Self-adaptive anti-interference method based on unmanned aerial vehicle communication interference monitoring

Abstract

The invention provides a self-adaptive anti-interference method based on unmanned aerial vehicle communication interference monitoring, and belongs to the technical field of unmanned aerial vehicle communication, and the method comprises the steps: obtaining all signal information in a communication range of an unmanned aerial vehicle, carrying out the spectrum analysis of the signal information, and recognizing a normal communication signal and an interference signal according to a spectrum analysis result; performing interference feature extraction on the interference signals, classifying the interference signals according to interference features, determining an interference source based on a classification result, and positioning the interference source; adjusting the original network topology of the unmanned aerial vehicle based on the positioning result, and performing deployment optimization on the relay node to obtain an updated network topology; the communication parameters and the flight path of the unmanned aerial vehicle are adjusted according to the updated network topology, the communication quality and the system adaptability are improved, and the reliability and the stability of a communication system are improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle communication technology, and in particular to an adaptive anti-interference method based on unmanned aerial vehicle communication interference monitoring. Background Art

[0002] With the rapid development of drone technology, more and more application scenarios require efficient and reliable communication systems. However, existing technologies are often unable to accurately identify and distinguish normal communication signals from interference signals in real time, resulting in fluctuations in communication quality and affecting the reliability of data transmission. Traditional interference source location methods usually rely on static models and cannot quickly respond to changes in dynamic environments.

[0003] Therefore, the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring. Summary of the invention

[0004] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which obtains signal information within the communication range of the UAV and performs spectrum analysis to identify normal signals and interference signals, then extracts and classifies interference features, determines the interference source and its location, optimizes the network topology and relay node deployment based on the positioning results, and finally adjusts the communication parameters and flight path of the UAV to improve communication quality and system adaptability, and enhance the reliability and stability of the communication system.

[0005] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, comprising: Step 1: Obtain all signal information within the communication range of the drone, perform spectrum analysis on the signal information, and identify normal communication signals and interference signals based on the spectrum analysis results; Step 2: extract interference features from the interference signal, classify the interference signal according to the interference features, determine the interference source based on the classification result, and locate the interference source; Step 3: Adjust the original network topology of the drone based on the positioning results, and optimize the deployment of relay nodes to obtain an updated network topology; Step 4: Adjust the drone’s communication parameters and flight path based on the updated network topology.

[0006] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which obtains all signal information within the communication range of the UAV, performs spectrum analysis on the signal information, and identifies normal communication signals and interference signals according to the spectrum analysis results, including: Using the communication equipment of the drone to obtain all signal information within the communication range of the drone, using fast Fourier transform on the signal information to obtain a frequency domain representation of the signal information, and determining the spectrum characteristics and phase characteristics of the signal information according to the frequency domain representation; Obtain the information processing requirements of the UAV and determine the time domain characteristics of the signal information based on the information processing requirements of the UAV; The spectrum features, phase features and time domain features are fused to form a multi-dimensional feature vector corresponding to each signal information, and normal communication signals and interference signals are identified based on the multi-dimensional vector features.

[0007] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which identifies normal communication signals and interference signals based on the multidimensional vector features, including: Select an adversarial network architecture according to the unmanned information processing requirements, and design a generator and a discriminator by combining the history-signal data table with the adversarial network architecture; Using the multidimensional feature vector and the generator to generate a training feature vector, and updating the weight of the discriminator when the number of updates of the training feature vector is less than or equal to a preset number of discriminant updates; If the number of updates is greater than the preset number of discriminant updates, the weight of the discriminator is fixed, and the weight of the generator is updated according to the probability of misjudgment of the training feature vector by the discriminator; According to the adversarial network architecture, the generator and the discriminator are used to identify normal communication signals and interference signals.

[0008] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, extracting interference features of the interference signal, classifying the interference signal according to the interference features, determining the interference source based on the classification result and locating the interference source, including: Comparing the multidimensional feature vector corresponding to the interference signal with the multidimensional feature vector corresponding to the normal communication signal, determining the interference feature of the interference signal according to the vector comparison result, performing cluster analysis on the interference feature, and identifying the interference type corresponding to the interference signal; Mapping the extracted interference features and the corresponding interference types to a known interference source-feature database for comparison, and determining a matching score for each interference feature based on the comparison results; Generate a candidate list of interference sources corresponding to each interference signal according to the matching score result; The generation environment corresponding to the interference signal is obtained, and the interference source candidate list is screened based on the generation environment and the matching score result to obtain the interference source corresponding to each interference signal, and the interference source is located to obtain the positioning result.

