Power distribution method and device for artificial noise beam, equipment, storage medium and product
Through the construction of the agent state and action value function table, the power allocation of artificial noise beams is dynamically adjusted, which solves the problem of preventing information stealing by eavesdroppers in 5G networks, and improves network security and channel adaptability.
Patent Information
- Application Number
- CN202411394492.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2025-01-10
AI Technical Summary
In 5G networks, it is difficult to dynamically adjust the beam power factor based on artificial noise, resulting in poor blocking of information stealing by eavesdroppers, especially in complex channel environments, which are difficult to effectively apply.
By determining the action value function based on the agent's state and actions, building an action value function table, dynamically adjusting the power allocation of the artificial noise beam, and verifying the power allocation by receiving signal quality to ensure that the legitimate user receives information correctly and preventing the stealing of the eavesdropper.
It realizes dynamic adjustment of artificial noise beam power factor in 5G network, improves the blocking effect of eavesdroppers, and ensures the security of legitimate user information and adaptability to the channel environment.
Smart Images
Figure CN119299041A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of communication technology, and in particular to a method, device, equipment, storage medium and product for allocating power of an artificial noise beam. Background Art
[0002] In the 5G era, advanced modulation and coding strategies, keys and authentication processes are generally used to enhance network security in response to network security issues. The 5G core network uses certificate-based authentication and 128bit-ZUC encryption and decryption algorithms to deal with active and passive attacks. In order to further improve the security of the access side, it is considered to apply physical layer security technology to the access side, especially to combine beamforming with artificial noise technology to ensure the security of broadcast system information and prevent malicious users from accessing base stations. The current 5G network security protection scheme based on artificial noise faces three major technical problems: First, it is difficult for the transmitter to safely obtain the instantaneous CSI of legitimate users and eavesdroppers in many scenarios; second, the statistical CSI of legitimate users and eavesdroppers is often difficult to effectively represent their channel status, resulting in poor performance of protection schemes based on statistical CSI; third, in scenarios with complex channel environments, it is difficult for traditional methods to model and analyze the channel, which limits the application of traditional CSI-based artificial noise schemes. Therefore, how to dynamically adjust the power factor of the artificial noise beam to prevent eavesdroppers from stealing information has become an urgent problem to be solved. Summary of the invention
[0003] The main purpose of this application is to provide a power allocation method, device, equipment, storage medium and product for an artificial noise beam, aiming to solve the technical problem of how to dynamically adjust the power factor of the artificial noise beam to prevent eavesdroppers from stealing information.
[0004] To achieve the above object, the present application provides a power allocation method for an artificial noise beam, the power allocation method for an artificial noise beam comprising the following steps:
[0005] Determine an action value function according to each agent state and agent action, and construct an action value function table under all agent states according to the action value function;
[0006] Determining the power distribution of each artificial noise beam according to the action value function table;
[0007] The user's received signal quality is determined according to the power allocation situation, and the power allocation situation is verified according to the received signal quality.
[0008] Optionally, the step of determining the action value function according to each agent state and agent action, and constructing the action value function table under all agent states according to the action value function specifically includes:
[0009] Determine the agent actions of the agent in each agent state;
[0010] Determining the agent reward under the state of each agent according to the agent action;
[0011] Determine, based on the agent reward, a cumulative reward for executing the agent action in each agent state;
[0012] An action value function is determined according to the accumulated reward, and an action value function table under all agent states is constructed according to the action value function.
[0013] Optionally, the step of determining the agent reward under each agent state according to the agent action specifically includes:
[0014] After the agent performs the agent action, determining a first received signal of the target eavesdropper within a first preset time period, and determining a first change in a block error rate corresponding to the first received signal;
[0015] Determine a second received signal of the target legitimate user within the first preset time period, and determine a second change in a signal-to-noise ratio corresponding to the second received signal;
[0016] The agent reward under each agent state is determined according to the first change situation and the second change situation.
[0017] Optionally, the step of determining the power distribution of each artificial noise beam according to the action value function table specifically includes:
[0018] Constructing an objective function according to the action-value function table and the agent reward;
[0019] An optimal action value function is determined according to the objective function, and the power allocation of each artificial noise beam is determined according to the optimal action value function.
