Unmanned aerial vehicle-based adaptive communication and inductance integrated power transmission line monitoring method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a self-adaptive sensing integrated power transmission line monitoring method and device based on an unmanned aerial vehicle, electronic equipment and a storage medium, and the method comprises the steps: obtaining environment parameters and line parameters sensed by a sensor of the unmanned aerial vehicle based on a constructed unmanned aerial vehicle communication sensing system model; and taking the environment parameters, the line parameters, the unmanned aerial vehicle energy consumption parameters and system parameters of the communication sensing system as current states, inputting the current states into a pre-constructed sensing strategy configuration model, and outputting a sensing strategy for unmanned aerial vehicle power transmission line detection by the sensing strategy configuration model. According to the invention, under the condition of ensuring reasonable utilization of unmanned aerial vehicle resources, the system performance in different environments can be ensured, and accurate perception and dynamic adaptation to a power transmission line detection task can be realized.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of power grid technology, and in particular to a method, device, electronic device, and storage medium for adaptive synaesthesia-integrated transmission line monitoring based on a drone. Background Art

[0002] With the development of the power industry and the continuous expansion of power grid coverage, the operation and maintenance of transmission lines face enormous challenges. Traditional transmission line monitoring relies primarily on manual inspections or fixed monitoring equipment. Traditional fixed equipment is deployed in fixed locations, making it difficult to comprehensively monitor large-scale transmission lines in real time, especially in remote areas such as mountainous areas and plateaus, where areas may be missed. Manual inspections are also inefficient and cannot quickly respond to emergencies such as windstorms and ice disasters.

[0003] In recent years, drones have become a crucial tool for power transmission line inspection due to their high flexibility, low cost, and wide coverage. Equipped with various inspection equipment, such as high-definition cameras and infrared imaging devices, they are capable of comprehensive, large-scale monitoring of power transmission lines. However, drones still face numerous challenges, including limited flight range, resource constraints for communication and perception tasks, and adaptability to complex environments. These include low perception efficiency, inefficient resource utilization, and insufficient adaptability. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present application is to propose an adaptive synaesthesia-integrated transmission line monitoring method, device, electronic device and storage medium based on drones to solve the problem of drone detection of transmission lines.

[0005] Based on the above objectives, the present invention provides an adaptive synaesthesia-integrated transmission line monitoring method based on a drone, including:

[0006] Based on the constructed UAV communication perception system model, the environmental parameters and line parameters perceived by the UAV’s sensors are obtained;

[0007] Taking the environmental parameters, line parameters, UAV energy consumption parameters, and system parameters of the communication perception system as the current state, the current state is input into a pre-built perception strategy configuration model, and the perception strategy configuration model outputs the perception strategy for UAV power transmission line detection.

[0008] Optionally, the perception strategy includes the perception duration, perception accuracy, sampling frequency, and sampling power of the drone; the perception strategy configuration model is implemented based on a deep Q network, and the reward function of the perception strategy configuration model is constructed according to preset perception duration, perception accuracy, drone energy consumption, and drone communication load reward rules.

[0009] Optionally, the reward function is:

[0010] R(S,A)=R 基础 (S,A)+R 规则 (S,A) (23)

[0011] R 基础 (S,A) =α·P accuracy -β·P energy -γ·P communication -δ·P penalty (twenty four)

[0012] Among them, R 基础 (S, A) is the multi-target reward, P accuracy is the perception accuracy, P energy is the energy consumption of the UAV, P communication is the communication load of the UAV, P penalty is a penalty term. When one or more of the sensing accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the penalty term is set to the corresponding penalty value. α, β, γ, and δ are weight coefficients. 规则 (S, A) is the rule-based reward value. When the executed action is consistent with the preset rule, a positive reward value is obtained. When the executed action is inconsistent with the preset rule, a negative reward value is obtained.