[0009] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which adjusts the original network topology of the UAV based on the positioning result, and optimizes the deployment of relay nodes to obtain an updated network topology, including: Obtain the interference property corresponding to the interference source, determine the influence range of the interference source on the UAV according to the interference property, evaluate the influence relationship of the positioning result on the original network topology of the UAV based on the influence range, and determine the influence of the interference signal on the communication between the UAV and other terminals according to the influence relationship; Identify weaknesses in the original network topology based on the communication impact, and analyze relay node requirements based on the weakness identification results and positioning results; According to the weakness identification results, positioning results and relay node requirements, the relay node deployment is optimized to obtain an updated network topology.

[0010] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which identifies weaknesses in the original network topology according to the communication impact, and analyzes relay node requirements by combining the weakness identification results with the positioning results, including: Collecting original topology network data, obtaining user connection requirements in the area around the positioning result based on the positioning result of the interference signal, and performing regional signal strength analysis according to the user connection requirements to obtain a weakness identification result; The relay point requirement is determined based on the weakness identification result and the user connection requirement.

[0011] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which optimizes the deployment of relay nodes according to the weakness identification results, positioning results and relay node requirements, and obtains an updated network topology, including: ,in, F represents the comprehensive objective function of evaluating the node deployment scheme; Indicates k The signal strength required for each weakness identification result; Indicates k The actual signal strength of each weakness identification result; K Indicates the total number of weakness identification results; N Indicates the total number of relay nodes; k An index representing the weakness identification result; Indicates i The relay node and j The distance between relay nodes; f Indicates the signal frequency of the drone communication; i and j Represents the index of the relay node; Indicates i The relay node and k The distance between the weakness identification results; and Respectively represent i The transmission power of the relay node isj The transmit power of the relay node; 20 is the unit conversion factor; a represents the constant term required to convert distance and frequency to dB, a =32.44; Indicates i The relay node and j The impact of the distance between relay nodes on signal strength; Indicates the effect of signal frequency on signal strength of drone communication; The links between relay nodes are optimized according to the comprehensive objective function to obtain an updated network topology.

[0012] The present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which adjusts the communication parameters and flight path of the UAV according to the updated network topology, including: Identifying a topology change of the updated network topology, and matching a corresponding adjustment instruction from a change-adjustment instruction table according to the topology change; According to the adjustment instruction, a first adjustment is made to the communication parameters of the UAV, a second adjustment is made to the flight path, and the first adjustment and the second adjustment are combined to perform an adaptive anti-interference operation on the interference signal.

[0013] Compared with the prior art, the beneficial effects of the present application are as follows: by acquiring signal information within the communication range of the drone and performing spectrum analysis, identifying normal signals and interference signals, then extracting and classifying interference features, determining the interference source and its location, optimizing the network topology and relay node deployment based on the positioning results, and finally adjusting the communication parameters and flight path of the drone to improve communication quality and system adaptability, and enhance the reliability and stability of the communication system.

[0014] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of an adaptive anti-interference method based on UAV communication interference monitoring provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] Embodiment 1: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, such as Figure 1 As shown, including: Step 1: Obtain all signal information within the communication range of the drone, perform spectrum analysis on the signal information, and identify normal communication signals and interference signals based on the spectrum analysis results; Step 2: extract interference features from the interference signal, classify the interference signal according to the interference features, determine the interference source based on the classification result, and locate the interference source; Step 3: Adjust the original network topology of the drone based on the positioning results, and optimize the deployment of relay nodes to obtain an updated network topology; Step 4: Adjust the drone’s communication parameters and flight path based on the updated network topology.

[0019] In this embodiment, the communication range of the drone is the area where the drone can effectively transmit and receive signals, which is limited by the transmission power and environmental factors. For example, in an open area, the communication range of the drone may reach several kilometers, while in an urban environment, the range may be reduced due to buildings.

[0020] In this embodiment, the signal information is all electromagnetic wave signals received during the drone communication process, including normal and interference signals, such as sensor data received by the drone when performing a mission and control signals from other drones.

[0021] In this embodiment, the spectrum analysis results include spectrum features, phase features and time domain features. The spectrum analysis process is to obtain signal information through the communication equipment of the UAV, and use fast Fourier transform to obtain the frequency domain representation of the signal, analyze its spectrum features and phase features, extract time domain features in combination with the information processing needs of the UAV, and fuse these features to form a multi-dimensional feature vector.

[0022] In this embodiment, the normal communication signal is a signal used for effective data transmission, with specific frequency and characteristics, such as the control signal between the drone and the ground control station. The interference signal is a signal that has a negative impact on normal communication and may come from other wireless devices or environmental noise, such as signal interference from adjacent wireless networks causing communication delays.

