the network QoS configuration list includes network service categories, maximum uplink and downlink rates, minimum guaranteed rate and preemption and reservation mechanism.

[0059] S4. After receiving the network QoS configuration, the computing network convergence control and scheduling network element converts the QoS configuration list into network parameters and sends them to the policy control network element through the existing N5 interface of the core network. This creates a computing bearer data channel designed specifically for computing power sessions between the terminal and the base station, and between the base station and the core network.

[0060] After receiving the computing power QoS configuration list, the S5 network convergence control and scheduling network element converts the configuration in the computing power QoS configuration list into computing power parameters, establishes computing tasks for the computing power session, selects the computing collaboration mode, computing nodes, candidate computing nodes, and computing path information, and then sends the specific task information to the selected computing nodes to pre-allocate computing power and network resources and establish computing data plane transmission tunnels; among them, computing nodes include master control nodes and slave node clusters;

[0061] S6. After the mobile terminal receives the response from the network element of the computing network convergence service orchestration and successfully creates the session, it obtains the master control node (usually the terminal itself) from the response information. The master control node starts the computing task and notifies the slave nodes to start the task collaborative computing.

[0062] Example 2:

[0063] This embodiment provides a 6G integrated network management computing power session system based on communication, sensing and computing. The system deploys integrated computing and network sensing network elements, integrated computing and network control and scheduling network elements, and integrated computing and network service orchestration network elements on the core network side, so that the improved core network has integrated communication, sensing and computing power functions.

[0064] Among them, the computing-network fusion sensing network element is used to detect and collect information on the quality status and computing resources of the surrounding network in real time, and to build a computing power sensing model and a network sensing model.

[0065] The network element for service orchestration in the computing-network convergence is used to identify service requests and execute service orchestration strategies;

[0066] The computing-network convergence control and scheduling network element is used to convert policies into specific parameters and execute resource scheduling.

[0067] As attached Figure 2 As shown, the specific working process of this system is as follows:

[0068] (0) Mobile terminal devices, wireless base stations and computing power servers respectively register computing power with the computing network convergence sensing network element;

[0069] (1) The mobile terminal device initiates a computing power session creation request to the computing network convergence service orchestration network element;

[0070] (2) The network element of the computing and network convergence service orchestration classifies the service request indicators and maps the indicators to the computing power QoS configuration list and the network QoS configuration list.

[0071] (3) The computing network convergence service orchestration network element sends the service orchestration results to the computing network convergence control and scheduling network element;

[0072] (4) The network-computing convergence control and scheduling network element converts the network QoS configuration into network parameters and creates computing bearer channels for sessions on the core network side;

[0073] (5) The network element of the computing network integration control and scheduling will distribute specific tasks to the computing server, wireless base station and mobile terminal device; among them, the specific task information includes task type, coordination method, node information and transmission tunnel information;

