A microservice-based intelligent airspace anti-interference method

Abstract

The present invention discloses a microservice-based intelligent airspace anti-interference method, which involves the intersection of array signal processing and artificial intelligence. The present invention first sends historical interference direction and required beam pointing data through the client. Then, in the server, the historical interference direction data is differentially processed to obtain the potential interference direction range. Secondly, the objective function is constructed in combination with the required beam pointing transmitted by the client, and the antenna array element phase is optimized by an improved quasi-annealing algorithm. Finally, the optimized antenna array element phase is returned to the client to form an antenna radiation pattern that can ensure the main lobe pointing and suppress interference, thereby realizing intelligent airspace anti-interference. The present invention achieves flexible acquisition of antenna array element phase by constructing a client and a server. And a balance is achieved between precise point prediction and full sidelobe suppression, achieving better beamforming effect in terms of anti-interference.

Description

Technical Field

[0001] The present invention discloses a microservice-based intelligent airspace anti-interference method, which belongs to the intersection of array signal processing and artificial intelligence. Background Art

[0002] As array antenna technology matures, frequency-based equipment is widely adopting array antennas to achieve high gain and strong anti-interference capabilities. By aligning the antenna elements and modulating them to different phases, it is possible to "null" the interference source while maintaining the main lobe's direction, thus achieving airspace anti-interference.

[0003] In the patent application number CN202410646145.2 filed by Sun Yat-sen University titled "A Hybrid Coherent Interference Suppression Beamforming Method in Impulse Noise Background," nonlinear compression processing and spatial decomposition coherence technology are combined to achieve optimal beamforming with the minimum variance distortion-free response criterion as the goal. This improves the robustness of the beamforming process while achieving stable anti-interference capabilities. However, this method has many steps to implement, and the implementation of each step requires a lot of professional knowledge and domain background, making it impossible to form a paradigm initial process.

[0004] Patent application number CN111030748B, filed by the 54th Research Institute of China Electronics Technology Group Corporation, titled "A Digital Beamforming Terminal Device for Satellite Communications," utilizes digital beamforming technology to null the antenna gain in the direction of interference, thereby achieving spatial interference mitigation. However, the patent fails to account for dynamic interference direction variations. Delays in acquiring interference direction information or in beamforming can prevent the null point from accurately aligning with the interference source.

[0005] In their paper "Adjacent Target Vital Sign Detection Based on Adaptive Beamforming," published in Radar Science and Technology, Xiong Junjun et al. proposed an adaptive beamforming method that creates a null in the direction of adjacent interference, thereby avoiding adjacent interference and improving target life detection. This method's application context also does not involve the impact of dynamic interference on beamforming.

[0006] In their paper "Interference Suppression in Worst-Case Conditions Based on Frequency-Steering Array Radar," published in Applied Science and Technology, Tao Xinke et al. proposed a worst-case performance optimization algorithm that forms a spot beam while simultaneously reducing sidelobe energy to achieve interference suppression. This algorithm is applicable to both uniform linear and circular frequency-steering arrays and has strong engineering applicability. However, this method focuses on overall sidelobe gain suppression, making limited use of information about the interference source and lacking precise interference rejection capabilities.

[0007] In addition, current anti-interference methods are mainly embedded in the system in a tightly coupled manner, which has poor capability reusability and is not easy to modify. Summary of the Invention

[0008] This paper provides a microservice-based intelligent airspace interference mitigation method, designed to flexibly address dynamic interference direction changes through the construction of microservices. By differentiating the collected historical interference direction data to obtain the interference direction range, this method uses the mainlobe direction to construct an objective function. Using an improved quasi-annealing algorithm, the method reduces the antenna beam gain in the interference direction area, thereby achieving airspace interference mitigation.

[0009] A microservice-based intelligent airspace anti-interference method includes the following steps:

[0010] Step 1: The client sends the historical interference data and required beam pointing parameters to the server through the array antenna;

[0011] Step 2: On the server side, historical interference direction data is differentially processed to obtain the potential interference direction range. This objective function is constructed based on the required beam pointing input by the client. The array antenna element phase is optimized using an improved quasi-annealing algorithm, and the optimized array antenna element phase is transmitted back to the client.

[0012] Step 3: The client adjusts the array antenna to form an antenna pattern using the optimized array antenna element phase.