[0023] In this embodiment, the recognition process is based on the adversarial network architecture, and the generator generates a training feature vector; the discriminator optimizes its weight within a set update number; after exceeding the update number, the discriminator weight is fixed, and the generator weight is updated based on the probability of misjudgment, and finally the normal communication signal and the interference signal are identified by the discriminator. For example, during the flight, the drone receives the signal in real time, generates a feature vector through the generator, and the discriminator determines the signal type.

[0024] In this embodiment, the interference feature is a feature extracted from the interference signal, including parameters such as frequency, amplitude, and phase, reflecting the characteristics of the interference signal. For example, the detected interference signal has a frequency of 2.4 GHz and an amplitude higher than that of a normal signal.

[0025] In this embodiment, the classification result is an interference type, which is a category of an identified interference signal, such as electromagnetic interference, signal loss, signal overlap, etc. For example, a certain interference signal is determined to be "radio frequency interference".

[0026] In this embodiment, the positioning result is the final result of determining the location of the interference source, which is usually expressed in coordinates or areas. For example, the positioning result shows that the interference source is located 100 meters outside the flight path of the drone.

[0027] In this embodiment, by comparing the multi-dimensional feature vectors of the interference signal and the normal communication signal, the interference feature is extracted and cluster analysis is performed to identify the interference type. The extracted interference feature is mapped to the known interference source-feature database for comparison, a matching score is generated, and a candidate list of interference sources is generated based on this. The candidate list is screened in combination with the generation environment of the interference signal, and finally the interference source is located and the positioning result is obtained.

[0028] In this embodiment, the original network topology is the connection structure between the nodes (drones, ground stations, relay nodes, etc.) in the drone communication system. For example, a typical original network topology may include the connection between a drone and multiple ground stations and relay nodes.

[0029] In this embodiment, deployment optimization is to adjust the layout of relay nodes based on the identified weaknesses and relay node requirements to improve the overall performance of the network. For example, the relay nodes are deployed on the opposite side of the interference source to ensure that the drone can obtain a more stable signal during flight.

[0030] In this embodiment, the updated network topology is an optimized network structure that reflects the new positions and connection relationships of the relay nodes. For example, the updated network topology may show newly added relay nodes and reconfigured communication links to improve the communication reliability of the drone.

[0031] In this embodiment, the interference properties of the interference source are obtained, the scope of its impact on the drone is evaluated, and the relationship of the impact on the original network topology is analyzed to identify weaknesses in the communication, combine the positioning results and relay node requirements, optimize the deployment of relay nodes, and finally update the network topology.

[0032] In this embodiment, the specific steps of adjusting the communication parameters and the flight path of the UAV are: performing a first adjustment on the communication parameters and performing a second adjustment on the flight path.

[0033] The working principle and beneficial effects of the above technical solution are: by acquiring signal information within the communication range of the drone and performing spectrum analysis, identifying normal signals and interference signals, then extracting and classifying interference features, determining the interference source and its location, optimizing the network topology and relay node deployment based on the positioning results, and finally adjusting the communication parameters and flight path of the drone to improve communication quality and system adaptability, and enhance the reliability and stability of the communication system.

[0034] Embodiment 2: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which obtains all signal information within the communication range of the UAV, performs spectrum analysis on the signal information, and identifies normal communication signals and interference signals according to the spectrum analysis results, including: Using the communication equipment of the drone to obtain all signal information within the communication range of the drone, using fast Fourier transform on the signal information to obtain a frequency domain representation of the signal information, and determining the spectrum characteristics and phase characteristics of the signal information according to the frequency domain representation; Obtain the information processing requirements of the UAV and determine the time domain characteristics of the signal information based on the information processing requirements of the UAV; The spectrum features, phase features and time domain features are fused to form a multi-dimensional feature vector corresponding to each signal information, and normal communication signals and interference signals are identified based on the multi-dimensional vector features.

[0035] In this embodiment, the communication equipment of the drone includes a radio transmitter, a receiver, an antenna and a signal processing unit. For example, a drone is equipped with a LoRa communication module for long-distance data transmission.

[0036] In this embodiment, the fast Fourier transform is an efficient algorithm for calculating the Fourier transform of a discrete signal. For example, the drone uses FFT to convert the received time domain signal into a frequency domain signal to analyze the frequency components.

[0037] In this embodiment, the frequency domain representation is the expression of the signal in the frequency domain, showing the amplitude and phase of each frequency component. For example, the FFT result shows that the amplitude of a signal at 2.4 GHz is higher than that of other frequencies, indicating that this frequency is the main signal frequency.

[0038] In this embodiment, the frequency spectrum feature is the amplitude spectrum obtained by FFT, which reflects the intensity of each frequency component in the signal. For example, the amplitude value of the signal at a certain frequency is 10 dB, indicating that the frequency component is strong. The phase feature is the phase information of each frequency component. For example, the phase of a certain frequency is 90 degrees, indicating the time delay of the signal.

