A 5.5G network encryption communication method based on quantum key distribution

Abstract

The present invention discloses a 5.5G network encryption communication method based on quantum key distribution, which relates to the technical field of quantum encryption communication. A channel characteristic data set, a device parameter data set and an environmental parameter data set are collected in advance, a channel prediction model is constructed based on the channel characteristic data set and the environmental parameter data set, a device optimization model is constructed based on the device parameter data set and the prediction result of the channel prediction model, a bit error rate optimization model of an output key management strategy is constructed based on the prediction result of the channel prediction model and the optimization result of the device optimization model, the optimized key management strategy is sent, and quantum key distribution is executed according to the key management strategy, channel parameters and device parameter changes are monitored in real time through the 5.5G network, and based on the real-time monitored channel parameters and device parameter changes, a genetic algorithm is used to adjust the quantum signal generation and transmission strategy, thereby enhancing the robustness and flexibility of 5.5G network communication.

Description

Technical Field

[0001] The present invention relates to the field of quantum encryption communication technology, and in particular to a 5.5G network encryption communication method based on quantum key distribution. Background Art

[0002] How to effectively integrate quantum key distribution (QKD) technology into the 5.5G network to ensure efficient and secure communication in a complex and changing network environment has become a hot topic in current research.

[0003] Existing technologies face multiple challenges in achieving the integration of QKD and 5.5G networks. First, with the rapid growth of data traffic and the number of users in 5.5G networks, traditional fixed key management strategies are difficult to quickly adapt to real-time changing channel conditions and network topology. Secondly, the generation and transmission of quantum signals are affected by multiple factors such as environmental noise and device status. Traditional static strategies often lead to increased bit error rates, thereby reducing the security and efficiency of communications. Therefore, an intelligent adjustment mechanism is needed to dynamically optimize key management strategies and quantum signal transmission strategies to adapt to complex network environments and device conditions.

[0004] The Chinese patent application with publication number CN110971407A discloses a quantum key-based IoT security gateway communication method, including: step one: capturing data packets in the Ethernet network; step two: access authentication, identity authentication, and unsealing quantum key encrypted data; step three: parsing network layer and transport layer data, and filtering according to ACL access control policy; step four: identifying the message protocol according to the port number and protocol fingerprint, and entering the corresponding DPI parsing module; parsing the message destination port number, if it is consistent with the Modbus protocol port 502 or the custom Modbus port number, further detecting the protocol fingerprint, otherwise discarding the message and generating an alarm log; however, the scheme fails to achieve dynamic adjustment of key management strategies and quantum signal generation and transmission strategies.

[0005] To this end, the present invention proposes a 5.5G network encryption communication method based on quantum key distribution. Summary of the invention

[0006] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a 5.5G network encryption communication method based on quantum key distribution, which enhances the robustness and flexibility of 5.5G network communication.

[0007] To achieve the above purpose, a 5.5G network encryption communication method based on quantum key distribution is proposed, comprising the following steps:

[0008] Step 1: Collect channel characteristic data sets, equipment parameter data sets and environment parameter data sets in advance;

[0009] Step 2: Construct a channel prediction model based on the channel characteristic data set and the environmental parameter data set;

[0010] Step 3: Building a device optimization model based on the device parameter data set and the prediction results of the channel prediction model;

[0011] Step 4: Based on the prediction results of the channel prediction model and the optimization results of the device optimization model, a bit error rate optimization model of the output key management strategy is constructed;

[0012] Step 5: Send the optimized key management strategy, perform quantum key distribution according to the key management strategy, and monitor the changes of channel parameters and device parameters in real time through the 5.5G network;

[0013] Step 6: Based on the real-time monitored channel parameters and device parameter changes, use genetic algorithms to adjust quantum signal generation and transmission strategies;

[0014] The method of pre-collecting the channel characteristic data set, the device parameter data set and the environment parameter data set is:

[0015] In the test environment, several communication experiments are conducted, and in each communication experiment, various channel parameters in the communication experiment are collected by a channel parameter collection device to form a channel feature vector, various device parameters in the communication experiment are collected by a device monitoring device to form a device parameter feature vector, and various environmental parameters of the environment in which the communication experiment is located are collected by an environmental sensor to form an environmental feature vector;