[0013] Furthermore, the specific method of step 1 is:

[0014] Step 1-1: Import the requests toolkit;

[0015] Step 1-2: Interference direction data collection: Using the array antenna as the origin, continuously collect interference direction observation data at T moments. Save as a list where ;

[0016] Step 1-3: Construct the anti-jamming requirement dictionary anti_jamming_dict, which includes the historical interference direction data history_data, the required beam pointing theta_target, the array element spacing d, and the number of array elements N;

[0017] Step 1-4: Set the URL address of the microservice and send the anti-jamming requirement dictionary anti_jamming_dict to the microservice through the function in the requests package requests.post(url, json=anti_jamming_dict).

[0018] Furthermore, the specific method of step 2 is:

[0019] Step 2-1: Import Flask, request, and jsonify functions from the flask toolkit;

[0020] Step 2-2: Define the function compute_anti_jamming_parameters;

[0021] Step 2-3: Generate a flask framework application, app = Flask(__name__), and bind the function compute_anti_jamming_parameters to the routing address, @app.route(' / compute_anti_jamming_parameter', methods=['POST']);

[0022] Step 2-4: Start the microservice;

[0023] Step 2-5: Get the anti-jamming requirement dictionary anti_jamming_dict transmitted by the client through request.get_json();

[0024] Step 2-6: Perform differential processing on the history_data data in the anti-jamming_dict dictionary to obtain the differential value ,at this time ;

[0025] Step 2-7: Get the maximum difference value among the difference values ;

[0026] Step 2-8: Get the current perceived interference to , the interference direction range is ;by As the resolution, the interference direction range is discretized and sampled to obtain the interference direction list. :

[0027] ;

[0028] in ,like is a positive integer, then ;otherwise ; Indicates rounding down;

[0029] Step 2-9: Initialize the candidate array antenna element phase vector, the candidate array antenna element phase vector is composed of N array antenna element phases, and the value range of the N array antenna element phases is Random numbers within;

[0030] Step 2-10: Construct the anti-interference objective function object_function; the input is the array element spacing d, the number of array elements N, and the required beam pointing , Interference source list , the array antenna element phase vector in the current iteration process and the maximum difference value ; Output the objective function value :

[0031] ;

[0032] in, is the array antenna element phase vector in the current iteration process The N array antenna element phases in ; Set the fitness value to be updated and the optimal antenna array element phase vector , The initial value of is to initialize the candidate array antenna element phase vector, The initial value of is the output objective function value obtained by substituting the initialized candidate array antenna element phase vector into the anti-interference objective function object_function;

[0033] Step 2-11: Set the temperature value and the final temperature value ; > ;

[0034] Step 2-12: Array antenna element phase vector for the current iteration process , the phase of each array antenna element The overlapping range is The uniformly distributed random number is used to update the phase vector of the array antenna element Numeric value;

[0035] Step 2-13: Calculate the phase vector of the superimposed array antenna element The corresponding objective function value ;

[0036] Step 2-14: If the new objective function value Greater than the fitness value to be updated or ,in is a random number between [0,1], then the new objective function value Assign the fitness value to be updated , the phase vector of the array antenna element Numerically assign the optimal antenna array element phase vector ; Otherwise, keep the fitness value to be updated and the optimal antenna array element phase vector constant;

[0037] Step 2-15: Repeat steps 2-12 to 2-14 for a total of L times;

[0038] Step 2-16: Update the temperature value ,in is the cooling rate;

[0039] Step 2-17: If the temperature value Greater than or equal to the final temperature value , then return to step 2-12; if the temperature value Less than the final temperature value , then the optimization ends and the final optimal antenna array element phase vector is recorded ;

[0040] Step 2-18: The final optimal antenna array element phase vector After being processed by the jsonify function, it is returned by the compute_anti_jamming_parameters function.

[0041] Furthermore, the specific method of step 3 is: the response is returned from requests.post(url, json=anti_jamming_dict), and after processing it through .json(), the final optimal antenna array element phase vector is obtained on the client. , set the phase parameters of each antenna element to form the antenna radiation pattern.

[0042] Due to the adoption of the above technical solution, the method of the present invention has the following advantages over the background technology:

[0043] 1. The present invention obtains the interference source area through differential processing. Considering that array antenna beamforming and interference source positioning will cause time delay, it is easy for the attenuation area to be misaligned with the interference source, resulting in reduced anti-interference effectiveness. However, sidelobe suppression directly outside the main lobe requires a high degree of difficulty for the beamforming algorithm and the suppression is not concentrated. By estimating the interference source area, the probability of the interference source being in the gain suppression area is increased, achieving a balance between accurate point prediction and full sidelobe suppression.