[0013] Optionally, when one or more of the sensing accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the penalty item is set to the corresponding penalty value, including:

[0014] When the perception accuracy is lower than the preset accuracy threshold θ accuracy When , the penalty value corresponding to the perception accuracy is:

[0015] P penalty_accuracy =λ accuracy max(0,θ accuracy -P accuracy ) (26)

[0016] When the energy consumption of the drone exceeds the preset energy consumption threshold θ energy When , the penalty value corresponding to the drone energy consumption is:

[0017] P penalty_energy =λ energy max(0,P energy -θ energy ) (28)

[0018] When the communication load exceeds the preset load threshold θ communication When , the penalty value corresponding to the communication load is:

[0019] Ppenalty_communication =λ communication max(0,P communication -θ communication ) (30)

[0020] Among them, λ accuracy is the penalty factor of perceptual accuracy, λ energy is the penalty factor for the UAV’s energy consumption, λ communication is the penalty factor for communication load.

[0021] Optionally, the preset rule includes a perception duration rule, and the perception duration rule includes adjusting the perception duration according to a degree of change in the target state between two adjacent perception tasks.

[0022] Optionally, adjusting the perception duration includes:

[0023] The perception duration is adjusted by setting the value of the perception indicator; when the value of the perception indicator is a first value, the drone provides communication and perception services in the downlink phase, and when the value of the perception indicator is a second value, the drone only provides communication services.

[0024] The present application also provides a drone-based adaptive synaesthesia integrated power transmission line monitoring device, comprising:

[0025] An acquisition module is used to obtain environmental parameters and line parameters perceived by the drone's sensors based on the constructed drone communication perception system model;

[0026] The perception strategy configuration module is used to take the environmental parameters, line parameters, UAV energy consumption parameters, and system parameters of the communication perception system as the current state, input the current state into a pre-built perception strategy configuration model, and output the perception strategy for UAV power transmission line detection from the perception strategy configuration model.

[0027] Optionally, the perception strategy includes the perception duration, perception accuracy, sampling frequency, and sampling power of the drone; the perception strategy configuration model is implemented based on a deep Q network, and the reward function of the perception strategy configuration model is constructed according to preset perception duration, perception accuracy, drone energy consumption, and drone communication load reward rules.

[0028] Optionally, the reward function is:

[0029] R(S,A)=R 基础 (S,A)+R 规则 (S,A) (23)

[0030] R 基础 (S, A) = α·P accuracy -β·P energy-γ·P communication -δ·P penalty (twenty four)

[0031] Among them, R 基础 (S, A) is the multi-target reward, P accuracy is the perception accuracy, P energy is the energy consumption of the UAV, P communication is the communication load of the UAV, P penalty is a penalty term. When one or more of the sensing accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the penalty term is set to the corresponding penalty value. α, β, γ, and δ are weight coefficients. 规则 (S, A) is the rule-based reward value. When the executed action is consistent with the preset rule, a positive reward value is obtained. When the executed action is inconsistent with the preset rule, a negative reward value is obtained.

[0032] Optionally, the perception strategy configuration module is used to determine when the perception accuracy is lower than a preset accuracy threshold θ accuracy When , the penalty value corresponding to the perception accuracy is:

[0033] P penalty_accuracy =λ accuracy max(0,θ accuracy -P accuracy ) (26)

[0034] When the energy consumption of the drone exceeds the preset energy consumption threshold θ energy When , the penalty value corresponding to the drone energy consumption is:

[0035] P penalty_energy =λ energy max(0,P energy -θ energy ) (28)

[0036] When the communication load exceeds the preset load threshold θ communication When , the penalty value corresponding to the communication load is:

[0037] P penalty_communication =λ communication max(0,P communication -θ communication ) (30)

[0038] Among them, λ accuracy is the penalty factor of perceptual accuracy, λ energy is the penalty factor for the UAV’s energy consumption, λ communication is the penalty factor for communication load.

[0039] Optionally, the preset rule includes a perception duration rule, and the perception duration rule includes adjusting the perception duration according to a degree of change in the target state between two adjacent perception tasks.