[0039] In this embodiment, the drone information processing requirements are the drone's requirements for real-time, accuracy, and reliability of data processing when performing tasks. For example, in a search and rescue mission, the drone needs to process sensor data in real time to quickly locate the target.

[0040] In this embodiment, the time domain characteristics describe the performance of the signal in the time domain, such as amplitude changes and waveform characteristics. For example, the waveform changes of the signal received by the drone within a specific time show the pulse characteristics of the signal.

[0041] In this embodiment, the multidimensional feature vector integrates spectrum features, phase features and time domain features into one vector. For example, one feature vector may contain multiple data points of amplitude, phase and time domain waveforms to form a vector with a length of N.

[0042] In this embodiment, the fusion process is to combine different features (frequency domain and time domain) to form a comprehensive feature vector. For example, spectral features (such as amplitude and phase) are combined with time domain features (such as signal strength) to generate a vector containing all key information.

[0043] The working principle and beneficial effects of the above technical solution are: signal information is obtained through the communication equipment of the UAV, and the frequency domain representation of the signal is obtained by fast Fourier transform, and its spectrum characteristics and phase characteristics are analyzed, and the time domain characteristics are extracted in combination with the information processing needs of the UAV. These features are fused to form a multi-dimensional feature vector, and normal communication signals and interference signals are identified based on this vector, so as to realize real-time and comprehensive analysis of signal characteristics, improve the recognition accuracy of normal communication signals and interference signals, and enhance the reliability of the UAV communication system.

[0044] Embodiment 3: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which identifies normal communication signals and interference signals based on the multidimensional vector features, including: Select an adversarial network architecture according to the unmanned information processing requirements, and design a generator and a discriminator by combining the history-signal data table with the adversarial network architecture; Using the multidimensional feature vector and the generator to generate a training feature vector, and updating the weight of the discriminator when the number of updates of the training feature vector is less than or equal to a preset number of discriminant updates; If the number of updates is greater than the preset number of discriminant updates, the weight of the discriminator is fixed, and the weight of the generator is updated according to the probability of misjudgment of the training feature vector by the discriminator; According to the adversarial network architecture, the generator and the discriminator are used to identify normal communication signals and interference signals.

[0045] In this embodiment, the adversarial network architecture is a generative adversarial network (GAN), which is a machine learning model consisting of a generator and a discriminator. The model performance is improved through adversarial training. For example, in drone communications, GAN is used to generate and identify signal features to distinguish normal signals from interference signals.

[0046] In this embodiment, the history-signal data table records the signal information received in the past, including characteristic data of normal signals and interference signals. For example, the signal data collected by the drone in different tasks, including spectral characteristics, time domain characteristics, etc., are used to train the model.

[0047] In this embodiment, the generator and the discriminator, the generator is responsible for generating a false signal feature vector similar to the real signal feature, for example, the generator generates a simulated interference signal feature based on the existing signal data, and the discriminator is responsible for determining whether the input feature vector is a real signal or a generated signal, for example, the discriminator analyzes the received signal feature to determine whether it is a normal communication signal.

[0048] In this embodiment, the training feature vector is a feature vector generated by a generator and is used to train the discriminator. For example, the signal feature vector generated by the generator may contain frequency, amplitude and phase information.

[0049] In this embodiment, the number of discriminant updates is the upper limit of the number of times the discriminator weight is updated during the training process. For example, setting the number of discriminant updates to 100 times means optimizing the performance of the discriminator within 100 updates.

[0050] In this embodiment, the weight of the critical discriminator is an important parameter used in the discriminator to determine signal characteristics. For example, after the weight of the discriminator is adjusted, interference signals from other drones may be more accurately identified.

[0051] In this embodiment, the false positive probability is the probability that the discriminator misjudges the signal feature, reflecting its recognition ability. For example, if the probability that the discriminator misjudges a normal signal as an interference signal is 5%, the false positive probability is 0.05.

[0052] The working principle and beneficial effect of the above technical solution are: using the adversarial network architecture, the generator generates training feature vectors, and optimizes the weight of the discriminator within the set update number. If the update number exceeds the preset value, the discriminator weight is fixed, and the generator weight is adjusted according to the discriminator's misjudgment probability, thereby improving the recognition accuracy of normal communication signals and interference signals.

[0053] Embodiment 4: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, extracting interference features of the interference signal, classifying the interference signal according to the interference features, determining the interference source based on the classification result and locating the interference source, including: Comparing the multidimensional feature vector corresponding to the interference signal with the multidimensional feature vector corresponding to the normal communication signal, determining the interference feature of the interference signal according to the vector comparison result, performing cluster analysis on the interference feature, and identifying the interference type corresponding to the interference signal; Mapping the extracted interference features and the corresponding interference types to a known interference source-feature database for comparison, and determining a matching score for each interference feature based on the comparison results; Generate a candidate list of interference sources corresponding to each interference signal according to the matching score result; The generation environment corresponding to the interference signal is obtained, and the interference source candidate list is screened based on the generation environment and the matching score result to obtain the interference source corresponding to each interference signal, and the interference source is located to obtain the positioning result.

