A trusted scheduling method and device for industrial wireless network based on dynamic blockchain

Abstract

The present application discloses a trusted scheduling method and device for industrial wireless networks based on dynamic blockchain, and relates to the field of transmission scheduling technology in the industrial Internet, wherein the method includes: constructing an industrial wireless network system based on a dynamic blockchain mechanism; based on the preset constraints corresponding to the scheduling stage and the consensus stage, constructing a model with the goal of maximizing the trusted processing efficiency of the task, and obtaining an optimization model, wherein the optimization model carries various parameters to be optimized; reconstructing the optimization model based on a preset multi-agent Markov decision process model, and obtaining a target optimization model; based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, optimizing the target optimization model using a preset rotating multi-agent deep reinforcement learning algorithm model, and obtaining the target parameter values ​​corresponding to each of the parameters to be optimized. The method of the present application improves the trusted processing efficiency of tasks in the industrial wireless network system.

Description

Technical Field

[0001] The present invention relates to transmission scheduling technology of industrial Internet, and in particular to a trusted scheduling method and device for industrial wireless networks based on dynamic blockchain. Background Art

[0002] With the rapid development of the industrial Internet, more and more industrial equipment are connected to the Internet, connecting people, machines and objects to each other, realizing highly intelligent industrial systems. However, due to the limited computing frequency and battery capacity of industrial equipment, running computationally intensive applications on these devices may cause significant computing delays and excessive energy consumption, seriously reducing the user experience. To solve this problem, edge computing came into being, allowing tasks to be offloaded to edge servers for real-time processing.

[0003] However, due to the access of a large number of heterogeneous industrial devices and the open wireless network environment, the credibility between industrial devices and edge servers in the Industrial Internet may be affected, and data and other information are easily stolen by attackers. Therefore, blockchain technology is introduced to enhance its security and privacy.

[0004] However, simply adding blockchain to industrial wireless networks may not guarantee trustworthiness between edge servers and industrial devices, and may even exacerbate overhead, leading to the failure of edge computing. Summary of the invention

[0005] In view of this, the present invention provides an industrial wireless network trusted scheduling method and device based on dynamic blockchain, the main purpose of which is to solve the current problems of low credibility between edge servers and industrial equipment and easy failure of edge computing in the joint scheduling of industrial wireless network tasks and resources.

[0006] To solve the above problems, the present application provides an industrial wireless network trusted scheduling method based on dynamic blockchain, including:

[0007] Build an industrial wireless network system based on dynamic blockchain mechanism;

[0008] Based on the preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the task trusted processing efficiency, and an optimization model for scheduling the industrial wireless network system is obtained, wherein the optimization model carries various parameters to be optimized;

[0009] Reconstructing the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model;

[0010] Based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

[0011] To solve the above problems, the present application provides an industrial wireless network trusted scheduling device based on dynamic blockchain, including:

[0012] Industrial wireless network system building module, used to build an industrial wireless network system based on a dynamic blockchain mechanism;

[0013] A model building module is used to build a model based on the preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, with the goal of maximizing the task trusted processing efficiency, to obtain an optimization model for scheduling the industrial wireless network system, wherein the optimization model carries various parameters to be optimized

[0014] A model reconstruction module is used to reconstruct the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model;

[0015] An optimization module is used to optimize the target optimization model based on the observation information of each industrial equipment in the industrial wireless network system collected in real time using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

[0016] To solve the above problems, the present application provides a storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned industrial wireless network trusted scheduling method based on dynamic blockchain are implemented.

[0017] To solve the above problems, the present application provides an electronic device, comprising at least a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program on the memory, the steps of the above-mentioned dynamic blockchain-based industrial wireless network trusted scheduling method are implemented.

[0018] Beneficial effects of the present application: The present application constructs an industrial wireless network system based on a dynamic blockchain mechanism; based on the preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the trusted processing efficiency of the task, and an optimization model for scheduling the industrial wireless network system is obtained, and the optimization model carries various parameters to be optimized; the dynamic blockchain mechanism is adopted to dynamically adjust the leader edge server and the blockchain timeout window according to the network status and task requirements, which not only ensures security and reliability, but also improves the flexibility and adaptability of the system. The optimization model is reconstructed based on a preset multi-agent Markov decision process model to obtain a target optimization model; based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model, and the target parameter values ​​corresponding to each of the parameters to be optimized for scheduling the industrial wireless network system are obtained, thereby improving the trusted processing efficiency of tasks in the industrial wireless network system.

[0019] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0021] Figure 1 A schematic diagram of a process of a trusted scheduling method for an industrial wireless network based on a dynamic blockchain provided in an embodiment of the present application is shown;

[0022] Figure 2 A schematic diagram of a process of a trusted scheduling method for an industrial wireless network based on a dynamic blockchain provided by another embodiment of the present application is shown;

[0023] Figure 3 A schematic diagram showing the structure of an industrial wireless network system according to an embodiment of the present application is shown;

[0024] Figure 4 A structural diagram of a preset rotation multi-agent deep reinforcement learning algorithm model provided in an embodiment of the present application is shown;

[0025] Figure 5A structural block diagram of an industrial wireless network trusted scheduling device based on dynamic blockchain provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] Various methods and features of the present application are described herein with reference to the accompanying drawings.

[0027] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0028] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0029] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0030] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.

[0031] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0032] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0033] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0034] The present application embodiment provides an industrial wireless network trusted scheduling method based on dynamic blockchain, such as Figure 1 As shown, including:

[0035] Step S101: constructing an industrial wireless network system based on a dynamic blockchain mechanism;

[0036] In the specific implementation process of this step, the industrial wireless network system includes multiple edge servers and multiple industrial devices, the edge servers are powered by the power grid and connected to each other by wires, and the multiple edge servers include edge computing servers, base stations, and blockchain node servers; the edge computing servers provide edge computing and content caching services; the base stations provide communication services; the blockchain node servers provide security for communication and computing services; the industrial devices generate tasks and perform local calculations on the tasks, and support migrating the tasks to the edge servers through wireless channels for edge computing; the industrial devices, such as robot vision sensors with computationally intensive tasks, are connected to the edge servers through wireless connections, and can offload tasks to the edge servers for collaborative computing; the dynamic blockchain mechanism, each edge server acts as a blockchain node, responsible for recording transaction information of task offloading and calculation. Here, the edge server plays two roles: leader and follower. The leader is responsible for verifying transactions and generating blocks, while the follower is responsible for initiating transactions and storing blocks. And the blockchain timeout window and the leader edge server will change dynamically with the environment.

