A resource management method for edge intelligent systems based on blockchain

Abstract

The present invention discloses a blockchain-based edge intelligence system resource management method, comprising a system controller sensing the current user device artificial intelligence task information and the system's current wireless environment information; at the same time, the system controller senses the computing resource information of the user device, edge server and cloud server; uploading relevant information from the corresponding device to the system controller via a wireless connection; inputting the current artificial intelligence task information and the system's current wireless environment information into a trained optimization model deployed in the system controller, calculating the user device transmission power control, artificial intelligence task data volume control, user device artificial intelligence task offloading decision based on the current state, and the computing resource allocation to be used in the reasoning process and block generation process of the artificial intelligence task, and transmitting the calculation to each computing entity for execution; the present invention utilizes task offloading and computing resource allocation algorithms to improve system efficiency and user experience.

Description

Technical Field

[0001] The present invention relates to the field of blockchain and edge intelligence technology, and specifically to a blockchain-based edge intelligence system resource management method. Background Art

[0002] Ubiquitous artificial intelligence (AI) is a key development trend in realizing intelligent applications in various scenarios. It is highly resource-intensive and latency-sensitive, placing significant demands on network communication and computing resources. Traditional cloud computing models suffer from long transmission distances and concentrated computing workloads. Edge intelligence, an extension of edge computing, deploys AI services at the edge, enabling them to analyze local data without constant reliance on cloud computing. This means AI reasoning can be performed closer to the data source, such as sensors, smart devices, and routers, reducing transmission latency and bandwidth pressure.

[0003] Because edge intelligence systems require user devices to offload their AI tasks to the edge for inference, some sensitive information will be transmitted from the user device. Consequently, edge intelligence systems face serious privacy risks. A secure and reliable edge intelligence system requires strict protection mechanisms. Blockchain is a decentralized ledger technology that links a growing number of blocks together to form a chain, recording a series of encrypted and verified transactions or data. These blocks are interconnected through special encryption algorithms to form a decentralized, tamper-proof database. This avoids the single point of failure and data tampering risks of traditional centralized databases. In blockchain technology, block generation is the computational process of verifying transactions and creating new blocks. To this end, the concept of a blockchain-assisted edge intelligence system has been proposed.

[0004] In a blockchain-assisted edge intelligence system, a blockchain module is installed within an edge server located at each base station to facilitate the block generation process. Simultaneously, AI models are deployed on all edge servers for AI task inference. When AI tasks are offloaded from user devices to edge servers via the user device-to-base station connection, or subsequently to cloud servers via the base station-to-cloud server connection, the relevant information needs to be recorded within transactions and then packaged into blocks. This requires the system to have sufficient blocks to support the number of AI tasks. Both the block generation process and the AI ​​task inference process consume computing resources on the edge servers and compete with each other. If the block generation process consumes more computing resources, block generation will be faster, but AI task inference will be slower. This can lead to redundant blocks in the blockchain system, resulting in wasted computing resources. If AI task inference consumes more computing resources, system throughput can be improved, but the reduced block generation speed makes it difficult to meet the recording requirements of AI task inference. Therefore, aligning the computing resource allocation between the block generation process and the AI ​​task inference process is a prerequisite for optimizing system performance.

[0005] However, current research treats block generation and AI task reasoning as independent processes, optimizing them separately without addressing the matching between them. Furthermore, these studies have not yet explored the differences in properties between AI tasks and traditional tasks, such as AI task reasoning accuracy. In particular, AI task reasoning accuracy is related to the amount of data required for the task, which has not been considered in related work. Summary of the Invention

[0006] (1) Technical issues to be resolved

[0007] In order to overcome the shortcomings of the above-mentioned prior art, the present invention is aimed at the tasks of the blockchain system based on mobile edge intelligence, and comprehensively considers factors such as the computing amount of artificial intelligence tasks and the network transmission rate in the system structure to determine the artificial intelligence task offloading decision, resource allocation strategy and artificial intelligence task data volume control strategy. The present invention is inherited to the system controller deployment module and resource configuration module of the edge server layer, combined with the network status perception and acquisition module to realize the dynamic optimization of artificial intelligence task offloading decision, resource allocation strategy and artificial intelligence task data volume control strategy. On the basis of considering practicality, it accelerates the neural network training process and optimization process, and improves the user experience.