[0054] In this embodiment, the comparison process is to compare the multidimensional feature vector of the interference signal with the multidimensional feature vector of the normal communication signal element by element to identify the differences. For example, the signal characteristics of the drone during normal flight are compared with the signal characteristics when interfered with to identify the impact of the interference.

[0055] In this embodiment, cluster analysis is to group the extracted interference features and aggregate similar interference signals together to identify different types of interference. For example, multiple interference signals (such as interference from different devices) are clustered into two categories: "electromagnetic interference" and "signal shielding".

[0056] In this embodiment, the interference source-signature database is a database that stores known interference sources and their features, and is used to compare newly identified interference features. For example, the database contains interference features of different devices (such as Wi-Fi routers and microwave ovens).

[0057] In this embodiment, the comparison result is the result of comparing the extracted interference feature with the feature in the database, indicating the degree of matching. For example, the comparison result shows that the matching degree between the newly identified interference feature and the feature of a Wi-Fi router in the database is 85%.

[0058] In this embodiment, the matching score is a score generated based on the comparison result, reflecting the similarity between the interference feature and the feature of the known interference source. For example, the matching score of an interference signal is 0.9, which indicates that it is very similar to the known interference source.

[0059] In this embodiment, the interference source candidate list is a list of potential interference sources generated according to the matching score. For example, the candidate list may include "Wi-Fi router", "Bluetooth device", "microwave oven" and the like.

[0060] In this embodiment, the generation environment refers to the specific environment in which the interference signal is generated, including the geographical location, equipment layout, etc. For example, a drone is flying in an urban environment with multiple radio transmitting devices around it.

[0061] In this embodiment, the screening process is to analyze the candidate list of interference sources according to the generation environment and the matching score, and remove irrelevant interference sources. For example, if in a rural environment, the interference sources in the urban environment are screened out and the equipment suitable for the rural environment is retained.

[0062] In this embodiment, the positioning process is to determine the specific location of the interference source by analyzing the interference signal and its characteristics in combination with environmental data. For example, the interference source is determined to be a specific Wi-Fi router through signal strength and direction positioning.

[0063] The working principle and beneficial effects of the above technical solution are: by comparing the multi-dimensional feature vectors of the interference signal and the normal communication signal, the interference features are extracted and cluster analysis is performed to identify the interference type. The extracted interference features are mapped to the known interference source-feature database for comparison, and a matching score is generated. Based on this, a candidate list of interference sources is generated. Combined with the generation environment of the interference signal, the candidate list is screened, and finally the interference source is located and the positioning result is obtained, which helps the UAV to effectively locate the interference source in complex scenarios, thereby optimizing data transmission and communication quality.

[0064] Embodiment 5: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which adjusts the original network topology of the UAV based on the positioning result, and optimizes the deployment of relay nodes to obtain an updated network topology, including: Obtain the interference property corresponding to the interference source, determine the influence range of the interference source on the UAV according to the interference property, evaluate the influence relationship of the positioning result on the original network topology of the UAV based on the influence range, and determine the influence of the interference signal on the communication between the UAV and other terminals according to the influence relationship; Identify weaknesses in the original network topology based on the communication impact, and analyze relay node requirements based on the weakness identification results and positioning results; According to the weakness identification results, positioning results and relay node requirements, the relay node deployment is optimized to obtain an updated network topology.

[0065] In this embodiment, the interference property is the signal characteristics generated by the interference source, including frequency, amplitude, modulation mode, etc., reflecting the type and intensity of the interference. For example, in drone communication, the interference property may be strong electromagnetic interference at a frequency of 2.4 GHz emitted by a certain device.

[0066] In this embodiment, the impact range is the area where the interference source affects the drone communication, which is usually expressed as a radius or coverage area. For example, if the impact range of a certain interference source is 200 meters, the communication quality of the drones within this range may be affected.

[0067] In this embodiment, the impact relationship is the degree and manner of the impact of the interference source on the original network topology of the drone, indicating how the interference changes the connectivity and communication quality of the network. For example, the presence of the interference source may cause the signal between the drone and the ground control station to be lost, thereby affecting its communication link.

[0068] In this embodiment, the communication impact refers to the degree of influence of the interference signal on the data transmission between the UAV and other communication endpoints (such as ground stations, relay nodes, etc.). For example, due to interference, the communication delay between the UAV and the ground control station increases, resulting in unstable data transmission.