[0037] Step S102: Based on the preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the task trusted processing efficiency, and an optimization model for scheduling the industrial wireless network system is obtained, wherein the optimization model carries various parameters to be optimized;

[0038] In the specific implementation of this step, each of the preset constraints includes a task offloading ratio constraint, a bandwidth allocation ratio constraint, a local computing frequency constraint, an energy consumption constraint, a blockchain security constraint, a computing frequency allocation constraint, a task deadline constraint, and a credibility constraint. Each of the parameters to be optimized includes the task division ratio, the communication bandwidth allocation ratio, the computing frequency of the edge server for offloading task processing and block generation, the dynamic consensus waiting window in the blockchain, and the leader agent elected by the edge server.

[0039] Step S103: reconstructing the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model;

[0040] In the specific implementation process of this step, an agent set, an agent observation state set, and an agent action set of the preset multi-agent Markov decision process model are constructed; a function is constructed based on a preset trusted computing reward function, a preset timeout penalty function, and a preset consensus penalty function to obtain a reward function of the preset multi-agent Markov decision process model; a model is constructed based on the agent set, the agent observation state set, the agent action set, and the reward function to obtain the preset multi-agent Markov decision process model; based on the preset multi-agent Markov decision process model and the reward function, the optimization model of industrial wireless network scheduling is transformed into a model to obtain a target optimization model.

[0041] Step S104: Based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

[0042] During the specific implementation of this step, the observation information of each industrial equipment in the industrial wireless network system obtained in real time is used for state prediction using a preset round-robin multi-agent deep reinforcement learning algorithm to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system; the target optimization model is used to perform calculations based on each target parameter value to obtain a target reward value; the target parameter value is executed to obtain the target observation information of each industrial equipment in the next state; each observation information, each target parameter value, the target reward value and the target observation information are entered into a preset experience database; this lays the foundation for offline updating of the preset round-robin multi-agent deep reinforcement learning algorithm model in subsequent specific applications.

[0043] This application constructs an industrial wireless network system based on a dynamic blockchain mechanism; based on the preset constraints corresponding to the task and resource joint scheduling stage of the industrial wireless network system and the consensus stage of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the trusted processing efficiency of the task, and an optimization model for scheduling the industrial wireless network system is obtained, and the optimization model carries various parameters to be optimized; the dynamic blockchain mechanism is adopted to dynamically adjust the leader edge server and the blockchain timeout window according to the network status and task requirements, which not only ensures security and reliability, but also improves the flexibility and adaptability of the system. The optimization model is reconstructed based on a preset multi-agent Markov decision process model to obtain a target optimization model; based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model, and the target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system are obtained, thereby improving the trusted processing efficiency of tasks in the industrial wireless network system.

[0044] Another embodiment of the present application provides another industrial wireless network trusted scheduling method based on dynamic blockchain, such as Figure 2 As shown, including:

[0045] Step S201: constructing an industrial wireless network system based on a dynamic blockchain mechanism;

[0046] In the specific implementation process of this step, Figure 3 The figure shows a schematic diagram of the structure of the industrial wireless network system described in the present application, wherein the industrial wireless network system includes M edge servers and N industrial devices, each of which has a collection of and The edge servers are powered by the power grid and connected to each other by wires. The edge servers include edge computing servers, base stations, and blockchain node servers. The edge computing servers provide edge computing and content caching services. The base stations provide communication services. The blockchain node servers provide security for communication and computing services. The industrial equipment generates tasks and performs local computing on the tasks, and supports migrating the tasks to the edge servers through wireless channels for edge computing. The industrial equipment, such as robot vision sensors with computationally intensive tasks, is connected to the edge servers through wireless connections, and can offload tasks to the edge servers for collaborative computing. In the dynamic blockchain mechanism, each edge server acts as a blockchain node, responsible for recording transaction information for task offloading and computing. Here, the edge server plays two roles: leader and follower. The leader is responsible for verifying transactions and generating blocks, while the follower is responsible for initiating transactions and storing blocks. And the blockchain timeout window and the leader edge server will change dynamically with the environment.

[0047] Step S202: constructing various preset constraint conditions;

[0048] In the specific implementation process of this step, a constraint condition is constructed based on the task ratio of each industrial device unloaded to each edge server, and a task unloading ratio constraint condition C1 in the task and resource joint scheduling stage is obtained; the mathematical expression of the task unloading ratio constraint condition can be expressed as the following formula (1):

[0049]

[0050] Among them, x n,m is the ratio of tasks offloaded from industrial device n to edge server m, x n,0 Indicates the proportion of local computation of the task. n,m = 1, it means that the nth industrial equipment offloads all tasks to the mth edge server for complete edge computing, and when x n,m =0, it means that the nth industrial device does not offload any tasks to the mth edge server.

[0051] Based on the bandwidth ratio allocated by each edge server to each industrial device, a constraint condition is constructed to obtain a bandwidth allocation ratio constraint condition C2 in the task and resource joint scheduling stage; the mathematical expression of the bandwidth allocation ratio constraint condition can be expressed as the following formula (2):

[0052]

[0053] Among them, r n,m It represents the bandwidth ratio of the mth edge server allocated to the task generated by the nth industrial device.