[0020] Optionally, the step of determining the received signal quality of the user according to the power allocation situation, and verifying the power allocation situation according to the received signal quality specifically includes:
[0021] Determine the quality of the user's received signal according to the power allocation situation, wherein the signal reception quality includes: an average block error rate of each eavesdropper's received signal within a second preset time period and an average signal-to-noise ratio of the legitimate user's received signal within a third preset time period;
[0022] The power allocation situation is verified according to the average block error rate and the average signal-to-noise ratio.
[0023] Optionally, the step of verifying the power allocation situation according to the average block bit error rate and the average signal-to-noise ratio specifically includes:
[0024] When the average signal-to-noise ratio is greater than a first preset threshold, determining whether the average block error rate is greater than a second preset threshold;
[0025] If yes, it is determined that the power allocation verification is passed;
[0026] If not, return to the step of determining the action value function according to the agent state and agent action at each moment, and constructing the action value function table at all moments, until the new power allocation situation is verified.
[0027] In addition, to achieve the above-mentioned purpose, the present application also provides a power distribution device for an artificial noise beam, and the power distribution device for an artificial noise beam comprises:
[0028] A function determination module, used to determine an action value function according to each agent state and agent action, and to construct an action value function table under all agent states according to the action value function;
[0029] A power allocation module, used to determine the power allocation of each artificial noise beam according to the action value function table;
[0030] The power verification module is used to determine the quality of the user's received signal according to the power allocation situation, and verify the power allocation situation according to the received signal quality.
[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a power distribution device for an artificial noise beam, and the power distribution device for an artificial noise beam includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the power distribution method for an artificial noise beam as described above.
[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the power allocation method of the artificial noise beam as described above are implemented.
[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the power allocation method of the artificial noise beam as described above are implemented.
[0034] This application determines the action value function according to each agent state and agent action, and constructs an action value function table under all agent states according to the action value function, and then determines the power distribution of each artificial noise beam according to the action value function table, and then determines the quality of the user's received signal according to the power distribution, and verifies the power distribution according to the received signal quality. This application first determines the action value function table under all agent states according to each agent state and agent action, and then determines the power distribution of each artificial noise beam according to the action value function table. It can dynamically adjust the power factor of the artificial noise beam according to the action value function table, and then verify the power distribution according to the received signal quality. It can further verify the power factor of the artificial noise beam, and effectively prevent eavesdroppers from stealing system information while ensuring that legitimate users correctly receive system information. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0037] Figure 1 A schematic diagram of a flow chart of a first embodiment of a power allocation method for an artificial noise beam of the present application;
[0038] Figure 2 A schematic diagram of a flow chart of a second embodiment of a power allocation method for an artificial noise beam of the present application;
[0039] Figure 3 A schematic diagram of a flow chart of a third embodiment of a method for allocating power of an artificial noise beam according to the present application;
[0040] Figure 4 This is a schematic diagram of the overall flow of an embodiment of a method for allocating power of an artificial noise beam in the present application;
[0041] Figure 5 This is a structural block diagram of a first embodiment of a power distribution device for an artificial noise beam of the present application;
[0042] Figure 6 It is a structural diagram of a power distribution device for an artificial noise beam in a hardware operating environment involved in an embodiment of the present application.
[0043] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0045] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0046] The main solution of the embodiment of the present application is: determine the action value function according to each agent state and agent action, and construct an action value function table under all agent states according to the action value function; determine the power distribution of each artificial noise beam according to the action value function table; determine the user's received signal quality according to the power distribution, and verify the power distribution according to the received signal quality.
[0047] In the 5G era, advanced modulation and coding strategies, keys and authentication processes are generally used to enhance network security in response to network security issues. The 5G core network uses certificate-based authentication and 128bit-ZUC encryption and decryption algorithms to deal with active and passive attacks. In order to further improve the security of the access side, it is considered to apply physical layer security technology to the access side, especially to combine beamforming with artificial noise technology to ensure the security of broadcast system information and prevent malicious users from accessing base stations. The current 5G network security protection scheme based on artificial noise faces three major technical problems: First, it is difficult for the transmitter to safely obtain the instantaneous CSI of legitimate users and eavesdroppers in many scenarios; second, the statistical CSI of legitimate users and eavesdroppers is often difficult to effectively represent their channel status, resulting in poor performance of protection schemes based on statistical CSI; third, in scenarios with more complex channel environments, it is difficult for traditional methods to model and analyze the channel, which limits the application of traditional CSI-based artificial noise schemes.