[0040] Optionally, the perception strategy configuration module is used to adjust the perception duration by setting the value of the perception indicator; wherein, when the value of the perception indicator is a first value, the drone provides communication and perception services in the downlink phase, and when the value of the perception indicator is a second value, the drone only provides communication services.

[0041] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the adaptive synaesthesia integrated transmission line monitoring method based on drones.

[0042] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the adaptive synaesthesia integrated transmission line monitoring method based on a drone is implemented.

[0043] As can be seen from the above, the adaptive synaesthesia integrated transmission line monitoring method, device, electronic device and storage medium based on drones provided in the embodiments of the present application are based on the constructed drone communication perception system model, obtain the environmental parameters and line parameters perceived by the drone's sensors, take the environmental parameters, line parameters, drone energy consumption parameters, and system parameters of the communication perception system as the current state, input the current state into a pre-built perception strategy configuration model, and the perception strategy configuration model outputs the perception strategy for drone transmission line detection. This application can ensure system performance in different environments while ensuring the rational use of drone resources, and achieve accurate perception and dynamic adaptation to transmission line detection tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 This is a schematic diagram of the method flow of an embodiment of the present application;

[0046] Figure 2 A schematic diagram of the system architecture of an embodiment of the present application;

[0047] Figure 3This is a schematic diagram of the time slot structure of an embodiment of the present application;

[0048] Figure 4 This is a pseudo-code diagram of the training process of the perception strategy configuration model according to an embodiment of the present application;

[0049] Figure 5 This is a block diagram of the device structure of an embodiment of the present application;

[0050] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0052] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the usual meanings understood by people with ordinary skills in the field to which this disclosure belongs. The "first", "second" and similar words used in the embodiments of the present application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0053] Among related technologies, drones, a crucial tool for power transmission line inspection, suffer from deficiencies in resource allocation and adaptability. Integrated Communication and Awareness (ISAC) technology aims to support both communication and perception tasks by sharing hardware resources (such as antenna arrays). This improves system resource utilization and provides new insights for multi-task collaborative optimization.

[0054] In view of this, an embodiment of the present application provides an adaptive synaesthesia integrated transmission line monitoring method based on drones, which applies communication and perception integration technology to drone transmission line detection, optimizes the resource allocation and perception strategy of drones, and can respond to different perception needs and environmental changes, thereby realizing efficient and accurate monitoring of complex transmission line environments.

[0055] The technical solution of the present application is further described in detail below through specific examples.

[0056] like Figure 1As shown, the embodiment of the present application provides a UAV-based adaptive synaesthesia integrated transmission line monitoring method, comprising:

[0057] S101: Based on the constructed UAV communication perception system model, obtain the environmental parameters and line parameters perceived by the UAV’s sensors;

[0058] In this embodiment, the communication and perception integration technology is applied to realize the detection of transmission lines by UAVs, and to build an adaptive communication and perception system for UAVs. Figure 2 As shown in the figure, the communication perception system includes a drone, multiple user equipment (UEs) and targets, where the user equipment includes intelligent sensor devices mounted on towers or transmission lines, such as vibration sensors, temperature and humidity sensors, etc., for communicating with the drone; the targets include transmission lines, towers, obstacles, etc., for being perceived and monitored by the drone; the drone is equipped with perception equipment such as radar and infrared cameras to perform perception tasks, and the drone is equipped with a vertically placed uniform linear array of antennas.

[0059] Within a given ISAC service period, T, the drone flies from a predetermined starting point to a final location, inspecting the transmission lines during flight. At the end of the service period, the drone must arrive at the final location. During this period, T, the drone communicates with K single-antenna user equipment (UEs) on the ground and performs sensing tasks on J targets based on sensing requirements. The drone senses the target by transmitting signals to it and estimates the target's relevant parameters by receiving the echo signals reflected by the target.