[0054] Based on the predetermined maximum computing frequency parameters corresponding to each of the industrial devices, a constraint condition is constructed to obtain a local computing frequency constraint condition C3 corresponding to each of the industrial devices. The mathematical expression of the local computing frequency constraint condition can be expressed as follows:

[0055]

[0056] Among them, f n Indicates the local computing frequency of the device used by the nth industrial device, and should not exceed the maximum computing frequency of the nth industrial device

[0057] Based on the computing energy consumption, task transmission energy consumption and maximum battery capacity corresponding to each of the industrial equipment, the constraint conditions are constructed to obtain the energy consumption constraint conditions C4 corresponding to each of the industrial equipment. The mathematical expression of the energy consumption constraint conditions can be expressed as the following formula (4):

[0058]

[0059] Among them, the main energy consumption of the nth industrial equipment is computing energy consumption and task transmission energy consumption, which should not exceed the maximum battery capacity of the industrial equipment.

[0060] Based on the predetermined successful processing task counting function of the dynamic blockchain mechanism, the preset Byzantine fault tolerance coefficient, the identification parameters of each edge server completing the unloading task of each industrial device, and the task ratio of each industrial device unloaded to each edge server, the constraint condition is constructed to obtain the blockchain security constraint condition C5 in the consensus stage; the mathematical expression of the blockchain security constraint condition in the consensus stage can be shown as the following formula (5):

[0061]

[0062] The blockchain security constraint should satisfy the Byzantine fault tolerance mechanism; Count() is a predetermined successful processing task counting function, which is used to calculate z n,m = the number of 1; z n,m ∈{-1,1} indicates whether the mth edge server has completed the task of unloading the nth industrial equipment within the task deadline, ρ is the Byzantine fault tolerance coefficient, that is, this constraint indicates that the number of transactions received within the maximum allowed consensus delay that completes the task calculation on time should not be less than the first preset threshold, The round-up symbol indicates that a decimal value is rounded to the nearest integer value that is not less than the original value.

[0063] Based on the maximum computing frequency of each edge server, the binary indicator variable of whether each edge server is a leader, and the computing frequency allocated to block generation when each edge server acts as a leader, a constraint condition is constructed to obtain a computing frequency allocation constraint condition C6 corresponding to each edge server; the mathematical expression of the computing frequency allocation constraint condition can be expressed as the following formula (6):

[0064]

[0065] in, is the maximum computation frequency of the mth edge server, l m ={0,1} is a binary leader indicator variable, assuming that the leader edge server is m *,but and Indicates the calculation frequency assigned to the task calculation; Indicates the computation frequency allocated to block generation when acting as a leader;

[0066] Based on the scheduled task deadline of each industrial device, a constraint condition is constructed to obtain a task deadline constraint condition C7 corresponding to each industrial device. The mathematical expression of the task deadline constraint condition can be expressed as the following formula (7):

[0067]

[0068] in, is the task deadline of the nth industrial equipment, that is, the maximum tolerable processing delay of the industrial equipment.

[0069] Based on the trust score of the successful completion amount of the tasks corresponding to each edge server and the predetermined threshold, the constraint condition is constructed to obtain the credibility constraint condition C8 corresponding to each edge server. The mathematical expression of the credibility constraint condition can be shown as the following formula (8):

[0070]

[0071] Among them, for the task completed by the mth edge server, the trust score v is calculated based on the number of tasks it successfully completed m Should be greater than the set threshold V th .

[0072] Step S203: constructing a task trusted processing efficiency function;

[0073] In the specific implementation process of this step, a function is constructed based on a preset credibility verification delay function, a preset task offloading transmission delay function, and a preset edge computing delay function to obtain a trusted computing process function; specifically, a function is constructed based on the data volume of the verified block and the communication rate function between each industrial device and each edge server to obtain the credibility verification delay function. The mathematical expression of the credibility verification delay function can be expressed as follows:

[0074]

[0075] Among them, VB is the amount of data in the verified block; R n,m is the communication rate function, and the mathematical expression of the communication rate function can be expressed as follows:

[0076]

[0077] Among them, rn,m represents the bandwidth ratio of edge server m allocated to industrial device n, B m represents the bandwidth of edge server m, p n is the transmission power of the nth industrial equipment, h n,m is the channel power gain between the nth industrial device and the mth edge server, and N0 is the noise power spectral density.

[0078] The preset task unloading transmission delay function is obtained by constructing a function based on the task ratio of each industrial device unloaded to each edge server, the task data volume of each industrial device unloaded to each edge server, and the communication rate function between each industrial device and each edge server. The mathematical expression of the preset task offloading transmission delay function can be expressed as the following formula (11):

[0079]

[0080] Among them, D n The amount of task data offloaded from the industrial device n to the edge server m.

[0081] The preset edge computing delay function is obtained by constructing a function based on the task ratio of each industrial device unloaded to each edge server, the computing frequency required for the task of each industrial device, and the computing frequency allocated to the industrial device by the edge server. The mathematical expression of the preset edge computing delay function can be expressed as the following formula (12):

[0082]

[0083] Among them, C n Represents the required computing frequency of the task of industrial equipment n.

[0084] The trusted computing process function The mathematical expression of can be expressed as follows:

[0085]

[0086] Based on the trusted computing process function, the preset transaction record report delay function, the preset maximum allowed consensus waiting time function, and the preset actual maximum consensus waiting time function, a function is constructed to obtain an actual consensus waiting delay function; specifically, based on the transaction record data volume TR and the transmission rate between the edge servers Build the function to get the preset transaction record report delay function The mathematical expression of the preset transaction record reporting delay function can be expressed as the following formula (14):

[0087]

[0088] Based on the trusted computing process function The preset transaction record report delay function And dynamic consensus waiting window Construct the function to obtain the maximum consensus waiting time function The mathematical expression of the maximum consensus waiting time function can be expressed as follows:

[0089]

[0090] Based on the trusted computing process function and the preset transaction record report delay function Construct the function to get the actual maximum consensus waiting time function The mathematical expression of the maximum consensus waiting time function can be expressed as follows:

[0091]

[0092] Based on the maximum allowed consensus waiting time function And the actual maximum consensus waiting time function Construct the function to obtain the actual consensus waiting delay function The mathematical expression of the actual consensus waiting delay function can be expressed as follows:

[0093]

[0094] Based on the actual consensus waiting delay function And the preset block generation delay function Build the function to get the edge trusted computing delay function The mathematical expression of the edge trusted computing delay function can be expressed as follows:

[0095]

[0096] Among them, the preset block generation delay function The mathematical expression of can be expressed as follows:

[0097]

[0098] in, It is the frequency of calculations assigned by the leader for producing blocks.

