Cyber-physical system communication method and apparatus, electronic device, and storage medium

Abstract

The application relates to an information physical system communication method, device, electronic device and storage medium, wherein the information physical system communication method comprises the following steps: performing identity authentication on a to-be-joined node, and determining a legal node in the to-be-joined node; the to-be-joined node is a node of a to-be-joined information physical system blockchain; a target communication decision is determined according to a preset communication training model of the information physical system and parameters of a receiving node in the legal node, and safe communication is performed according to the target communication decision. Through the application, the communication security problem existing in the information physical system is solved.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular to a communication method, apparatus, electronic device, and storage medium for cyber-physical systems. Background Technology

[0002] Cyber-physical systems (CPS) are systems that deeply integrate information technology and physical technology to achieve the efficient flow and sharing of resources such as energy, materials, and information. CPS has broad application prospects in fields such as smart grids, intelligent transportation, and smart manufacturing, but it also faces severe security challenges. Because the physical network and information network in a CPS are interdependent and coupled, an attack on either will affect the secure operation of the other. Therefore, unified security protection for both the physical and information layers is necessary for CPS.

[0003] Current security protection relies heavily on key encryption to safeguard information networks. However, with the further development of chip computing power, the security performance of methods based on computational complexity is constantly declining. Therefore, it is urgent to strengthen the communication security of cyber-physical systems.

[0004] There is currently no effective solution to the communication security problems existing in cyber-physical systems in related technologies. Summary of the Invention

[0005] This embodiment provides a cyber-physical system communication method, apparatus, electronic device, and storage medium to address communication security issues in cyber-physical systems in related technologies.

[0006] Firstly, this embodiment provides a cyber-physical system communication method, the method comprising:

[0007] The identity of the nodes to be joined is verified to determine the legitimate nodes among them; the nodes to be joined are nodes of the blockchain of the cyber-physical system to be joined.

[0008] Based on the communication training model preset by the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes, a target communication decision is determined, and secure communication is performed based on the target communication decision.

[0009] In some embodiments, the step of authenticating the nodes to be joined and determining the legitimate nodes among those to be joined includes:

[0010] After the certificate authority performs real-name authentication on the node to be added, it generates a digital certificate; wherein, the certificate authority is a third-party organization of the cyber-physical system;

[0011] The node to be joined is authenticated based on a digital certificate; the digital certificate is generated after the node to be joined has been verified by a third-party certification authority.

[0012] Once the node to be added is authenticated, it is determined to be an on-chain node.

[0013] The on-chain node is placed into the blockchain, and the legitimate nodes among the on-chain nodes are identified.

[0014] In some embodiments, determining the legitimate nodes among the on-chain nodes includes:

[0015] Once the on-chain node is placed into the blockchain, it sends an access request to the legitimate authentication node in the blockchain; the legitimate authentication node is an existing legitimate node in the blockchain, used to determine whether the on-chain node is a legitimate node.

[0016] When the digital certificate of the on-chain node exists, the public key of the digital certificate is used to decrypt the random string; wherein, the legitimate authentication node generates access information in response to the access request, and encrypts the access information according to the private key of the on-chain node to obtain the random string;

[0017] When the decrypted random string matches the random string generated by the legitimate authentication node, the on-chain node is determined to be successfully authenticated, and the on-chain node is determined to be a legitimate node among the nodes to be added.

[0018] In some embodiments, determining the target communication decision based on a pre-set communication training model of the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes includes:

[0019] The communication parameters of the receiving node among the legitimate nodes are obtained, and the communication parameters of the eavesdropping node are preset; wherein, the communication parameters include channel gain, channel capacity, communication interference, and signal-to-noise ratio; the eavesdropping node is the node of the eavesdropper preset in the communication training model;

[0020] Based on the communication parameters of the legitimate node and the eavesdropping node, a communication training model for the cyber-physical system is established.

[0021] Based on the communication training model, a first confidentiality rate is obtained, which is the confidentiality rate of the receiving node within a preset range;

[0022] The target communication decision is determined based on the first security rate.

[0023] In some of these embodiments, the legitimate nodes include relay nodes and interference nodes;

[0024] The relay node is a legitimate node within the preset range of the receiving node, and the interference node is a legitimate node within the preset range of the eavesdropping node.

[0025] In some embodiments, determining the target communication decision based on a pre-set communication training model of the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes includes:

[0026] The confidentiality rate of the receiving node is obtained by considering the channel gain, communication interference, and signal-to-noise ratio during communication transmission from the sending node to the eavesdropping node.

[0027] The information of the communication channel between the sending node and the receiving node, which is being eavesdropped on by the eavesdropping node, is obtained; the information of the communication channel includes channel gain, communication interference, and signal-to-noise ratio.

[0028] Based on the information of the communication channel, the communication training model, and the first security rate, a second security rate is obtained; wherein, the second security rate is the total security rate of the receiving node; a target communication decision is determined based on the total security rate, the target communication decision including the number and location of relay nodes and interference nodes corresponding to each receiving node.

[0029] In some embodiments, determining the target communication decision based on a pre-set communication training model of the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes includes:

[0030] By using a preset algorithm, the total security rate corresponding to multiple communication decisions is traversed, and the difference between multiple total security rates and the preset total security capacity is calculated to obtain the communication decision corresponding to the total security rate whose difference is within a preset range.

[0031] The communication decision is determined to be the target communication decision, and secure communication is performed based on the target communication decision.

[0032] Secondly, this embodiment provides a cyber-physical system communication device, the device comprising: an authentication module and a communication module;

[0033] The authentication module is used to authenticate the identity of the nodes to be joined and determine the legitimate nodes among them; the nodes to be joined are nodes of the blockchain of the cyber-physical system to be joined.

[0034] The communication module is used to determine the target communication decision based on the communication training model preset by the cyber-physical system and the parameters of the receiving node among the legitimate nodes, and to perform secure communication based on the target communication decision.