[0008] (2) Technical solution

[0009] To solve the above technical problems, the present invention proposes a blockchain-based edge computing system resource management method, which includes the following steps:

[0010] S1: The system controller senses the AI ​​task information generated by the current user device and the current wireless environment of the system. At the same time, the system controller senses the computing resource information of the user device, edge server, and cloud server. The relevant information is uploaded from the corresponding user device to the system controller via a wireless connection.

[0011] S2: Input the current AI task information and the system's current wireless environment information described in step S1 into a trained optimization model deployed in the system controller to calculate the current state of user equipment transmit power control, user equipment AI task offloading decision, user equipment AI task data volume control, and the allocation of computing resources to be used in the AI ​​task reasoning process and block generation process;

[0012] S3: Extracting the user device artificial intelligence task offloading decision information obtained in step S2. If the information indicates that the artificial intelligence task is being inferred locally, the system controller sends a corresponding artificial intelligence task offloading decision instruction to the user device via a wireless connection, and the user device directly infers the artificial intelligence task locally.

[0013] S4: Extract the user device artificial intelligence task offloading decision information obtained in step S2. If the information indicates that the artificial intelligence task is inferred on the edge server or cloud server, the system controller sends the corresponding artificial intelligence task offloading decision instruction, artificial intelligence task data volume control instruction, and transmission power control instruction to the user device via a wireless connection. The user device transmits the artificial intelligence task to the base station according to the corresponding transmission power and joins the blockchain to execute the block generation process. If the artificial intelligence task is inferred on the edge server, the system controller sends a computing resource allocation instruction to the edge server via a wireless connection. After the task inference process and the block generation process are all completed, the result is sent back to the user device. If the artificial intelligence task is inferred on the cloud server, the system controller sends a computing resource allocation instruction to the cloud server via a wired link. The artificial intelligence task needs to be further transmitted from the base station to the cloud server via a wired link for inference. The above instructions are used to control the parallel execution of the inference process and block generation process of the artificial intelligence task.

[0014] Furthermore, the step S1 is specifically as follows:

[0015] The network architecture of this method is characterized by represents the edge server (base station) set, One of the base stations exist In the example, edge server m (base station) covers N m User devices, represents the user equipment set under base station m, One of the user devices In addition, a system controller is placed at the edge layer to control the operation of the entire method.

[0016] The algorithm is deployed on a system controller to work. The system controller perceives the current user equipment artificial intelligence task information and the current wireless environment information of the system. The artificial intelligence task characteristics are composed of the amount of calculation, the amount of data and the inference accuracy. Let c mn Indicates the computational load of the AI ​​task generated by each user device, Let d mn Indicates the amount of data generated by each user device for the artificial intelligence task, Let μ mn represents the inference accuracy of the artificial intelligence task generated by each user device; the current wireless environment feature is composed of the channel gain from the user device to the base station, let g mn represents the channel gain from user equipment mn to its corresponding base station, At the same time, the system controller perceives the computing resource information of user devices, edge servers and cloud servers, and and F CS are the upper bounds of computing resources of user device mn, edge server m, and cloud server respectively.

[0017] During the working process, the system controller will upload the above information from the corresponding user equipment to the system controller through a wireless connection.

[0018] Furthermore, the step S2 is specifically as follows:

[0019] The data volume d of the current artificial intelligence task obtained in step S1 and the current channel gain g between the user equipment and the base station are input into the trained optimization model deployed on the system controller to obtain computing resource management instructions.

[0020] First, a fast numerical method is designed to obtain the transmit power control command of the user equipment in the current state, and the transmit power control command is separated from other optimization variables. Among them, p mn The total delay of the optimization target of this method decreases monotonically with the increase of the transmission power. Therefore, the transmission power control instruction can be obtained by increasing the transmission power so that the energy consumption of the user equipment reaches the energy consumption constraint.