[0048] This application determines the action value function according to each agent state and agent action, and constructs an action value function table under all agent states according to the action value function, and then determines the power distribution of each artificial noise beam according to the action value function table, and then determines the quality of the user's received signal according to the power distribution, and verifies the power distribution according to the received signal quality. This application first determines the action value function table under all agent states according to each agent state and agent action, and then determines the power distribution of each artificial noise beam according to the action value function table. It can dynamically adjust the power factor of the artificial noise beam according to the action value function table, and then verify the power distribution according to the received signal quality. It can further verify the power factor of the artificial noise beam, and effectively prevent eavesdroppers from stealing system information while ensuring that legitimate users correctly receive system information.
[0049] It should be noted that the execution subject of the present application may be a computing service device with data processing, network communication and program running functions, such as a computer, or an electronic device capable of realizing the above functions, a power distribution device for an artificial noise beam, etc. The power distribution device for an artificial noise beam is taken as an example to illustrate this embodiment and the following embodiments.
[0050] Based on this, the embodiment of the present application provides a power allocation method for an artificial noise beam, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of a method for allocating power of an artificial noise beam in the present application.
[0051] In this embodiment, the power allocation method of the artificial noise beam includes the following steps:
[0052] Step S10: Determine the action value function according to each agent state and agent action, and construct an action value function table under all agent states.
[0053] It is understandable that this embodiment can be applied to 5G communications, and specifically to a general 5G NR downlink multi-eavesdropper scenario, in which there is a base station Alice with M antennas, a single-antenna legitimate user Bob, and Q single-antenna eavesdroppers Eve-EveQ. Assume that over a period of time, the channel factor of each user changes little, and Alice can collect part of the channel state information of Bob and Eves in advance. The channel state information may include, for example: statistical state information or azimuth information of Bob and Eves, which can be obtained by pre-measuring the channel and the like.
[0054] It should be understood that the agent can be an intelligent entity of reinforcement learning. The object of the agent's action: the power factor g of each artificial noise beam, g∈{g an，1 , g an，2 , ..., g an，Q}. Agent state s t : represents the state observed by the agent in the environment. The state is the basis for the agent to make decisions. The agent selects corresponding actions to interact with the environment according to the current state. t is the state observed by the agent at the tth moment. In this embodiment, this state is defined as the power allocation of the current artificial noise beam, the combination of Bob's received signal SINR and Eves' received signal SINR. Agent action a t :Used to indicate that the agent is in s tThe action space can be continuous, representing different power factor allocations, or discrete, for example, divided into several predefined power factor adjustment methods. To ensure the stability and reliability of the final output result, the power factor adjustment step size can be set to g. c , and 0<g c <1, then the agent action a t It can be defined as a t ∈{g+g c ,gg c}, where g is the power factor g an，1 , g an，2 , ..., g an，Q Any one of .
[0055] In a specific implementation, the action value function can be determined based on each agent state and agent action. The action value function can represent the cumulative reward of the agent for performing the agent action in the agent state, and an action value function table under all agent states can be constructed.
[0056] Step S20: determining the power distribution of each artificial noise beam according to the action value function table.
[0057] It is understandable that the power distribution of each artificial noise beam can be determined based on the action value function table. Specifically, the action value function in the action value function table can be optimized to obtain the optimal action value function, and the power distribution can be determined based on the target state corresponding to the optimal action value function.
[0058] Step S30: determining the user's received signal quality according to the power allocation situation, and verifying the power allocation situation according to the received signal quality.
[0059] It should be understood that users may include legitimate users and eavesdroppers, and the quality of the legitimate user's received signal and the quality of the eavesdropper's received signal may be determined based on the power allocation situation. The power allocation situation may be verified based on the received signal quality to determine whether the power allocation situation can be applied to actual scenarios.