[0035] Thirdly, this embodiment provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the cyber-physical system communication method described in the first aspect above.

[0036] Fourthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the cyber-physical system communication method described in the first aspect above.

[0037] Compared with related technologies, the cyber-physical system communication method provided in this embodiment improves the communication security of the cyber-physical system by authenticating the identity of the node to be joined, identifying the legitimate node among the nodes to be joined, and determining the target communication decision based on the communication training model preset by the cyber-physical system and the parameters of the receiving node among the legitimate nodes, and conducting secure communication based on the target communication decision.

[0038] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0039] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0040] Figure 1 This is a hardware structure block diagram of the terminal of the cyber-physical system communication method in this embodiment;

[0041] Figure 2 This is a flowchart of the cyber-physical system communication method in this embodiment;

[0042] Figure 3 This is a flowchart of the cyber-physical system communication method according to this specific embodiment;

[0043] Figure 4 This is a schematic diagram of the identity certificate being uploaded to the blockchain in this specific embodiment;

[0044] Figure 5 This is a flowchart of the on-chain identity authentication process in this specific embodiment;

[0045] Figure 6 This is a diagram of a smart grid CPS communication scenario according to a specific embodiment;

[0046] Figure 7 This is a model diagram of the D3QN algorithm based on this specific embodiment;

[0047] Figure 8 This is the reward convergence graph of the D3QN model training in this specific embodiment;

[0048] Figure 9 This is a performance graph of the secure transmission rate during the training process of the D3QN model in this specific embodiment;

[0049] Figure 10 This is a graph showing the secure transmission rate performance of the algorithm under different threshold settings in this specific embodiment;

[0050] Figure 11 This is a performance graph of the system's secure transmission rate under different blocking penetration coefficients in this specific embodiment;

[0051] Figure 12 This is a structural block diagram of the cyber-physical system communication device in this embodiment. Detailed Implementation

[0052] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0053] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0054] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal of the cyber-physical system communication method in this embodiment. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0055] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the cyber-physical system communication method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0056] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0057] Blockchain technology is a mechanism for exchanging information and value in an untrusted environment, and it forms the cornerstone of building the future Internet of Value. The development of blockchain can be broadly divided into three periods, and its application scope has expanded from its initial focus on digital currencies or assets to all aspects of modern socio-economic life. Currently, the application of blockchain technology has transcended the financial sector and is gradually being implemented in areas such as supply chain management, credit reporting, identity authentication, public welfare and charity, and the Internet of Things.

[0058] Identity authentication is the process of verifying whether a user's true identity matches their public persona, thereby determining the reliability of user information, preventing unauthorized users from impersonating legitimate users to obtain various permissions, and ensuring the security of user information and their legitimate interests. With the development of internet technology, identity authentication technology is also constantly evolving and improving. Currently, commonly used identity authentication methods in computer and network systems include: passwords, IC card authentication, dynamic passwords, and USB key authentication.

[0059] Cyber-physical systems (CPS) are systems that deeply integrate information technology and physical technology to achieve the efficient flow and sharing of resources such as energy, materials, and information. CPS has broad application prospects in fields such as smart grids, intelligent transportation, and smart manufacturing, but it also faces serious security challenges. Because the physical network and information network in a CPS are interdependent and coupled, an attack on either one will affect the secure operation of the other.

[0060] Physical layer security technology refers to leveraging the diversity and uniqueness of physical layer resources, such as channel states, device fingerprints, and signal modulation, to achieve confidentiality, integrity, and availability of data transmission in wireless communication systems. Physical layer security technology does not rely on traditional encryption algorithms and key management mechanisms; instead, it improves the eavesdropping channel capacity or the main channel capacity by reducing the signal-to-interference-plus-noise ratio (SNR) at the eavesdropper's location or increasing the SNR at the legitimate user's location. Physical layer security technology can be combined with upper-layer security mechanisms to form cross-layer collaborative security schemes.

[0061] Deep Reinforcement Learning (DRL) is a technique that combines deep neural networks with reinforcement learning. It can handle high-dimensional, nonlinear, complex, and uncertain systems. DRL enables autonomous learning and decision-making, making it valuable in the field of artificial intelligence. DRL can also be used in Computer-Physical Systems (CPS) to achieve intelligent control, improving system performance and decision-making efficiency.

[0062] DRL-based CPS physical layer security algorithms utilize DRL to optimize physical device or channel parameters in CPS, thereby improving confidentiality, integrity, and availability during communication or control processes. These algorithms can dynamically adjust strategies based on environmental changes, enhancing system robustness and adaptability.

[0063] This embodiment provides a cyber-physical system communication method. Figure 2 This is a flowchart of the cyber-physical system communication method in this embodiment, such as... Figure 2 As shown, the process includes the following steps:

[0064] Step S210: Authenticate the identity of the node to be joined to determine the legitimate node among the nodes to be joined; the node to be joined is a node of the blockchain of the cyber-physical system to be joined.

[0065] Specifically, the processor authenticates the nodes to be added to the cyber-physical system's blockchain, distinguishing between legitimate and illegitimate nodes, thereby identifying the legitimate nodes and adding them to the cyber-physical system's blockchain.

[0066] Step S220: Based on the communication training model preset by the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes, determine the target communication decision and perform secure communication based on the target communication decision.

[0067] Specifically, the processor determines the target communication decision based on the communication training model preset by the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes, and performs secure communication based on the target communication decision.

