Method and apparatus for secure communication and resource allocation of power grid cyber-physical systems

Abstract

The application relates to a power grid information physical system security communication and resource allocation method and device. The method comprises the following steps: constructing an initial communication resource allocation model, obtaining state parameters and action parameters corresponding to the state parameters based on the communication resource allocation model; updating the initial communication resource allocation model based on the system delay of the power grid information physical system to obtain a target communication resource allocation model corresponding to target action parameters with the shortest system delay; and performing security communication and resource allocation on the power grid information physical system through the target action parameters. The method has the advantages of short system delay of security communication and resource allocation, short time of obtaining the communication and resource allocation mode, and high efficiency of communication and resource allocation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication resource allocation, in particular to a secure communication and resource allocation method and device of a power grid cyber-physical system. BACKGROUND

[0002] The power grid cyber-physical system is a multi-dimensional complex system integrating computing, network and physical environment. In the power grid cyber-physical system, the sensors in the system perception layer are the end devices of the cyber-physical system, which mainly function to collect information data in the environment and send them to the server in a timely manner. The server processes the information data received and returns the corresponding resource allocation mode to the physical end device. In this process, resource allocation needs to be performed under the premise of ensuring the secure communication of information.

[0003] The traditional technology is based on the characteristics of the wireless channel. In the power grid cyber-physical system, the traditional intelligent optimization algorithm is used to ensure the security of the information transmission process from the physical layer security direction. However, the process of resource allocation in the traditional intelligent optimization algorithm is slow, time-consuming and low in resource allocation efficiency. SUMMARY

[0004] Therefore, it is necessary to provide a secure communication and resource allocation method and device of a power grid cyber-physical system to solve the above technical problems.

[0005] In a first aspect, the present application provides a secure communication and resource allocation method of a power grid cyber-physical system. The method comprises:

[0006] An initial communication resource allocation model is constructed, and state parameters and action parameters corresponding to the state parameters are obtained based on the communication resource allocation model;

[0007] The initial communication resource allocation model is updated based on the system delay of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter with the shortest system delay;

[0008] The power grid cyber-physical system is subjected to secure communication and resource allocation through the target action parameter.

[0009] In one embodiment, the initial communication resource allocation model is updated based on the system delay of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter with the shortest system delay, which comprises:

[0010] A target function used to represent the system delay is obtained, and the target function includes a variable term configured according to the action parameter;

[0011] A training function is determined through the target function, and the training function is used to train the initial communication resource allocation model;

[0012] updating the initial communication resource allocation model according to the action parameter and the training function to obtain a target communication resource allocation model.

[0013] In one of the embodiments, the updating of the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model comprises:

[0014] obtaining the reward value of the action parameter corresponding to the current state parameter according to the training function, and determining the action parameter corresponding to the maximum reward value;

[0015] iteratively updating the initial communication resource allocation model until the target action parameter is obtained, and obtaining the target communication resource allocation model according to the target action parameter.

[0016] In one of the embodiments, the obtaining of the target function for representing the system delay further comprises:

[0017] obtaining a constraint condition of the target function, and the constraint condition is used to constrain the range of the resource allocation of the power information physical system.

[0018] In one of the embodiments, the state parameter comprises a channel gain parameter and an iteration parameter, and the method further comprises:

[0019] obtaining a transmission rate and a calculation rate of the power information physical system according to the channel gain parameter and the action parameter;

[0020] obtaining the system delay according to the transmission rate and the calculation rate;

[0021] updating the state parameter and the corresponding action parameter through the iteration parameter to obtain an updated system delay, so as to obtain the target communication resource allocation model.

[0022] In one of the embodiments, the obtaining of the transmission rate and the calculation rate of the power information physical system according to the channel gain parameter and the action parameter comprises:

[0023] obtaining a transmission rate from a sending end to a receiving end and a transmission rate from the sending end to a third party according to the channel gain parameter, so as to obtain an initial transmission rate;

[0024] if the initial transmission rate is greater than zero, taking the initial transmission rate as a target transmission rate, so as to perform data transmission through the target transmission rate.

[0025] In a second aspect, the application further provides a device for secure communication and resource allocation of a power information physical system. The device comprises:

[0026] a model construction module, configured to construct an initial communication resource allocation model, obtain a state parameter based on the communication resource allocation model, and obtain an action parameter corresponding to the state parameter;

[0027] a model training module configured to update an initial communication resource allocation model based on system latency of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when system latency is shortest;

[0028] a model allocation module configured to perform secure communication and resource allocation on the power grid cyber-physical system by using the target action parameter.

