Ai inference task orchestration method for radio access network, apparatus, device and storage medium

Abstract

Provided in the present disclosure are an artificial intelligence (AI) inference task orchestration method for a radio access network, an apparatus, a device and a storage medium. AI technology is introduced to an RAN side. The method comprises: receiving an AI inference task assurance policy for an AI inference model that is sent by a non-real-time wireless controller, and acquiring terminal information of at least one terminal, the AI inference task assurance policy defining an optimization objective for the radio access network and feature information of the AI inference model, and the terminal information comprising computing resource information and communication resource information; and, on the basis of the AI inference task assurance policy and the terminal information, generating an AI inference task orchestration scheme for the radio access network.

Description

AI reasoning task scheduling method, device, equipment and storage medium for wireless access network

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311733048.9 filed in China on December 15, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of wireless communication technologies, and in particular to a method, apparatus, device, and storage medium for orchestrating AI reasoning tasks in a wireless access network. Background Art

[0004] With the continuous deepening of research on the openness of computing capabilities in wireless local area networks, base stations as an edge computing platform are increasingly valued by the industry, and wireless local area networks are developing towards the integration of communication and computing. Although existing research has provided solutions for balancing accuracy and latency in device-edge computing collaboration, these studies mainly focus on edge servers and cannot be directly applied to computing collaboration between base stations and terminals. The computing resources in base stations are shared by communication processing and computing tasks, and there is a competitive relationship between the two. Therefore, when computing resources and communication bandwidth resources are limited, the Radio Access Network (RAN) side needs to perform near-real-time adaptive orchestration of multi-base station and multi-terminal tasks based on dynamically changing channel states and different information of different tasks.

[0005] The Near-Real-Time RAN Intelligent Controller (Near-RT RIC) in traditional Open Radio Access Networks (O-RAN) can collect near-real-time communication-related parameters through a standardized E2 interface to intelligently optimize system performance. However, this only collects and optimizes communication-related parameters on the RAN side and lacks unified perception and scheduling capabilities for computing and communication resources. This leads to inefficient resource allocation and collaborative computing on the RAN side, resulting in degraded system performance. Summary of the Invention

[0006] The purpose of the embodiments of the present disclosure is to provide a method for orchestrating AI reasoning tasks in a wireless access network. By introducing artificial intelligence (AI) technology on the RAN side, the method can perform near-real-time collaborative orchestration of AI reasoning tasks for computing nodes on the RAN side based on real-time communication status and computing capabilities, thereby improving the efficiency of resource allocation and collaborative computing on the RAN side, thereby enhancing system performance.

[0007] To achieve the above objectives, an embodiment of the present disclosure provides a method for orchestrating AI reasoning tasks in a wireless access network, which is applied to a near-real-time wireless controller. The method includes:

[0008] Receiving an AI reasoning task assurance policy for an AI reasoning model sent by a non-real-time wireless controller; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance policy defines an optimization goal of the wireless access network and characteristic information of the AI ​​reasoning model;

[0009] Acquire terminal information of at least one terminal; wherein the terminal information includes computing resource information and communication resource information;

[0010] Generate an AI reasoning task scheduling plan for the wireless access network based on the AI ​​reasoning task assurance strategy and the terminal information.

[0011] As an improvement to the above solution, generating an AI reasoning task scheduling scheme for a wireless access network based on the AI ​​reasoning task assurance strategy and the terminal information includes:

[0012] According to the optimization goal of the wireless access network, determining the node to be assigned and the corresponding computing node based on each terminal information, and selecting the corresponding split point and exit point from the feature information of the AI ​​reasoning model based on each terminal information; wherein the split point and the exit point are one layer of the AI ​​reasoning model;

[0013] The AI ​​reasoning task scheduling scheme is composed of the nodes to be assigned and their corresponding computing nodes, the split points and the exit points.

[0014] As an improvement to the above solution, after generating the AI ​​reasoning task scheduling scheme for the wireless access network according to the AI ​​reasoning task assurance strategy and the terminal information, the method further includes:

[0015] The AI ​​reasoning task scheduling scheme is sent to the node to be assigned and the corresponding computing node, so that the node to be assigned and the corresponding computing node complete their respective reasoning computing tasks.

[0016] As an improvement to the above solution, when the terminal is a user equipment, obtaining terminal information of at least one terminal includes:

[0017] Sending a request message to the base station where the user equipment resides, so that the base station reports the terminal information of the user equipment according to the request message; or,

[0018] The terminal information is subscribed to a base station where the user equipment resides, so that the base station reports the terminal information of the user equipment.

