Base station signal recovery method based on deep neural network to achieve interference suppression

Abstract

This invention discloses a base station signal recovery method based on deep neural networks to achieve interference suppression, comprising the following steps: S1. Constructing a communication scenario for the base station; S2. An edge server traverses all combinations of interference signals selected by each jammer, and constructs a sample set for each combination; S3. Constructing a base station signal recovery model based on a deep neural network algorithm, training the base station signal recovery model using signal samples from the sample set, obtaining a trained base station signal recovery model, and transmitting it to base station B; S4. Base station A sends a communication signal to base station B, while the edge server selects interference signals generated by each jammer and transmits them to base station B and each jammer. Base station B recovers the communication signal from the received signal based on the base station signal recovery model. This invention, by increasing the number of jammers and combining it with deep neural networks, can achieve base station signal recovery even when randomly selecting combinations of jammer interference signals.

Description

Technical Field

[0001] This invention relates to the field of base station communication, and in particular to a base station signal recovery method based on deep neural networks to achieve interference suppression. Background Technology

[0002] In the field of base station communication, interference is often used to prevent eavesdropping devices from obtaining communication signals. The specific method is as follows: an interference device generates an interference signal known to the communication base station, and then interferes with the communication signal. When the base station receives the signal, it can recover the communication signal from the received signal because it knows the interference signal. However, since the eavesdropping device does not know the interference signal, it cannot extract the communication signal from the received signal.

[0003] However, a single jammer is easy to crack. Once the eavesdropping device can crack the jamming signal and its channel, it is still possible to recover the communication signal from the combined signal of the communication signal and the jamming signal, thus causing information leakage. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a base station signal recovery method based on deep neural networks to achieve interference suppression. By increasing the number of jammers and combining them with deep neural networks, base station signal recovery can be achieved even when randomly selecting jammer interference signal combinations.

[0005] The objective of this invention is achieved through the following technical solution: a base station signal recovery method based on deep neural networks to suppress interference, comprising the following steps:

[0006] S1. Constructing the communication scenario for the base station:

[0007] The system includes base station A, base station B, an edge server, and multiple jammers. Each jammer can generate various jamming signals. When base station A sends a desired signal to base station B, the edge server selects the jamming signals generated by each jammer and transmits them to base station B and each jammer. Based on the selection by the edge server, each jammer simultaneously generates jamming signals and transmits them in coordination to interfere with the desired signal sent by base station A, thereby preventing eavesdropping devices from eavesdropping on the desired signal. When base station B receives the signal, it recovers the desired signal from the received signal based on the jamming signals from each jammer, completing the signal transmission between base station A and base station B.

[0008] S2. The edge server iterates through all combinations of interference signals selected by each jammer, and collects information under each combination in the base station communication scenario to build a sample set for all combinations.

[0009] S3. Construct a base station signal recovery model based on a deep neural network algorithm, train the base station signal recovery model using signal samples from the sample set, obtain the trained base station signal recovery model, and transmit it to base station B;

[0010] S4. In a real-world communication scenario, base station A sends a communication signal to base station B. At the same time, the edge server selects the interference signals generated by each jammer and transmits them to base station B and each jammer. Based on the base station recovery signal model, base station B recovers the communication signal from the received signal.

[0011] The beneficial effects of the present invention are: (1) By using multiple jammers to transmit jamming signals simultaneously, the present invention can increase the complexity of the jamming signals and prevent information leakage caused by being cracked by eavesdropping devices;

[0012] (2) This invention combines a neural network to train a base station signal recovery model. By selecting a combination of multiple jammers to send interference signals, the model is trained to obtain the signal characteristics composed of the received signal, known channel information, time delay information, and the selected interference signal combination, and the relationship with the communication signal. Then, in actual communication, the model is trained to obtain the signal characteristics composed of the received signal, known channel information, time delay information, and the selected interference signal combination, so that the base station signal can be directly recovered. With the help of neural networks, signal recovery can be made simpler and more effective.

[0013] (3) In actual communication scenarios, the present invention allows the edge server to randomly select a combination of interference signals, which increases the randomness of the interference signals, further increases the difficulty of cracking the interference signals, and improves the security of communication. Attached Figure Description

[0014] Figure 1 Flow chart of the method of the present invention. Detailed Implementation

[0015] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings, but the scope of protection of the present invention is not limited to the following description.