[0044] 2. The present invention adopts an improved quasi-annealing optimization method. By improving the annealing law, the temperature does not drop continuously, but satisfies the sine function law and has a temperature rise phenomenon during the drop process, thereby enhancing the probability of the quasi-annealing algorithm jumping out of the local optimal value and improving the ability to obtain the global optimal value, making the beamforming effect in terms of anti-interference better.

[0045] 3. This invention provides intelligent airspace anti-interference capabilities through a microservices framework. By using a microservices framework to host the core anti-interference method, the capability is modularized and independently processed, allowing all devices in the network to access it through the server, thereby obtaining optimized antenna array element phases and achieving intelligent airspace anti-interference capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a method flow chart of a microservice-based intelligent airspace anti-interference method in an embodiment of the present invention.

[0047] Figure 2 Schematic diagram of interference source observation data in an embodiment of the present invention.

[0048] Figure 3 Schematic diagram of the difference of interference-source observation data in an embodiment of the present invention.

[0049] Figure 4 The optimal value varies with temperature in the embodiment of the present invention.

[0050] Figure 5 Schematic diagram of antenna pattern comparison in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0052] A microservice-based intelligent airspace anti-interference method, the overall process is as follows Figure 1 The specific steps are as follows:

[0053] Step 1: The client sends historical interference data and required beam pointing parameters to the server;

[0054] The client refers to the phased array antenna, and the server refers to the computing and processing center. The client specifies the required parameters for phased array antenna optimization. After the server completes antenna beam optimization, it returns the phase of each antenna to the client, achieving flexible acquisition of antenna element phases through "centralized calculation and distributed use."

[0055] Step 1-1: Import the requests toolkit;

[0056] Step 1-2: Interference direction data collection: Using the array antenna as the origin, continuously collect interference direction observation data at T moments. Save as a list where , T is 100, such as Figure 2 shown.

[0057] Step 1-3: Construct the anti-interference requirement dictionary anti_jamming_dict, which includes the historical interference direction data history_data, the required beam pointing theta_target, the array element spacing d, and the number of array elements N.

[0058] anti_jamming_dict = {'history_data': [-49.05401933 - 53.00770256 -50.09575992 - 54.90413872

[0059] - 58.69484854 - 60.69905881 - 56.35090798 - 56.18562937 - 55.13574698- 53.80290047

[0060] - 57.51515798 - 53.27817762 - 57.3564365 - 55.64489685 - 51.3912332

[0061] - 51.75682654 - 54.7452387 - 58.7875423 - 63.50236881 - 63.83478632

[0062] - 68.46184085 - 67.49060189 - 67.37568536 - 68.48579776 - 70.4616519

[0063] - 69.38602106 - 72.14030558 - 69.03715136 - 67.64552818 - 67.99037603

[0064] - 63.21392391 - 59.16183118 - 54.25211866 - 50.25031746 - 46.84548763

[0065] - 48.68349035 - 46.91765144 - 51.47297335 - 52.09212519 - 47.8605501

[0066] - 50.80578655 - 46.0973724 - 48.86001672 - 50.30728429 - 47.82087116

[0067] - 47.29617171 - 42.43492919 - 45.59434953 - 45.07799935 - 40.83129651

[0068] - 43.5535794 - 45.7176746 - 44.31950188 - 39.45971212 - 34.52068327

[0069] - 30.76475617 - 26.90702218 - 29.77809234 - 25.50468986 - 24.15166433

[0070] - 28.84765781 - 28.3012196 - 33.14057907 - 28.62813308 - 30.91025464

[0071] - 29.97427368 - 30.75257854 - 32.61891927 - 27.63111511 - 23.29666842

[0072] - 28.26180665 - 28.38007384 - 25.73529672 - 27.07890262 - 29.72888276

[0073] - 27.66953931 - 26.59776839 - 30.82254258 - 27.9638306 - 25.94469437

[0074] - 22.35258757 - 23.92826514 - 28.45733605 - 26.22554607 - 25.16568161

[0075] - 25.0898955 - 21.31000726 - 17.16158893 - 21.95933163 - 23.38276178

[0076] - 24.86843994 - 23.72825611 - 19.44301989 - 21.94404244 - 23.22363348

[0077] - 26.96105628 - 29.56431569 - 26.10967205 - 23.82280526 - 27.81776342 ],

[0078] 'theta_target':30,

[0079] 'd':0.5,

[0080] 'N':32,}

[0081] Step 1-4: Set the URL of the microservice to "http: / / 127.0.0.1:5000 / compute_anti_jamming_parameters" and send the anti-jamming requirement dictionary anti_jamming_dict to the microservice through the function in the requests package: requests.post(url, json=anti_jamming_dict).