[0068] Through the above steps, the processor authenticates the nodes to be added to the cyber-physical system's blockchain, distinguishing them into legitimate and illegitimate nodes. Legitimate nodes are then added to the cyber-physical system's blockchain, which helps prevent unauthorized nodes from intruding into the cyber-physical system, thereby improving its security. Subsequently, based on the relevant parameters of the receiving nodes among the legitimate nodes, the processor determines the target communication decision within the cyber-physical system's pre-set communication training model. Secure communication is then conducted based on this target communication decision. This method of secure communication, based on the target communication decision determined by the pre-set communication training model and the relevant parameters of the legitimate nodes, improves the communication security of the cyber-physical system and also increases the efficiency with which legitimate nodes obtain communication decisions.

[0069] In some embodiments, step S210 includes steps S211 to S214.

[0070] Step S211: After the certificate authority performs real-name authentication on the node to be joined, it generates a digital certificate; wherein, the certificate authority is a third-party organization of the cyber-physical system.

[0071] Specifically, when a third-party organization in a cyber-physical system, namely a certificate authority, performs real-name authentication on the node to be joined, the processor generates a digital certificate.

[0072] Step S212: Authenticate the node to be joined based on the digital certificate; the digital certificate is generated after the node is verified by a third-party certification authority.

[0073] Specifically, after the processor generates a digital certificate, it performs identity authentication on the node to be joined based on the digital certificate.

[0074] Step S213: After the node to be added passes the authentication, the node to be added is determined to be an on-chain node.

[0075] Specifically, after the processor passes the authentication of the node to be added, the node to be added is determined as an on-chain node.

[0076] Step S214: Place the on-chain node into the blockchain and determine the legitimate nodes among the on-chain nodes.

[0077] Specifically, the processor places the confirmed on-chain nodes into the blockchain of the cyber-physical system, and determines whether multiple on-chain nodes are legitimate nodes based on the legitimate nodes in the blockchain.

[0078] Through the above steps, after the processor performs real-name authentication on the node to be joined through a third-party institution in the cyber-physical system, namely a certificate authority, it generates a digital certificate and uses the digital certificate to authenticate the node's identity. Once the processor successfully authenticates the node, it designates it as a node to be added to the blockchain. The added node is then placed into the blockchain, and the legitimate nodes among those added are identified. By having the node undergo real-name authentication by a third-party institution, the node to be joined is confirmed as a node to be added to the blockchain, thus determining the legitimate nodes among those added. Adding nodes to the blockchain after real-name authentication by a certificate authority improves the accuracy of node authentication and further enhances the communication security of the cyber-physical system.

[0079] In some of these embodiments, step S214 includes steps S2141 to S2143.

[0080] Step S2141: After the node is added to the blockchain, it sends an access request to the legitimate authentication node in the blockchain; the legitimate authentication node is an existing legitimate node in the blockchain, used to determine whether the node added to the blockchain is a legitimate node.

[0081] Specifically, once a node is added to the blockchain, the processor sends an access request to the legitimate authentication node in the blockchain, which is used to determine whether the node is a legitimate node.

[0082] Step S2142: When the digital certificate of the on-chain node exists, the public key of the digital certificate is used to decrypt the random string; wherein, the legitimate authentication node responds to the access request to generate access information, and encrypts the access information according to the private key of the on-chain node to obtain the random string.

[0083] Specifically, the legitimate authentication node in the processor responds to the access request by generating access information, encrypting the access information using the private key of the on-chain node to obtain a random string; the processor determines whether the digital certificate of the on-chain node exists, and if the digital certificate of the on-chain node exists, it decrypts the random string using the public key of the digital certificate.

[0084] Step S2143: When the decrypted random string matches the random string generated by the legitimate authentication node, the on-chain node is confirmed to be successfully authenticated, and the on-chain node is confirmed to be a legitimate node among the nodes to be added.

[0085] Specifically, when the decrypted random string matches the random string generated by the legitimate authentication node, the processor determines that the on-chain node has been authenticated and identifies the on-chain node as a legitimate node among the nodes to be added.

[0086] Through the above steps, after a node is added to the blockchain, the processor sends an access request to the legitimate authentication node in the blockchain, which is used to determine whether the node is legitimate. The legitimate authentication node in the processor responds to the access request by generating access information and encrypting the access information using the node's private key to obtain a random string. The processor then checks if the node's digital certificate exists. If the certificate exists, the processor decrypts the random string using the certificate's public key. When the decrypted random string matches the random string generated by the legitimate authentication node, the processor determines that the node has been successfully authenticated and identifies it as a legitimate node among the nodes to be added. Verifying the legitimacy of each other through random strings, private keys, public keys, and decryption processes among legitimate nodes improves the security and legitimacy of nodes to be added, and further enhances communication security in the subsequent cyber-physical system.

[0087] In some embodiments, step S220 includes steps S221 to S224.

[0088] Step S221: Obtain the communication parameters of the receiving node among the legitimate nodes, and preset the communication parameters of the eavesdropping node; wherein, the communication parameters include channel gain, channel capacity, communication interference, and signal-to-noise ratio; the eavesdropping node is the node of the eavesdropper preset in the communication training model. Legitimate nodes include relay nodes and interference nodes. Relay nodes are legitimate nodes within the preset range of the receiving node, and interference nodes are legitimate nodes within the preset range of the eavesdropping node.

[0089] Specifically, the processor obtains the communication parameters of the receiving node among the legitimate nodes and presets the communication parameters of the eavesdropping node. The communication parameters include channel gain, channel capacity, communication interference, and signal-to-noise ratio.

[0090] Step S222: Establish a communication training model for the cyber-physical system based on the communication parameters of the legitimate nodes and the eavesdropping nodes.

[0091] Specifically, the processor establishes a communication training model for the cyber-physical system based on the communication parameters of legitimate nodes and eavesdropping nodes.

[0092] Step S223: Based on the communication training model, obtain the first confidentiality rate, which is the confidentiality rate of the receiving node within a preset range.

[0093] Specifically, the processor obtains the confidentiality rate of the receiving node within a preset range based on the communication training model.

[0094] Step S224: Determine the target communication decision based on the first security rate.