[0099] Based on the edge trusted computing delay function and the local delay function corresponding to each of the industrial devices Construct the function and obtain the task trusted computing delay function T corresponding to each industrial equipment n The mathematical expression of the task trusted computing delay function can be expressed as follows:

[0100]

[0101] Based on the trusted computing delay function T of the task corresponding to the same industrial equipment n And the task data volume D n Perform function construction to obtain the trusted processing efficiency function U corresponding to the same industrial equipment n The mathematical expression of the trusted processing efficiency function can be expressed as follows:

[0102]

[0103] Step S204: Based on the preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the task trusted processing efficiency to obtain an optimization model for scheduling the industrial wireless network system;

[0104] In the specific implementation process of this step, the mathematical expression of the optimization model can be expressed as follows:

[0105]

[0106] The optimization model represents maximizing the task trust processing efficiency. is the set of parameters to be optimized, is the set of task division ratios, is the set of communication bandwidth allocation ratios, It is the set of computing frequencies assigned to task computing and block generation by the edge server. It is a collection of dynamic consensus waiting windows in the blockchain. It is the set of leaders elected by all edge servers.

[0107] Step S205: constructing a preset multi-agent Markov decision process model;

[0108] In the specific implementation process of this step, the agent set, agent observation state set, and agent action set of the preset multi-agent Markov decision process model are constructed; specifically, the agent set is That is, each edge server is regarded as an intelligent agent, which learns its own optimal action strategy by observing the environment state and cooperates with other intelligent agents to achieve the maximum trusted processing efficiency of the task. The intelligent agent observation state set includes: task state, industrial equipment state and edge server state. At each decision time t, the task state includes the task size D n (t), required calculation frequency C n (t) and task deadline Industrial equipment status includes transmission power p n (t), channel power gain h n,m (t), battery capacity and the device local calculation frequency Edge server status including edge computing frequency Bandwidth B m (t) and the trust score v m (t). Therefore, the entire environment state can be expressed as follows:

[0109]

[0110] Among them, by observing the state of the environment, each agent will obtain its own state, represented by S m (t). The action set is a set of action strategies taken by the agent. The mathematical expression of the action strategy set can be expressed as follows:

[0111]

[0112] Among them, the task division ratio x n,m (t), communication bandwidth allocation r n,m (t), calculate frequency allocation and Consensus waiting time window and leader election m (t).

[0113] The mathematical expression of the preset trusted computing reward function can be expressed as the following formula (25):

[0114]

[0115] in, It is the penalty for calculating timeout. is the penalty for consensus failure, α and β are the weight factors of the penalty respectively. The mathematical expression of can be expressed as follows:

[0116]

[0117] Consensus Failure Penalty The mathematical expression of can be shown as follows:

[0118]

[0119] Based on the preset trusted computing reward function, the preset timeout penalty function and the preset consensus penalty function, a function is constructed to obtain a reward function of the preset multi-agent Markov decision process model; the mathematical expression of the reward function can be shown as follows:

[0120]

[0121] The preset multi-agent Markov decision process model is obtained by constructing a model based on the agent set, the agent observation state set, the agent action set and the reward function.

[0122] Step S206: reconstructing the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model;

[0123] In the specific implementation process of this step, the mathematical expression of the target optimization model can be expressed as follows:

[0124]

[0125] That is, it is necessary to maximize the long-term cumulative reward while satisfying the constraints, that is, to maximize the trusted processing efficiency of the task.

[0126] Step S207: constructing a preset rotation multi-agent deep reinforcement learning algorithm model;

[0127] In the specific implementation process of this step, Figure 4 As shown, this is a structural diagram of the preset rotation multi-agent deep reinforcement learning algorithm model of the present application, and an initial model corresponding to each of the edge servers is constructed, and the initial model includes an initial actor neural network, two initial critic neural networks, and two initial target critic neural networks;

[0128] Initializing the initial model corresponding to the predetermined initial leader agent in each edge server to obtain initial model parameters corresponding to the initial leader agent;

[0129] Based on each historical experience data, each initial model parameter, a preset first loss function, a preset second loss function, a preset third loss function, and a preset entropy regularization loss function, each initial model is trained to obtain a target deep reinforcement learning model corresponding to each edge server, so as to obtain the preset rotation multi-agent deep reinforcement learning algorithm model; specifically, in the first decision period, a leader election is performed based on the initial calculation frequency, initial trust score and initial channel state of each edge server to obtain an initial leader agent; the initial trust score v m The calculation formula is as shown in the following formula (30):

[0130]

[0131] Among them, z n,m ∈{1,-1} indicates whether the mth edge server has completed the unloading task of the nth industrial equipment on schedule, 1 for completion and -1 for incompleteness.

[0132] Based on a preset first loss function, a preset second loss function, a preset third loss function, and a preset entropy regularization loss function, the initial model corresponding to the initial leader intelligent agent is trained to obtain a current first model corresponding to the initial leader intelligent agent; specifically, based on a set of historical experience data randomly drawn, the first loss function is used for calculation processing to obtain first model parameters of the first initial critic neural network; based on another set of historical experience data randomly drawn, the second loss function is used for calculation processing to obtain second model parameters of the second initial critic neural network; the first model parameters are obtained by minimizing the first loss function; the second model parameters are obtained by minimizing the second loss function; the first loss function L Q The calculation formula of (ω1) can be expressed as follows:

[0133]

[0134] Among them, ω1 is the first model parameter; Ω(t) = {S(t), A(t), R(t), S(t+1)} is the historical experience data of group λ, where S(t) is the observed state at time t, that is, the state of the entire system; A(t) is the action strategy at time t; R(t) is the reward value obtained by executing the action at time t; S(t+1) is the observed state of the entire industrial wireless network system at the next moment after executing the action at time t. is the first initial critic neural network; μ is the entropy regularization coefficient; is the expected value calculation function; γ is the discount factor. The second loss function L QThe calculation formula of (ω2) can be expressed as follows:

[0135]

[0136] Where: ω2 is the second model parameter; is the second initial critic neural network.