[0016] The channel feature vectors of all communication experiments constitute a channel feature data set, the device parameter feature vectors of all communication experiments constitute a device parameter data set, and the environment feature vectors of all communication experiments constitute an environment parameter data set;

[0017] The channel prediction model is constructed based on the channel characteristic data set and the environmental parameter data set as follows:

[0018] The channel prediction model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the channel prediction model, each neuron corresponds to a channel parameter to be predicted; each neuron in the output layer outputs a parameter value sequence of the channel parameter in a future time window;

[0019] The channel parameters and environmental parameters collected in each communication experiment in the channel characteristic data set and the environmental parameter data set are divided into fixed time windows according to the time sequence of collection, and a number of channel parameter sequences and environmental parameter sequences are respectively divided for each channel parameter and environmental parameter;

[0020] In each time window, a channel parameter sequence and an environmental parameter sequence corresponding to each channel parameter and environmental parameter are selected as a first input sample of the channel prediction model;

[0021] All input environmental parameters and channel parameters are characterized and standardized using standard normal distribution;

[0022] For each time window, construct the first input sample as a three-dimensional input tensor;

[0023] Combining a plurality of first input samples into a batch for batch training of a channel prediction model;

[0024] The actual parameter values ​​of various channel parameters of various communication experiments in the next time window in the channel characteristic data set are used as prediction targets of the channel prediction model;

[0025] Using the constructed first input sample to train the channel prediction model, so that the channel prediction model learns how to predict the future channel state according to the channel characteristics and environmental parameters over a period of time in the past;

[0026] The method of constructing the device optimization model based on the device parameter data set and the prediction result of the channel prediction model is as follows:

[0027] Manually select high-quality communication experiments from each time window of all communication experiments;

[0028] The device optimization model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the device optimization model, each neuron corresponds to a device parameter that needs to be predicted, and each neuron in the output layer of the device optimization model outputs a parameter value sequence of various device parameters of the device within a future time window;

[0029] The channel prediction model is used to obtain in real time the parameter value sequence of each channel parameter in a future time window of each time window in the high-quality communication experiment;

[0030] Collect the parameter values ​​of various device parameters in each time window in the high-quality communication experiment and arrange them in chronological order to form a device parameter sequence;

[0031] The predicted parameter value sequence and device parameter sequence of the channel parameters corresponding to each time window in the high-quality communication experiment are used as a second input sample;

[0032] The actual parameter value sequence of each device parameter of each high-quality communication experiment in the next time window in the device parameter data set is used as the prediction target of the device optimization model;

[0033] The constructed second input sample is used to train the device optimization model, so that the device optimization model can learn how to adjust the future device state according to the channel characteristics in the future period and the current device parameters in the high-quality communication experiment;

[0034] The method of constructing the bit error rate optimization model of the output key management strategy based on the prediction result of the channel prediction model and the optimization result of the device optimization model is:

[0035] For each high-quality communication experiment, the current management strategy in each time window is collected; the current management strategy includes a configuration set of various policy parameters;

[0036] For each time window, respectively, a predicted parameter value sequence of each channel parameter of the next time window is obtained through the channel prediction model, and a predicted parameter value sequence of each device parameter of the next time window is obtained through the device optimization model;

[0037] The predicted parameter value sequence of each channel parameter and the predicted parameter value sequence of each device parameter together constitute a third input sample;

[0038] The bit error rate optimization model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the bit error rate optimization model, each neuron corresponds to a strategy parameter that needs to be predicted, and each neuron in the output layer of the bit error rate optimization model outputs the value of the corresponding strategy parameter in the next time window;

[0039] The actual parameter values ​​of various strategy parameters of various high-quality communication experiments in the next time window are used as the prediction targets of the bit error rate optimization model;

[0040] Using the constructed third input sample to train the bit error rate optimization model; thereby ensuring that each output parameter of the bit error rate optimization model corresponds to a component of the key management strategy;