[0016] like Figure 1 As shown, the base station signal recovery method based on deep neural networks for interference suppression includes the following steps:

[0017] S1. Constructing the communication scenario for the base station:

[0018] The system includes base station A, base station B, an edge server, and multiple jammers. Each jammer can generate various jamming signals. When base station A sends a desired signal to base station B, the edge server selects the jamming signals generated by each jammer and transmits them to base station B and each jammer. Based on the selection by the edge server, each jammer simultaneously generates jamming signals and transmits them in coordination to interfere with the desired signal sent by base station A, thereby preventing eavesdropping devices from eavesdropping on the desired signal. When base station B receives the signal, it recovers the desired signal from the received signal based on the jamming signals from each jammer, completing the signal transmission between base station A and base station B.

[0019] S2. The edge server iterates through all combinations of interference signals selected by each jammer, and collects information under each combination in the base station communication scenario to build a sample set for all combinations.

[0020] S3. Construct a base station signal recovery model based on a deep neural network algorithm, train the base station signal recovery model using signal samples from the sample set, obtain the trained base station signal recovery model, and transmit it to base station B;

[0021] S4. In a real-world communication scenario, base station A sends a communication signal to base station B. At the same time, the edge server selects the interference signals generated by each jammer and transmits them to base station B and each jammer. Based on the base station recovery signal model, base station B recovers the communication signal from the received signal.

[0022] In the embodiments of this application, each jammer includes a carrier frequency and multiple different baseband jamming signals;

[0023] The edge server selects the baseband interference signal of each jammer, thereby enabling each jammer to generate and transmit the corresponding interference signal.

[0024] The step S2 comprises:

[0025] S201. Suppose there are M jammers in total, and each jammer includes N types of jamming signals. The N types of jamming signals for the i-th jammer are denoted as: ;in, Let j represent the j-th type of jamming signal from the i-th jammer, where i = 1, 2, ..., M; j = 1, 2, ..., N;

[0026] Therefore, when M jammers transmit jamming signals simultaneously, there are a total of M*N possible combinations of jamming signals;

[0027] S202.M jammers, using any combination of jamming signals, collect information in a base station communication scenario to construct a sample set under the current combination of jamming signals:

[0028] Step S202 includes:

[0029] A1. Base station A generates a test signal. The signal is transmitted to base station B, and simultaneously, M jammers generate corresponding jamming signals and transmit them according to the combination selected by the edge server; the signal received by base station B at this time is denoted as... Base station B transmits the received signal to the edge server;

[0030] In the edge server, the interference signals of the selected M jammers are denoted as follows: ,in This represents the interference signal of the i-th jammer selected in the current combination. , i=1,2,…,M;

[0031] Let the channels from M jammers to base station B be denoted as follows: The transmission delay is ,in, This represents the channel from the i-th jammer to base station B. Let represent the propagation delay from the i-th jammer to base station B, where i = 1, 2, ..., M;

[0032] Meanwhile, it is known that the channel from base station A to base station B is... The propagation delay from base station A to base station B is ;

[0033] A2. Construct signal samples (L, under the current combination of interference signals) ):

[0034] The sample features are denoted as:

[0035] The sample label is denoted as: ;

[0036] A3. Repeat steps A1~A2 multiple times to add them to a set to obtain the sample set under the current interference signal combination.

[0037] S203. When each of the M jammers uses a different combination of jamming signals, steps S201 to S202 are repeated to obtain a sample set for each combination of jamming signals. The signal samples in the sample sets for all combinations of jamming signals are then added to the same set to form a sample set for all combinations.

[0038] In step S3, when training the base station signal recovery model using signal samples from the sample set, the sample features from the sample set are used as model inputs and the sample labels corresponding to the sample features are used as the expected outputs of the model for training in each training process; after all signal samples in the sample set have been trained, the trained base station signal recovery model is considered to have been obtained.

[0039] Step S4 includes:

[0040] S401. The edge server randomly selects jammer interference signals, which are denoted as follows: ,in This represents the interference signal selected by the i-th jammer in the current combination. , i=1,2,…,M; transmit the selected interference signals to base station B and the corresponding jammer respectively;

[0041] S402. Base station A generates and transmits communication signals. Each jammer sends jamming signals from the server. The signal received by base station B is recorded as... ;

[0042] S403. Base Station B constructs signal characteristics :

[0043] ;

[0044] S404. Base station B will construct signal characteristics Input the trained base station signal recovery model, and the base station signal recovery model will recover the communication signal.