[0060] This embodiment determines the action value function according to each agent state and agent action, and constructs an action value function table under all agent states according to the action value function, and then determines the power distribution of each artificial noise beam according to the action value function table, and then determines the quality of the user's received signal according to the power distribution, and verifies the power distribution according to the received signal quality. This embodiment first determines the action value function table under all agent states according to each agent state and agent action, and then determines the power distribution of each artificial noise beam according to the action value function table, can dynamically adjust the power factor of the artificial noise beam according to the action value function table, and then verifies the power distribution according to the received signal quality, and can further verify the power factor of the artificial noise beam, and effectively prevents eavesdroppers from stealing system information on the premise of ensuring that legitimate users correctly receive system information.
[0061] refer to Figure 2 , Figure 2 This is a flow chart of a second embodiment of a method for allocating power of an artificial noise beam in the present application.
[0062] Based on the above first embodiment, in this embodiment, step S10 includes:
[0063] Step S101: Determine the agent actions of the agent in each agent state.
[0064] It is understandable that the model used in this embodiment uses Epsilon-Greedy as the action selection algorithm, which is an action selection method based on a random strategy. Agent A will randomly select an action with a certain probability ε when selecting an action, and select the current optimal action with a probability 1-ε, where is a decimal between 0 and 1. Therefore, this embodiment can determine the agent action under each agent state through the above action selection algorithm.
[0065] Step S102: Determine the agent reward under each agent state according to the agent action.
[0066] It should be understood that the agent reward r t It is the instant reward obtained by the agent based on the selected agent action and the feedback of the environment, which is used to evaluate the quality of the agent action. In this embodiment, the change of Bob's received signal SINR and Eves' received signal SINR can be used as a reference for setting the reward value.
[0067] Furthermore, in order to accurately determine the agent reward under each agent state, in the present embodiment, the step S102 includes: after the agent performs the agent action, determining a first received signal of the target eavesdropper within a first preset time period, and determining a first change in the block error rate corresponding to the first received signal; determining a second received signal of the target legitimate user within the first preset time period, and determining a second change in the signal-to-noise ratio corresponding to the second received signal; and determining the agent reward under each agent state according to the first change and the second change.
[0068] It is understandable that when the agent performs an agent action a t After that, the first received signal of the target eavesdropper within the first preset time period h can be determined. The target eavesdropper can be any one of all eavesdroppers, and the first change of the block error rate corresponding to the first received signal can be determined. The block error rate corresponding to the first received signal can be expressed as That is, agent A chooses agent action a at time t t The average BLER of the received signal of the e-th eavesdropper in the h (h>0) period after
[0069] It should be understood that the second received signal of the target legitimate user within the first preset time period h can also be determined, and the second change of the signal-to-noise ratio corresponding to the second received signal can be determined. The signal-to-noise ratio corresponding to the second received signal can be expressed as That is, agent A chooses agent action a at time t t The average SINR of the signal received by Bob in the h period after that.
[0070] In the specific implementation, The first change and The second change of the agent state determines the agent reward r t ,Right now:
[0071]
[0072] Among them, r1, r2, r3, r4 are reward coefficients, and r1, r2, r3, r4>0, is the received signal SINR demodulation threshold and
[0073] Step S103: Determine the cumulative reward for executing the agent action in each agent state according to the agent reward.
[0074] It can be understood that the Q value (action value function) represents the state of the agent s t Execute an agent action a tThe expected value of the long-term cumulative reward. Q value function Q(s t , a t ) receives an agent state s t and an agent action a t , output execution agent action a t After that, in the agent state s t The expected cumulative reward that can be obtained under the Q value, and the higher the Q value, the higher the expected value of executing the action.
[0075] Step S104: Determine an action value function according to the accumulated reward, and construct an action value function table under all agent states according to the action value function.
[0076] It should be understood that the accumulated reward can be used as the action value function under each agent state, and an action value function table under all agent states can be constructed.
[0077] Furthermore, in order to effectively obtain the power distribution of each artificial noise beam, in this embodiment, the step S20 includes: constructing an objective function according to the action value function table and the agent reward; determining the optimal action value function according to the objective function, and determining the power distribution of each artificial noise beam according to the optimal action value function.