[0029] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0030] constructing an initial communication resource allocation model, obtaining a state parameter based on the communication resource allocation model, and an action parameter corresponding to the state parameter;

[0031] updating the initial communication resource allocation model based on system latency of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when system latency is shortest;

[0032] performing secure communication and resource allocation on the power grid cyber-physical system by using the target action parameter.

[0033] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0034] constructing an initial communication resource allocation model, obtaining a state parameter based on the communication resource allocation model, and an action parameter corresponding to the state parameter;

[0035] updating the initial communication resource allocation model based on system latency of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when system latency is shortest;

[0036] performing secure communication and resource allocation on the power grid cyber-physical system by using the target action parameter.

[0037] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program is executed by a processor to implement the following steps:

[0038] constructing an initial communication resource allocation model, obtaining a state parameter based on the communication resource allocation model, and an action parameter corresponding to the state parameter;

[0039] updating the initial communication resource allocation model based on system latency of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when system latency is shortest;

[0040] Secure communication and resource allocation for power grid cyber-physical systems through target action parameters.

[0041] The secure communication and resource allocation method and device for the power grid cyber-physical system constructs an initial communication resource allocation model, obtains state parameters and action parameters corresponding to the state parameters based on the communication resource allocation model, updates the initial communication resource allocation model based on the system delay of the power grid cyber-physical system, obtains a target communication resource allocation model corresponding to a target action parameter with the shortest system delay, and performs secure communication and resource allocation for the power grid cyber-physical system through the target action parameter. The method directly obtains the action parameter corresponding to the shortest system delay by inputting the state parameter into the target communication resource allocation model obtained through training, and then completes the communication and resource allocation of the power grid cyber-physical system according to the obtained action parameter. The method has a short system delay for secure communication and resource allocation, and a short time for obtaining the communication and resource allocation mode, which is beneficial to improving the efficiency of communication and resource allocation. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 An application environment diagram of the secure communication and resource allocation method for the power grid cyber-physical system in one embodiment;

[0043] Figure 2 A flowchart of the secure communication and resource allocation method for the power grid cyber-physical system in one embodiment;

[0044] Figure 3 An experimental data diagram of the iteration number and return reward value of the secure communication and resource allocation method for the power grid cyber-physical system in one embodiment;

[0045] Figure 4 A flowchart of the secure communication and resource allocation method for the power grid cyber-physical system in another embodiment;

[0046] Figure 5 A scene diagram of the secure communication and resource allocation method for the power grid cyber-physical system in another embodiment;

[0047] Figure 6 A structural block diagram of the secure communication and resource allocation device for the power grid cyber-physical system in one embodiment;

[0048] Figure 7 An internal structure diagram of the computer device as a server in one embodiment;

[0049] Figure 8 An internal structure diagram of the computer device as a terminal in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0051] The method for secure communication and resource allocation of the power grid cyber-physical system provided by the embodiments of the present application can be applied to the application environment of the method for secure communication and resource allocation of the power grid cyber-physical system as shown in Figure 1 . Among them, the terminal 102 constructs an initial communication resource allocation model, obtains state parameters and action parameters corresponding to the state parameters based on the communication resource allocation model, updates the initial communication resource allocation model based on the system delay of the power grid cyber-physical system, obtains a target communication resource allocation model corresponding to a target action parameter with the shortest system delay, and performs secure communication and resource allocation on the power grid cyber-physical system through the target action parameter. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0052] In one embodiment, as shown in Figure 2 , a method is provided, which will be described below by taking the terminal 102 in Figure 1 as an example, including the following steps:

[0053] Step 202, constructing an initial communication resource allocation model, obtaining state parameters and action parameters corresponding to the state parameters based on the communication resource allocation model.

[0054] Among them, the state parameters include channel gain parameters and iteration parameters. Channel gain refers to channel coefficient, which is used to describe the attenuation and fading characteristics of the channel itself, that is, to describe the transmission capability characteristics of the channel itself, for example, there is an information channel between the sensor and the grid controller in the power grid cyber-physical system, and the channel coefficient of the information channel is the channel gain between the sensor and the grid controller. Iteration is a repeated feedback process, and the result of each iteration becomes the initial value of the next iteration. The action parameters include the sending power and the calculation resource block, for example, the sending power of the sensor in the power grid cyber-physical system to send information data to the grid controller is the action parameter, and the size of the edge computing resource block of the information data processed by the edge computing server is also the action parameter.