[0045] The foregoing description illustrates and describes a preferred embodiment of the present invention. However, as previously stated, it should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the inventive concept described herein through the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A base station signal recovery method based on deep neural networks to achieve interference suppression, characterized in that: Includes the following steps: S1. Constructing the communication scenario for the base station: It includes base station A, base station B, an edge server, and multiple jammers; each of the jammers is capable of generating multiple jamming signals; S2. The edge server iterates through all combinations of interference signals selected by each jammer, and collects information under each combination in the base station communication scenario to build a sample set for all combinations. The step S2 comprises: S201. Suppose there are M jammers in total, and each jammer includes N types of jamming signals. The N types of jamming signals for the i-th jammer are denoted as: ;in, Let j represent the j-th type of jamming signal from the i-th jammer, where i = 1, 2, ..., M; j = 1, 2, ..., N; Therefore, when M jammers transmit jamming signals simultaneously, there are a total of M*N possible combinations of jamming signals; S202.M jammers, using any combination of jamming signals, collect information in a base station communication scenario to construct a sample set under the current combination of jamming signals: S203. When M jammers use each combination of jamming signals, repeat steps S201~S202 to obtain a sample set under each combination of jamming signals, and add the signal samples in the sample sets under all combinations of jamming signals to the same set to form a sample set under all combinations. S3. Construct a base station signal recovery model based on a deep neural network algorithm, train the base station signal recovery model using signal samples from the sample set, obtain the trained base station signal recovery model, and transmit it to base station B; In step S3, when training the base station signal recovery model using signal samples from the sample set, the sample features from the sample set are used as model inputs and the sample labels corresponding to the sample features are used as the expected outputs of the model during each training process. After all signal samples in the sample set have been trained, the trained base station signal recovery model is considered to have been obtained. S4. In a real communication scenario, base station A sends a communication signal to base station B. At the same time, the edge server selects the interference signals generated by each jammer and transmits them to base station B and each jammer. Based on the base station recovery signal model, base station B recovers the communication signal from the received signal. Step S4 includes: S401. The edge server randomly selects jammer interference signals, which are denoted as follows: ,in This represents the interference signal selected by the i-th jammer in the current combination. , i=1,2,…,M; transmit the selected interference signals to base station B and the corresponding jammer respectively; S402. Base station A generates and transmits communication signals. Each jammer sends jamming signals from the server. The signal received by base station B is recorded as... ; S403. Base Station B constructs signal characteristics : ； S404. Base station B will construct signal characteristics Input the trained base station signal recovery model, and the communication signal is recovered from the base station signal recovery model.

2. The base station signal recovery method based on deep neural network for interference suppression according to claim 1, characterized in that: Each jammer includes a carrier frequency and multiple different baseband jamming signals; The edge server selects the baseband interference signal of each jammer, thereby enabling each jammer to generate and transmit the corresponding interference signal.

3. The base station signal recovery method based on deep neural network for interference suppression according to claim 1, characterized in that: Step S202 includes: A1. Base station A generates a test signal. The signal is transmitted to base station B, and simultaneously, M jammers generate corresponding jamming signals and transmit them according to the combination selected by the edge server; the signal received by base station B at this time is denoted as... Base station B transmits the received signal to the edge server; In the edge server, the interference signals of the selected M jammers are denoted as follows: ,in This represents the interference signal of the i-th jammer selected in the current combination. , i=1,2,…,M; Let the channels from M jammers to base station B be denoted as follows: The transmission delay is ,in, This represents the channel from the i-th jammer to base station B. Let represent the propagation delay from the i-th jammer to base station B, where i = 1, 2, ..., M; Meanwhile, it is known that the channel from base station A to base station B is... The propagation delay from base station A to base station B is ; A2. Construct signal samples under the current combination of interference signals. : The sample features are denoted as: The sample label is denoted as: ; A3. Repeat steps A1~A2 multiple times to add them to a set to obtain the sample set under the current interference signal combination.

Images