[0137] The first model parameter and the second model parameter are screened to obtain a target model parameter; the first model parameter and the second model parameter are compared to determine the smaller model parameter as the target model parameter. Based on the target model parameter and the historical experience data, the third loss function of the initial actor neural network is used for calculation and processing to obtain the third model parameter θ when the loss value of the third loss function is the smallest; the mathematical expression of the third loss function can be shown as the following formula (33):

[0138]

[0139] Wherein, θ is the third model parameter; π θ is the initial actor neural network; f θ is a reparameterized function for action sampling. ε is a noise random variable that satisfies the policy Gaussian distribution

[0140] Based on the historical experience data, a preset entropy regularization loss function is used for calculation and processing to obtain a regularization coefficient when the loss value of the preset entropy regularization loss function is the smallest. The mathematical expression of the preset entropy regularization loss function can be shown as the following formula (34):

[0141]

[0142] Among them, H0 is the target entropy;

[0143] Based on the first model parameter, the second model parameter, the third model parameter and the regularization coefficient, the model is updated to obtain the first current critic neural network, the second current critic neural network, the current actor model and the current entropy regularization loss function; specifically, based on the first model parameter, the first initial critic neural network is updated to obtain the first current critic neural network; based on the second model parameter, the second initial critic neural network is updated to obtain the second current critic neural network; based on the third model parameter, the initial actor neural network is updated to obtain the current actor model; based on the regularization coefficient, the preset entropy regularization loss function is updated to obtain the current entropy regularization loss function. Specifically, the following soft update function can be used to update each model, and the mathematical expression of the soft update function can be shown as follows:

[0144]

[0145] where τ∈[0,1] is the parameter update rate.

[0146] The first current critic neural network, the second current critic neural network, the current actor model and the current entropy regularization loss function are iteratively updated in a loop until the reward function value obtained by optimizing the target optimization model of industrial wireless network scheduling using each state parameter value obtained by using the updated current actor model to perform state prediction on each of the historical experience data meets the preset conditions, thereby obtaining the current first model. The model parameters of the current first model are sent to each first edge server that is not the initial leader intelligent agent, so as to update the initial models corresponding to each first edge server based on the model parameters, and obtain the current first model corresponding to each first edge server, wherein the model parameters include the first model parameter, the second model parameter, the third model parameter and the first entropy regularization coefficient corresponding to the initial leader intelligent agent; in a non-first decision period, the leader election is re-performed based on the current calculation frequency, the current trust score and the current channel state of each edge server to obtain the current leader intelligent agent; the current first model corresponding to the current leader intelligent agent is trained based on the preset first loss function, the preset second loss function, the preset third loss function and the preset entropy regularization loss function to update the current first model; the updated model parameters of the current first model are sent to each second edge server that is not the current leader intelligent agent, so as to update the current first model corresponding to each second edge server based on the model parameters, and the algorithm is iterated repeatedly until the algorithm converges, and the preset rotating multi-agent deep reinforcement learning algorithm model is obtained by training. The target deep reinforcement learning model includes: a target actor neural network, each critic neural network, and a target critic neural network corresponding to each critic neural network for stabilizing the critic neural network.

[0147] Step S208: Based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

[0148] During the specific implementation of this step, the observation information of each industrial equipment in the industrial wireless network system obtained in real time is used for state prediction using a preset round-robin multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​that satisfy each observation information; based on each target parameter value, an optimization model for scheduling the industrial wireless network system is used to perform calculations to obtain a target reward value; the target parameter value is executed to obtain the target observation information of each industrial equipment in the next state; each observation information, each target parameter value, the target reward value and the target observation information are entered into a preset experience database; this lays the foundation for offline updating of the preset round-robin multi-agent deep reinforcement learning algorithm model in subsequent specific applications.

[0149] The end-edge collaborative trusted computing process adopted in this application is as follows: Figure 4 As shown, it mainly includes the following steps:

[0150] Step 1: The edge server performs dynamic leader agent election and establishes a trusted blockchain;

[0151] Step 2: The industrial device verifies the credibility of the target edge server for task offloading and performs task offloading for end-edge collaborative trusted computing;

[0152] Step 3: The follower agent reports the transaction record to the leader agent and waits for consensus;

[0153] Step 4: The leader agent verifies the block and broadcasts the verified block to update the blockchain.

[0154] This application implements dynamic leader election and dynamic consensus waiting mechanism in a trusted edge computing environment. The ability to dynamically adjust the leader edge server and blockchain timeout window according to network status and task requirements not only ensures security and reliability, but also improves the flexibility and adaptability of the system. Comprehensively considering constraints such as task size and deadline, communication, computing and energy resources, and credibility, the task allocation, communication and computing frequency allocation, leader election, and consensus waiting window are jointly optimized, so that the scheduling of tasks and resources can be dynamically adjusted according to changes in the scene, while ensuring security and reliability, and efficiently completing task calculations. The architecture of preset round-robin training distributed execution is adopted to improve the trusted processing efficiency of tasks in industrial wireless network systems.

[0155] Another embodiment of the present application provides an industrial wireless network trusted scheduling device based on dynamic blockchain, such as Figure 5 As shown, including:

[0156] Industrial wireless network system building module 1, used to build an industrial wireless network system based on a dynamic blockchain mechanism;

[0157] Model building module 2, used to build a model based on the preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, with the goal of maximizing the task trusted processing efficiency, to obtain an optimization model for scheduling the industrial wireless network system, wherein the optimization model carries various parameters to be optimized;

[0158] A model reconstruction module 3 is used to reconstruct the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model;

[0159] Optimization module 4 is used to optimize the target optimization model based on the observation information of each industrial equipment in the industrial wireless network system collected in real time using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