[0041] The method of performing quantum key distribution according to the key management strategy is:

[0042] generating a quantum key using a quantum key generation method;

[0043] performing quantum key distribution according to the key management policy generated in each time window;

[0044] The method of generating the quantum key is:

[0045] Generate quanta using a quantum source;

[0046] The receiver randomly selects the same or different measurement basis to measure the received quantum state, and the measurement result is used as the initial raw key bit;

[0047] Through the communication channel, the receiver and sender disclose the measurement basis they choose, and after removing the bits that are different in the basis, an initial key is generated;

[0048] Use part of the initial key to estimate the bit error rate, determine the possible monitoring risk in the channel, and use the classic error correction algorithm to correct the error;

[0049] Privacy amplification technology is used to eliminate information leakage caused by bit errors and potential monitoring, and ultimately generate a shared security key;

[0050] Load the generated security key to the encryption device;

[0051] Ensure that the device can call the required keys for data encryption and decryption at any time during communication;

[0052] The method of real-time monitoring of channel parameters and device parameter changes through the 5.5G network is:

[0053] In real time during 5.5G network communication, the channel parameter changes of various channel parameters and the device parameter changes of various device parameters are collected;

[0054] The method of using genetic algorithm to adjust quantum signal generation and transmission strategy based on real-time monitoring of channel parameters and device parameter changes is as follows:

[0055] Step 61: setting a population individual parameter configuration; the specific individual parameters in the population individual parameter configuration correspond to a quantum signal generation and transmission strategy;

[0056] Step 62: randomly generate a group of individuals to form an initial population; each individual corresponds to a group of individual parameters;

[0057] Step 63: construct a fitness function based on the weighted sum of the bit error rate, channel utilization and power consumption;

[0058] Step 64: Use roulette wheel selection or tournament selection to select N individuals with the highest fitness from the initial population as parents; N is the preset number of individuals;

[0059] Step 65: Crossover the selected parent generation to generate offspring individuals. Use single-point crossover or multi-point crossover method to combine some strategy parameters of the parent generation to form new individuals;

[0060] Step 66: randomly changing one or more strategy parameters of the individual by a preset mutation probability to mutate the offspring individual;

[0061] Step 67: At the end of each genetic algorithm iteration cycle, the real-time monitored channel parameter changes and device parameter changes are used to adjust the population to adapt to the environment; the adjustment includes: if the real-time monitoring shows that the change of a channel parameter or the change of a device parameter is greater than a preset change threshold, then the relevant strategy parameters of the individual are adjusted accordingly to improve the dynamic response capability of the fitness calculation;

[0062] Step 68: Configure quantum signal generation and transmission devices according to the individuals optimized by the genetic algorithm.

[0063] Step 69: Through real-time monitoring, feedback data is continuously collected, including bit error rate, channel utilization, and device parameter changes, as input for the next iteration of the genetic algorithm.

[0064] An electronic device is proposed, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0065] The processor executes the above-mentioned 5.5G network encryption communication method based on quantum key distribution by calling the computer program stored in the memory.

[0066] A computer-readable storage medium is provided, on which a rewritable computer program is stored;

[0067] When the computer program runs on a computer device, the computer device executes the above-mentioned 5.5G network encryption communication method based on quantum key distribution.

[0068] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention collects channel characteristics, equipment parameters and environmental parameter data in advance, and constructs a channel prediction model based on these data. Then, using the prediction results and equipment parameter data, the equipment optimization model is designed, and the bit error rate optimization model is further constructed to output the optimized key management strategy. Quantum key distribution is performed through the optimized strategy, and the changes in channel and equipment parameters are monitored in real time during the process. The scheme uses genetic algorithms to dynamically adjust the generation and transmission strategies of quantum signals to ensure the efficient and safe operation of quantum communication systems under different channel conditions; it significantly improves the adaptability and efficiency of quantum communication systems, and realizes dynamic adjustment of quantum key distribution and encrypted communication by combining channel prediction, equipment optimization, bit error rate optimization and genetic algorithms. The scheme can maintain low bit error rates and high key generation rates under real-time changing channel conditions, enhance the robustness and flexibility of 5.5G network communications, and further improve the security and performance of communications. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1This is a flow chart of a 5.5G network encryption communication method based on quantum key distribution in Embodiment 1 of the present invention;