[0078] It is understandable that the objective function in this embodiment can be expressed as: Q(s t , a t )=(1-α)Q(s t , a t )+a[r t +γmax Q(s t+1 , a t )], where α is the learning rate. To ensure the convergence of the Q-Learning algorithm, the learning rate a must satisfy: 1. 2. 3. When t→∞, Q(s t , a t ) will converge to the optimal Q value Q with probability 1 * (s t , a t ). The learning ends after the Q value converges to the optimal Q value. Thus, the optimal action value function Q can be determined by the above objective function. * (s t , a t ), and determine all target agent states corresponding to the optimal action value function. Each target agent state may include the power allocation of the current artificial noise beam, so the power allocation factor of each artificial noise beam corresponding to all target agent states can be obtained.
[0079] This embodiment determines the agent action of the agent in each agent state, then determines the agent reward in each agent state according to the agent action, then determines the cumulative reward for executing the agent action in each agent state according to the agent reward, then determines the action value function according to the cumulative reward, and constructs the action value function table in all agent states according to the action value function. This embodiment determines the cumulative reward for executing the agent action in each agent state according to the agent reward, and then determines the action value function according to the cumulative reward, and can accurately obtain the action value function in each agent state through the Q-Learning algorithm.
[0080] refer to Figure 3 , Figure 3 This is a flow chart of a third embodiment of a method for allocating power of an artificial noise beam in the present application.
[0081] Based on the above embodiments, in this embodiment, step S30 includes:
[0082] Step S301: determining the quality of the user's received signal according to the power allocation situation, wherein the signal reception quality includes: an average block error rate of each eavesdropper's received signal within a second preset time period and an average signal-to-noise ratio of the legitimate user's received signal within a third preset time period.
[0083] Understandably, referring to Figure 4 , Figure 4 The figure is a schematic diagram of the overall flow of an embodiment of the power allocation method of the artificial noise beam of the present application. Specifically, the power allocation method of the artificial noise beam proposed in the present embodiment may include an initialization phase, a learning phase, and an end phase. In the initialization phase, step 1: determine the power factor g of each artificial noise beam, g∈{g an，1 , g an，2 , ..., g an，Q}, and initialized to g = (1-g ini ) / Q,g ini is the initial power of the confidential signal beam, and 0<g ini <1. Step 2: Set the upper limit of learning times T max Step 3: Initialize the Q value, at initialization time t = 0, initialize the Q value table used to store the Q value of each state and action combination of the intelligent agent.
[0084] It should be understood that in the learning phase, step 4: let t = t + 1, update the state s t Step 5: Use the Epsilon-Greedy algorithm to select action a tIf choosing this action at this moment can increase the immediate reward, then keep this action with probability 1-ε in the next learning, and randomly choose another non-optimal action with probability ε. Step 6: Calculate the immediate reward r t Step 7: Update the Q value and store it in the Q value table. Step 8: Determine whether the maximum learning limit T is reached max , if the learning limit T is reached max , then end this learning. If the learning limit is not reached, return to step 4, that is, if t==T max , then the learning ends; otherwise, return to step 4 to continue learning.
[0085] In the specific implementation, in the end stage, step nine: complete the Q table update, and determine the power allocation of each artificial noise beam according to the Q table. Step ten: design a protection scheme based on the power allocation of the artificial noise beam, and test run the scheme to verify the learning effect. For step ten, the user's received signal quality can be determined according to the power allocation situation. The signal reception quality includes: the average block error rate BLER of the received signal of each eavesdropper in the second preset time period, and an average signal-to-noise ratio SINR of a legitimate user received signal within a third preset time period, the second preset time period may be 10 minutes, and the third preset time period may be 20 minutes.
[0086] In addition, in order to calculate the average block error rate BLER of the signals received by each eavesdropper in the second preset time period and the average signal-to-noise ratio SINR of the signals received by the legitimate users in the third preset time period, this embodiment also proposes that when Eves attempts to steal the confidential information s transmitted by Alice to Bob b Alice can send an artificial noise signal s an To interfere with Eves, the transmitted signal can be defined as:
[0087]
[0088] Among them, g b and g an，q They are s b and an The transmission power, w b and w an，q They are s b and an The beam vector of q = 1, ..., Q, and w an，q For an The qth beam vector of . Then the received signals of Alice and the nth Eve can be expressed as:
[0089]
[0090] Among them, Hb and H e，n are the channel factors of the main channel and the nth Eve’s eavesdropping channel, n b and n e，n are additive Gaussian white noise and their variances are σ b and σ e，n Therefore, assuming s b and an The power of is normalized to 1, then the SINR expectations of the received signals of Bob and the nth Eve can be expressed as:
[0091]
[0092] Since in some scenarios, the channel factor H b and H e，n It may be more complicated, and it is difficult to model and analyze the expected SINR. Therefore, it is possible to consider using reinforcement learning methods to optimize the power allocation factors of the signal beam and the artificial noise beam.