[0019] As an improvement to the above solution, when the terminal is a user equipment, the user equipment supports information interaction with a near real-time wireless controller; then, obtaining terminal information of at least one terminal includes:

[0020] sending a request message to the user equipment so that the user equipment reports the terminal information according to the request message; or

[0021] Subscribe the terminal information to the user equipment so that the user equipment reports the terminal information.

[0022] To achieve the above objectives, the present disclosure further provides a method for orchestrating AI reasoning tasks in a wireless access network, which is applied to a non-real-time wireless controller. The method includes:

[0023] Obtain model information of the AI ​​inference model;

[0024] Generating an AI reasoning task assurance strategy based on the model information; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance strategy defines an optimization goal of the wireless access network and characteristic information of the AI ​​reasoning model;

[0025] The AI ​​reasoning task guarantee policy is sent to a near real-time wireless controller, so that the near real-time wireless controller generates an AI reasoning task scheduling plan for the wireless access network based on the AI ​​reasoning task guarantee policy and terminal information; wherein the terminal information includes computing resource information and communication resource information.

[0026] As an improvement to the above solution, the model information includes feature information of the AI ​​reasoning model and performance guarantee parameters of the AI ​​reasoning task; wherein, the performance guarantee parameters include but are not limited to model reasoning accuracy and the number of reasoning calculations per unit time.

[0027] To achieve the above objectives, the present disclosure further provides an AI reasoning task scheduling device for a wireless access network, including:

[0028] An AI inference task assurance policy receiving module, configured to receive an AI inference task assurance policy of an AI inference model sent by a non-real-time wireless controller; wherein the AI ​​inference model is deployed in a wireless access network, and the AI ​​inference task assurance policy defines an optimization objective of the wireless access network and characteristic information of the AI ​​inference model;

[0029] A terminal information acquisition module, configured to acquire terminal information of at least one terminal; wherein the terminal information includes computing resource information and communication resource information;

[0030] An AI reasoning task scheduling scheme generation module is used to generate an AI reasoning task scheduling scheme for a wireless access network based on the AI ​​reasoning task assurance strategy and the terminal information.

[0031] To achieve the above objectives, the present disclosure further provides an AI reasoning task scheduling device for a wireless access network, including:

[0032] Model information acquisition module, used to obtain model information of AI reasoning models;

[0033] An AI reasoning task assurance strategy generation module, configured to generate an AI reasoning task assurance strategy based on the model information; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance strategy defines an optimization goal of the wireless access network and characteristic information of the AI ​​reasoning model;

[0034] An AI reasoning task guarantee policy sending module is configured to send the AI ​​reasoning task guarantee policy to a near real-time wireless controller, so that the near real-time wireless controller generates an AI reasoning task orchestration plan for the wireless access network based on the AI ​​reasoning task guarantee policy and terminal information; wherein the terminal information includes computing resource information and communication resource information.

[0035] To achieve the above-mentioned objectives, an embodiment of the present disclosure also provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the AI ​​reasoning task orchestration method for the wireless access network as described in any of the above embodiments.

[0036] To achieve the above-mentioned purpose, an embodiment of the present disclosure also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the AI ​​reasoning task orchestration method for the wireless access network as described in any of the above embodiments.

[0037] Compared with related technologies, the AI ​​reasoning task scheduling method, device, equipment and storage medium of the wireless access network disclosed in the present invention introduce artificial intelligence technology on the RAN side. First, the AI ​​reasoning task guarantee policy of the AI ​​reasoning model sent by the non-real-time wireless controller is received, and the terminal information of at least one terminal is obtained, wherein the AI ​​reasoning task guarantee policy defines the optimization goals of the wireless access network and the characteristic information of the AI ​​reasoning model, and the terminal information includes computing resource information and communication resource information; then, the AI ​​reasoning task scheduling scheme of the wireless access network is generated according to the AI ​​reasoning task guarantee policy and the terminal information. According to the real-time communication status and computing power, the computing nodes on the RAN side can perform near-real-time AI reasoning task collaborative scheduling, thereby improving the efficiency of resource allocation and collaborative computing on the RAN side, thereby improving system performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] FIG1 is a flowchart of a method for orchestrating AI reasoning tasks in a wireless access network provided by an embodiment of the present disclosure;

[0039] FIG2 is a schematic diagram of information interaction between a near real-time wireless controller and a non-real-time wireless controller provided by an embodiment of the present disclosure;

[0040] FIG3 is a flow chart of a first method for acquiring terminal information of a user equipment provided by an embodiment of the present disclosure;

[0041] FIG4 is a flow chart of a second method for acquiring terminal information of a user equipment provided by an embodiment of the present disclosure;