[0055] Exemplarily, an initial communication resource allocation model with three full connection layers is constructed, applied to the power grid information physical system, the channel gain parameters corresponding to the communication channel for data communication of the current system are obtained, and the iteration round number and iteration value corresponding to the current state parameter are obtained, and the state parameter is input into the initial communication resource allocation model to obtain a plurality of action parameters corresponding to the state parameter.

[0056] In step 204, the initial communication resource allocation model is updated based on the system delay of the power grid information physical system to obtain a target communication resource allocation model corresponding to a target action parameter with the shortest system delay.

[0057] The system delay refers to the time required for the information data of the power grid information physical system to communicate and process according to the state parameter and the action parameter.

[0058] Exemplarily, a plurality of system delays can be obtained based on the obtained state parameter and a plurality of action parameters, and the system delay is calculated according to the current state parameter and the randomly selected action parameter and iteratively trained, and the initial communication resource allocation model is updated in the process of iterative training until the target action parameter corresponding to the shortest system delay is selected, and then the target communication resource allocation model is obtained.

[0059] In step 206, the power grid information physical system is communicated and resource allocated by the target action parameter.

[0060] Exemplarily, the transmission power of the sensor and the size of the computing resource block in the edge computing server when the system delay is the shortest are obtained according to the target action parameter, the system is communicated safely according to the transmission power, and the information data is processed according to the selected computing resource block.

[0061] The above-mentioned method and device for safe communication and resource allocation of the power grid information physical system construct an initial communication resource allocation model, obtain state parameters and action parameters corresponding to the state parameters based on the communication resource allocation model, update the initial communication resource allocation model based on the system delay of the power grid information physical system to obtain a target communication resource allocation model corresponding to a target action parameter with the shortest system delay, and communicate and resource allocate the power grid information physical system by the target action parameter. The method directly obtains the action parameter corresponding to the shortest system delay by inputting the state parameter into the target communication resource allocation model obtained by training, and then completes the communication and resource allocation of the power grid information physical system according to the obtained action parameter. The method realizes short system delay for safe communication and resource allocation, and short time for obtaining communication and resource allocation mode, which is beneficial to improve the efficiency of communication and resource allocation.

[0062] In one embodiment, the system delay of the power grid information physical system updates the initial communication resource allocation model to obtain a target communication resource allocation model corresponding to a target action parameter at a shortest system delay, including: obtaining a target function for characterizing the system delay, the target function including a variable term according to the action parameter configuration; determining a training function through the target function, the training function being used for training the initial communication resource allocation model; and updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model.

[0063] The target function refers to a target function obtained according to an optimization target in a model training process, for example, the optimization target in the power grid information physical system is to minimize the time delay of sensor safe communication and information data processing, and a target function corresponding to the time delay minimization can be obtained. The training function refers to a training function used for model training, for example, a deep reinforcement learning model applied in the power grid information physical system, based on which an output value related to the system delay can be obtained, the output value being a prediction value of the model, and the model is trained according to the difference between the prediction value and a sample value of the target function, and the calculation formula of the difference value for model training is the training function of the model.

[0064] For example, in the power grid information physical system, a target function related to the system delay can be obtained based on the calculation of the time delay of sensor safe communication and information data processing, the system delay can be calculated according to the state parameter and the action parameter obtained by the initial communication resource allocation model, and the system delay corresponding to different action parameters under the current state parameter can be obtained by taking the action parameter as a variable term of the target function. The training function corresponding to the target function obtained by the communication resource allocation model constructed based on the deep reinforcement learning algorithm is a Q function, and then the reward value corresponding to different action parameters can be obtained. The initial communication resource allocation model is iteratively updated according to the reward value, and the action parameter corresponding to the current state parameter and the system delay corresponding to the action parameter are reobtained. The target action parameter is obtained at the shortest system delay, the iterative training of the initial communication resource allocation model is completed when the target action parameter is obtained, and the target communication resource allocation model is obtained.

[0065] In this embodiment, the communication resource allocation model is trained through the target function and the training function related to the system delay, and the communication resource allocation model obtained can output the target action parameter at the shortest system delay, that is, the system delay required for communication and resource allocation according to the target action parameter is the shortest, and the efficiency of communication and resource allocation is improved.

[0066] In one embodiment, updating the initial communication resource allocation model based on action parameters and a training function to obtain the target communication resource allocation model includes: obtaining the reward value of the action parameter corresponding to the current state parameter based on the training function, determining the action parameter when the reward value is maximized; iteratively updating the initial communication resource allocation model until the target action parameter is obtained, and obtaining the target communication resource allocation model based on the target action parameter.