[0093] Next, design a one-dimensional DFT codebook F :
[0094]
[0095] Among them, each column vector of F can represent a fixed feature of a certain plane channel model.
[0096] Afterwards, the confidential signal beam number s corresponding to Bob (which can produce the best gain effect for Bob) is determined based on the previously acquired statistical CSI of Bob b , the confidential signal beam number within a certain time period can be determined through the pre-acquired data set, and the confidential signal beam (corresponding to Bob) can be expressed as:
[0097]
[0098] Among them, s b is the beam selection factor of Bob corresponding to the confidential signal, is the sth b A column vector.
[0099] Afterwards, the AN beam number s1, s2, ..., s corresponding to each Eve (with the best protection effect for the Eve) is determined based on the statistical CSI of the Eves obtained in advance. Q , the artificial noise beam number within a certain time period can be determined by the pre-acquired data set. For example, let the qth artificial noise beam point to the location of the qth Eve, then the qth artificial noise beam (corresponding to Eve) can be expressed as:
[0100]
[0101] Among them, s q is the artificial noise beam selection factor corresponding to the qth Eve, is the sth q A column vector.
[0102] Step S302: verifying the power allocation situation according to the average block error rate and the average signal-to-noise ratio.
[0103] Furthermore, in order to effectively verify the power allocation situation, in the present embodiment, the step S302 includes: when the average signal-to-noise ratio is greater than a first preset threshold, determining whether the average block bit error rate is greater than a second preset threshold; if so, determining that the power allocation situation has been verified; if not, returning to the step of determining the action value function according to the agent state and agent action at each moment, and constructing an action value function table at all moments, until the new power allocation situation has been verified.
[0104] It is understandable that if the average signal-to-noise ratio SINR is greater than the first preset threshold And the average block error rate BLER is greater than the second preset threshold e1, for example, e1 = 0.1, then it is determined that the power allocation verification is passed, and the artificial noise beam power allocation factors g1, g2, ..., g q , and the learning ends. If the average signal-to-noise ratio SINR is greater than the first preset threshold And the average block error rate BLER is not greater than the second preset threshold e1, let g ini =g ini -Δ, Δ is the power adjustment factor of the initial power, 20<Δ<1, and return to step 1. If the average signal-to-noise ratio SINR is not greater than the first preset threshold Let g ini =g ini -Δ, and return to step 1 until the new power allocation is verified.
[0105] This embodiment determines the quality of the user's received signal according to the power allocation situation, and the signal reception quality includes: the average block error rate of the received signal of each eavesdropper in the second preset time period and the average signal-to-noise ratio of the received signal of the legitimate user in the third preset time period, and then verifies the power allocation situation according to the average block error rate and the average signal-to-noise ratio. This embodiment verifies the power allocation situation according to the average block error rate of the received signal of each eavesdropper in the second preset time period and the average signal-to-noise ratio of the received signal of the legitimate user in the third preset time period, and can effectively verify the power factor of the artificial noise beam, thereby effectively preventing the eavesdropper from stealing system information.
[0106] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the power distribution device for artificial noise beam of the present application.
[0107] like Figure 5 As shown, the power distribution device of the artificial noise beam proposed in the embodiment of the present application includes:
[0108] A function determination module 10 is used to determine an action value function according to each agent state and agent action, and to construct an action value function table under all agent states according to the action value function;
[0109] A power allocation module 20, used to determine the power allocation of each artificial noise beam according to the action value function table;
[0110] The power verification module 30 is used to determine the quality of the user's received signal according to the power allocation situation, and verify the power allocation situation according to the received signal quality.
[0111] This embodiment determines the action value function according to each agent state and agent action, and constructs an action value function table under all agent states according to the action value function, and then determines the power distribution of each artificial noise beam according to the action value function table, and then determines the quality of the user's received signal according to the power distribution, and verifies the power distribution according to the received signal quality. This embodiment first determines the action value function table under all agent states according to each agent state and agent action, and then determines the power distribution of each artificial noise beam according to the action value function table, can dynamically adjust the power factor of the artificial noise beam according to the action value function table, and then verifies the power distribution according to the received signal quality, and can further verify the power factor of the artificial noise beam, and effectively prevents eavesdroppers from stealing system information on the premise of ensuring that legitimate users correctly receive system information.