[0082] Step 2: On the server side, differentially process historical interference direction data to obtain the potential interference direction range. Combined with the beam pointing data received from the client, the objective function is constructed. The antenna element phase is optimized using an improved quasi-annealing algorithm, and the optimized antenna element phase is transmitted back to the client.

[0083] Step 2-1: Import Flask, request, and jsonify functions from the flask toolkit;

[0084] Step 2-2: Define the function compute_anti_jamming_parameters,

[0085] Step 2-3: Generate a flask framework application, app = Flask(__name__), and bind the function compute_anti_jamming_parameters to the routing address, @app.route(' / compute_anti_jamming_parameters', methods=['POST']);

[0086] Step 2-4: Start the microservice;

[0087] if __name__ == '__main__':

[0088] app.run(host='0.0.0.0', port=5000, debug=True)

[0089] Step 2-5: Get the anti-jamming requirement dictionary anti_jamming_dict transmitted by the client through request.get_json();

[0090] Step 2-6: Perform differential processing on the history_data data in the anti-jamming_dict dictionary to obtain the differential value ,at this time ,like Figure 3 As shown;

[0091] Step 2-7: Get the maximum difference value among the difference values = 4.97°;

[0092] Step 2-8: Get the current perceived interference to , the interference direction range is .by As the resolution, take 1°, discretize the interference range and sample the interference direction list. It can be expressed as

[0093] ;

[0094] in ,like is a positive integer, then ;otherwise ; Indicates rounding down;

[0095] Step 2-9: Construct the anti-interference objective function object_function. The input is the preset pointing direction , Interference source list , antenna array element phase vector and the maximum difference value . Antenna array element phase vector The phase of each antenna element Composition, of which , N is the number of array elements, which is 32. The output value is

[0096] ;

[0097] Where d is the antenna array element spacing, which is 0.5m;

[0098] Step 2-10: Initialize the candidate antenna array element phase vector , the phase of each antenna element Composition, the value range is . Point the preset in the direction =30°, interference direction list =[-70°,…,-60°], antenna element phase vector and the maximum difference value Substitute the anti-interference objective function to obtain the fitness value In addition, the adaptation value Assign optimal fitness value , and the candidate antenna array element phase vector Assign the optimal antenna array element phase vector ;

[0099] Step 2-11: Set the temperature value =1000 and the final temperature value =1;

[0100] Step 2-12: The phase vector of the array antenna element in the current iteration process Medium antenna element phase The average superposition range is The uniformly distributed random number is used to update the phase vector of the array antenna element Numeric value;

[0101] Among them, if it is the first iteration process, then That is to initialize the candidate antenna array element phase vector ;

[0102] Step 2-13: Calculate the phase vector of the superimposed array antenna element Numerical objective function value update ;

[0103] Step 2-14: If the new objective function value Greater than the optimal fitness value or ,in is a random number between [0,1], then the new objective function value Assign optimal fitness value , the candidate antenna element phase vector Numerically assign the optimal antenna array element phase vector ; Otherwise, keep the fitness value to be updated and the optimal antenna array element phase vector constant;

[0104] Step 2-15: Repeat steps 2-12 to 2-14 for a total of L times, taking 1000 times;

[0105] Step 2-16: Update the temperature value ,in is the cooling rate, which is taken as 0.9;

[0106] Step 2-17: If the temperature value Greater than or equal to the final temperature value , then return to step 2-8; if the temperature value Less than the final temperature value , then the optimization ends and the final optimal antenna array element phase vector is recorded ,like Figure 4 As shown;

[0107] Step 2-18: The final optimal antenna array element phase vector After being processed by the jsonify function, it is returned by the compute_anti_jamming_parameters function.

[0108] Step 3: Use the optimized antenna element phase to form the antenna pattern.

[0109] The response will be returned from requests.post(url, json=anti_jamming_dict). After processing it through .json(), the optimal antenna array element phase vector is obtained on the client side. , set the phase parameters of each antenna element to form the antenna pattern, such as Figure 5 shown.

[0110] Comparing this method with the traditional quasi-annealing method, the optimal value changes with temperature as shown in Figure 4 As shown. It can be seen that when the temperature reaches the end, the optimal value of the antenna pattern formed by the improved method is higher. The antenna pattern formed by the optimal antenna array element phase vector is as follows Figure 5 It is obvious that the antenna pointing gain formed by this method is higher, and the width of the concave formed in the interference direction is wider than that formed by the traditional quasi-annealing method.

[0111] In summary, it can be seen that this patented technology can intelligently implement anti-interference beamforming.