[0042] FIG5 is a flowchart of another method for orchestrating AI reasoning tasks in a wireless access network provided by an embodiment of the present disclosure;

[0043] FIG6 is a structural block diagram of an AI reasoning task scheduling device for a wireless access network provided by an embodiment of the present disclosure;

[0044] FIG7 is a structural block diagram of another device for orchestrating AI reasoning tasks in a wireless access network provided by an embodiment of the present disclosure;

[0045] FIG8 is a structural block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0047] With the rise of emerging applications such as extended reality (XR), autonomous driving, and industrial intelligent control, deep learning algorithms, such as image recognition, are gaining increasing attention for computationally intensive tasks. However, mobile devices have limited capabilities and cannot meet their stringent computational and latency requirements. Therefore, AI edge computing can be used to collaboratively complete computational tasks. AI edge computing can be implemented by building deep neural network models. Since the convolutional layer in a deep neural network model structure performs a dot product operation on the spatial dimensions of the input tensor to generate a feature map of the output tensor, the convolutional layer can serve as a split point in the model, allowing multiple computing nodes to collaboratively complete model inference. Furthermore, by adding branch classifiers to the model structure, inference can be exited early at the expense of accuracy, reducing resource waste. Based on early exit mechanisms and model segmentation techniques, there is currently a lot of research on collaborative inference among edge computing nodes. By selecting appropriate split and exit points for AI inference tasks, latency and inference accuracy requirements can be met within the constraints of computing resources and system bandwidth. Therefore, in the embodiments of this disclosure, AI technology is introduced on the RAN side to assist terminals in completing computational tasks.

[0048] Referring to FIG. 1 , FIG. 1 is a flowchart of a method for orchestrating AI reasoning tasks in a wireless access network provided by an embodiment of the present disclosure. The method for orchestrating AI reasoning tasks in a wireless access network is implemented by a near real-time wireless controller. The method includes:

[0049] S11, receiving the AI ​​reasoning task assurance policy of the AI ​​reasoning model sent by the non-real-time wireless controller;

[0050] S12. Acquire terminal information of at least one terminal;

[0051] S13. Generate an AI reasoning task scheduling plan for the wireless access network based on the AI ​​reasoning task assurance strategy and the terminal information.

[0052] It is worth noting that O-RAN includes a near real-time controller (Near-Real-Time RAN Intelligent Controller, Near-RT RIC) and a non-real-time controller (Non-Real-Time RAN Intelligent Controller, Non-RT RIC). The terminal includes but is not limited to a base station, a centralized unit, a distributed unit (Distributed Unit, DU) and a user equipment (User Equipment, UE). The centralized unit includes (Centralized Unit, CU), a centralized unit control plane (Centralized Unit-Control Plane, CU-CP) and a distributed unit user plane (Centralized Unit-User Plane, CU-UP). Referring to Figure 2 , Figure 2 is a schematic diagram of information interaction between a near-real-time wireless controller and a non-real-time wireless controller provided in an embodiment of the present disclosure. The non-real-time controller is connected to the near-real-time controller via an open and standardized A1 interface. The purpose of the non-real-time controller is to provide a corresponding machine learning model to support RAN intelligence, and the non-real-time controller provides the near-real-time controller with an AI inference model and data. Due to the real-time requirements in the O-RAN architecture, the near-real-time controller performs related operations by utilizing an existing AI inference model when providing corresponding functions. The AI ​​inference model can perform one or more calculations selected from fault alarm analysis, coverage optimization, parameter optimization, spectrum analysis, inter-station collaboration, mobility management, slice management, wireless positioning, and environmental perception and recognition. The near-real-time controller and the terminal exchange information through the E2 interface. In the embodiment of the present disclosure, the functions of the E2 interface and the A1 interface in the O-RAN architecture are enhanced. The AI ​​inference task assurance policy generated by the non-real-time controller based on the model information of the AI ​​inference model is sent to the near-real-time controller through the A1 interface. The E2 interface then collects real-time terminal information, and performs near-real-time AI inference task collaborative orchestration based on the terminal information and the AI ​​inference task assurance policy, thereby improving resource allocation and collaborative computing efficiency on the RAN side and enhancing system performance.

[0053] Specifically, in step S11, the non-real-time wireless controller generates the AI ​​reasoning task guarantee strategy based on the model information of the AI ​​reasoning model; wherein the model information includes feature information of the AI ​​reasoning model and performance guarantee parameters of the AI ​​reasoning task.