[0021] The characteristics of the artificial intelligence task scheduling of this method are as follows: regarding the artificial intelligence task offloading decision of the user device, let α mn =1 means that the AI ​​task mn is offloaded to the edge server for inference, otherwise, α mn =0; similarly, βmn =1 means that the AI ​​task mn is offloaded to the cloud server for inference, otherwise, β mn =0; obviously, 1-α mn -β mn =1 means that the AI ​​task mn is inferred locally on the user device mn, At the same time, regarding the allocation of computing resources used in the artificial intelligence task reasoning process and block generation process, The computing resources allocated to the user device mn for the reasoning process of the artificial intelligence task mn, make and are the computing resources allocated by edge server m to the block generation process and the reasoning process of artificial intelligence task mn, respectively. make The computing resources allocated by the cloud server to the reasoning process of the artificial intelligence task mn, The above optimization variables are designed based on the deep reinforcement learning technology to design the optimization algorithm and establish the Markov decision process, in which the state space of this method is set to s = {c, g} and the action space is set to a = {α, β, f MINE ,f ES ,f CS ,f U ,d}. Finally, according to the algorithm output, the optimization result is obtained.

[0022] Furthermore, the step S3 is specifically as follows:

[0023] Extract the offloading decision information obtained in step S2. If the information indicates that the artificial intelligence task is inferred locally on the user device, the network controller sends the artificial intelligence task offloading decision instructions α and β, the artificial intelligence task data volume control instruction d, and the user device computing resource allocation instruction f to the user device via a wireless connection. U , execute the instruction as described in step S3, and directly transmit the result back to the user device.

[0024] Furthermore, the step S4 is specifically as follows:

[0025] Extract the offloading decision information obtained in step S2. If the information indicates that the artificial intelligence task is executed on the edge server or cloud server, the network controller sends the artificial intelligence task offloading decision instructions α and β, the transmission power control instruction p, and the artificial intelligence task data volume control instruction d to the user device via a wireless connection, and sends the computing resource allocation instruction f to the edge server via a wireless connection. MINE and f ES , or send computing resource allocation instructions to the cloud server through a wired link f C, and execute the instructions as described in step S4. After the AI ​​task reasoning process and block generation process are completed, the results are returned to the user device. After the corresponding instructions are executed, the total latency is obtained, which is the sum of the larger of the AI ​​task reasoning latency and the block generation latency and the AI ​​task transmission latency. The formula is:

[0026] t TOTAL =t TRAN +max(t INF ,t BC )

[0027] Among them, t TOTAL is the total processing delay of the AI ​​task, t TRAN is the transmission delay of the artificial intelligence task (if the artificial intelligence task is executed on the user device, the value is 0), t INF is the inference latency of the artificial intelligence task, t BC Delay for block generation.

[0028] (3) Beneficial effects

[0029] Compared with the prior art, the present invention adopts the above technical solution and has the following beneficial effects:

[0030] 1. When making AI task offloading decisions, resource allocation, and AI task data volume control, through analysis of actual scenarios, we jointly optimize task inference latency and block generation latency, making this technology more practical;

[0031] 2. A Markov decision process was constructed for AI task offloading decisions, resource allocation, and AI task data volume control. Based on deep reinforcement learning technology, a neural network was used to solve complex optimization problems, making it more practical.

[0032] 3. By analyzing and optimizing the target structure, the original problem is decomposed into two sub-problems for solution, which greatly reduces the learning difficulty of deep reinforcement learning and significantly improves the calculation speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a schematic diagram of a system model of an embodiment;

[0034] Figure 2 It is a schematic diagram of the training process of AI task offloading decision, resource allocation, and AI task data volume control;

[0035] Figure 3 It is a schematic diagram of the application process of AI task offloading decision-making, resource allocation, and AI task data volume control;

[0036] Figure 4This is a diagram comparing the rewards of this scheme with other schemes as the computational load of AI tasks increases;

[0037] Figure 5 This is a diagram comparing the rewards of this scheme with other schemes as the bandwidth increases;

[0038] Figure 6 This is a comparison diagram of the rewards of this scheme and other schemes as the transmission rate between base stations increases. DETAILED DESCRIPTION

[0039] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0040] The present invention proposes a task scheduling method that combines an edge intelligence system with a blockchain system. The embodiment includes the following steps:

[0041] Step 1: The system controller senses the AI ​​task information generated by the current user device and the current wireless environment of the system. It also senses the computing resource information of the user device, edge server, and cloud server. The relevant information is uploaded from the corresponding user device to the system controller via a wireless connection.