[0070] Figure 2 This is a flow chart of quantum signal generation and transmission strategy adjustment in Example 1 of the present invention. DETAILED DESCRIPTION

[0071] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] Example 1

[0073] like Figure 1 As shown, a 5.5G network encryption communication method based on quantum key distribution includes the following steps:

[0074] Step 1: Collect channel characteristic data sets, equipment parameter data sets and environment parameter data sets in advance;

[0075] Step 2: Construct a channel prediction model based on the channel characteristic data set and the environmental parameter data set;

[0076] Step 3: Building a device optimization model based on the device parameter data set and the prediction results of the channel prediction model;

[0077] Step 4: Based on the prediction results of the channel prediction model and the optimization results of the device optimization model, a bit error rate optimization model of the output key management strategy is constructed;

[0078] Step 5: Send the optimized key management strategy, perform quantum key distribution according to the key management strategy, and monitor the changes of channel parameters and device parameters in real time through the 5.5G network;

[0079] Step 6: Based on the real-time monitored channel parameters and device parameter changes, use genetic algorithms to adjust quantum signal generation and transmission strategies;

[0080] The method of pre-collecting the channel characteristic data set, the device parameter data set and the environment parameter data set is:

[0081] In the test environment, several communication experiments are conducted, and in each communication experiment, various channel parameters in the communication experiment are collected by a channel parameter collection device to form a channel feature vector, various device parameters in the communication experiment are collected by a device monitoring device to form a device parameter feature vector, and various environmental parameters of the environment in which the communication experiment is located are collected by an environmental sensor to form an environmental feature vector;

[0082] The channel feature vectors of all communication experiments constitute a channel feature data set, the device parameter feature vectors of all communication experiments constitute a device parameter data set, and the environment feature vectors of all communication experiments constitute an environment parameter data set;

[0083] It should be noted that the test environment refers to an experimental device that simulates actual operation. The experimental device can use network simulation tools to set different conditions to simulate channel characteristics under controllable conditions to simulate the operation of 5.5G networks and quantum key distribution systems; including the use of real or simulated hardware devices and software environments to collect important data related to channels, devices and environments. The test environment allows accurate data collection without affecting real user communications to support model development and optimization;

[0084] Further, the channel parameters include but are not limited to the channel noise level used to evaluate the degree of interference of the environment and equipment to the signal, the channel attenuation coefficient used to indicate the degree to which the signal is weakened during the transmission process, the bit error rate used to evaluate the accuracy of the received signal, the channel bandwidth used to indicate the available spectrum range and the data transmission rate, and the channel delay used to indicate the time delay of the signal propagating in the channel; wherein the channel noise level, channel attenuation coefficient and channel bandwidth can be collected using a spectrum analyzer, and the bit error rate and channel delay can be collected in real time using field test equipment;

[0085] Furthermore, the equipment parameters include but are not limited to transmitter power, laser temperature, laser wavelength, receiver sensitivity and equipment calibration status; and the above equipment parameters are recorded and saved in real time using real-time monitoring software recording equipment;

[0086] Furthermore, the environmental parameters include, but are not limited to, ambient temperature, ambient humidity, weather conditions, and also include the location and material characteristics and structural characteristics of buildings, obstacles, etc.;

[0087] Furthermore, the channel prediction model is constructed based on the channel characteristic data set and the environmental parameter data set in the following manner:

[0088] The channel prediction model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the channel prediction model, each neuron corresponds to a channel parameter to be predicted; each neuron in the output layer outputs a parameter value sequence of the channel parameter in a future time window;

[0089] Preferably, the channel prediction model can also simultaneously add multiple LSTM layers to increase the depth of the model to enhance the model's ability to capture complex time-dependent characteristics;