[0067] For example, an initial communication resource allocation model can be constructed based on a deep reinforcement learning algorithm. The reward values ​​corresponding to different action parameters can be obtained based on the Q function of the model. The action parameters corresponding to the maximum reward value can be obtained. The model parameters and iterative parameters in the state parameters of the initial communication resource allocation model can be updated based on the obtained reward values. The updated initial communication resource allocation model can be iteratively trained to obtain the action parameters corresponding to the updated state parameters, and the reward values ​​corresponding to the action parameters can be recalculated.

[0068] like Figure 3 The experimental data diagram showing the number of iteration rounds and the returned reward value shows that the maximum reward value can be obtained when the iteration value in the iteration parameter is reduced from 1 to 0.02. Then, the action parameter with the shortest system delay is obtained as the target action parameter. After obtaining the target action parameter, the iterative training is stopped, and the target communication resource allocation model is obtained.

[0069] In this embodiment, the initial communication resource allocation model is updated by selecting the action parameter with the largest reward value in each iteration, thereby obtaining action parameters with increasingly larger reward values ​​until the target action parameter is selected. This method is simple and efficient, saving the exhaustive operation that may be needed to find the target action parameter, that is, the optimal solution of the objective function, and can obtain an approximate optimal solution that is close to the optimal solution.

[0070] In one embodiment, obtaining the objective function for characterizing system delay further includes obtaining constraints on the objective function, the constraints being used to constrain the range of resource allocation for the power grid cyber-physical system.

[0071] For example, in a power grid cyber-physical system, the formula for calculating constraints is:

[0072]

[0073]

[0074]

[0075]

[0076] Among them, F M N represents the maximum computing speed of the edge server.u This represents the number of existing sensors. C1 ensures that the total number of processes does not exceed the number of edge servers. Constraints C2 and C3 ensure that each sensor can only select one transmit power and one computing resource block. C4 specifies that the variables in the optimization objective function are binary variables.

[0077] In this embodiment, the constraints of the objective function are clearly defined, thus realizing the role of defining the range of values ​​for variables in the objective function.

[0078] In one embodiment, the state parameters include channel gain parameters and iteration parameters. The method further includes: obtaining the transmission rate and computing rate of the power grid cyber-physical system based on the channel gain parameters and action parameters; obtaining the system delay based on the transmission rate and computing rate; and updating the state parameters and corresponding action parameters through iteration parameters to obtain the updated system delay, thereby obtaining the target communication resource allocation model.

[0079] The channel gain can be composed of large-scale fading and small-scale fading.

[0080] For example, in a power grid cyber-physical system, the channel gain can be obtained based on the fading value from the sensor to the power grid controller, and the calculation formula is as follows:

[0081] g k = k h k

[0082] Among them, g k α represents the channel gain. k Indicates large-scale fading, h k This indicates small-scale fading.

[0083] The transmission rate of information data from the sensor to the grid controller can be obtained based on the channel gain obtained from the sensor. The calculation formula is as follows:

[0084]

[0085]

[0086]

[0087] in, This represents the transmission rate at which the i-th sensor sends data to the grid controller. G represents the transmission power of the i-th sensor. i,B Let σ represent the channel gain from the i-th sensor to the grid controller. 2 This represents noise. Among them... This indicates that the i-th sensor selects the m-th transmit power P. mas its transmission power, indicates that the i-th sensor does not select the m-th transmission power P m as its transmission power.

[0088] The transmission delay of the sensor transmitting information data to the grid controller is calculated, and the calculation formula is as follows:

[0089]

[0090] where B i indicates the size of the calculated information data.

[0091] The time of the i-th sensor calculating information data on the edge server can be represented as:

[0092]

[0093] where B i indicates the size of the calculated information data, z i [k] = 1 indicates that the k-th resource block is allocated to the i-th sensor for use, z i [k] = 0 indicates that the k-th resource block is not allocated to the i-th sensor for use, u represents the computing intensity on the processor, N b indicates the number of resource blocks of the edge processor, f k indicates the computing speed of the k-th resource block.

[0094] The system delay required by the i-th sensor in the entire communication and resource allocation calculation process can be obtained, and the calculation formula is as follows:

[0095]

[0096] The updated transmission rate and calculation rate can be obtained by updating the action parameter, and then the updated system delay can be obtained. The action parameter corresponding to the minimum system delay in this iteration round can be selected, and the initial communication resource allocation model can be updated according to the action parameter, until the iteration value in the iteration parameter is stable, the iteration training is ended, and the target communication resource allocation model is obtained.