[0054] Exemplarily, the model information is obtained by the non-real-time wireless controller from the service management and process orchestration framework (Service Management and Orchestration, SMO), and the source of the model information in the SMO can be directly configured by the operator or obtained by interacting with external applications. When the model information is obtained through interaction with external applications, relevant interfaces or application programming interfaces (Application Programming Interface, API) can be pre-designed, and a connection with the external application can be established through an authorization and authentication mechanism to obtain the model information.

[0055] Exemplarily, the characteristic information of the AI ​​reasoning model includes the AI ​​reasoning model identifier (ID), the number of model layers, the type of each layer, the amount of output data for each layer, the computational effort for each layer, the location of the split point, the location of the exit point, the accuracy of the exit point, and the computational effort of the exit point classifier. The meaning of each characteristic information item can be found in Table 1, and specific examples can be found in Table 2.

[0056] Table 1 Characteristic parameters and their corresponding meanings

[0057] Table 2 Example of feature information of ResNet-18 model

[0058] In Table 2, "conv" represents a convolutional layer, "max pool" represents a maximum pooling layer, "avg pool" represents an average pooling layer, "fc" represents a fully connected layer, and "Exit" represents the exit point. The ResNet-18 model has four exit points: Exit 1 at layer 5, Exit 2 at layer 9, Exit 3 at layer 13, and Exit 4 at layer 18. The remaining layers can be used as split points. The exit point accuracy evaluates the classification accuracy when that layer is selected as the exit point. The accuracy values ​​shown in the table are for illustrative purposes only.

[0059] For example, the performance guarantee parameters include, but are not limited to, model inference accuracy, number of inference calculations per unit time, model inference round trip delay, and model spectrum efficiency. The meaning of each performance guarantee parameter can be found in Table 3.

[0060] Table 3 Performance guarantee parameters and their corresponding meanings

[0061] Furthermore, after receiving the model information, the non-real-time wireless controller generates an AI reasoning task assurance strategy based on the model information. The AI ​​reasoning task assurance strategy defines the optimization objectives of the wireless access network, optimizable parameters, and characteristic information of the AI ​​reasoning model. The optimization objectives of the wireless access network refer to the overall optimization objectives of the assurance strategy in the current system, such as maximizing the accuracy of model reasoning in the system and minimizing the round-trip delay of model reasoning in the system. The optimizable parameters refer to parameters that the near-real-time wireless controller can adjust to ensure the AI ​​reasoning task, such as the selection of split points and exit points of the AI ​​reasoning model. Assuming that the optimization objectives of the wireless access network are to maximize the accuracy of model reasoning in the system and minimize the round-trip delay of model reasoning in the system, after selecting the split point and the exit point, the model reasoning accuracy must be maximized and the round-trip delay of model reasoning must be minimized. This can be obtained by polling and calculating each split point and exit point.

[0062] Specifically, in step S12, the terminal information includes but is not limited to: computing resource information, communication resource information, current cell service user information, and terminal preference information for AI reasoning tasks. Among them, the computing resource information includes but is not limited to: the central processing unit (CPU) utilization of the base station and the terminal, CPU frequency, CPU core binding status, the number of remaining CPU cores, CPU / Graphics Processing Unit (GPU) / embedded neural network processor (Neural-network Processing Unit, NPU) floating point operations per second (Floating Point Operations Per Second, FLOPS), GPU memory capacity / remaining memory, GPU cuda core number / remaining core number, etc.; the communication resource information includes but is not limited to: the total uplink / downlink bandwidth of the base station, the remaining bandwidth, the number of physical resource blocks (PRB), PRB utilization, etc., and may also include the channel conditions of the terminal, the communication link delay from the base station to the neighboring station, etc. For example, the channel conditions of the terminal include the signal-to-noise ratio (SNR), the received signal strength indicator (RSI), the signal-to-noise ratio (SNR ... Indication, RSSI), etc.; the current cell service user information includes but is not limited to: user type identification (non-AI user or AI user), AI reasoning task model identification (for example: ResNet-18, Visual Geometry Group (Visual Geometry Group, VGG), etc.); the terminal's preference information for AI reasoning tasks includes but is not limited to: preference for split point selection for each AI reasoning task, etc.

[0063] It is worth noting that when the terminal is a base station or the base station where the centralized unit and the distributed unit are located, the terminal information can be sent directly by the base station to the near real-time wireless controller. When the terminal is a user device, the embodiments of the present disclosure provide two methods for obtaining the terminal information of the user device: the first method is to obtain it through the base station, and the second method is to obtain it directly through the user device. The base station described in the embodiments of the present disclosure may have various forms, such as a macro base station, a micro base station, a relay station, or an access point. The base station can be an integrated base station, or it can be a base station including a centralized unit CU and a distributed unit DU.