[0090] The channel parameters and environmental parameters collected in each communication experiment in the channel characteristic data set and the environmental parameter data set are divided into fixed time window sizes according to the time sequence of collection, and a number of channel parameter sequences and environmental parameter sequences are respectively divided for each channel parameter and environmental parameter; for example, the time window of the past 24 hours or 7 days is selected as the input sample size;

[0091] In each time window, a channel parameter sequence and an environmental parameter sequence corresponding to each channel parameter and environmental parameter are selected as a first input sample of the channel prediction model;

[0092] It should be noted that for non-digital parameters, they can be processed in a digital way, for example, sunny day = 0, rainy day = 1;

[0093] All input environmental parameters and channel parameters are characterized and standardized using standard normal distribution;

[0094] For each time window, construct the first input sample as a three-dimensional input tensor;

[0095] Combining a plurality of first input samples into a batch for batch training of a channel prediction model;

[0096] The actual parameter values ​​of various channel parameters of various communication experiments in the next time window in the channel characteristic data set are used as prediction targets of the channel prediction model;

[0097] Using the constructed first input sample to train the channel prediction model, so that the channel prediction model learns how to predict the future channel state according to the channel characteristics and environmental parameters over a period of time in the past;

[0098] It can be understood that through the construction and training of the multi-output LSTM model, the time series data of channel characteristics and environmental parameters can be effectively processed and multi-parameter prediction can be provided, thus ensuring that the model has good prediction performance and generalization ability in complex and changing communication environments;

[0099] Furthermore, the device optimization model is constructed based on the device parameter data set and the prediction result of the channel prediction model in the following manner:

[0100] Manually select a high-quality communication experiment from each time window of all communication experiments; the high-quality communication experiment refers to a communication experiment with a low bit error rate and good communication quality. It can be understood that in the high-quality communication experiment, the device parameters used by the signal sending device and the receiving device are parameter values ​​suitable for the current channel conditions and environmental conditions;

[0101] The device optimization model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the device optimization model, each neuron corresponds to a device parameter that needs to be predicted, and each neuron in the output layer of the device optimization model outputs a parameter value sequence of various device parameters of the device within a future time window;

[0102] The channel prediction model is used to obtain in real time the parameter value sequence of each channel parameter in a future time window of each time window in the high-quality communication experiment;

[0103] Collect the parameter values ​​of various device parameters in each time window in the high-quality communication experiment and arrange them in chronological order to form a device parameter sequence;

[0104] The predicted parameter value sequence and device parameter sequence of the channel parameters corresponding to each time window in the high-quality communication experiment are used as a second input sample;

[0105] The actual parameter value sequence of each device parameter of each high-quality communication experiment in the next time window in the device parameter data set is used as the prediction target of the device optimization model;

[0106] The constructed second input sample is used to train the device optimization model, so that the device optimization model can learn how to adjust the future device state according to the channel characteristics in the future period and the current device parameters in the high-quality communication experiment, so as to adjust the device parameters before the channel state changes, thereby improving the system performance;

[0107] Furthermore, the method of constructing the bit error rate optimization model of the output key management strategy based on the prediction result of the channel prediction model and the optimization result of the device optimization model is:

[0108] For each high-quality communication experiment, the current management strategy in each time window is collected; specifically, the current management strategy includes a configuration set of various policy parameters, and the policy parameters include but are not limited to: a key update frequency that determines the frequency of updating the key; an error correction code selection that selects a suitable error correction coding scheme according to the current bit error rate and the predicted bit error rate; a load balancing parameter for adjusting the key distribution load between different channels;

[0109] For each time window, respectively, a predicted parameter value sequence of each channel parameter of the next time window is obtained through the channel prediction model, and a predicted parameter value sequence of each device parameter of the next time window is obtained through the device optimization model;

[0110] The predicted parameter value sequence of each channel parameter and the predicted parameter value sequence of each device parameter together constitute a third input sample;

[0111] The bit error rate optimization model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the bit error rate optimization model, each neuron corresponds to a strategy parameter that needs to be predicted, and each neuron in the output layer of the bit error rate optimization model outputs the value of the corresponding strategy parameter in the next time window;