[0042] Step 2: Input the current AI task information and the system's current wireless environment information described in Step 1 into a trained optimization model deployed in the system controller to calculate the current state of the user equipment transmit power control, user equipment AI task offloading decision, user equipment AI task data volume control, and the allocation of computing resources to be used in the AI ​​task reasoning process and block generation process;

[0043] Step 3: Extracting the user device AI task offloading decision information obtained in step 2. If the information indicates that the AI ​​task is being inferred locally, the system controller sends a corresponding AI task offloading decision instruction to the user device via a wireless connection, and the user device directly infers the AI ​​task locally.

[0044] Step 4: Extract the user device artificial intelligence task offloading decision information obtained in step 2. If the information indicates that the artificial intelligence task is inferred on the edge server or cloud server, the system controller sends the corresponding artificial intelligence task offloading decision instruction, artificial intelligence task data volume control instruction, and transmission power control instruction to the user device via a wireless connection. The user device transmits the artificial intelligence task to the base station according to the corresponding transmission power and joins the blockchain to execute the block generation process. If the artificial intelligence task is inferred on the edge server, the system controller sends a computing resource allocation instruction to the edge server via a wireless connection. After the task inference process and the block generation process are all completed, the result is sent back to the user device. If the artificial intelligence task is inferred on the cloud server, the system controller sends a computing resource allocation instruction to the cloud server via a wired link. The artificial intelligence task needs to be further transmitted from the base station to the cloud server via a wired link for inference. The above instructions are used to control the parallel execution of the inference process and block generation process of the artificial intelligence task.

[0045] Furthermore, the step 1 includes:

[0046] The network architecture of this method is characterized by represents the edge server (base station) set, One of the base stations exist In the example, edge server m (base station) covers N m User devices, represents the user equipment set under base station m, One of the user devices In addition, a system controller is placed at the edge layer to control the operation of the entire method.

[0047] The algorithm is deployed on a system controller to work. The system controller perceives the current user equipment artificial intelligence task information and the current wireless environment information of the system. The artificial intelligence task characteristics are composed of the amount of calculation, the amount of data and the inference accuracy. Let c mn Indicates the computational load of the AI ​​task generated by each user device, Let d mn Indicates the amount of data generated by each user device for the artificial intelligence task, Let μ mn represents the inference accuracy of the artificial intelligence task generated by each user device; the current wireless environment feature is composed of the channel gain from the user device to the base station, let g mn represents the channel gain from user equipment mn to its corresponding base station, At the same time, the system controller perceives the computing resource information of user devices, edge servers and cloud servers, and and FCS are the upper bounds of computing resources of user device mn, edge server m, and cloud server respectively.

[0048] During the working process, the system controller will upload the above information from the corresponding user equipment to the system controller through a wireless connection.

[0049] Furthermore, the step 2 includes:

[0050] The data volume d of the current artificial intelligence task obtained in step 1 and the channel gain g between the current user equipment and the base station are input into the trained optimization model deployed on the system controller to obtain computing resource management instructions.

[0051] First, a fast numerical method is designed to obtain the transmit power control command of the user equipment in the current state, and the transmit power control command is separated from other optimization variables. Among them, p mn The transmission power allocated to the user equipment mn. The transmission delay from the user equipment to the base station and transmission energy consumption for:

[0052]

[0053] Among them, the wireless transmission rate from user equipment to base station for:

[0054]

[0055] Where W is the bandwidth, is the noise power, and χ is the inter-channel interference. The optimization target total delay of this method decreases monotonically with the increase of transmit power. Therefore, the transmit power control instruction can be obtained by increasing the transmit power so that the energy consumption of the user equipment meets the energy consumption constraint.

[0056] The characteristics of the artificial intelligence task scheduling of this method are as follows: regarding the artificial intelligence task offloading decision of the user device, let α mn =1 means that the AI ​​task mn is offloaded to the edge server for inference, otherwise, α mn =0; similarly, β mn =1 means that the AI ​​task mn is offloaded to the cloud server for inference, otherwise, β mn =0; obviously, 1-α mn -β mn =1 means that the AI ​​task mn is inferred locally on the user device mn, At the same time, regarding the allocation of computing resources used in the artificial intelligence task reasoning process and block generation process, The computing resources allocated to the user device mn for the reasoning process of the artificial intelligence task mn, make and are the computing resources allocated by edge server m to the block generation process and the reasoning process of artificial intelligence task mn, respectively. make The computing resources allocated by the cloud server to the reasoning process of the artificial intelligence task mn, The above optimization variables are designed based on the deep reinforcement learning technology to design the optimization algorithm and establish the Markov decision process, in which the state space of this method is set to s = {c, g} and the action space is set to a = {α, β, f MINE ,f ES ,f CS ,f U ,d}. Finally, according to the algorithm output, the optimization result is obtained.