[0095] Specifically, the processor determines the target communication decision of the cyber-physical system based on the first security rate.

[0096] Through the above steps, the processor acquires the communication parameters of the receiving node among the legitimate nodes and presets the communication parameters of the eavesdropping node. These parameters include channel gain, channel capacity, communication interference, and signal-to-noise ratio. Based on the communication parameters of the legitimate and eavesdropping nodes, a communication training model for the cyber-physical system is established. Using this model, the secure rate of the receiving node within a preset range is obtained, and the target communication decision is determined. By using legitimate nodes near the receiving node as relay nodes in the presence of an eavesdropper and employing relay communication to determine the target communication decision for the cyber-physical system, channel congestion can be avoided, and anti-eavesdropping performance can be improved, thus ensuring the communication security of the cyber-physical system.

[0097] In some embodiments, step S220 further includes steps S225 to S227.

[0098] Step S225: Obtain the confidentiality rate of the receiving node by measuring the channel gain, communication interference, and signal-to-noise ratio during communication transmission from the sending node to the eavesdropping node.

[0099] Specifically, the processor calculates the security rate of the receiving node by considering the channel gain, communication interference, and signal-to-noise ratio (SNR) during communication transmission between the sending node and the eavesdropping node. Specifically, communication interference is calculated using the channel gain, and the SNR is calculated using both the channel gain and the communication interference.

[0100] Step S226: Obtain information about the communication channel between the sending node and the receiving node that the eavesdropping node is listening to; the information about the communication channel includes channel gain, communication interference, and signal-to-noise ratio.

[0101] Specifically, the processor acquires information about the communication channel between the sending and receiving nodes that the eavesdropping node is listening to.

[0102] Step S227: Based on the information of the communication channel, the communication training model, and the first security rate, obtain the second security rate; wherein, the second security rate is the total security rate of the receiving node; determine the target communication decision based on the total security rate, the target communication decision including the number and location of relay nodes and interference nodes corresponding to each receiving node.

[0103] Specifically, the processor obtains the total security rate of the receiving node based on the information of the communication channel, the communication training model, and the security rate of the receiving node within a preset range; and determines the target communication decision based on the total security rate of the receiving node, wherein the target communication decision includes the number and location of relay nodes and interference nodes corresponding to each receiving node.

[0104] Through the above steps, the processor calculates the security rate of the receiving node by considering the channel gain, communication interference, and signal-to-noise ratio (SNR) during communication transmission between the sending node and the eavesdropping node. Simultaneously, it acquires the channel gain, communication interference, and SNR between the sending and receiving nodes being eavesdropped on by the eavesdropping node. Specifically, communication interference is calculated using the channel gain, and the SNR is calculated using both the channel gain and communication interference. Based on the communication channel information, the communication training model, and the receiving node's security rate within a preset range, the processor obtains the total security rate of the receiving node. Based on the total security rate of the receiving node, it determines multiple target communication decisions. Once a legitimate node in the cyber-physical system is confirmed, the preset model learns and trains on the location and channel information of the legitimate node. This improves the efficiency of acquiring target communication decisions, avoids channel congestion, enhances anti-eavesdropping performance, and ultimately ensures the communication security of the cyber-physical system.

[0105] In some embodiments, step S220 further includes steps S228 to S229.

[0106] Step S228: Using a preset algorithm, traverse the total security rate corresponding to multiple communication decisions, calculate the difference between the multiple total security rates and the preset total security capacity, and obtain the communication decision corresponding to the total security rate whose difference is within the preset range.

[0107] Specifically, the processor uses a preset algorithm, more specifically, deep reinforcement learning, to traverse the total security rate corresponding to multiple communication decisions, calculate the difference between the multiple total security rates and the preset total security capacity, and obtain the communication decision corresponding to the total security rate whose difference is within a preset range.

[0108] Step S229: Determine the communication decision as the target communication decision, and conduct secure communication based on the target communication decision.

[0109] Specifically, the processor determines the communication decision as the target communication decision and performs secure communication based on the target communication decision.

[0110] Through the above steps, the processor uses pre-defined deep reinforcement learning to traverse the total security rate corresponding to multiple communication decisions, calculates the difference between the multiple total security rates and the pre-defined total security capacity, obtains the communication decision corresponding to the total security rate with a difference within a pre-defined range, and determines the communication decision as the target communication decision. Secure communication is then performed based on the target communication decision. This is beneficial for improving the performance and decision-making efficiency of cyber-physical systems, thereby enhancing the robustness and adaptability of cyber-physical systems.

[0111] The present embodiment will now be described and illustrated through preferred embodiments.

[0112] Figure 3 This is a flowchart of a cyber-physical system communication method according to a specific embodiment. Figure 3 As shown, this cyber-physical system communication method is applied in a smart grid and includes the following steps:

[0113] Step S310: Upload the digital identity certificate of the smart grid node to the blockchain.

[0114] Specifically, nodes on the smart grid CPS (cyber-physical system) blockchain are functionally categorized into authentication nodes, sorting nodes, and submission nodes. When a new grid node joins the blockchain, its identity certificate on-chain process is as follows: Figure 4 , Figure 4 The following is a schematic diagram of the on-chain identity certificate in this specific embodiment:

[0115] First, the Certificate Authority (CA) authenticates and registers the new grid nodes, obtaining their public and private key pairs. The new grid nodes safeguard their private keys, while the CA generates a digital certificate for the public key and sends this digital certificate as a proposal to a certain number of authentication nodes. The CA is typically a trusted third party within the cyber-physical system. The digital certificate contains the new grid node's public key, identity information, certificate validity period, and the signature information of the CA's private key.