[0160] In the specific implementation process, the industrial wireless network trusted scheduling device based on dynamic blockchain also includes: each preset constraint condition construction module, and each preset constraint condition construction module is specifically used to: construct constraints based on the task ratio of each industrial device unloaded to each edge server, and obtain the task unloading ratio constraint condition in the task and resource joint scheduling stage; construct constraints based on the bandwidth ratio allocated to each industrial device by each edge server, and obtain the bandwidth allocation ratio constraint condition in the task and resource joint scheduling stage; construct constraints based on the predetermined maximum computing frequency parameters corresponding to each industrial device, and obtain the local computing frequency constraints corresponding to each industrial device; construct constraints based on the computing energy consumption, task transmission energy consumption and maximum battery capacity corresponding to each industrial device, and obtain the energy consumption constraints corresponding to each industrial device; based on the dynamic blockchain machine The predetermined successful processing task counting function, the preset Byzantine fault tolerance coefficient, the identification parameters of each edge server completing the unloading task of each industrial device, and the task ratio of each industrial device unloaded to each edge server are used to construct constraint conditions to obtain the blockchain security constraint conditions in the consensus stage; based on the maximum computing frequency of each edge server, the binary indicator variable of whether each edge server is a leader, and the computing frequency allocated to block generation when each edge server acts as a leader, the constraint conditions are constructed to obtain the computing frequency allocation constraint conditions corresponding to each edge server; based on the predetermined task deadline of each industrial device, the constraint conditions are constructed to obtain the task deadline constraint conditions corresponding to each industrial device; based on the trust score and the predetermined threshold of the successful completion amount of the task corresponding to each edge server, the constraint conditions are constructed to obtain the credibility constraint conditions corresponding to each edge server.

[0161] In the specific implementation process, the industrial wireless network trusted scheduling device based on dynamic blockchain also includes: a trusted processing efficiency function construction module, and the trusted processing efficiency function construction module is specifically used to: construct a function based on a preset credibility verification delay function, a preset task offloading transmission delay function and a preset edge computing delay function to obtain a trusted computing process function; construct a function based on the trusted computing process function, a preset transaction record report delay function, a preset allowed maximum consensus waiting time function, and a preset actual maximum consensus waiting time function to obtain an actual consensus waiting delay function; construct a function based on the actual consensus waiting delay function and the preset block generation delay function to obtain an edge trusted computing delay function; construct a function based on the edge trusted computing delay function and the local delay function corresponding to each of the industrial equipment to obtain a task trusted computing delay function corresponding to each industrial equipment; construct a function based on the task trusted computing delay function corresponding to the same industrial equipment and the task data volume to obtain the trusted processing efficiency function corresponding to the same industrial equipment.

[0162] In the specific implementation process, the industrial wireless network trusted scheduling device based on dynamic blockchain also includes: a preset multi-agent Markov decision process model construction module, and the preset multi-agent Markov decision process model construction module is specifically used to: construct the agent set, agent observation state set, and agent action set of the preset multi-agent Markov decision process model; construct functions based on a preset trusted computing reward function, a preset timeout penalty function, and a preset consensus penalty function to obtain the reward function of the preset multi-agent Markov decision process model; construct a model based on the agent set, the agent observation state set, the agent action set, and the reward function to obtain the preset multi-agent Markov decision process model.

[0163] In the specific implementation process, the industrial wireless network trusted scheduling device based on dynamic blockchain also includes: a preset rotating multi-agent deep reinforcement learning algorithm model construction module, and the preset rotating multi-agent deep reinforcement learning algorithm model construction module is specifically used to: construct an initial model corresponding to each edge server, the initial model includes an initial actor neural network, two initial critic neural networks and two initial target critic neural networks; initialize the initial model corresponding to the predetermined initial leader agent in each edge server to obtain the initial model parameters corresponding to the initial leader agent; based on each historical experience data, each initial model parameter, a preset first loss function, a preset second loss function, a preset third loss function, and a preset entropy regularization loss function, each initial model is trained to obtain a target deep reinforcement learning model corresponding to each edge server, so as to obtain the preset rotating multi-agent deep reinforcement learning algorithm model; wherein, the target deep reinforcement learning model includes: a target actor neural network, each critic neural network and a target critic neural network corresponding to each critic neural network for stabilizing the critic neural network.

[0164] In the specific implementation process, the preset rotating multi-agent deep reinforcement learning algorithm model construction module is also used to: in the first decision-making period, based on the initial calculation frequency, initial trust score and initial channel state of each edge server, perform leader election to obtain an initial leader agent; based on a preset first loss function, a preset second loss function, a preset third loss function, and a preset entropy regularization loss function, perform model training on the initial model corresponding to the initial leader agent to obtain a current first model corresponding to the initial leader agent; send the model parameters of the current first model to each first edge server that is not the initial leader agent, so as to update the initial model corresponding to each first edge server based on the model parameters to obtain the current first model corresponding to each first edge server, and the model parameters include the initial leader The first model parameters, second model parameters, third model parameters and first entropy regularization coefficients corresponding to the agent; in a non-first decision period, re-elect a leader based on the current calculation frequency, current trust score and current channel state of each edge server to obtain the current leader agent; perform model training on the current first model corresponding to the current leader agent based on the preset first loss function, the preset second loss function, the preset third loss function, and the preset entropy regularization loss function to update the current first model; send the updated model parameters of the current first model to each second edge server that is not the current leader agent, so as to update the current first model corresponding to each second edge server based on the model parameters, iterate repeatedly until the algorithm converges, and train to obtain the preset rotating multi-agent deep reinforcement learning algorithm model.

[0165] In the specific implementation process, the optimization module 4 is specifically used to: based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, use the target actor neural network in the preset rotating multi-agent deep reinforcement learning algorithm model to perform state prediction, and obtain the target parameter value corresponding to each parameter to be optimized for scheduling the industrial wireless network system; each parameter to be optimized includes: task division ratio, communication bandwidth allocation ratio, edge server computing frequency for offloading task processing and block generation, dynamic consensus waiting window in the blockchain, and leader agent elected by the edge server.