[0060] In some embodiments, the period T is divided into N time slots, with a time slot length τ = T / N, n∈{1,2,…,N}, and each time slot operates in a time division duplex mode, consisting of a downlink phase duration and an uplink phase duration. Figure 3 As shown in the figure, the services that drones can provide include communication-only services and integrated communication and perception services. In each time slot, when the drone provides communication-only services, it transmits downlink communication signals and receives uplink communication signals from user equipment. When the drone provides integrated communication and perception services, it transmits ISAC signals to enable downlink communication and perception signals, while simultaneously receiving uplink communication signals and echo signals reflected by targets. The communication signals and echo signals share the same uniform linear array, and the ISAC signal is a superposition of separately precoded communication and perception signals.

[0061] In some embodiments, considering that communication and perception generally have different performance requirements for waveforms during the communication and perception process, for example, the communication waveform has a high requirement for high data rate, while the perception waveform has a high requirement for constant envelope and good correlation, this embodiment uses different waveforms for communication and perception. Specifically, in the downlink phase (DL phase) when the drone sends a signal to the user equipment, the transmitted signal of the drone in time slot n is:

[0062]

[0063] in is the transmit beamforming vector of the communication signal transmitted by the UAV to the user equipment k in time slot n, is the transmit beamforming vector of the sensing signal transmitted by the UAV to the target j at time slot n, Q is the dimension of the transmit beamforming vector, that is, the number of antennas in the antenna array configured by the UAV; is the unrelated communication signal transmitted by the UAV to the user equipment k in time slot n, that is, the communication signals in the downlink phase are independent. is the perception signal transmitted by the UAV to the target j in time slot n, The elements of are independent, and each element has zero mean and unit variance.

[0064] In the uplink phase (UL phase) when the user equipment sends a signal to the drone, the transmission signal of the user equipment k is:

[0065]

[0066] in, is the transmitted signal of user equipment k in time slot n, p k is the transmit power of user equipment k, is the communication signal sent by user equipment k in time slot n.

[0067] The communication channel and the sensing channel of this embodiment both adopt a probabilistic line-of-sight channel model. In time slot n, the probability of LoS between the drone and user device k or target j is:

[0068]

[0069] in, is the probability of line-of-sight communication between target m and the UAV in time slot n, C and D are constant parameters in rural, urban or dense urban propagation environments; θ m,n is the elevation angle between the UAV and the target m at time slot n, d m,n is the three-dimensional Euclidean distance between the UAV and the target m in time slot n, which is calculated as follows:

[0070]

[0071] Among them, z n is the height of the drone at time slot n (vertical coordinate), q n is the three-dimensional spatial position of the UAV at time slot n, including horizontal and vertical coordinates, q m,n is the three-dimensional spatial position of the target or user equipment m in time slot n.

[0072] Therefore, the probability of non-LoS (NLoS) occurrence is:

[0073]

[0074] In this embodiment, for the communication signal model part of the system, use To simulate the path loss between the user equipment and the drone link under low-altitude and non-low-altitude conditions, β0 represents the channel power gain at the reference distance d0 = 1~m. κ<1 is the additional attenuation factor caused by the NLoS condition. It is assumed that the uplink and downlink channels are reciprocal. is the wireless channel between the UAV and user equipment k in time slot n, and its expression is:

[0075]

[0076] Among them, hLoS k,n =a k,n , a k,n is the emission direction vector, and its expression is:

[0077]

[0078] Where d is the antenna spacing, λ is the carrier wavelength, and θ k , n is the incident angle of the user equipment. hNLoS k,n is a complex Gaussian random vector with zero mean and the identity covariance matrix.

[0079] The communication signal received by the user equipment is:

[0080]

[0081] in, is the target communication signal sent by the UAV to the user device k, is the interference signal of user equipment i, is the perceived signal interference of target j, is the additive white Gaussian noise of user equipment k; ψ n ∈{0,1}; is the downlink wireless channel vector from the UAV to user equipment k, yes The conjugate transpose of is used in matrix multiplication to compute the received signal.