[0116] Secondly, the authentication node checks the certificate format, certificate validity period, and CA's private key signature information of the new grid node. Once the authentication node confirms the new grid node's information is legitimate, it returns a successful endorsement message, i.e., a proposal response, to the new grid node. According to the consensus algorithm, when the new grid node receives successful authentication messages from a certain number of authentication nodes, it packages the digital certificate and endorsement information into a transaction and submits the transaction to the sorting node. The sorting node's role is to assemble the blockchain structure according to the transaction time order and broadcast it to the committing node maintaining the blockchain for block delivery. Finally, the committing node receives the transaction packet sent by the sorting node, verifies the certificate structure, confirms the new grid node as an on-chain node, adds the new grid node to a block in the blockchain, and recalculates the hash value of the next block in the blockchain. More specifically, the new grid node is the node to be added in the above embodiment, and the authentication node, sorting node, and committing node are all legitimate nodes in the above embodiment.

[0117] Step S320: On-chain identity authentication of the smart grid cyber-physical system.

[0118] Specifically, refer to Figure 5 , Figure 5 This is a flowchart of the on-chain identity authentication process in this specific embodiment. For example... Figure 5 As shown, firstly, the on-chain node, i.e., grid node B, sends an access request to the legitimate node, i.e., grid node A. Upon receiving the access request, grid node A returns a random string to grid node B. Secondly, grid node B encrypts the random string using its stored private key and returns its identity certificate and the encrypted string to grid node A. At this point, grid node A receives the encrypted random string and grid node B's identity certificate. Subsequently, grid node A queries the blockchain based on grid node B's identity certificate to check if it has been revoked. If grid node B's identity certificate has been revoked, authentication fails, and grid node B's access is rejected. If grid node B's identity certificate has not been revoked, grid node A finds its public key and uses it to decrypt the encrypted random string received by grid node A. The decrypted string is then compared to the original random string randomly generated by grid node A. If they are equal, grid node A successfully authenticates grid node B; otherwise, authentication fails.

[0119] Step S330: Establish the communication model of the smart grid cyber-physical system. Step S330 includes steps S331 to S333.

[0120] Step S331: Establish a smart grid CPS communication scenario.

[0121] Specifically, refer to Figure 6 , Figure 6 This is a smart grid CPS communication scenario diagram according to a specific embodiment. In the smart grid CPS communication scenario, the nodes in the physical network represent various types of sensors used to collect the operating status of grid equipment and exchange data with the information network. The nodes in this communication scenario include information network nodes (senders), grid physical nodes, relay nodes, trusted nodes, interference nodes, and eavesdropping nodes. Among them, the information network nodes are the sending nodes in the aforementioned embodiments, the grid physical nodes are the receiving nodes in the aforementioned embodiments, and the trusted nodes are the legitimate nodes in the aforementioned embodiments. In the smart grid CPS communication scenario, grid physical nodes and information network nodes may not be able to directly transmit due to excessive distance or obstacles affecting transmission quality. Therefore, relay transmission is used to enhance the signal between nodes, dividing the transmission process into a first relay stage and a second relay stage; or a direct transmission process can be achieved through trusted nodes. In addition, relay transmission needs to consider the location of the eavesdropper, requiring the information end to select a suitable relay node for communication, and also requiring the selection of a suitable interference node to artificially interfere with the eavesdropper's eavesdropping node. For the aforementioned communication scenarios, the information network utilizes trusted nodes verified by the blockchain as relay transmission nodes and cooperative interference nodes for collaborative communication. While relaying data, idle nodes are used to conduct cooperative interference to reduce the signal-to-noise ratio (SNR) of eavesdroppers, thereby achieving the purpose of secure communication.

[0122] Step S332: Model the communication parameters of legitimate nodes during the communication process.

[0123] Specifically, the channel gain from the sender to the receiver during communication is as follows:

[0124] g=αL

[0125] Where α is the blocking coefficient, representing the impact of obstacles on channel gain in communication; L represents the path loss from the sender to the receiver.

[0126] Communication between multiple legitimate nodes employs beamforming technology for directional high-gain signal transmission. The receiving node achieves greater communication gain within the main lobe of the beam, but less gain within the side lobes. The gain under beamforming technology is expressed as follows:

[0127]

[0128] in, The range of the main lobe is represented by ζ, and the range of the side lobes is represented by ζ. ζ∈{t,r} represents the gain of the transmitter and receiver, respectively.

[0129] The communication process is divided into two phases: the first phase is communication from the sending node to the trusted relay node, and the second phase is communication from the trusted relay node to the receiving node. Communication includes direct transmission and relay transmission. The relay process uses Amplify and Forward (AF) mode. Cooperative interference continues throughout the communication process; therefore, cooperative interference nodes aim their main lobe at the eavesdropping node to send interference signals. From the above, the communication interference in the two transmission phases from the information network node to the sensor network (i.e., the power grid physical node) is as follows:

[0130]

[0131]

[0132] in, This indicates interference in the first stage of both direct and relay transmission. This represents the interference in the second stage under direct transmission. μ[i′] is a transmission type indicator; μ[i′] = 1 indicates that the i′-th target node uses direct transmission, and μ[i′] = 0 indicates that the i′-th target node uses relay transmission. P t This represents the transmit power of the source node. G t This represents the transmitter's antenna gain, i.e., the main lobe gain. G r The antenna gain of the receiver varies depending on the positional relationship between the transmitting and receiving nodes, resulting in different main lobe and side lobe gains.

[0133] The interference in the second stage under relay transmission is as follows:

[0134]

[0135] Where P represents the transmit power of the relay node, ι k [i′] is the relay transmission indicator, ι k [i′] = 1 indicates that the k-th trusted node is selected as a relay to forward the signal to the i′-th target receiving node; otherwise, ι k [i′]=0, G k and G i G represents the gain of the relay node and the receiver node, respectively. k，i This indicates the gain of the channel from the relay node to the receiving node.