[0112] The actual parameter values ​​of various strategy parameters of various high-quality communication experiments in the next time window are used as the prediction targets of the bit error rate optimization model;

[0113] The constructed third input sample is used to train the bit error rate optimization model; thereby ensuring that each output parameter of the bit error rate optimization model corresponds to a component of the key management strategy, and by combining these parameters, a complete strategy is formed to ensure efficient key management in a dynamic network environment;

[0114] Furthermore, the method of performing quantum key distribution according to the key management strategy is:

[0115] generating a quantum key using a quantum key generation method;

[0116] performing quantum key distribution according to the key management policy generated in each time window;

[0117] Specifically, the method of generating the quantum key is:

[0118] Use a quantum source to generate quanta; generally, a quantum is the polarization state of a photon, which can be horizontal, vertical, +45 degrees, and -45 degrees, and is used to encode information;

[0119] The receiver selects the same or different measurement basis to measure the received quantum state, and the measurement result is used as the initial raw key bit;

[0120] Through the communication channel, the receiver and sender disclose the measurement basis they choose, and after removing the bits that are different in the basis, an initial key is generated;

[0121] Use part of the initial key to estimate the bit error rate, determine the possible monitoring risk in the channel, use the classic error correction algorithm to correct the error, and ensure that the keys of both parties are consistent;

[0122] Privacy amplification technology is used to eliminate information leakage caused by bit errors and potential monitoring, and ultimately generate a shared security key;

[0123] Furthermore, the method of performing quantum key distribution according to the key management strategy generated in each time window includes but is not limited to:

[0124] Determine the key update frequency and scheduling timing based on the optimized key management strategy, ensure that keys can be generated and distributed in a timely manner when needed, maintain key lifecycle management, and regularly update or destroy expired keys;

[0125] securely loading the generated security key to the encryption device;

[0126] Ensure that the device can call the required keys for data encryption and decryption at any time during communication;

[0127] Furthermore, the method of monitoring the changes of channel parameters and device parameters in real time through the 5.5G network is:

[0128] In real time during 5.5G network communication, the channel parameter changes of various channel parameters and the device parameter changes of various device parameters are collected;

[0129] Specifically, the channel parameter change amount can be set to the difference between the average value of the channel parameter in the current time window and the average value of the channel parameter in the previous time window. Similarly, the device parameter change amount can be set to the difference between the average value of the device parameter in the current time window and the average value of the device parameter in the previous time window.

[0130] Further, such as Figure 2 As shown in the flow chart of quantum signal generation and transmission strategy adjustment, the method of using genetic algorithm to adjust quantum signal generation and transmission strategy based on real-time monitoring of channel parameters and device parameter changes is as follows:

[0131] Step 61: Setting the population individual parameter configuration; specifically, the specific individual parameters in the population individual parameter configuration correspond to a quantum signal generation and transmission strategy, such as but not limited to transmitter power setting, laser wavelength, receiver sensitivity, and signal modulation format;

[0132] Step 62: randomly generate a group of individuals to form an initial population; each individual corresponds to a group of individual parameters;

[0133] Step 63: construct a fitness function based on the weighted sum of the bit error rate, channel utilization and power consumption;

[0134] For example, the fitness function can be set as:

[0135] ; Where F is the fitness function, BER is the bit error rate. CU is the channel utilization, PC is the power consumption, w1, w2 and w3 are all preset proportional coefficients; the bit error rate, channel utilization and power consumption can be obtained through real-time collection, or a fitting function can be constructed based on the history of communication experiments for fitting prediction;

[0136] Step 64: Use roulette wheel selection or tournament selection to select N individuals with the highest fitness from the initial population as parents; N is the preset number of individuals;

[0137] Step 65: Crossover the selected parent generation to generate offspring individuals. Use single-point crossover or multi-point crossover method to combine some strategy parameters of the parent generation to form new individuals; the specific number of some strategy parameters is set according to the actual situation, generally 50% is selected;

[0138] Step 66: randomly changing one or more strategy parameters of the individual by a preset mutation probability to mutate the offspring individual;