[0166] This application constructs an industrial wireless network system based on a dynamic blockchain mechanism; based on the preset constraints corresponding to the task and resource joint scheduling stage of the industrial wireless network system and the consensus stage of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the trusted processing efficiency of the task, and an optimization model for scheduling the industrial wireless network system is obtained, and the optimization model carries various parameters to be optimized; the dynamic blockchain mechanism is adopted to dynamically adjust the leader edge server and the blockchain timeout window according to the network status and task requirements, which not only ensures security and reliability, but also improves the flexibility and adaptability of the system. The optimization model is reconstructed based on a preset multi-agent Markov decision process model to obtain a target optimization model; based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model, and the target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system are obtained, thereby improving the trusted processing efficiency of tasks in the industrial wireless network system.

[0167] Another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented:

[0168] Step 1: Build an industrial wireless network system based on a dynamic blockchain mechanism;

[0169] Step 2: Based on the preset constraints corresponding to the task and resource joint scheduling stage of the industrial wireless network system and the consensus stage of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the task trusted processing efficiency to obtain an optimization model for scheduling the industrial wireless network system, wherein the optimization model carries various parameters to be optimized;

[0170] Step 3: reconstructing the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model;

[0171] Step 4: Based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

[0172] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0173] The specific implementation process of the above method steps can be found in any of the above-mentioned embodiments of the industrial wireless network trusted scheduling method based on dynamic blockchain, and this embodiment will not be repeated here.

[0174] This application constructs an industrial wireless network system based on a dynamic blockchain mechanism; based on the preset constraints corresponding to the task and resource joint scheduling stage of the industrial wireless network system and the consensus stage of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the trusted processing efficiency of the task, and an optimization model for scheduling the industrial wireless network system is obtained, and the optimization model carries various parameters to be optimized; the dynamic blockchain mechanism is adopted to dynamically adjust the leader edge server and the blockchain timeout window according to the network status and task requirements, which not only ensures security and reliability, but also improves the flexibility and adaptability of the system. The optimization model is reconstructed based on a preset multi-agent Markov decision process model to obtain a target optimization model; based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model, and the target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system are obtained, thereby improving the trusted processing efficiency of tasks in the industrial wireless network system.

[0175] Another embodiment of the present application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the following method steps when executing the computer program in the memory:

[0176] Step 1: Build an industrial wireless network system based on a dynamic blockchain mechanism;

[0177] Step 2: Based on the preset constraints corresponding to the task and resource joint scheduling stage of the industrial wireless network system and the consensus stage of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the task trusted processing efficiency to obtain an optimization model for scheduling the industrial wireless network system, wherein the optimization model carries various parameters to be optimized;

[0178] Step 3: reconstructing the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model;

[0179] Step 4: Based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

[0180] The specific implementation process of the above method steps can be found in any of the above-mentioned embodiments of the industrial wireless network trusted scheduling method based on dynamic blockchain, and this embodiment will not be repeated here.

[0181] This application constructs an industrial wireless network system based on a dynamic blockchain mechanism; based on the preset constraints corresponding to the task and resource joint scheduling stage of the industrial wireless network system and the consensus stage of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the trusted processing efficiency of the task, and an optimization model for scheduling the industrial wireless network system is obtained, and the optimization model carries various parameters to be optimized; the dynamic blockchain mechanism is adopted to dynamically adjust the leader edge server and the blockchain timeout window according to the network status and task requirements, which not only ensures security and reliability, but also improves the flexibility and adaptability of the system. The optimization model is reconstructed based on a preset multi-agent Markov decision process model to obtain a target optimization model; based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model, and the target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system are obtained, thereby improving the trusted processing efficiency of tasks in the industrial wireless network system.

[0182] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A trusted scheduling method for industrial wireless networks based on dynamic blockchain, characterized in that: The method comprises: Build an industrial wireless network system based on dynamic blockchain mechanism; Based on the preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, a model is constructed with the goal of maximizing the task trusted processing efficiency, and an optimization model for scheduling the industrial wireless network system is obtained, wherein the optimization model carries various parameters to be optimized; Reconstructing the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model; Based on the observation information of each industrial equipment in the industrial wireless network system collected in real time, the target optimization model is optimized using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

2. The method according to claim 1, characterized in that Before constructing a model with the goal of maximizing task trusted processing efficiency based on preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, the method further includes: constructing each preset constraint; The construction of the preset constraint conditions specifically includes: Based on the task ratio of each industrial device offloaded to each edge server, a constraint condition is constructed to obtain a task offloading ratio constraint condition in the task and resource joint scheduling stage; Based on the bandwidth ratio allocated by each edge server to each industrial device, a constraint condition is constructed to obtain a bandwidth allocation ratio constraint condition in the task and resource joint scheduling stage; Based on the predetermined maximum computing frequency parameters corresponding to each of the industrial equipment, a constraint condition is constructed to obtain a local computing frequency constraint condition corresponding to each of the industrial equipment; Based on the computing energy consumption, task transmission energy consumption and maximum battery capacity corresponding to each of the industrial equipment, constraint conditions are constructed to obtain energy consumption constraint conditions corresponding to each of the industrial equipment; Based on the predetermined successful processing task counting function of the dynamic blockchain mechanism, the preset Byzantine fault tolerance coefficient, the identification parameters of each edge server completing the unloading task of each industrial device, and the task ratio of each industrial device unloaded to each edge server, the constraint conditions are constructed to obtain the blockchain security constraint conditions in the consensus stage; Based on the maximum computing frequency of each edge server, a binary indicator variable indicating whether each edge server acts as a leader, and the computing frequency allocated to block generation when each edge server acts as a leader, a constraint condition is constructed to obtain a computing frequency allocation constraint condition corresponding to each edge server; Constructing constraint conditions based on the scheduled task deadlines of each of the industrial equipment to obtain task deadline constraint conditions corresponding to each of the industrial equipment; Constraint conditions are constructed based on the trust scores of the successful completion amounts of tasks corresponding to each edge server and a predetermined threshold, so as to obtain the credibility constraint conditions corresponding to each edge server.