[0136] The relay will forward the interference received in the first phase, which includes the following:

[0137]

[0138] in, This represents the interference in the first stage under direct transmission and relay transmission, γ represents the amplification and forwarding coefficient, and g k,i G represents the gain of the channel from the relay node to the receiving node. t This represents the antenna gain of the transmitting node, i.e., the main lobe gain. G r This represents the antenna gain of the receiving node.

[0139] Furthermore, interference from interfering nodes is represented as follows:

[0140] I j,ξ =Pg j,ξ G j G ξ ,

[0141] Where P represents the transmit power of the relay node, ξ∈{k,i}, g j，ξ G represents the channel gain between the interfering node and any node between the relay node and the receiving node. j G represents the antenna gain of the interfering node. ξ This represents the antenna gain of any node between the relay node and the receiving node.

[0142] Therefore, the interference experienced in the two transmission stages is obtained as follows:

[0143]

[0144]

[0145]

[0146] in, This indicates the interference experienced during the first stage of direct transmission and relay transmission. This indicates the interference experienced during the second stage of direct transmission. This indicates the interference experienced during the second stage of relay transmission. This indicates interference in the first stage of both direct and relay transmission, I. j，k This indicates that the relay node has received interference from the interfering node, I j，i This indicates that the receiving node has received interference from the interfering node. "I" indicates interference in the second stage of direct transmission, while "I" indicates interference in the second stage of relay transmission.

[0147] From the above, the signal-to-noise ratios from the sending node to the relay node and from the relay node to the receiving node are respectively:

[0148]

[0149]

[0150]

[0151] in, This represents the signal-to-noise ratio (SNR) in the first stage of direct or relay transmission. This represents the signal-to-noise ratio (SNR) in the second stage of the direct transmission process. G represents the signal-to-noise ratio (SNR) in the second stage of relay transmission. t G represents the antenna gain of the transmitting node. r For the antenna gain of the receiving node, P represents the interference experienced in the first stage of direct transmission and relay transmission. t g represents the transmit power of the transmitting node. k Indicates the channel gain from the transmitting node to the relay node; g i σ represents the channel gain from the relay node to the receiving node. 2 Indicates noise power; M B and M V G represents the gain of the transmitting node signal and the receiving node signal, respectively. k,i γ represents the channel gain from the relay node to the receiving node, and γ represents the amplification and forwarding coefficient.

[0152] The security rate C of the i-th target node i It can be represented as:

[0153]

[0154] in, Indicates direct transmission mode. This indicates that the i-th target node is transmitted by the k-th relay node, and W represents the bandwidth.

[0155] Step S333: Model the communication model of the eavesdropping node during the communication process.

[0156] Specifically, the target user's confidentiality rate is used as the optimization objective. The eavesdropper randomly selects a target receiving node as the eavesdropping target and aims the beam at the transmitting node to eavesdrop on information. Similar to the analysis in step S332, the interference in downlink transmission and communication can be expressed as:

[0157]

[0158] I j,e =Pg j,e M V G V ,

[0159]

[0160] in, This indicates the interference experienced by the channel from the eavesdropping node to the sending node, Ij，e This indicates the interference received in the channel between the sending node and the receiving node. P represents the total interference during downlink transmission. t g represents the transmit power of the transmitting node. e G represents the channel gain from the interfering node to the transmitting node. t G represents the antenna gain of the transmitting node. r M represents the antenna gain of the receiving node. V Gv represents the gain of the receiving node's signal, and Gv represents the antenna gain of the interfering node.

[0161] The signal-to-noise ratio of the eavesdropping node is:

[0162]

[0163] in, P represents the total interference during downlink transmission. t g represents the transmit power of the transmitting node. e G represents the channel gain from the interfering node to the transmitting node. t G represents the antenna gain of the transmitting node. r σ represents the antenna gain of the receiving node. 2 Indicates noise power.

[0164] The security rate of the eavesdropping node is:

[0165]

[0166] Among them, Q={q[i],i=1,2,3,…,N t}, q[i] = 1 indicates that the i-th target node is being eavesdropped on, otherwise q[i] = 0, and W represents the bandwidth.

[0167] The final optimization objective is to maximize the total security rate for all users, expressed by the following formula:

[0168]

[0169]

[0170]

[0171] Among them, ι k [i′] is the relay transmission indicator, ι k [i′] = 1 indicates that the k-th trusted node is selected as a relay to forward the signal to the i′-th target receiving node; otherwise, ι k [i′] = 0, C1 means that a target node can only choose one trusted relay node to forward, and a trusted relay node can only forward signals for one target node. It is a binary jammer selection indicator. This indicates that the j-th potential interference node has been selected as a cooperative interference node to interfere with the eavesdropping vehicle; otherwise... C2 indicates that during a transmission cycle, the eavesdropping node will eavesdrop on and only eavesdrop on one target node, and there is one and only one cooperating interference node cooperating in the transmission.

[0172] Step S340: Use the D3QN algorithm to determine the target communication decision.

[0173] Specifically, Figure 7 This is a model diagram of the D3QN algorithm based on this specific embodiment, as shown below. Figure 7 As shown, the Dual-Duel Deep Q-Network (D3QN) algorithm is used to make decisions on relay selection and interference selection. Several verified trusted nodes near the target node in the environment are selected as potential relay nodes, and several friendly nodes near the eavesdropper are selected as potential interference nodes. The algorithm's environment includes the locations of potential relay nodes, potential interference nodes, the target node, and the selected beam. The deep reinforcement learning algorithm of the transmitting node makes user communication decisions sequentially based on the environment, and finally updates the neural network parameters based on the capacity of all user communications to obtain a reward.

[0174] Specifically, the formula for calculating the target Q value using the D3QN algorithm is as follows:

[0175]

[0176] Where R is the reward at time t, a is the action at time t, a' is the action at time (t+1), θ is the parameters of the action network, θ- is the parameters of the target network, and γ is the discount factor. Q(s',a') is the Q-value of the action network output. It is the Q-value output by the target network.