[0139] Step 67: At the end of each genetic algorithm iteration cycle, the real-time monitored channel parameter change and device parameter change are used to adjust the population for environmental adaptation; the adjustment includes: if the real-time monitoring shows that a channel parameter change or a device parameter change is greater than a preset change threshold, then the relevant strategy parameters of the individual are adjusted accordingly to improve the dynamic response capability of the fitness calculation; specifically, the relevant strategy parameters of the individual are adjusted accordingly to be guiding strategies pre-set according to physical principles, for example: if the noise level increases, then the variation frequency and amplitude of the power-related parameters in the strategy are increased;

[0140] Step 68: Configure quantum signal generation and transmission devices according to the individuals optimized by the genetic algorithm.

[0141] Step 69: Through real-time monitoring, feedback data is continuously collected, including bit error rate, channel utilization, and device parameter changes, as input for the next iteration of the genetic algorithm.

[0142] Example 2

[0143] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memory stores a computer-readable code, and when the computer-readable code is executed by one or more processors, it can execute a 5.5G network encryption communication method based on quantum key distribution as described above.

[0144] The method or device according to the embodiment of the present application can also be implemented with the aid of the architecture of the electronic device disclosed in the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in an electronic device, such as a ROM or a hard disk, can store a 5.5G network encryption communication method based on quantum key distribution provided in the present application.

[0145] Furthermore, the electronic device may also include a user interface. Of course, the architecture disclosed in this application is only exemplary, and when implementing different devices, one or more components in the electronic device disclosed in this application may be omitted according to actual needs.

[0146] Example 3

[0147] The present application also discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, a 5.5G network encryption communication method based on quantum key distribution disclosed in the present application can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0148] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, and when the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0149] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0150] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0151] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0152] The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained through large-scale data simulation.

[0153] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A 5.5G network encryption communication method based on quantum key distribution, characterized in that: The following steps are involved: Step 1: Collect channel characteristic data sets, equipment parameter data sets and environment parameter data sets in advance; Step 2: Construct a channel prediction model based on the channel characteristic data set and the environmental parameter data set; Step 3: Building a device optimization model based on the device parameter data set and the prediction results of the channel prediction model; Step 4: Based on the prediction results of the channel prediction model and the optimization results of the device optimization model, a bit error rate optimization model of the output key management strategy is constructed; Step 5: Send the optimized key management strategy, perform quantum key distribution according to the key management strategy, and monitor the changes of channel parameters and device parameters in real time through the 5.5G network; Step 6: Based on the real-time monitored channel parameters and device parameter changes, use genetic algorithms to adjust quantum signal generation and transmission strategies; The method of constructing the device optimization model based on the device parameter data set and the prediction result of the channel prediction model is as follows: The device optimization model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the device optimization model, each neuron corresponds to a device parameter that needs to be predicted, and each neuron in the output layer of the device optimization model outputs a parameter value sequence of various device parameters of the device within a future time window; The channel prediction model is used to obtain in real time a parameter value sequence of each channel parameter in a future time window of each time window in a high-quality communication experiment.

2. According to a 5.5G network encryption communication method based on quantum key distribution according to claim 1, it is characterized in that: The method of pre-collecting the channel characteristic data set, the device parameter data set and the environment parameter data set is: In the test environment, a communication experiment is conducted, and during each communication experiment, various channel parameters in the communication experiment are collected through a channel parameter collection device to form a channel feature vector, various device parameters in the communication experiment are collected through a device monitoring device to form a device parameter feature vector, and various environmental parameters of the environment in which the communication experiment is located are collected through an environmental sensor to form an environmental feature vector; The channel feature vectors of all communication experiments constitute a channel characteristic data set, the device parameter feature vectors of all communication experiments constitute a device parameter data set, and the environment feature vectors of all communication experiments constitute an environment parameter data set.