[0082] The combined signal received by the drone is the sum of signals from multiple user devices and targets, including target signals, inter-user interference, perceived interference, and noise, and is expressed as:

[0083]

[0084] in is the unit norm receive beamforming vector, is the target communication signal sent by user equipment k to the UAV, is the interference signal of user equipment i, is the perceived interference signal of target j, is the additive white Gaussian noise (AWGN) at the UAV, ξ n ∈{0,1} indicates signal overlap. If the uplink communication signal overlaps with the echo, then ξ n = 1, if there is no overlap, then ξ n =0;G j,n represents the channel gain between the UAV and target j at time slot n, is the conjugate transpose of the receive beamforming vector of user equipment k in time slot n.

[0085] The signal-to-noise ratio of user equipment k in the downlink phase is:

[0086]

[0087] is the noise power in the downlink.

[0088] The signal-to-noise ratio of user equipment k in the uplink phase is:

[0089]

[0090] is the noise power in the uplink received by the UAV.

[0091] in, is the co-channel interference in the downlink phase, is the co-channel interference in the uplink phase, expressed as:

[0092]

[0093] When user equipment k is in time slot n, the throughput in the downlink phase is:

[0094]

[0095] in, is the duration of the down phase.

[0096] The uplink throughput of user equipment k in time slot n is:

[0097]

[0098] in, for ξ n =1, the duration of the downward phase, for ξ n = 0. When there is no echo interference in time slot n, that is, ψ n =0, and Remain unchanged. for ξ n =1 when the signal-to-noise ratio is for ξ n =0 when the signal-to-noise ratio.

[0099] In this embodiment, for the system's sensing signal model, the drone's transmitted signal is reflected by the target and then received by the drone. Assuming the Doppler shift caused by the target and drone motion is constant within a time slot, it can be well compensated. The sensing channel for target j can be modeled as:

[0100]

[0101] in, is the complex reflection coefficient, σ j represents the complex radar cross section, b j,n is the launch steering vector, expressed as for b j,n The conjugate transpose of , the beamforming weight vector used for signal processing, is related to the signal propagation directionality. is a complex Gaussian random variable with zero mean and unit variance; Describe the power of line-of-sight and non-line-of-sight signals respectively.

[0102] Because the communication signal interferes with the reflected echo, sensing performance is reduced. To improve sensing performance, the drone subtracts the known uplink communication signal and the decoded user device communication signal from the received combined signal to extract the sensing signal. The extracted sensing signal is the echo signal reflected from the target. By adopting appropriate self-interference cancellation methods, it is assumed that the self-interference caused by simultaneous transmission and reception during the sensing process can be eliminated. Therefore, the reflected echo signal received by the drone can be expressed as:

[0103]

[0104] After the drone receives the reflected echo signal, it needs to estimate the unknown parameters, including the complex reflection coefficient and AoD angle θ j,n Since it is difficult to Extract target information from the , this embodiment mainly estimates the AoD angle θ j,n For parameter estimators in radar sensing, the Cramér-Rao Bound (CRB) is used as an important perceptual performance metric to provide a lower bound for the mean square error of the parameter estimator.

[0105] Given other target directions, estimate θ j,n The CRB indicator is expressed as:

[0106]

[0107] in, Indicates B j,n θ j,n The partial derivative of

[0108] In some embodiments, based on the established communication and perception system, drones, while providing communication and perception services, acquire perception parameters sensed by sensors. The drones are configured with the necessary sensors based on the power transmission line inspection task and, based on the different types of sensors configured, collect and acquire perception parameters detected by each sensor. In some implementations, drones are equipped with wind speed sensors, humidity sensors, temperature sensors, lidar, infrared sensors, high-definition cameras, and other sensors capable of sensing environmental parameters such as wind speed and humidity. Accelerometers or vibration sensors are used to detect the vibration frequency of the power transmission line, infrared sensors are used to detect the line temperature gradient, and lidar is used to detect the distance and angle between the drone and the power transmission line. Line parameters such as position are estimated based on these distances and angles.

[0109] S102: Taking environmental parameters, line parameters, drone energy consumption parameters, and system parameters as the current state, the current state is input into a pre-built perception strategy configuration model, and the perception strategy configuration model outputs the perception strategy for the drone to perform transmission line detection.