[0097] In this embodiment, the way of calculating the system delay according to the obtained state parameter and action parameter is determined, and the calculation efficiency in the initial communication resource allocation model is improved.

[0098] In one of the embodiments, the transmission rate and the calculation rate of the power grid information physical system are obtained according to the channel gain parameter and the action parameter, including: obtaining the transmission rate from the sending end to the receiving end and the transmission rate from the sending end to the third party according to the channel gain parameter, to obtain the initial transmission rate; if the initial transmission rate is greater than zero, the initial transmission rate is taken as the target transmission rate, so that data transmission is carried out through the target transmission rate.

[0099] For example, in the power grid information physical system, there are malicious third parties eavesdropping, and these eavesdroppers will eavesdrop the information data sent by the sensor to the nearby power grid controller, causing data leakage and reducing the security of the power grid information physical system. The transmission rate from the sensor to the third party can be obtained according to the channel gain from the sensor to the third party, and the calculation formula is as follows:

[0100]

[0101] Wherein, wherein represents the transmission power of the i th sensor, g i,n represents the channel gain from the i th sensor to the third party, σ 2 represents the noise.

[0102] According to the transmission rate from the sensor to the power grid controller and the third party, the target transmission rate can be obtained, and the calculation formula is as follows:

[0103]

[0104] It can be obtained that when the transmission rate from the sensor to the power grid controller is not greater than the transmission rate from the sensor to the third party, the target transmission rate of the sensor is zero, that is, no information data transmission is carried out. When the transmission rate from the sensor to the power grid controller is greater than the transmission rate from the sensor to the third party, the sensor transmits information data according to the target transmission rate, which improves the security of information transmission.

[0105] In this embodiment, the influence of the third party on the security of the information data transmission process is considered, and the transmission rate of the sensor is further clarified, which improves the security of the information transmission process.

[0106] As Figure 4 The flowchart of the power grid information physical system security communication and resource allocation method in one embodiment is shown, which is applied in the application scenario diagram of the power grid information physical system as Figure 5 The power grid information physical system security communication and resource allocation method includes the following steps:

[0107] In step 402, an initial communication resource allocation model is constructed, a state parameter is obtained based on the communication resource allocation model, and an action parameter corresponding to the state parameter is obtained, wherein the state parameter includes a channel gain parameter and an iteration parameter, and the action parameter includes a sending power and a calculation resource block.

[0108] In step 404, a transmission rate from a sending end to a receiving end and a transmission rate from the sending end to a third party are obtained according to the channel gain parameter and the sending power, so as to obtain an initial transmission rate.

[0109] In step 406, if the initial transmission rate is greater than zero, the initial transmission rate is taken as a target transmission rate, so as to perform data transmission through the target transmission rate.

[0110] In step 408, a calculation rate of a power information physical system is obtained according to the channel gain parameter and a size of the calculation resource block.

[0111] In step 410, a target function used for representing a system delay is obtained according to the target transmission rate and the calculation rate.

[0112] In step 412, a constraint condition of the target function is obtained, and the constraint condition is used for constraining a range of resource allocation of the power information physical system.

[0113] In step 414, a training function is determined through the target function, and the training function is used for training the initial communication resource allocation model.

[0114] In step 416, a reward value of an action parameter corresponding to a current state parameter is obtained according to the training function, and the action parameter when the reward value is maximum is determined.

[0115] In step 418, the initial communication resource allocation model is iteratively updated until a target action parameter is obtained, and a target communication resource allocation model is obtained according to the target action parameter.

[0116] In step 420, the power information physical system is performed for secure communication and resource allocation through the target action parameter.

[0117] In the embodiment, the initial communication resource allocation model is trained through the target function related to the system delay and the training function related to the reward value obtained according to the system delay, so that a target communication resource allocation model quickly obtaining the target action parameter from the current state parameter can be obtained, and then the secure communication and the resource allocation of the system can be realized according to the output target action parameter, and the efficiency of the communication and the resource allocation is improved.

[0118] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiments of the present application also provide a power grid cyber-physical system security communication and resource allocation device for implementing the power grid cyber-physical system security communication and resource allocation method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more power grid cyber-physical system security communication and resource allocation device embodiments provided below can refer to the limitations of the power grid cyber-physical system security communication and resource allocation method described above, and will not be repeated here.