[0069] In this embodiment, the relay node requirement is to determine the number, location and link connection of relay nodes that need to be added or optimized under the influence of identified weaknesses and interference. For example, if the communication quality in a certain area is poor, it may be necessary to add a relay node to improve signal coverage.

[0070] In this embodiment, weakness identification is to analyze the vulnerable links in the network topology and identify the nodes or links that may be interfered with or signal attenuated. For example, it is identified that the signal link between the drone and a ground station is prone to failure due to interference.

[0071] The working principle and beneficial effects of the above technical solution are: by obtaining the interference properties of the interference source, evaluating its impact range on the drone, and analyzing the relationship between the impact and the original network topology, the weaknesses in the communication are identified, and the deployment of relay nodes is optimized by combining the positioning results and the requirements of relay nodes. Finally, the network topology is updated to improve the reliability and stability of the drone communication system, ensure the reliability of data transmission, thereby meeting the needs of diversified application scenarios and significantly improving the adaptability of the drone communication system in a dynamic environment.

[0072] Embodiment 6: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which identifies weaknesses in the original network topology according to the communication impact, and analyzes relay node requirements in combination with the weakness identification results and positioning results, including: Collecting original topology network data, obtaining user connection requirements in the area around the positioning result based on the positioning result of the interference signal, and performing regional signal strength analysis according to the user connection requirements to obtain a weakness identification result; The relay point requirement is determined based on the weakness identification result and the user connection requirement.

[0073] In this embodiment, the weakness identification result is to identify the communication weaknesses in a specific area by analyzing the network signal strength, the location of the interference source and the user's connection requirements. These weaknesses may cause poor signal quality, unstable connection or data loss. For example, in drone communication, the weakness identification result may show that the signal strength in a certain area (such as the city center) is lower than -85dBm, causing the drone to be unable to maintain stable communication with the ground control station in this area.

[0074] In this embodiment, determining the relay point demand is to analyze the user connection demand, understand the number and type of drones that need to be connected in the area based on the user connection demand in the surrounding area of ​​the positioning result, combine the weakness identification result, compare the weakness identification result with the user connection demand, determine which areas need to enhance signal coverage, calculate the number and location of relay points, evaluate the signal coverage of each relay node based on the weakness identification result, and calculate the required number of relay nodes to ensure that each user can obtain sufficient signal strength. For example, if in a certain area, the user connection demand shows that 8 drones need to be connected at the same time, and the weakness identification result shows that the signal strength in the area is lower than -85dBm, it may be necessary to deploy 2 relay nodes to ensure signal coverage and meet the connection needs of all drones.

[0075] In this embodiment, the original topological network data includes node information, including the location, type and function of the drone, ground control station, and relay node, connection status, communication link status between nodes, including signal strength, delay and bandwidth, etc., geographic information, geographical features of the coverage area, such as buildings, trees and other obstacles that may affect signal propagation, interference source information, known interference source locations and their characteristics (such as frequency and strength). For example, the original topological network data may include signal strength data between a drone (location: longitude, latitude) and two ground control stations (position 1, position 2), the distribution of relay nodes (such as relay node A is on the top of a building with a signal strength of -70dBm), and geographic information showing that there are tall buildings in a certain area, which may affect signal propagation.

[0076] The working principle and beneficial effects of the above technical solution are: by collecting original topological network data, analyzing the positioning results of interference signals, evaluating user connection needs in the positioning area, conducting regional signal strength analysis, identifying communication weaknesses, and finally determining the deployment of relay points based on the weakness identification results and user needs, so as to optimize the communication quality and stability between the UAV and the ground control station, ensure that user connection needs can still be met in an interference environment, and optimize the layout of relay nodes.

[0077] Embodiment 7: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which optimizes the deployment of relay nodes according to the weakness identification results, positioning results and relay node requirements, and obtains an updated network topology, including: ,in, F represents the comprehensive objective function of evaluating the node deployment scheme; Indicates k The signal strength required for each weakness identification result; Indicates k The actual signal strength of each weakness identification result; K Indicates the total number of weakness identification results; N Indicates the total number of relay nodes; k An index representing the weakness identification result; Indicates i The relay node and j The distance between relay nodes; f Indicates the signal frequency of the drone communication; i and j Represents the index of the relay node; Indicates i The relay node and k The distance between the weakness identification results; and Respectively represent i The transmission power of the relay node is j The transmit power of the relay node; 20 is the unit conversion factor; a represents the constant term required to convert distance and frequency to dB, a =32.44; Indicates i The relay node and j The impact of the distance between relay nodes on signal strength; Indicates the effect of signal frequency on signal strength of drone communication; The links between relay nodes are optimized according to the comprehensive objective function to obtain an updated network topology.