[0110] In this embodiment, based on the constructed drone communication perception system, the drone acquires various environmental and line parameters. These parameters, along with drone energy consumption parameters and the system parameters of the communication perception system, are used as the current state of the drone. These parameters are then input into a pre-built perception strategy configuration model. The perception strategy configuration model then outputs the optimal perception strategy for the drone to detect power transmission lines. The drone energy consumption parameter includes the drone's remaining battery life, while the system parameters include signal interference parameters and sensor errors of various sensors. The perception strategy for power transmission line detection includes the drone's perception duration, perception accuracy, sampling frequency, and sampling power.

[0111] In some embodiments, the perception strategy configuration model is implemented based on a reinforcement learning model using a deep Q-network. It combines state space, action space, and reward mechanisms to intelligently optimize perception task strategies. The state space is composed of perceived environmental parameters, route parameters, drone energy consumption parameters, and communication system parameters, while the action space is composed of perception strategy items such as perception duration, perception accuracy, sampling frequency, and sampling power. The intelligent agent, based on the current state space, constructs a reward function according to preset reward rules, aiming to maximize the cumulative discounted reward. By dynamically adjusting perception strategy items such as perception duration, perception accuracy, sampling frequency, and power, and continuously providing feedback to the learning environment, the intelligent agent obtains the optimal perception strategy, thereby improving the drone's resource utilization and detection efficiency.

[0112] In some embodiments, the state space S is used to describe the dynamic changes in the transmission line monitoring environment. As shown in Table 1, various state variables are constructed by analyzing the UAV operating environment and the detection indicators of the transmission line:

[0113] Table 1 State variables

[0114]

[0115]

[0116] Each state variable is updated in real time using sensors or historical monitoring data and normalized to ensure dimensional consistency across variables. For example, the remaining battery life of a drone can be predicted and updated by combining real-time monitoring with historical energy consumption and flight history, enabling more accurate assessment of mission sustainability. Transmission line vibration frequency can be updated through statistical analysis of real-time monitoring and historical vibration frequency data.

[0117] In some ways, the state space can be represented as:

[0118] S n ={ν wind , h humidity , E battery , d dis tance , fvibration , T gradient , n noise , e sensor} (20)

[0120] The action space defines all the perception strategies that the drone can adopt, ensuring efficient resource allocation based on the dynamic changes in the environment. To adapt to different mission requirements, the action space includes multi-level adjustable perception duration, perception accuracy, sampling frequency, sampling power, motion state, etc. Specifically:

[0121] The perception duration can be flexibly adjusted at multiple levels, including a small increase of one time slot, a large increase of two time slots, a small decrease of one time slot, and a large decrease of two time slots. This allows for flexible adjustment of the perception duration based on real-time changes in target state and environment to maximize resource utilization while avoiding oversampling or interruption of perception tasks. For example, when the target state changes significantly or the environment is complex, the perception duration can be significantly increased to ensure comprehensiveness and accuracy of data collection. When the target state changes little or the environment is relatively stable, the perception duration can be shortened to save power and bandwidth.

[0122] Perception accuracy refers to the accuracy of target position estimation. Depending on the importance and urgency of the detection task, you can choose high-precision mode or low-precision mode. The high-precision mode is suitable for key areas or high-risk tasks to ensure high accuracy and reliability of detection data; the low-precision mode is suitable for regular areas.

[0123] It can save resources and improve energy efficiency.

[0124] The sampling frequency is the number of times a drone transmits sensing signals per unit time. It determines the frequency and periodicity of the drone's sensing signals to the target, directly impacting the temporal resolution of the target's motion. The sampling frequency can be increased or decreased based on the target's dynamic characteristics and sensing requirements. For fast-moving targets, a higher sampling frequency is recommended to ensure sufficient detail is captured. For stationary or slow-moving targets, a lower sampling frequency can be used to minimize energy consumption.