[0064] In a first embodiment, when the terminal is a user device, obtaining the terminal information of at least one terminal includes: sending a request message to the base station where the user device resides, so that the base station reports the terminal information of the user device according to the request message; or, subscribing to the terminal information to the base station where the user device resides, so that the base station reports the terminal information of the user device.

[0065] For example, as shown in Figure 3, the near-real-time wireless controller subscribes to or requests terminal information from the base station where the user device resides via the E2 interface. This can be periodic subscription or event-triggered reporting. Event triggers include, but are not limited to, fluctuations in base station computing power, terminal computing power, base station bandwidth, terminal power, and changes in terminal segmentation mode preferences. The base station collects air interface and terminal data from the user device as needed, aggregates it into terminal information, and reports the user device's terminal information to the near-real-time wireless controller. Furthermore, the base station also synchronously reports its own terminal information to the near-real-time wireless controller.

[0066] In a second embodiment, when the terminal is a user device, the user device supports information interaction with a near real-time wireless controller; then, obtaining terminal information of at least one terminal includes: sending a request message to the user device so that the user device reports the terminal information according to the request message; or subscribing to the terminal information to the user device so that the user device reports the terminal information.

[0067] For example, as shown in Figure 4 , the user equipment and the near-real-time wireless controller, based on existing protocol stacks, enable information exchange by enabling both parties to support corresponding interface application layer protocols. The near-real-time wireless controller then subscribes to or requests terminal information from the user equipment via the E2 interface. This can be periodic subscription or event-triggered reporting. The user equipment collects air interface and terminal data as needed, aggregates it into terminal information, and reports this terminal information to the near-real-time wireless controller. The near-real-time wireless controller synchronously sends a request message to the base station or subscribes to the base station's terminal information, prompting the base station to report its own terminal information.

[0068] Specifically, in step S13, generating an AI reasoning task scheduling scheme for a wireless access network according to the AI ​​reasoning task assurance strategy and the terminal information includes:

[0069] S131. Determine, according to the optimization goal of the wireless access network, a node to be assigned and a corresponding computing node based on each terminal information, and select, based on each terminal information, a corresponding split point and exit point from the feature information of the AI ​​reasoning model; wherein the computing node is a base station, and the split point and the exit point are one layer in the AI ​​reasoning model;

[0070] S132. The AI ​​reasoning task scheduling scheme is composed of the nodes to be assigned and their corresponding computing nodes, the split points, and the exit points.

[0071] Exemplarily, the node to be assigned is a terminal that cannot meet its own computing requirements and needs to rely on a computing node to share inference computing tasks; the computing node is a terminal that can receive inference computing tasks from the node to be assigned. After receiving terminal information sent by at least one terminal, the near-real-time wireless controller determines the node to be assigned and the computing node, and applies an optimization algorithm (such as a differential algorithm) to evaluate the computing nodes required by these nodes to be assigned, and selects split points and exit points. If it is determined according to the computing resource information that one of the nodes to be allocated requires a larger amount of computing power, more layers (i.e., the number of layers between the split point and the exit point is larger) can be allocated to this node to be allocated, otherwise fewer layers can be allocated; if it can be determined according to the communication resource information that this node to be allocated requires a computing node with a larger remaining bandwidth, computing nodes that meet the conditions are preferentially allocated as computing nodes for this node to be allocated; if at this time one of the terminal information gives an AI reasoning task model identifier, then when generating the AI ​​reasoning task scheduling plan, the corresponding AI reasoning model will be selected according to the AI ​​reasoning task model identifier to perform the reasoning task; if at this time one of the terminal information gives a split point selection preference for each AI reasoning task, then when generating the AI ​​reasoning task scheduling plan, the split point will be allocated preferentially according to the split point selection preference of this node to be allocated.

[0072] Specifically, after generating the AI ​​reasoning task scheduling scheme of the wireless access network according to the AI ​​reasoning task guarantee strategy and the terminal information, the method further includes:

[0073] S14. Send the AI ​​reasoning task scheduling plan to the node to be assigned and the corresponding computing node, so that the node to be assigned and the corresponding computing node complete their respective reasoning computing tasks.

[0074] For example, assume that the nodes to be assigned are user devices and the computing nodes are base stations. Terminal information for three user devices and two base stations is collected. The two base stations and three user devices meet the following conditions: Base station A provides communication connectivity services for user device 1, and base station B provides communication connectivity services for user devices 2 and 3. Both base stations A and B provide computing services, and the AI ​​inference model is ResNet-18 as shown in Table 2. Assuming that the orchestration plan selects appropriate computing nodes for user devices 1-3 and selects the split and exit points for the AI ​​inference task, the AI ​​inference task orchestration plan is shown in Table 4 below.