[0120] In one embodiment, as shown in Figure 6 A power grid cyber-physical system security communication and resource allocation device 600 is provided, comprising a model construction module 602, a model training module 604 and a model allocation module 606, wherein:

[0121] The model construction module 602 is configured to construct an initial communication resource allocation model, obtain state parameters based on the communication resource allocation model, and action parameters corresponding to the state parameters;

[0122] The model training module 604 is configured to update the initial communication resource allocation model based on the system delay of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter with the shortest system delay;

[0123] The model allocation module 606 is configured to perform security communication and resource allocation on the power grid cyber-physical system through the target action parameter.

[0124] In one embodiment, the model training module 604 is further configured to obtain a target function for characterizing the system delay, the target function including a variable term configured according to the action parameter; determine a training function through the target function, the training function being used to train the initial communication resource allocation model; and update the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model.

[0125] In an embodiment, the model training module 604 is further configured to obtain a reward value of the action parameter corresponding to the current state parameter according to the training function, and determine the action parameter corresponding to the maximum reward value; and iteratively update the initial communication resource allocation model until the target action parameter is obtained, and obtain the target communication resource allocation model according to the target action parameter.

[0126] In an embodiment, the model training module 604 is further configured to obtain a constraint condition of the target function, and the constraint condition is used to constrain the range of the power grid cyber-physical system allocating resources.

[0127] In an embodiment, the apparatus is further configured to obtain a transmission rate and a calculation rate of the power grid cyber-physical system according to the channel gain parameter and the action parameter; obtain a system delay according to the transmission rate and the calculation rate; and obtain an updated system delay by iteratively updating the state parameter and the corresponding action parameter, so as to obtain the target communication resource allocation model.

[0128] In an embodiment, the apparatus is further configured to obtain a transmission rate from a sending end to a receiving end and a transmission rate from the sending end to a third party according to the channel gain parameter, so as to obtain an initial transmission rate; and if the initial transmission rate is greater than zero, take the initial transmission rate as a target transmission rate, so as to perform data transmission through the target transmission rate.

[0129] The above-mentioned various modules in the power grid cyber-physical system secure communication and resource allocation apparatus can be all or partially realized by software, hardware, and a combination thereof. The above-mentioned various modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform the operations corresponding to the above-mentioned various modules.

[0130] In an embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in FIG. 8. Figure 7As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the secure communication and resource allocation data of the power grid cyber physical system. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a power grid cyber physical system secure communication and resource allocation method.

[0131] In one embodiment, a computer device is provided, which can be a terminal, and its internal structure diagram can be as shown in the figure. Figure 8 As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the secure communication and resource allocation data of the power grid cyber physical system. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a power grid cyber physical system secure communication and resource allocation method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0132] Those skilled in the art can understand that the foregoing structure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0133] In one embodiment, the processor, when executing the computer program, also implements the following steps: constructing an initial communication resource allocation model, obtaining a state parameter based on the communication resource allocation model, and an action parameter corresponding to the state parameter; updating the initial communication resource allocation model based on the system delay of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is shortest; and performing secure communication and resource allocation on the power grid cyber-physical system through the target action parameter.

[0134] In one embodiment, the processor, when executing the computer program, also implements the following steps: updating the initial communication resource allocation model based on the system delay of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is shortest, including: obtaining a target function for representing the system delay, the target function including a variable term configured according to the action parameter; determining a training function through the target function, the training function being used to train the initial communication resource allocation model; and updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model.

[0135] In one embodiment, the processor, when executing the computer program, also implements the following steps: updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model, including: obtaining a reward value of the action parameter corresponding to the current state parameter according to the training function, and determining the action parameter when the reward value is maximum; and iteratively updating the initial communication resource allocation model until the target action parameter is obtained, and obtaining the target communication resource allocation model according to the target action parameter.

[0136] In one embodiment, the processor, when executing the computer program, also implements the following steps: obtaining a target function for representing the system delay, and further including: obtaining a constraint condition of the target function, the constraint condition being used to constrain the range of the resource allocation of the power grid cyber-physical system.

[0137] In one embodiment, the processor, when executing the computer program, also implements the following steps: the state parameter includes a channel gain parameter and an iteration parameter, and the method further includes: obtaining a transmission rate and a calculation rate of the power grid cyber-physical system according to the channel gain parameter and the action parameter; obtaining the system delay according to the transmission rate and the calculation rate; and updating the state parameter and the corresponding action parameter through the iteration parameter to obtain an updated system delay, so as to obtain the target communication resource allocation model.