[0112] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present application. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.
[0113] In addition, for technical details not described in detail in this embodiment, reference can be made to the power allocation method of the artificial noise beam provided in any embodiment of the present application, which will not be repeated here.
[0114] Based on the above-mentioned first embodiment of the power distribution device for an artificial noise beam of the present application, a second embodiment of the power distribution device for an artificial noise beam of the present application is proposed.
[0115] In this embodiment, the function determination module 10 is also used to determine the agent's action in each agent state; determine the agent reward in each agent state according to the agent action; determine the cumulative reward for performing the agent action in each agent state according to the agent reward; determine the action value function according to the cumulative reward, and construct an action value function table under all agent states according to the action value function.
[0116] Furthermore, the function determination module 10 is also used to determine, after the agent executes the agent action, a first received signal of the target eavesdropper within a first preset time period, and determine a first change in a block error rate corresponding to the first received signal; determine a second received signal of the target legitimate user within the first preset time period, and determine a second change in a signal-to-noise ratio corresponding to the second received signal; and determine an agent reward under each agent state based on the first change and the second change.
[0117] Furthermore, the power allocation module 20 is also used to construct an objective function based on the action value function table and the agent reward; determine the optimal action value function based on the objective function, and determine the power allocation of each artificial noise beam based on the optimal action value function.
[0118] Furthermore, the power verification module 30 is also used to determine the user's received signal quality based on the power allocation situation, and the signal reception quality includes: the average block error rate of each eavesdropper's received signal within the second preset time period and the average signal-to-noise ratio of the legitimate user's received signal within the third preset time period; the power allocation situation is verified based on the average block error rate and the average signal-to-noise ratio.
[0119] Furthermore, the power verification module 30 is also used to determine whether the average block bit error rate is greater than a second preset threshold when the average signal-to-noise ratio is greater than a first preset threshold; if so, it is determined that the power allocation situation has been verified; if not, it returns to the step of determining the action value function according to the agent state and agent action at each moment, and constructing an action value function table at all moments, until the new power allocation situation is verified.
[0120] Other embodiments or specific implementations of the power distribution device for the artificial noise beam of the present application can refer to the above-mentioned method embodiments, which will not be described in detail here.
[0121] The present application provides a power distribution device for an artificial noise beam, and the power distribution device for an artificial noise beam includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the power distribution method for the artificial noise beam in the above-mentioned embodiment 1.
[0122] Reference below Figure 6 , which shows a schematic diagram of the structure of a power distribution device for an artificial noise beam suitable for implementing an embodiment of the present application. The power distribution device for an artificial noise beam in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The power distribution device of the artificial noise beam shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0123] like Figure 6As shown, the power distribution device of the artificial noise beam may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the power distribution device of the artificial noise beam are also stored. The processing device 1001, the ROM 1002 and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the power distribution device for artificial noise beams to communicate wirelessly or wired with other devices to exchange data. Although the power distribution device for artificial noise beams having various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.
[0124] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0125] The power distribution device for an artificial noise beam provided by the present application adopts the power distribution method for an artificial noise beam in the above-mentioned embodiment, and can solve the technical problem of how to dynamically adjust the power factor of the artificial noise beam to prevent eavesdroppers from stealing information. Compared with the prior art, the beneficial effects of the power distribution device for an artificial noise beam provided by the present application are the same as the beneficial effects of the power distribution method for an artificial noise beam provided by the above-mentioned embodiment, and the other technical features in the power distribution device for an artificial noise beam are the same as the features disclosed in the method of the previous embodiment, and are not described in detail here.
[0126] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0127] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0128] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the power allocation method of the artificial noise beam in the above-mentioned embodiment.
[0129] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0130] The computer-readable storage medium may be included in the power distribution device of the artificial noise beam; or may exist independently without being assembled into the power distribution device of the artificial noise beam.