[0057] Furthermore, the step three includes:

[0058] Extract the offloading decision information obtained in step 2. If the information indicates that the AI ​​task is inferred locally on the user device, the network controller sends the AI ​​task offloading decision instructions α and β, the AI ​​task data volume control instruction d, and the user device computing resource allocation instruction f to the user device via a wireless connection. U , execute the instruction as described in step S3, and directly transmit the result back to the user device.

[0059] During the local reasoning process, the reasoning delay for:

[0060]

[0061] in, The amount of computing required for inference of artificial intelligence tasks on user devices, The computing resources of the user device. The computing energy consumption of local inference for:

[0062]

[0063] where κ is the computational efficiency of the GPU.

[0064] Furthermore, the step 4 includes:

[0065] Extract the offloading decision information obtained in step 2. If the information indicates that the AI ​​task is inferred on the edge server or cloud server, the network controller sends the AI ​​task offloading decision instructions α and β, the transmission power control instruction p, and the AI ​​task data volume control instruction d to the user device via a wireless connection, and sends the computing resource allocation instruction f to the edge server via a wireless connection. MINE and f ES , or send computing resource allocation instructions to the cloud server through a wired link f C , and execute the instructions in the manner described in step S4, and after the artificial intelligence task reasoning process and the block generation process are all completed, the results are returned to the user device.

[0066] Among them, during the edge server inference process, the inference delay for:

[0067]

[0068] in, The amount of computing required for AI tasks to be inferred on edge servers or cloud servers. During the inference process on cloud servers, the inference latency for:

[0069]

[0070] At the same time, during cloud server inference, the wired transmission delay from the base station to the cloud server is:

[0071]

[0072] in, It is the wired transmission rate from the base station to the cloud server.

[0073] At the same time, based on the proof of work, the block generation delay is calculated Calculate the total delay of AI task processing:

[0074]

[0075] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the claims of the present invention.

Claims

1. A blockchain-based edge intelligence system resource management method, characterized in that: The following steps are involved: S1: The system controller senses the AI ​​task information generated by the current user device and the current wireless environment of the system. At the same time, the system controller senses the computing resource information of the user device, edge server, and cloud server. The relevant information is uploaded from the corresponding user device to the system controller via a wireless connection. S2: Input the current AI task information and the current system wireless environment information described in step S1 into a trained optimization model deployed in the system controller to calculate the user equipment transmit power control, user equipment AI task offloading decision, user equipment AI task data volume control, and the allocation of computing resources to be used in the AI ​​task reasoning process and block generation process based on the current state; S3: Extracting the user device artificial intelligence task offloading decision information obtained in step S2. If the information indicates that the artificial intelligence task is being inferred locally, the system controller sends a corresponding artificial intelligence task offloading decision instruction to the user device via a wireless connection, and the user device directly infers the artificial intelligence task locally. S4: Extracting the user device artificial intelligence task offloading decision information obtained in step S2. If the information indicates that the artificial intelligence task is being inferred on the edge server or cloud server, the system controller sends the corresponding artificial intelligence task offloading decision instruction, artificial intelligence task data volume control instruction, and transmission power control instruction to the user device via a wireless connection. The user device transmits the artificial intelligence task to the base station according to the corresponding transmission power and joins the blockchain to execute the block generation process. If the AI ​​task is inferred on the edge server, the system controller sends a computing resource allocation instruction to the edge server via a wireless connection. After the task inference process and block generation process are completed, the result is transmitted back to the user device. If the AI ​​task is inferred on the cloud server, the system controller sends a computing resource allocation instruction to the cloud server via a wired link. The AI ​​task needs to be further transmitted from the base station to the cloud server via a wired link for inference. The above instructions control the parallel execution of the inference process and block generation process of artificial intelligence tasks; Step S2 includes: inputting the data volume d of the current artificial intelligence task and the current channel gain g between the user equipment and the base station obtained in step S1 into a trained optimization model deployed on the system controller to obtain a computing resource management instruction; First, a fast numerical method is designed to obtain the transmit power control command of the user equipment in the current state, and the transmit power control command is separated from other optimization variables. Among them, p mn The transmit power allocated to user equipment mn; the optimization target total delay decreases monotonically with increasing transmit power, so the transmit power control instruction can be obtained by increasing the transmit power so that the energy consumption of the user equipment meets the energy consumption constraint; The characteristics of AI task scheduling are: regarding the AI ​​task offloading decision of user devices, let α mn =1 means that the AI ​​task mn is offloaded to the edge server for inference, otherwise, α mn =0; similarly, β mn =1 means that the AI ​​task mn is offloaded to the cloud server for inference, otherwise, β mn =0; obviously, 1-α mn -β mn =1 means that the AI ​​task mn is inferred locally on the user device mn, At the same time, regarding the allocation of computing resources used in the artificial intelligence task reasoning process and block generation process, The computing resources allocated to the user device mn for its artificial intelligence task reasoning process, make and are the computing resources allocated by edge server m to the block generation process and the reasoning process of artificial intelligence task mn, respectively. make The computing resources allocated by the cloud server to the reasoning process of the artificial intelligence task mn, Based on deep reinforcement learning technology, an optimization algorithm is designed to solve the above variables and establish a Markov decision process, in which the state space is set to s = {c, g} and the action space is set to a = {α, β, f MINE ,f ES ,f CS ,f U ,d}; Finally, the optimization result is obtained according to the algorithm output.