[0074] (6) The network element responds to the successful creation of the computing power session, obtains the main control node in the response information, starts the computing task, and notifies the wireless base station and computing power server to start the task collaborative computing.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A 6G-based integrated network management computing power session method based on sensing algorithm, characterized by The method is to deploy an algorithm network fusion perception network element, an algorithm network fusion control scheduling network element and an algorithm network fusion service arrangement network element on the core network side, so that the improved core network has the integration function of communication, perception and computing power; And by analyzing and identifying the computing power application request index, the computing power service arrangement, the computing power and network Qos configuration mapping, and the decision and scheduling of algorithm network fusion resources, the distributed collaborative computing task is issued to complete the computing power session creation to meet the different computing power needs of mobile terminals; Among them, the algorithm network fusion perception network element detects and collects the surrounding network quality status and computing power resource information in real time and constructs the computing power perception model and the network perception model; The algorithm network fusion service arrangement network element is used to identify service requests and execute service arrangement strategies; The algorithm network fusion control scheduling network element is used to convert the strategy into specific parameters and execute resource scheduling; After the algorithm network fusion perception network element is started, the network quality status information and computing power resource information of the surrounding equipment are collected in real time, and the network perception model and the computing power perception model are constructed based on the network quality perception information and the computing power resource information respectively, forming a dynamic computing power and network resource pool; wherein the network quality status information includes broadband, delay, jitter, packet loss rate and load information; the computing power resource information includes computing power device type, computing power metric value, computing power storage performance and size information; The decision and scheduling of algorithm network fusion resources are as follows: After the mobile terminal accesses the improved core network, it initiates a computing power session creation request to the service interface of the algorithm network fusion service arrangement network element through the HTTP2 protocol, carrying the computing service type and the required network quality requirement and inference computing power requirement fields; The analysis and identification of computing power application request index and computing power and network Qos configuration mapping are as follows: The algorithm network fusion service arrangement network element analyzes and identifies the service index of the computing power session request; The result of the analysis and identification is calculated into the total service computing power network demand metric value through data modeling, and the formula is as follows: ; where E represents the total service computing power network demand metric value; represents the computing power demand of the service in terms of computing; represents the computing power demand of the service in terms of network; and are the weight proportion coefficients corresponding to computing and network, respectively. Through the table lookup matching method, the Qos model index with the highest similarity of the total service computing power network demand metric value is retrieved from the local configuration, so as to convert the service demand index into the computing power Qos configuration list and the network Qos configuration list; wherein the computing power Qos configuration list includes the computing collaborative mode, the resource node number, the computing priority and the load scheduling; the network Qos configuration list includes the network service category, the maximum uplink and downlink rate, the minimum guaranteed rate and the preemption reservation mechanism; The computing power service arrangement is as follows: When the mobile terminal accesses the improved core network, the mobile terminal initiates a computing power session creation based on the AI computing power application, the algorithm network fusion service arrangement network element selects a service arrangement strategy according to the network quality requirement and the computing power requirement of the computing power application request and the result of the information collected by the algorithm network fusion perception network element, and uses the data modeling method to comprehensively consider the network state, the computing power node load and the service priority, so as to realize the full utilization and optimized configuration of computing power resources; Distributed collaborative computing tasks are generated according to the business orchestration strategy, and dedicated computing channels are created for the session. Specific task information is sent to the selected computing power nodes, thereby completing the allocation of computing resources and opening up data transmission paths, so that end-user applications can obtain good computing network integration services through computing power sessions. The specific steps for issuing distributed collaborative computing tasks and establishing computing power sessions are as follows: After receiving the network QoS configuration, the computing network convergence control and scheduling network element converts the QoS configuration list into network parameters and sends them to the policy control network element through the existing N5 interface of the core network. This creates a computing bearer data channel designed specifically for computing power sessions between the terminal and the base station, and between the base station and the core network. After receiving the computing power QoS configuration list, the computing power QoS configuration network element converts the configuration in the list into computing power parameters, establishes computing tasks for the computing power session, selects the computing collaboration mode, computing nodes, candidate computing nodes, and computing path information, and then sends the specific task information to the selected computing nodes to pre-allocate computing power and network resources and establish computing data plane transmission tunnels; among them, computing nodes include master control nodes and slave node clusters; After the mobile terminal receives a response from the network element of the computing network convergence service orchestration, indicating that the session has been successfully created, it obtains the master control node from the response information. The master control node then starts the computing task and notifies the slave nodes to start collaborative computing.

2. A 6G sense algorithm integrated network management computing power session system based on, characterized in that, This system is used to implement the 6G integrated network management computing power session method as described in claim 1; the system deploys integrated computing and network sensing network elements, integrated computing and network control and scheduling network elements, and integrated computing and network service orchestration network elements on the core network side, so that the improved core network has integrated communication, sensing and computing power functions; Among them, the computing-network fusion sensing network element is used to detect and collect information on the quality status and computing resources of the surrounding network in real time, and to build a computing power sensing model and a network sensing model. The network element for service orchestration in the computing-network convergence is used to identify service requests and execute service orchestration strategies; The computing-network convergence control and scheduling network element is used to convert policies into specific parameters and execute resource scheduling. The system works as follows: (0) Mobile terminal devices, wireless base stations and computing power servers respectively register computing power with the computing network fusion sensing network element; (1) The mobile terminal device initiates a computing power session creation request to the computing network convergence service orchestration network element; (2) The network elements of the computing and network convergence service orchestration classify the service request indicators and map the indicators to the computing power QoS configuration list and the network QoS configuration list; (3) The computing-network convergence service orchestration network element sends the service orchestration results to the computing-network convergence control and scheduling network element; (4) The network-computer convergence control and scheduling network element converts the network QoS configuration into network parameters and creates computing bearer channels for sessions on the core network side; (5) The computing network integration control and scheduling network element will distribute specific tasks to the computing server, wireless base station and mobile terminal device; among which, the specific task information includes task type, coordination method, node information and transmission tunnel information; (6) The network element responds to the successful creation of the computing power session, obtains the main control node in the response information, starts the computing task, and notifies the wireless base station and computing power server to start the task collaborative computing.

Images