[0177] D3QN uses gradient descent to update network parameters, and the loss function of the neural network is:

[0178] L = [y t -Q(s t ,a t ;θ)] 2

[0179] The overall algorithm flow is as follows: The sending node, acting as an agent, first obtains the location of the target node, the location of the eavesdropping node, the location of the trusted relay node, and the selected beam configuration in the environment as the input state s of the algorithm. t， Then, the action network outputs a decision 'a' for relay selection, cooperative interference node selection, and beam selection to the current target node. tThe algorithm then receives a reward *r* and randomly selects a batch of data from the experience replay pool, updating the network parameters through backpropagation according to the aforementioned loss function formula. The action network influences the algorithm's environment, replicates the network parameters, and proceeds to the next state *s*. t+1 Make decisions for the next target network node. After making decisions for all target nodes, store all values ​​of s, a, r, and s' from this round into the experience replay pool. By repeating the above training process, the algorithm learns the positional relationships between nodes and achieves excellent communication decision-making performance.

[0180] Regarding the reward setting for the algorithm, in order to more accurately evaluate the quality of the algorithm's decision in the current state, the reward is set as r = k(C). b -C d ), where C b C is the total confidentiality capacity of the optimal solution obtained by traversing all cases. d It represents the total confidentiality capacity of the D3QN algorithm decision, and k is a constant used to adjust the fluctuation range of the reward. Figure 8 This is the reward convergence graph for training the D3QN model in this specific embodiment. (Reference) Figure 8 , is the reward convergence graph for training the D3QN model, where the horizontal axis represents the training episode and the vertical axis represents the reward. The reward gradually approaches 0 from a large negative value as the algorithm trains. When the reward is 0, the D3QN decision is the optimal solution. Figure 9 This is a performance graph of the secure transmission rate during the training process of the D3QN model in this specific embodiment. (Reference) Figure 9 The horizontal axis represents the training episode, and the vertical axis represents the secure transmission efficiency. As the reward-following algorithm's training process gradually approaches zero from a large negative value, the secure transmission rate also gradually approaches a stable value. After an appropriate training process, the algorithm converges, and its performance reaches a level close to the optimal solution. The secure transmission rate of the decision steadily increases with each training round. After training, the sender's D3QN model can make the correct selection to determine the relay transmission node and the transmission interference node, enabling secure communication for multiple users. Figure 10 This is a graph showing the secure transmission rate performance of the algorithm under different threshold settings in this specific embodiment. (Reference) Figure 10 The horizontal axis represents the number of iterations, and the vertical axis represents the probability of secure connections under different threshold settings. During the training of the D3QN model, as the number of iterations increases, the probability of secure connections under different threshold settings gradually tends to a stable value. During the training process, the probability of secure connections at different thresholds increases with the number of training rounds and tends to 1 after 1500 training rounds, which reflects the training stability of the algorithm.

[0181] Figure 11 This is a performance graph of the system's secure transmission rate under different blocking penetration coefficients in this specific embodiment. (Reference) Figure 11 The performance graph shows the blocking coefficient on the horizontal axis and the secure transmission efficiency on the vertical axis. With half the beam blocked, the blocking coefficient varies from 0.01 to 0.1, approaching the optimal solution under varying blocking coefficient conditions. As the blocking coefficient increases, i.e., the blocking level decreases, the performance of direct transmission slightly improves, while the optimal solution and the D3QN scheme slightly decrease. This is because the communication gain from relay transmission causes the optimal solution and the D3QN scheme to tend to choose relay transmission entirely, resulting in minimal impact of blocking changes on legitimate users' communication. For eavesdroppers in the first stage of eavesdropping, a decrease in blocking level benefits their eavesdropping information; therefore, the secure capacity of the optimal solution and the D3QN scheme slowly decreases as the blocking level decreases. Thus, after trust authentication of nodes using blockchain technology, the cyber-physical system secure communication scheme based on the D3QN algorithm exhibits stability and robustness, adapts to different blocking environments, and has a stable training process with a maximum secure transmission efficiency close to the optimal solution.

[0182] This embodiment also provides a cyber-physical system communication device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. The terms "module," "unit," and "subunit," etc., used below refer to combinations of software and / or hardware that perform a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0183] This specific embodiment employs a blockchain-based distributed secure identity authentication mechanism to verify the legitimacy of power grid CPS nodes, ensuring that nodes accessing the power grid CPS system are trustworthy. This identity authentication mechanism, integrated with blockchain technology, offers advantages such as distributed storage, data immutability, and traceability, effectively preventing unauthorized nodes from intruding into the power grid CPS system. Furthermore, during communication, node identity is first verified to select trustworthy nodes in the network. Then, the D3QN algorithm is used to learn and train the location and channel information of the power grid nodes, enabling them to make excellent communication decisions in a short time. The D3QN algorithm incorporates the ideas of the Double DQN algorithm based on the Dueling DQN algorithm, effectively solving the problem of inaccurate channel state information caused by transmission delay in physical layer security. Simultaneously, suitable interference nodes are selected, and artificial noise is transmitted from appropriate interference locations, reducing the impact of noise on communication users and ensuring communication security at the physical layer, thereby addressing the problem of overly powerful eavesdroppers.

[0184] Figure 12 This is a structural block diagram of the cyber-physical system communication device in this embodiment, as shown below. Figure 12As shown, the device includes: an authentication module 10 and a communication module 20;

[0185] The authentication module 10 is used to authenticate the identity of the nodes to be joined and to determine the legitimate nodes among the nodes to be joined; the nodes to be joined are the nodes of the blockchain of the cyber-physical system to be joined.