3. A 5.5G network encryption communication method based on quantum key distribution according to claim 2, characterized in that: The channel prediction model is constructed based on the channel characteristic data set and the environmental parameter data set as follows: The channel prediction model is set to a multi-output LSTM model, which is implemented by using multiple neurons in the output layer of the channel prediction model, each neuron corresponds to a channel parameter to be predicted; each neuron in the output layer outputs a parameter value sequence of the channel parameter in a future time window; The channel parameters and environmental parameters collected in each communication experiment in the channel characteristic data set and the environmental parameter data set are divided into fixed time windows of size according to the time sequence of collection, and a channel parameter sequence and an environmental parameter sequence are respectively divided for each channel parameter and environmental parameter; In each time window, a channel parameter sequence and an environmental parameter sequence corresponding to each channel parameter and environmental parameter are selected as a first input sample of the channel prediction model; All input environmental parameters and channel parameters are characterized and standardized using standard normal distribution; For each time window, construct the first input sample as a three-dimensional input tensor; Combining a plurality of first input samples into a batch for batch training of a channel prediction model; The actual parameter values ​​of various channel parameters of various communication experiments in the next time window in the channel characteristic data set are used as prediction targets of the channel prediction model; The channel prediction model is trained using the constructed first input sample, so that the channel prediction model learns how to predict the future channel state according to the channel characteristics and environmental parameters over a period of time in the past.

4. A 5.5G network encryption communication method based on quantum key distribution according to claim 3, characterized in that: The method of performing quantum key distribution according to the key management strategy is: generating a quantum key using a quantum key generation method; Quantum key distribution is performed according to the key management policy generated in each time window.

5. A 5.5G network encryption communication method based on quantum key distribution according to claim 4, characterized in that: The method of generating the quantum key is: Generate quanta using a quantum source; The receiver randomly selects the same or different measurement basis to measure the received quantum state, and the measurement result is used as the initial raw key bit; Through the communication channel, the receiver and sender disclose the measurement basis they choose, and after removing the bits that are different in the basis, an initial key is generated; Use part of the initial key to estimate the bit error rate, determine the possible monitoring risk in the channel, and use the classic error correction algorithm to correct the error; Privacy amplification technology is used to eliminate information leakage caused by bit errors and potential monitoring, and ultimately generate a shared security key; Load the generated security key to the encryption device; Ensure that the device can call the required keys for data encryption and decryption at any time during communication.

6. A 5.5G network encryption communication method based on quantum key distribution according to claim 5, characterized in that: The method of real-time monitoring of channel parameters and device parameter changes through the 5.5G network is: In real time during 5.5G network communication, the channel parameter changes of various channel parameters and the device parameter changes of various device parameters are collected; The method of using genetic algorithm to adjust quantum signal generation and transmission strategy based on real-time monitoring of channel parameters and device parameter changes is as follows: Step 61: setting a population individual parameter configuration; the individual parameters in the population individual parameter configuration correspond to a quantum signal generation and transmission strategy; Step 62: randomly generate a group of individuals to form an initial population; each individual corresponds to a group of individual parameters; Step 63: construct a fitness function based on the weighted sum of the bit error rate, channel utilization and power consumption; Step 64: Use roulette wheel selection or tournament selection to select N individuals with the highest fitness from the initial population as parents; N is the preset number of individuals; Step 65: crossover the selected parent generation to generate offspring individuals; use a single-point crossover or multi-point crossover method to combine some of the parent generation's strategy parameters to form new individuals; Step 66: randomly changing one or more strategy parameters of the individual by a preset mutation probability to mutate the offspring individual; Step 67: At the end of each genetic algorithm iteration cycle, the population is adjusted to adapt to the environment using the channel parameter changes and device parameter changes monitored in real time; Step 68: configuring quantum signal generation and transmission equipment according to the individuals optimized by the genetic algorithm; Step 69: Through real-time monitoring, feedback data is continuously collected, including bit error rate, channel utilization, and device parameter changes, as input for the next iteration of the genetic algorithm.

7. A 5.5G network encryption communication method based on quantum key distribution according to claim 6, characterized in that: The environmental adaptation adjustment of the population includes: if real-time monitoring shows that the change in a channel parameter or a device parameter is greater than a preset change threshold, then the relevant strategy parameters of the individual are adjusted accordingly to improve the dynamic response capability of the fitness calculation.

Images