2. The method for managing edge intelligent system resources based on blockchain according to claim 1, characterized in that: The step S1 includes: the network architecture is characterized by: Represents a collection of edge servers, One of the base stations exist In the example, edge servers m cover N m User devices, represents the user equipment set under base station m, One of the user devices In addition, a system controller is placed at the edge layer to control the operation of the entire method; The algorithm is deployed on a system controller to work. The system controller perceives the current user equipment artificial intelligence task information and the current wireless environment information of the system. The artificial intelligence task characteristics are composed of the amount of calculation, the amount of data and the inference accuracy. Let c mn Indicates the computational load of the AI ​​task generated by each user device, Let d mn Indicates the amount of data generated by each user device for the artificial intelligence task, Let μ mn represents the inference accuracy of the artificial intelligence task generated by each user device; the current wireless environment feature is composed of the channel gain from the user device to the base station, let g mn represents the channel gain from user equipment mn to its corresponding base station, At the same time, the system controller perceives the computing resource information of user devices, edge servers and cloud servers, and and F CS are the upper bounds of computing resources of user device mn, edge server m, and cloud server respectively; During the working process, the system controller will upload the above information from the corresponding user equipment to the system controller through a wireless connection.

3. The method for managing resources of an edge intelligent system based on blockchain according to claim 1, characterized in that: The step S3 includes: extracting the offloading decision information obtained in step S2, and if the information indicates that the artificial intelligence task is inferred locally on the user device, the network controller sends the artificial intelligence task offloading decision instructions α and β, the artificial intelligence task data volume control instruction d, and the user device computing resource allocation instruction f to the user device via a wireless connection. U , execute the instruction in the manner described in step S3 of claim 1, and directly return the result to the user device.

4. The method for managing resources of an edge intelligent system based on blockchain according to claim 1, characterized in that: The step S4 includes: extracting the offloading decision information obtained in step S2, and if the information indicates that the artificial intelligence task is inferred on the edge server or cloud server, the network controller sends the artificial intelligence task offloading decision instructions α and β, the transmission power control instruction p, the artificial intelligence task data volume control instruction d to the user device via a wireless connection, and sends the computing resource allocation instruction f to the edge server via a wireless connection. MINE and f ES , or send computing resource allocation instructions to the cloud server through a wired link f C , and execute the instructions in the manner described in step S4 of claim 1, and after the artificial intelligence task reasoning process and the block generation process are all completed, transmit the results back to the user device; after the corresponding instructions are executed, the total delay is obtained, that is, the sum of the larger of the artificial intelligence task reasoning delay and the block generation delay and the artificial intelligence task transmission delay, and the formula is: t TOTAL =t TRAN +max(t INF ,t BC ) Among them, t TOTAL is the total processing delay of the AI ​​task, t TRAN is the transmission delay of the artificial intelligence task. If the artificial intelligence task is inferred on the user device, the value is 0. INF is the inference latency of the artificial intelligence task, t BC Delay for block generation.

Images