[0112] Those skilled in the art will appreciate that the embodiments described are intended to help readers understand the principles of the present invention and should be understood that the scope of protection of the present invention is not limited to the embodiments described. It will be apparent to those skilled in the art that various modifications and variations are possible in the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A microservice-based intelligent airspace anti-interference method, characterized in that: The following steps are involved: Step 1: The client sends the historical interference data and required beam pointing parameters to the server through the array antenna; specifically: Step 1-1: Import the requests toolkit; Step 1-2: Interference direction data collection: Using the array antenna as the origin, continuously collect interference direction observation data at T moments. Save as a list where ; Step 1-3: Construct the anti-jamming requirement dictionary anti_jamming_dict, which includes the historical interference direction data history_data, the required beam pointing theta_target, the array element spacing d, and the number of array elements N; Step 1-4: Set the URL address of the microservice and send the anti-jamming requirement dictionary anti_jamming_dict to the microservice through the function in the requests package requests.post(url, json=anti_jamming_dict); Step 2: On the server side, differentially process historical interference direction data to obtain the potential interference direction range. Combined with the required beam pointing input by the client, the objective function is constructed. The array antenna element phase is optimized using an improved quasi-annealing algorithm, and the optimized array antenna element phase is transmitted back to the client. Specifically: Step 2-1: Import Flask, request, and jsonify functions from the flask toolkit; Step 2-2: Define the function compute_anti_jamming_parameters; Step 2-3: Generate a flask framework application, app = Flask(__name__), and bind the function compute_anti_jamming_parameters to the routing address, @app.route(' / compute_anti_jamming_parameter', methods=['POST']); Step 2-4: Start the microservice; Step 2-5: Get the anti-jamming requirement dictionary anti_jamming_dict transmitted by the client through request.get_json(); Step 2-6: Perform differential processing on the history_data data in the anti-jamming_dict dictionary to obtain the differential value ,at this time ; Step 2-7: Get the maximum difference value among the difference values ; Step 2-8: Get the current perceived interference to , the interference direction range is ;by As the resolution, the interference direction range is discretized and sampled to obtain the interference direction list. : ； in ,like is a positive integer, then ;otherwise ; Indicates rounding down; Step 2-9: Initialize the candidate array antenna element phase vector, the candidate array antenna element phase vector is composed of N array antenna element phases, and the value range of the N array antenna element phases is Random numbers within; Step 2-10: Construct the anti-interference objective function object_function; the input is the array element spacing d, the number of array elements N, and the required beam pointing , Interference source list , the array antenna element phase vector in the current iteration process and the maximum difference value ; Output the objective function value : ； in, is the array antenna element phase vector in the current iteration process The N array antenna element phases in ; Set the fitness value to be updated and the optimal antenna array element phase vector , The initial value of is to initialize the candidate array antenna element phase vector, The initial value of is the output objective function value obtained by substituting the initialized candidate array antenna element phase vector into the anti-interference objective function object_function; Step 2-11: Set the temperature value and the final temperature value ; > ; Step 2-12: Array antenna element phase vector for the current iteration process , the phase of each array antenna element The overlapping range is The uniformly distributed random number is used to update the phase vector of the array antenna element Numeric value; Step 2-13: Calculate the phase vector of the superimposed array antenna element The corresponding objective function value ; Step 2-14: If the new objective function value Greater than the fitness value to be updated or ,in is a random number between [0,1], then the new objective function value Assign the fitness value to be updated , the phase vector of the array antenna element Numerically assign the optimal antenna array element phase vector ; Otherwise, keep the fitness value to be updated and the optimal antenna array element phase vector constant; Step 2-15: Repeat steps 2-12 to 2-14 for a total of L times; Step 2-16: Update the temperature value ,in is the cooling rate; Step 2-17: If the temperature value Greater than or equal to the final temperature value , then return to step 2-12; if the temperature value Less than the final temperature value , then the optimization ends and the final optimal antenna array element phase vector is recorded ; Step 2-18: The final optimal antenna array element phase vector After being processed by the jsonify function, it is returned by the compute_anti_jamming_parameters function; Step 3: The client adjusts the array antenna to form an antenna pattern using the optimized array antenna element phase.

2. The microservice-based intelligent airspace anti-interference method according to claim 1 is characterized in that: The specific method of step 3 is: the response is returned from requests.post(url, json=anti_jamming_dict), and after processing it through .json(), the final optimal antenna array element phase vector is obtained on the client. , set the phase parameters of each antenna element to form the antenna radiation pattern.

Images