[0138] In one embodiment, the processor, when executing the computer program, also implements the following steps: obtaining a transmission rate and a calculation rate of the power grid cyber-physical system according to the channel gain parameter and the action parameter, comprising: obtaining a transmission rate from the sending end to the receiving end and a transmission rate from the sending end to the third party according to the channel gain parameter to obtain an initial transmission rate; if the initial transmission rate is greater than zero, taking the initial transmission rate as a target transmission rate to perform data transmission through the target transmission rate.

[0139] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program, when executed by a processor, implements the following steps: constructing an initial communication resource allocation model, obtaining a state parameter and an action parameter corresponding to the state parameter based on the communication resource allocation model; updating the initial communication resource allocation model based on a system delay of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is the shortest; and performing secure communication and resource allocation on the power grid cyber-physical system through the target action parameter.

[0140] In one embodiment, the computer program, when executed by a processor, implements the following steps: updating the initial communication resource allocation model based on a system delay of the power grid cyber-physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is the shortest, comprising: obtaining a target function for representing the system delay, the target function including a variable term configured according to the action parameter; determining a training function through the target function, the training function being used to train the initial communication resource allocation model; and updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model.

[0141] In one embodiment, the computer program, when executed by a processor, also implements the following steps: updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model, comprising: obtaining a reward value of the action parameter corresponding to the current state parameter according to the training function, and determining the action parameter when the reward value is the largest; and iteratively updating the initial communication resource allocation model until the target action parameter is obtained, and obtaining the target communication resource allocation model according to the target action parameter.

[0142] In one embodiment, the computer program, when executed by a processor, also implements the following steps: obtaining a target function for representing the system delay, and further comprising: obtaining a constraint condition of the target function, the constraint condition being used to constrain a range of the power grid cyber-physical system allocating resources.

[0143] In one embodiment, the computer program, when executed by the processor, further implements the following steps: the state parameter comprises a channel gain parameter and an iteration parameter, and the method further comprises: obtaining a transmission rate and a calculation rate of the power grid cyber physical system according to the channel gain parameter and the action parameter; obtaining a system delay according to the transmission rate and the calculation rate; updating the state parameter and the corresponding action parameter through the iteration parameter to obtain an updated system delay, so as to obtain the target communication resource allocation model.

[0144] In one embodiment, the computer program, when executed by the processor, further implements the following steps: obtaining a transmission rate and a calculation rate of the power grid cyber physical system according to the channel gain parameter and the action parameter, comprising: obtaining a transmission rate from the sending end to the receiving end and a transmission rate from the sending end to the third party according to the channel gain parameter, to obtain an initial transmission rate; if the initial transmission rate is greater than zero, taking the initial transmission rate as a target transmission rate, so as to perform data transmission through the target transmission rate.

[0145] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps: constructing an initial communication resource allocation model, obtaining a state parameter based on the communication resource allocation model, and an action parameter corresponding to the state parameter; updating the initial communication resource allocation model based on a system delay of the power grid cyber physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is shortest; and performing secure communication and resource allocation on the power grid cyber physical system through the target action parameter.

[0146] In one embodiment, the computer program, when executed by the processor, further implements the following steps: updating the initial communication resource allocation model based on a system delay of the power grid cyber physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is shortest, comprising: obtaining a target function for representing the system delay, the target function comprising a variable term configured according to the action parameter; determining a training function through the target function, the training function being used to train the initial communication resource allocation model; and updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model.

[0147] In one embodiment, the computer program, when executed by the processor, further implements the following steps: updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model, comprising: obtaining a reward value of the action parameter corresponding to the current state parameter according to the training function, and determining the action parameter when the reward value is maximum; and iteratively updating the initial communication resource allocation model until the target action parameter is obtained, and obtaining the target communication resource allocation model according to the target action parameter.

[0148] In an embodiment, the computer program, when executed by the processor, further implements the following steps: obtaining the objective function for characterizing the system delay, and further comprising: obtaining a constraint condition of the objective function, the constraint condition being used to constrain a range of the power grid cyber-physical system allocating resources.

[0149] In an embodiment, the computer program, when executed by the processor, further implements the following steps: the state parameter comprises a channel gain parameter and an iteration parameter, and the method further comprises: obtaining a transmission rate and a calculation rate of the power grid cyber-physical system according to the channel gain parameter and the action parameter; obtaining the system delay according to the transmission rate and the calculation rate; updating the state parameter and the corresponding action parameter through the iteration parameter to obtain an updated system delay, so as to obtain the target communication resource allocation model.