[0078] In this embodiment, the specific process of optimizing the links between relay nodes by the comprehensive objective function is to collect the original topological network data, including the relay node location, signal strength, user connection requirements and interference signal information, set the comprehensive objective function F, which usually includes variables such as signal strength, distance, and transmission power, and use an optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) to solve the objective function to find the best relay node layout and transmission power configuration, adjust the links between relay nodes through iterative calculation, and gradually approach the optimal value of the objective function, and update the network topology according to the optimization results to ensure that the layout of the relay nodes can effectively cover all weakness identification areas.

[0079] The working principle and beneficial effects of the above technical solution are: by establishing a comprehensive objective function, evaluating the relay node deployment plan, optimizing the relationship between signal strength and distance, and ensuring that the signal strength of each weakness identification result meets the requirements. By dynamically adjusting the transmission power and layout of the relay nodes, the coverage and quality of drone communications are improved, thereby updating the network topology and improving the overall communication performance.

[0080] Embodiment 8: The embodiment of the present invention provides an adaptive anti-interference method based on UAV communication interference monitoring, which adjusts the communication parameters and flight path of the UAV according to the updated network topology, including: Identifying a topology change of the updated network topology, and matching a corresponding adjustment instruction from a change-adjustment instruction table according to the topology change; According to the adjustment instruction, a first adjustment is made to the communication parameters of the UAV, a second adjustment is made to the flight path, and the first adjustment and the second adjustment are combined to perform an adaptive anti-interference operation on the interference signal.

[0081] In this embodiment, topology change refers to changes in the location, connection status or signal strength of nodes (such as drones and relay nodes) in the network. For example, when a drone is flying in an urban environment, the signal strength decreases due to obstruction by buildings, and the network topology needs to be re-evaluated.

[0082] In this embodiment, the change-adjustment instruction table is a table that records adjustment instructions corresponding to different topology changes. For example, if the signal strength is lower than a certain threshold, the instructions in the table may indicate increasing the transmission power or changing the flight path.

[0083] In this embodiment, the adjustment instruction is a specific operation instruction generated according to the topology change, which is used to optimize the communication performance. For example, the instruction may include "increase the transmission power of relay node A by 10%" or "adjust the altitude of the drone to 150 meters."

[0084] In this embodiment, the communication parameters are parameters that affect the communication quality between the drone and the relay node, such as transmission power, frequency, modulation mode, etc. For example, in an area with strong interference, the transmission power is adjusted to enhance the signal.

[0085] In this embodiment, the first adjustment is to adjust the communication parameters of the drone to optimize the signal quality, for example, after interference is identified, the transmission power of the drone is increased.

[0086] In this embodiment, the flight path is the flight route of the drone when performing a mission. For example, the flight path of the drone is changed according to real-time signal strength data to avoid signal interference areas.

[0087] In this embodiment, the second adjustment is to adjust the flight path of the drone to improve communication stability, for example, replanning the flight route so that the drone flies over an area with strong signals or bypasses interference sources.

[0088] In this embodiment, the adaptive anti-interference operation automatically adjusts the communication parameters and flight path according to environmental changes to resist the influence of interference signals. For example, the UAV monitors the signal strength in real time during the flight and automatically adjusts the transmission power and flight altitude according to the changes to ensure stable communication.

[0089] The working principle and beneficial effect of the above technical solution are: by real-time identification of network topology changes, matching adjustment instructions to optimize the communication parameters and flight path of the drone. By combining the first adjustment (communication parameters) with the second adjustment (flight path), adaptive anti-interference operation of interference signals is achieved, thereby improving communication quality and reliability.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An adaptive anti-interference method based on UAV communication interference monitoring, characterized in that: include: Step 1: Obtain all signal information within the communication range of the drone, perform spectrum analysis on the signal information, and identify normal communication signals and interference signals based on the spectrum analysis results; Step 2: extract interference features from the interference signal, classify the interference signal according to the interference features, determine the interference source based on the classification result, and locate the interference source; Step 3: Adjust the original network topology of the drone based on the positioning results, and optimize the deployment of relay nodes to obtain an updated network topology; Step 4: Adjust the drone’s communication parameters and flight path based on the updated network topology.

2. According to claim 1, the adaptive anti-interference method based on UAV communication interference monitoring is characterized in that: Obtain all signal information within the communication range of the drone, perform spectrum analysis on the signal information, and identify normal communication signals and interference signals based on the spectrum analysis results, including: Using the communication equipment of the drone to obtain all signal information within the communication range of the drone, using fast Fourier transform on the signal information to obtain a frequency domain representation of the signal information, and determining the spectrum characteristics and phase characteristics of the signal information according to the frequency domain representation; Obtain the information processing requirements of the UAV and determine the time domain characteristics of the signal information based on the information processing requirements of the UAV; The spectrum features, phase features and time domain features are fused to form a multi-dimensional feature vector corresponding to each signal information, and normal communication signals and interference signals are identified based on the multi-dimensional vector features.