[0131] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the power allocation device of the artificial noise beam, the power allocation device of the artificial noise beam determines the action value function according to each agent state and agent action, and constructs an action value function table under all agent states according to the action value function; determines the power allocation of each artificial noise beam according to the action value function table; determines the user's received signal quality according to the power allocation situation, and verifies the power allocation situation according to the received signal quality.
[0132] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0133] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0134] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0135] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned power allocation method of the artificial noise beam, and can solve the technical problem of how to dynamically adjust the power factor of the artificial noise beam to prevent eavesdroppers from stealing information. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the power allocation method of the artificial noise beam provided by the above-mentioned embodiment, and will not be repeated here.
[0136] The present application also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the power allocation method for the artificial noise beam as described above are implemented.
[0137] The computer program product provided by the present application can solve the technical problem of how to dynamically adjust the power factor of the artificial noise beam to prevent eavesdroppers from stealing information. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the power allocation method of the artificial noise beam provided by the above embodiment, which will not be repeated here.
[0138] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A power allocation method for an artificial noise beam, characterized in that: The power allocation method of the artificial noise beam comprises the following steps: Determine an action value function according to each agent state and agent action, and construct an action value function table under all agent states according to the action value function; Determining the power distribution of each artificial noise beam according to the action value function table; The user's received signal quality is determined according to the power allocation situation, and the power allocation situation is verified according to the received signal quality.
2. The power allocation method of the artificial noise beam according to claim 1, characterized in that: The step of determining the action value function according to each agent state and agent action, and constructing the action value function table under all agent states according to the action value function specifically includes: Determine the agent actions of the agent in each agent state; Determining the agent reward under the state of each agent according to the agent action; Determine, based on the agent reward, a cumulative reward for executing the agent action in each agent state; An action value function is determined according to the accumulated reward, and an action value function table under all agent states is constructed according to the action value function.
3. The power allocation method of the artificial noise beam according to claim 2, characterized in that: The step of determining the agent reward under each agent state according to the agent action specifically includes: After the agent performs the agent action, determining a first received signal of the target eavesdropper within a first preset time period, and determining a first change in a block error rate corresponding to the first received signal; Determine a second received signal of the target legitimate user within the first preset time period, and determine a second change in a signal-to-noise ratio corresponding to the second received signal; The agent reward under each agent state is determined according to the first change situation and the second change situation.
4. The power allocation method of the artificial noise beam according to claim 2, characterized in that: The step of determining the power distribution of each artificial noise beam according to the action value function table specifically includes: Constructing an objective function according to the action-value function table and the agent reward; An optimal action value function is determined according to the objective function, and the power allocation of each artificial noise beam is determined according to the optimal action value function.
5. The power allocation method of an artificial noise beam according to any one of claims 1 to 4, characterized in that: The step of determining the received signal quality of the user according to the power allocation situation, and verifying the power allocation situation according to the received signal quality specifically includes: Determine the quality of the user's received signal according to the power allocation situation, wherein the signal reception quality includes: an average block error rate of each eavesdropper's received signal within a second preset time period and an average signal-to-noise ratio of the legitimate user's received signal within a third preset time period; The power allocation situation is verified according to the average block error rate and the average signal-to-noise ratio.
6. The power allocation method of the artificial noise beam according to claim 5, characterized in that: The step of verifying the power allocation situation according to the average block error rate and the average signal-to-noise ratio specifically includes: When the average signal-to-noise ratio is greater than a first preset threshold, determining whether the average block error rate is greater than a second preset threshold; If yes, it is determined that the power allocation verification is passed; If not, return to the step of determining the action value function according to the agent state and agent action at each moment, and constructing the action value function table at all moments, until the new power allocation situation is verified.
7. A power distribution device for an artificial noise beam, characterized in that: The power distribution device of the artificial noise beam comprises: A function determination module, used to determine an action value function according to each agent state and agent action, and to construct an action value function table under all agent states according to the action value function; A power allocation module, used to determine the power allocation of each artificial noise beam according to the action value function table; The power verification module is used to determine the quality of the user's received signal according to the power allocation situation, and verify the power allocation situation according to the received signal quality.
8. A power distribution device for an artificial noise beam, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the power allocation method for an artificial noise beam according to any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the power allocation method of the artificial noise beam according to any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for allocating power of an artificial noise beam according to any one of claims 1 to 6 are implemented.