[0075] Table 4 Examples of AI reasoning task orchestration solutions

[0076] For example, using user device 1 as an example according to Table 4, the computing node selected for user device 1 is base station A. That is, base station A and user device 1 jointly complete the computation task. The split point is layer 3, and the exit point is Exit 2. Base station A then performs the computation for layers 3 through 9. Based on the selected split point, user device 1 completes the inference computations for the first few layers. After the feature map generated at the split point is transmitted to base station A, base station A completes the inference computations from layers 3 through 9, ultimately transmitting the generated results back to user device 1. Therefore, the selection of the split point and exit point determines the computational effort of the assigned node and the computing node, respectively. The choice of the exit point also determines the accuracy of the model.

[0077] Compared with related technologies, the AI ​​reasoning task scheduling method for a wireless access network disclosed in the present invention introduces artificial intelligence technology on the RAN side. First, the AI ​​reasoning task guarantee policy of the AI ​​reasoning model sent by the non-real-time wireless controller is received, and the terminal information of at least one terminal is obtained. The AI ​​reasoning task guarantee policy defines the optimization goals of the wireless access network and the characteristic information of the AI ​​reasoning model, and the terminal information includes computing resource information and communication resource information. Then, an AI reasoning task scheduling scheme for the wireless access network is generated based on the AI ​​reasoning task guarantee policy and the terminal information. By selecting computing nodes, task splitting points and exit points, near-real-time AI reasoning task collaborative scheduling can be performed for computing nodes on the RAN side based on real-time communication status and computing capabilities, thereby improving the efficiency of resource allocation and collaborative computing on the RAN side, thereby improving system performance.

[0078] Referring to FIG. 5 , FIG. 5 is a flowchart of another method for orchestrating AI reasoning tasks in a wireless access network provided by an embodiment of the present disclosure. The method for orchestrating AI reasoning tasks in a wireless access network is implemented by a non-real-time wireless controller. The method includes:

[0079] S21. Obtain model information of the AI ​​reasoning model;

[0080] S22. Generate an AI reasoning task assurance strategy based on the model information;

[0081] S23. Send the AI ​​reasoning task guarantee policy to the near real-time wireless controller, so that the near real-time wireless controller generates an AI reasoning task scheduling plan for the wireless access network according to the AI ​​reasoning task guarantee policy and terminal information.

[0082] Specifically, the model information includes characteristic information of the AI ​​reasoning model and performance guarantee parameters of the AI ​​reasoning task; wherein, the performance guarantee parameters include but are not limited to model reasoning accuracy and the number of reasoning calculations per unit time.

[0083] It is worth noting that the specific working process of the AI ​​reasoning task scheduling method for the wireless access network described in the embodiment of the present disclosure can be referred to the above embodiment and will not be repeated here.

[0084] 6 , which is a structural block diagram of an AI reasoning task scheduling device 100 for a wireless access network provided by an embodiment of the present disclosure, wherein the AI ​​reasoning task scheduling device 100 for a wireless access network includes:

[0085] An AI reasoning task assurance policy receiving module 11 is configured to receive an AI reasoning task assurance policy of an AI reasoning model sent by a non-real-time wireless controller; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance policy defines an optimization goal of the wireless access network and characteristic information of the AI ​​reasoning model;

[0086] The terminal information acquisition module 12 is configured to acquire terminal information of at least one terminal; wherein the terminal information includes computing resource information and communication resource information;

[0087] The AI ​​reasoning task scheduling scheme generating module 13 is used to generate an AI reasoning task scheduling scheme for the wireless access network according to the AI ​​reasoning task guarantee strategy and the terminal information.

[0088] Specifically, the AI ​​reasoning task scheduling scheme generation module 13 is specifically used to:

[0089] According to the optimization goal of the wireless access network, determining the node to be assigned and the corresponding computing node based on each terminal information, and selecting the corresponding split point and exit point from the feature information of the AI ​​reasoning model based on each terminal information; wherein the computing node is a base station, and the split point and the exit point are one layer of the AI ​​reasoning model;

[0090] The AI ​​reasoning task scheduling scheme is composed of the nodes to be assigned and their corresponding computing nodes, the split points and the exit points.

[0091] Specifically, the AI ​​reasoning task scheduling device 100 for the wireless access network further includes:

[0092] The AI ​​reasoning task scheduling scheme sending module is used to send the AI ​​reasoning task scheduling scheme to the to-be-assigned node and the corresponding computing node, so that the to-be-assigned node and the corresponding computing node complete their respective reasoning computing tasks.