[0150] In an embodiment, the computer program, when executed by the processor, further implements the following steps: obtaining the transmission rate and the calculation rate of the power grid cyber-physical system according to the channel gain parameter and the action parameter, comprising: obtaining a transmission rate from a sending end to a receiving end and a transmission rate from the sending end to a third party according to the channel gain parameter, to obtain an initial transmission rate; if the initial transmission rate is greater than zero, taking the initial transmission rate as a target transmission rate, so as to perform data transmission through the target transmission rate.

[0151] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0152] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. The non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0153] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0154] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for secure communication and resource allocation of power grid cyber-physical system, characterized in that, The method comprises: building an initial communication resource allocation model, obtaining a state parameter based on the communication resource allocation model, and an action parameter corresponding to the state parameter; the state parameter comprises a channel gain parameter and an iteration parameter; updating the initial communication resource allocation model based on the system delay of the power grid information physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is shortest; performing secure communication and resource allocation on the power grid information physical system through the target action parameter; The method further comprises: obtaining the transmission rate and the calculation rate of the power grid information physical system according to the channel gain parameter and the action parameter; obtaining the system delay according to the transmission rate and the calculation rate; updating the state parameter and the corresponding action parameter through the iteration parameter to obtain an updated system delay, so as to obtain the target communication resource allocation model; wherein, obtaining the transmission rate and the calculation rate of the power grid information physical system according to the channel gain parameter and the action parameter comprises: obtaining the transmission rate from the sending end to the receiving end and the transmission rate from the sending end to the third party according to the channel gain parameter; obtaining an initial transmission rate according to the difference between the transmission rate from the sending end to the receiving end and the transmission rate from the sending end to the third party; if the initial transmission rate is greater than zero, taking the initial transmission rate as the target transmission rate to perform data transmission through the target transmission rate; if the initial transmission rate is less than or equal to zero, taking zero as the target transmission rate.

2. The method of claim 1, wherein, The method further comprises: obtaining a target function for representing the system delay, the target function comprising a variable term configured according to the action parameter; determining a training function through the target function, the training function being used for training the initial communication resource allocation model; and updating the initial communication resource allocation model according to the action parameter and the training function to obtain the target communication resource allocation model. The method further comprises: obtaining a reward value of the action parameter corresponding to the current state parameter according to the training function, and determining the action parameter when the reward value is maximum; and iteratively updating the initial communication resource allocation model until the target action parameter is obtained, and obtaining the target communication resource allocation model according to the target action parameter. The method further comprises: obtaining a constraint condition of the target function, the constraint condition being used for constraining the range of resource allocation of the power grid information physical system. The channel gain parameter is obtained according to a fading value from the sending end to the receiving end.

3. The method of claim 2, wherein, The fading value comprises a large-scale fading value and a small-scale fading value. The device comprises: ​ 4. The method of claim 3, wherein, ​ ​ 5. The method of claim 1, wherein, ​ 6. The method of claim 5, wherein, ​ 7. A secure communication and resource allocation apparatus for power grid cyber-physical systems, characterized in that, ​ A model construction module is configured to construct an initial communication resource allocation model, obtain a state parameter based on the communication resource allocation model, and obtain an action parameter corresponding to the state parameter; the state parameter includes a channel gain parameter and an iteration parameter; A model training module is configured to update the initial communication resource allocation model based on a system delay of a power grid information physical system to obtain a target communication resource allocation model corresponding to a target action parameter when the system delay is the shortest; A model allocation module is configured to perform secure communication and resource allocation on the power grid information physical system through the target action parameter; The model training module is further configured to obtain a transmission rate and a calculation rate of the power grid information physical system according to the channel gain parameter and the action parameter, obtain the system delay according to the transmission rate and the calculation rate, and update the state parameter and the corresponding action parameter through the iteration parameter to obtain an updated system delay, so as to obtain the target communication resource allocation model; The method further includes: obtaining a transmission rate from a sending end to a receiving end and a transmission rate from the sending end to a third party according to the channel gain parameter; obtaining an initial transmission rate according to a difference between the transmission rate from the sending end to the receiving end and the transmission rate from the sending end to the third party; if the initial transmission rate is greater than zero, taking the initial transmission rate as a target transmission rate to perform data transmission through the target transmission rate; if the initial transmission rate is less than or equal to zero, taking zero as the target transmission rate. 8.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images