[0186] The communication module 20 is used to determine the target communication decision based on the communication training model preset by the cyber-physical system and the parameters of the receiving node among the legitimate nodes, and to conduct secure communication based on the target communication decision.

[0187] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0188] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0189] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0190] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0191] Step 1: Authenticate the identity of the nodes to be joined to determine the legitimate nodes among them; the nodes to be joined are the nodes of the blockchain of the cyber-physical system to be joined.

[0192] Step two: Based on the pre-set communication training model of the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes, determine the target communication decision and conduct secure communication based on the target communication decision.

[0193] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0194] Furthermore, in conjunction with the cyber-physical system communication methods provided in the above embodiments, this embodiment can also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements any of the cyber-physical system communication methods described in the above embodiments.

[0195] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0196] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0197] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0198] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A communication method for a cyber-physical system, characterized in that, The method includes: The process involves authenticating the identity of nodes to be added, identifying legitimate nodes among them, where each node is a node in the cyber-physical system's blockchain. This authentication process includes: generating a digital certificate after a certificate authority (CA) performs real-name authentication on the node; the CA being a third-party certification authority within the cyber-physical system; authenticating the node based on the digital certificate; confirming the node as an on-chain node after successful authentication; placing the on-chain node into the blockchain and identifying legitimate nodes among them. Once the on-chain node is placed into the blockchain, it sends an access request to the legitimate authentication node in the blockchain; the legitimate authentication node is an existing legitimate node in the blockchain, used to determine whether the on-chain node is a legitimate node. When the digital certificate of the on-chain node exists, the public key of the digital certificate is used to decrypt the random string; wherein, the legitimate authentication node generates access information in response to the access request, and encrypts the access information according to the private key of the on-chain node to obtain the random string; When the decrypted random string matches the random string generated by the legitimate authentication node, the on-chain node is determined to be successfully authenticated, and the on-chain node is determined to be a legitimate node among the nodes to be added. The legitimate nodes include relay nodes and interference nodes; the relay nodes are legitimate nodes within a preset range of the receiving node, and the interference nodes are legitimate nodes within a preset range of the eavesdropping node. Based on the communication training model preset by the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes, a target communication decision is determined, and secure communication is performed based on the target communication decision.

2. The cyber-physical system communication method according to claim 1, characterized in that, The step of determining the target communication decision based on the pre-set communication training model of the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes includes: The communication parameters of the receiving node among the legitimate nodes are obtained, and the communication parameters of the eavesdropping node are preset; wherein, the communication parameters include channel gain, channel capacity, communication interference, and signal-to-noise ratio; the eavesdropping node is the node of the eavesdropper preset in the communication training model; Based on the communication parameters of the legitimate node and the eavesdropping node, a communication training model for the cyber-physical system is established. Based on the communication training model, a first confidentiality rate is obtained, which is the confidentiality rate of the receiving node within a preset range; The target communication decision is determined based on the first security rate.

3. The cyber-physical system communication method according to claim 2, characterized in that, The step of determining the target communication decision based on the pre-set communication training model of the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes includes: The confidentiality rate of the receiving node is obtained by considering the channel gain, communication interference, and signal-to-noise ratio during communication transmission from the sending node to the eavesdropping node. The information of the communication channel between the sending node and the receiving node, which is being eavesdropped on by the eavesdropping node, is obtained; the information of the communication channel includes channel gain, communication interference, and signal-to-noise ratio. Based on the information of the communication channel, the communication training model, and the first security rate, a second security rate is obtained; wherein, the second security rate is the total security rate of the receiving node; a target communication decision is determined based on the total security rate, the target communication decision including the number and location of relay nodes and interference nodes corresponding to each receiving node.

4. The cyber-physical system communication method according to claim 1, characterized in that, The step of determining the target communication decision based on the pre-set communication training model of the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes includes: By using a preset algorithm, the total security rate corresponding to multiple communication decisions is traversed, and the difference between multiple total security rates and the preset total security capacity is calculated to obtain the communication decision corresponding to the total security rate whose difference is within a preset range. The communication decision is determined to be the target communication decision, and secure communication is performed based on the target communication decision.

5. A cyber-physical system communication device, characterized in that, The device includes: an authentication module and a communication module; The authentication module is used to authenticate the identity of the node to be joined and determine the legitimate nodes among them. The node to be joined is a node in the blockchain of the cyber-physical system to be joined. Authentication of the node to be joined and determination of the legitimate nodes among them includes: generating a digital certificate after a certificate authority performs real-name authentication on the node to be joined; wherein the certificate authority is a third-party certification authority of the cyber-physical system; authenticating the node to be joined based on the digital certificate; determining the node to be joined as an on-chain node after successful authentication; placing the on-chain node into the blockchain and determining the legitimate nodes among them; and sending an access request to the legitimate authentication nodes in the blockchain after the on-chain node is placed into the blockchain. The legitimate authentication nodes are existing legitimate nodes in the blockchain used to determine whether the on-chain node is a legitimate node in the blockchain. Legitimate nodes; when the digital certificate of the on-chain node exists, the public key of the digital certificate is used to decrypt the random string; wherein, the legitimate authentication node generates access information in response to the access request, and encrypts the access information according to the private key of the on-chain node to obtain the random string; when the decrypted random string is consistent with the random string generated by the legitimate authentication node, it is determined that the on-chain node has been authenticated and that the on-chain node is a legitimate node among the nodes to be added; the legitimate nodes include relay nodes and interference nodes; the relay nodes are legitimate nodes within a preset range of the receiving nodes, and the interference nodes are legitimate nodes within a preset range of the eavesdropping nodes; the communication module is used to determine the target communication decision according to the communication training model preset by the cyber-physical system and the parameters of the receiving nodes among the legitimate nodes, and to perform secure communication according to the target communication decision.

6. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the cyber-physical system communication method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the cyber-physical system communication method according to any one of claims 1 to 4.

Images