[0093] Specifically, when the terminal is a user device, the terminal information acquisition module 12 is specifically used to: send a request message to the base station where the user device resides, so that the base station reports the terminal information of the user device according to the request message; or, subscribe to the terminal information to the base station where the user device resides, so that the base station reports the terminal information of the user device.

[0094] Specifically, when the terminal is a user device, the user device supports information interaction with a near real-time wireless controller; then, the terminal information acquisition module 12 is specifically used to: send a request message to the user device so that the user device reports the terminal information according to the request message; or subscribe to the terminal information to the user device so that the user device reports the terminal information.

[0095] 7 , which is a structural block diagram of another device 200 for orchestrating AI reasoning tasks in a wireless access network provided by an embodiment of the present disclosure. The device 200 for orchestrating AI reasoning tasks in a wireless access network includes:

[0096] Model information acquisition module 21, used to obtain model information of the AI ​​reasoning model;

[0097] An AI reasoning task assurance strategy generation module 22 is configured to generate an AI reasoning task assurance strategy based on the model information; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance strategy defines an optimization goal of the wireless access network and characteristic information of the AI ​​reasoning model;

[0098] The AI ​​reasoning task guarantee policy sending module 23 is used to send the AI ​​reasoning task guarantee policy to the near real-time wireless controller, so that the near real-time wireless controller generates an AI reasoning task scheduling plan for the wireless access network based on the AI ​​reasoning task guarantee policy and terminal information; wherein the terminal information includes computing resource information and communication resource information.

[0099] Specifically, the model information includes characteristic information of the AI ​​reasoning model and performance guarantee parameters of the AI ​​reasoning task; wherein, the performance guarantee parameters include but are not limited to model reasoning accuracy and the number of reasoning calculations per unit time.

[0100] Compared with related technologies, the AI ​​reasoning task scheduling device for a wireless access network disclosed in the present invention introduces artificial intelligence technology on the RAN side. It first receives the AI ​​reasoning task guarantee policy of the AI ​​reasoning model sent by the non-real-time wireless controller, and obtains terminal information of at least one terminal, wherein the AI ​​reasoning task guarantee policy defines the optimization goals of the wireless access network and the characteristic information of the AI ​​reasoning model, and the terminal information includes computing resource information and communication resource information; then, an AI reasoning task scheduling scheme for the wireless access network is generated based on the AI ​​reasoning task guarantee policy and the terminal information. By selecting computing nodes, task splitting points and exit points, near-real-time AI reasoning task collaborative scheduling can be performed on the computing nodes on the RAN side according to the real-time communication status and computing power, thereby improving the efficiency of resource allocation and collaborative computing on the RAN side, thereby improving system performance.

[0101] Referring to Figure 8, Figure 8 is a structural block diagram of an electronic device 300 provided in an embodiment of the present disclosure. The electronic device 300 includes a processor 31, a memory 32, and a computer program stored in the memory 32 and executable on the processor 31. When the processor 31 executes the computer program, the steps in the aforementioned embodiments of the method for orchestrating AI reasoning tasks in wireless access networks are implemented, such as steps S11 to S13 and S21 to S23.

[0102] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor 31 to implement the present disclosure. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 300.

[0103] The electronic device 300 may include, but is not limited to, a processor 31 and a memory 32. Those skilled in the art will appreciate that the schematic diagram is merely an example of the electronic device 300 and does not limit the electronic device 300. The electronic device 300 may include more or fewer components than shown, or may combine certain components or different components. For example, the electronic device 300 may further include input and output devices, network access devices, buses, and the like.

[0104] The processor 31 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor 31 is the control center of the electronic device 300 and connects various parts of the entire electronic device 300 using various interfaces and lines.

[0105] The memory 32 can be used to store the computer programs and / or modules. The processor 31 implements the various functions of the electronic device 300 by running or executing the computer programs and / or modules stored in the memory 32 and accessing the data stored in the memory 32. The memory 32 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 32 may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0106] Wherein, if the module / unit integrated in the electronic device 300 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present disclosure implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor 31, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0107] The above is a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications are also considered to be within the scope of protection of the present disclosure.

Claims

1. A method for scheduling AI reasoning tasks in a wireless access network, applied to a near real-time wireless controller, the method comprising: Receiving an AI reasoning task assurance strategy of an AI reasoning model sent by a non-real-time wireless controller; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance strategy defines an optimization goal of the wireless access network and characteristic information of the AI ​​reasoning model; Acquire terminal information of at least one terminal; wherein the terminal information includes computing resource information and communication resource information; Generate an AI reasoning task scheduling plan for the wireless access network according to the AI ​​reasoning task assurance strategy and the terminal information.