3. The method according to claim 1, characterized in that Before constructing a model with the goal of maximizing task trusted processing efficiency based on preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, the method further includes: constructing a task trusted processing efficiency function; The construction task trusted processing efficiency function specifically includes: Based on the preset credibility verification delay function, the preset task offloading transmission delay function and the preset edge computing delay function, a function is constructed to obtain a trusted computing process function; Based on the trusted computing process function, the preset transaction record report delay function, the preset maximum allowed consensus waiting time function, and the preset actual maximum consensus waiting time function, a function is constructed to obtain an actual consensus waiting delay function; A function is constructed based on the actual consensus waiting delay function and the preset block generation delay function to obtain an edge trusted computing delay function; A function is constructed based on the edge trusted computing delay function and the local delay function corresponding to each of the industrial devices to obtain a task trusted computing delay function corresponding to each of the industrial devices; A function is constructed based on the task trusted computing delay function and task data volume corresponding to the same industrial equipment to obtain the trusted processing efficiency function corresponding to the same industrial equipment.

4. The method according to claim 1, characterized in that Before reconstructing the optimization model based on the preset multi-agent Markov decision process model, the method further includes: constructing a preset multi-agent Markov decision process model; The construction of the preset multi-agent Markov decision process model specifically includes: Constructing an agent set, an agent observation state set, and an agent action set of the preset multi-agent Markov decision process model; Constructing a function based on a preset trusted computing reward function, a preset timeout penalty function, and a preset consensus penalty function to obtain a reward function of the preset multi-agent Markov decision process model; The preset multi-agent Markov decision process model is obtained by constructing a model based on the agent set, the agent observation state set, the agent action set and the reward function.

5. The method according to claim 2, characterized in that Before optimizing the target optimization model using a preset rotation multi-agent deep reinforcement learning algorithm model based on the observation information of each industrial device in the industrial wireless network system collected in real time, the method further includes: constructing a preset rotation multi-agent deep reinforcement learning algorithm model; The construction of a preset rotational multi-agent deep reinforcement learning algorithm model specifically includes: Constructing an initial model corresponding to each edge server, the initial model comprising an initial actor neural network, two initial critic neural networks, and two initial target critic neural networks; Initializing the initial model corresponding to the predetermined initial leader agent in each edge server to obtain initial model parameters corresponding to the initial leader agent; Based on each historical experience data, each initial model parameter, a preset first loss function, a preset second loss function, a preset third loss function, and a preset entropy regularization loss function, each initial model is trained to obtain a target deep reinforcement learning model corresponding to each edge server, so as to obtain the preset rotation multi-agent deep reinforcement learning algorithm; The target deep reinforcement learning model includes: a target actor neural network, each critic neural network, and a target critic neural network corresponding to each critic neural network for stabilizing the critic neural network.

6. The method according to claim 5, characterized in that The method of performing model training on each of the initial models based on each of the historical experience data, each of the initial model parameters, a preset first loss function, a preset second loss function, a preset third loss function, and a preset entropy regularization loss function to obtain a target deep reinforcement learning model corresponding to each of the edge servers, so as to obtain the preset rotation multi-agent deep reinforcement learning algorithm model, specifically includes: In the first decision period, a leader election is performed based on the initial calculation frequency, the initial trust score and the initial channel state of each edge server to obtain an initial leader intelligent agent; Based on a preset first loss function, a preset second loss function, a preset third loss function, and a preset entropy regularization loss function, the initial model corresponding to the initial leader intelligent agent is trained to obtain a current first model corresponding to the initial leader intelligent agent; Sending the model parameters of the current first model to each first edge server that is not the initial leader intelligent agent, and updating the initial models corresponding to each first edge server based on the model parameters to obtain the current first model corresponding to each first edge server, wherein the model parameters include the first model parameter, the second model parameter, the third model parameter and the first entropy regularization coefficient corresponding to the initial leader intelligent agent; In non-first decision-making periods, a leader is re-elected based on the current computing frequency, the current trust score and the current channel state of each edge server to obtain a current leader agent; a current first model corresponding to the current leader agent is trained based on a preset first loss function, a preset second loss function, a preset third loss function and a preset entropy regularization loss function to update the current first model; the updated model parameters of the current first model are sent to each second edge server that is not the current leader agent, and the current first model corresponding to each second edge server is updated based on the model parameters, and the cycle is iterated until the algorithm converges, and the preset rotating multi-agent deep reinforcement learning algorithm model is obtained by training.

7. The method according to claim 6, characterized in that The observation information of each industrial device in the industrial wireless network system collected in real time is optimized by using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain the target parameter value corresponding to each parameter to be optimized for scheduling the industrial wireless network system, specifically including: Based on the observation information of each industrial device in the industrial wireless network system collected in real time, a target actor neural network in a preset rotating multi-agent deep reinforcement learning algorithm model is used to perform state prediction, and a target parameter value corresponding to each parameter to be optimized for scheduling the industrial wireless network system is obtained; The parameters to be optimized include: task division ratio, communication bandwidth allocation ratio, edge server computing frequency for offloading task processing and block generation, dynamic consensus waiting window in blockchain, and leader agent elected by edge server.

8. An industrial wireless network trusted scheduling device based on dynamic blockchain, characterized in that: include: Industrial wireless network system building module, used to build an industrial wireless network system based on a dynamic blockchain mechanism; A model building module, for building a model based on preset constraints corresponding to the task and resource joint scheduling phase of the industrial wireless network system and the consensus phase of the dynamic blockchain mechanism, with the goal of maximizing the task trusted processing efficiency, to obtain an optimization model for scheduling the industrial wireless network system, wherein the optimization model carries various parameters to be optimized; A model reconstruction module is used to reconstruct the optimization model based on a preset multi-agent Markov decision process model to obtain a target optimization model; An optimization module is used to optimize the target optimization model based on the observation information of each industrial equipment in the industrial wireless network system collected in real time using a preset rotating multi-agent deep reinforcement learning algorithm model to obtain target parameter values ​​corresponding to each parameter to be optimized for scheduling the industrial wireless network system.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the industrial wireless network trusted scheduling method based on dynamic blockchain described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: At least includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program on the memory, the steps of the industrial wireless network trusted scheduling method based on dynamic blockchain as described in any one of claims 1 to 7 are implemented.

Images