3. The adaptive anti-interference method based on UAV communication interference monitoring according to claim 2 is characterized in that: Identifying normal communication signals and interference signals based on the multidimensional vector features includes: Select an adversarial network architecture according to the unmanned information processing requirements, and design a generator and a discriminator by combining the history-signal data table with the adversarial network architecture; Using the multidimensional feature vector and the generator to generate a training feature vector, and updating the weight of the discriminator when the number of updates of the training feature vector is less than or equal to a preset number of discriminant updates; If the number of updates is greater than the preset number of discriminant updates, the weight of the discriminator is fixed, and the weight of the generator is updated according to the probability of misjudgment of the training feature vector by the discriminator; According to the adversarial network architecture, the generator and the discriminator are used to identify normal communication signals and interference signals.

4. The adaptive anti-interference method based on UAV communication interference monitoring according to claim 1 is characterized in that: Extracting interference features from the interference signal, classifying the interference signal according to the interference features, determining the interference source based on the classification result, and locating the interference source, including: Comparing the multidimensional feature vector corresponding to the interference signal with the multidimensional feature vector corresponding to the normal communication signal, determining the interference feature of the interference signal according to the vector comparison result, performing cluster analysis on the interference feature, and identifying the interference type corresponding to the interference signal; Mapping the extracted interference features and the corresponding interference types to a known interference source-feature database for comparison, and determining a matching score for each interference feature based on the comparison results; Generate a candidate list of interference sources corresponding to each interference signal according to the matching score result; The generation environment corresponding to the interference signal is obtained, and the interference source candidate list is screened based on the generation environment and the matching score result to obtain the interference source corresponding to each interference signal, and the interference source is located to obtain the positioning result.

5. The adaptive anti-interference method based on UAV communication interference monitoring according to claim 1 is characterized in that: Based on the positioning results, the original network topology of the drone is adjusted, and the deployment of relay nodes is optimized to obtain an updated network topology, including: Obtain the interference property corresponding to the interference source, determine the influence range of the interference source on the UAV according to the interference property, evaluate the influence relationship of the positioning result on the original network topology of the UAV based on the influence range, and determine the influence of the interference signal on the communication between the UAV and other terminals according to the influence relationship; Identify weaknesses in the original network topology based on the communication impact, and analyze relay node requirements based on the weakness identification results and positioning results; According to the weakness identification results, positioning results and relay node requirements, the relay node deployment is optimized to obtain an updated network topology.

6. The adaptive anti-interference method based on UAV communication interference monitoring according to claim 5 is characterized in that: According to the communication impact, the original network topology is identified for weaknesses, and the relay node requirements are analyzed by combining the weakness identification results with the positioning results, including: Collecting original topology network data, obtaining user connection requirements in the area around the positioning result based on the positioning result of the interference signal, and performing regional signal strength analysis according to the user connection requirements to obtain a weakness identification result; The relay point requirement is determined based on the weakness identification result and the user connection requirement.

7. The adaptive anti-interference method based on UAV communication interference monitoring according to claim 5 is characterized in that: According to the weakness identification results, positioning results and relay node requirements, the relay node deployment is optimized to obtain an updated network topology, including: ,in, F represents the comprehensive objective function of evaluating the node deployment scheme; Indicates k The signal strength required for each weakness identification result; Indicates k The actual signal strength of each weakness identification result; K Indicates the total number of weakness identification results; N Indicates the total number of relay nodes; k An index representing the weakness identification result; Indicates i The relay node and j The distance between relay nodes; f Indicates the signal frequency of the drone communication; i and j Represents the index of the relay node; Indicates i The relay node and k The distance between the weakness identification results; and Respectively represent i The transmission power of the relay node is j The transmit power of the relay node; 20 is the unit conversion factor; a represents the constant term required to convert distance and frequency to dB, a =32.44; Indicates i The relay node and j The impact of the distance between relay nodes on signal strength; Indicates the effect of signal frequency on signal strength of drone communication; The links between relay nodes are optimized according to the comprehensive objective function to obtain an updated network topology.

8. The adaptive anti-interference method based on UAV communication interference monitoring according to claim 1 is characterized in that: Adjust the drone’s communication parameters and flight paths based on the updated network topology, including: Identifying a topology change of the updated network topology, and matching a corresponding adjustment instruction from a change-adjustment instruction table according to the topology change; According to the adjustment instruction, a first adjustment is made to the communication parameters of the UAV, a second adjustment is made to the flight path, and the first adjustment and the second adjustment are combined to perform an adaptive anti-interference operation on the interference signal.

Images