2. The method for scheduling AI reasoning tasks in a wireless access network according to claim 1, wherein: The generating of the AI ​​reasoning task scheduling scheme of the wireless access network according to the AI ​​reasoning task assurance strategy and the terminal information includes: According to the optimization goal of the wireless access network, determine the node to be allocated and the corresponding computing node according to each terminal information, and select the corresponding split point and exit point from the feature information of the AI ​​reasoning model according to each terminal information; wherein the split point and the exit point are one layer in the AI ​​reasoning model; The AI ​​reasoning task scheduling scheme is composed of the nodes to be allocated and their corresponding computing nodes, the splitting points and the exit points.

3. The method for scheduling AI reasoning tasks in a wireless access network according to claim 2, wherein: After generating an AI reasoning task scheduling scheme for a wireless access network according to the AI ​​reasoning task assurance strategy and the terminal information, the method further includes: The AI ​​reasoning task scheduling scheme is sent to the node to be assigned and the corresponding computing node, so that the node to be assigned and the corresponding computing node can complete their respective reasoning computing tasks.

4. The method for scheduling AI reasoning tasks in a wireless access network according to claim 1, wherein: When the terminal is a user equipment, the acquiring terminal information of at least one terminal includes: Sending a request message to a base station where the user equipment resides, so that the base station reports the terminal information of the user equipment according to the request message; or, The terminal information is subscribed to a base station where the user equipment resides, so that the base station reports the terminal information of the user equipment.

5. The method for scheduling AI reasoning tasks in a wireless access network according to claim 1, wherein: When the terminal is a user equipment, the user equipment supports information interaction with a near real-time wireless controller; then, acquiring terminal information of at least one terminal includes: sending a request message to the user equipment so that the user equipment reports the terminal information according to the request message; or, Subscribe the terminal information to the user equipment so that the user equipment reports the terminal information.

6. A method for scheduling AI reasoning tasks in a wireless access network, applied to a non-real-time wireless controller, the method comprising: Get model information of AI reasoning model; Generate an AI reasoning task assurance strategy according to the model information; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance strategy defines an optimization goal of the wireless access network and characteristic information of the AI ​​reasoning model; The AI ​​reasoning task guarantee strategy is sent to a near real-time wireless controller, so that the near real-time wireless controller generates an AI reasoning task scheduling plan for the wireless access network according to the AI ​​reasoning task guarantee strategy and terminal information; wherein the terminal information includes computing resource information and communication resource information.

7. The method for scheduling AI reasoning tasks in a wireless access network according to claim 6, wherein: The model information includes feature information of the AI ​​reasoning model and performance guarantee parameters of the AI ​​reasoning task; wherein the performance guarantee parameters include but are not limited to model reasoning accuracy and the number of reasoning calculations per unit time.

8. An AI reasoning task scheduling device for a wireless access network, comprising: An AI reasoning task assurance strategy receiving module, used to receive an AI reasoning task assurance strategy of an AI reasoning model sent by a non-real-time wireless controller; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance strategy defines an optimization target of the wireless access network and characteristic information of the AI ​​reasoning model; A terminal information acquisition module, used to acquire terminal information of at least one terminal; wherein the terminal information includes computing resource information and communication resource information; The AI ​​reasoning task scheduling scheme generation module is used to generate an AI reasoning task scheduling scheme for the wireless access network according to the AI ​​reasoning task guarantee strategy and the terminal information.

9. An AI reasoning task scheduling device for a wireless access network, comprising: Model information acquisition module, used to obtain model information of AI reasoning model; An AI reasoning task assurance strategy generation module, used to generate an AI reasoning task assurance strategy according to the model information; wherein the AI ​​reasoning model is deployed in a wireless access network, and the AI ​​reasoning task assurance strategy defines an optimization target of the wireless access network and characteristic information of the AI ​​reasoning model; An AI reasoning task guarantee strategy sending module is used to send the AI ​​reasoning task guarantee strategy to a near real-time wireless controller, so that the near real-time wireless controller generates an AI reasoning task scheduling plan for the wireless access network according to the AI ​​reasoning task guarantee strategy and terminal information; wherein the terminal information includes computing resource information and communication resource information.

10. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for scheduling AI reasoning tasks in a wireless access network as described in any one of claims 1 to 7 is implemented.

11. A computer-readable storage medium, the computer-readable storage medium comprising a stored computer program, wherein: When the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the AI ​​reasoning task scheduling method for a wireless access network as described in any one of claims 1 to 7.

12. A computer program product comprising computer instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

Images