[0125] Sampling power refers to the signal power used by a drone when transmitting its sensing signal, specifically, the strength of the transmitted signal. This directly affects the signal's range and penetration during transmission, as well as the strength of the echo signal reflected from the target. The sampling power can be increased or decreased based on the target distance and signal strength. If the target is far away or the signal attenuation in the environment is high, the sampling power should be increased to ensure adequate signal reflection and reception quality. Conversely, if the target is close or signal conditions are good, the sampling power can be reduced to save energy and minimize interference with other devices.

[0126] The drone's motion state can be selected based on the task being performed in different sensing scenarios: hovering, constant-speed flight, or maintaining the current state. For example, in key or high-risk areas, the drone can choose hovering mode to ensure accurate sensing; in routine monitoring missions, it can choose constant-speed flight to cover a wider area.

[0127] In summary, the action space is expressed as:

[0128] A={+1,-1,+2,-2,P 高精度 , P 低精度 , F 增频 , F 减频 , W 增强功率 , W 减少功率 , S 悬停 , S 匀速 ,0} (twenty one)

[0130] Among them, 0 means no action, that is, keep the current state.

[0131] In some embodiments, the perception strategy configuration model executes all possible actions in the action space A based on the current state of the input, calculates the reward value according to the constructed reward function, and calculates the Q value obtained based on the reward value. The drone selects the action with the largest Q value as the current optimal perception strategy, executes the optimal perception strategy, obtains an updated environmental state after executing the action, and maximizes the cumulative discounted reward by continuously interacting with the environment. The Q value function is expressed as:

[0132]

[0133] Among them, γ t is the discount factor for time slot t, which is used to balance the importance of current rewards and future rewards,

[0134] R(S t ,A t ) is the immediate reward of time slot t.

[0135] The reward function R(S,A) is used to quantify the quality of the action performed in the current state. The reward function is constructed based on the preset reward rules for perception time, perception accuracy, drone energy consumption, and drone communication load. The goal is to achieve optimal system performance and the best detection task by balancing perception accuracy, perception time, drone energy consumption, and communication load. The constructed reward function is:

[0136] R(S,A)=R 基础 (S,A)+R 规则 (S,A) (23)

[0137] Among them, R 基础 (S, A) is the multi-target reward, R 规则 (S, A) is the rule-based reward value. When the executed action is consistent with the preset rules, a positive reward is obtained. When the executed action is inconsistent with the preset rules, a negative reward is obtained.

[0138] Among them, the multi-objective reward R 基础 (S,A) is expressed as:

[0139] R 基础 (S, A) = α·P accuracy -β·P energy -γ·P communication -δ·P penalty (twenty four)

[0140] Among them, P accuracy is the perception accuracy, P energy is the energy consumption of the UAV, P communication is the communication load of the UAV; P penalty is a penalty item. When one or more of the perception accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the value of the penalty item is the corresponding penalty value. α, β, γ, and δ are weight coefficients used to dynamically adjust the importance of each indicator.

[0141] Perception accuracy P accuracy It is calculated by the inverse of the target position error (MSE) and is used to measure the effectiveness of the sampled data. The higher the perception accuracy, the higher the reward value obtained. The calculation formula is:

[0142]

[0143] When the perception accuracy P accuracy Below the preset accuracy threshold θ accuracy When , the penalty value corresponding to the perception accuracy is:

[0144] P penalty_accuracy =λ accuracy max(0,θ accuracy -Paccuracy ) (26)

[0145] Among them, λ accuracy is the penalty factor for perceptual accuracy.

[0146] UAV energy consumption P energy Refers to the amount of power consumed by the drone during the perception mission. To save energy, the system encourages the reduction of unnecessary perception missions. The lower the drone's energy consumption, the higher the reward value it receives. The calculation formula is:

[0147]

[0148] Among them, E battery_nitial is the initial power of the drone, E battery_current The current battery level of the drone.

[0149] When the UAV energy consumption P energy Exceeds the preset energy consumption threshold θ energy When , the penalty value corresponding to the drone energy consumption is:

[0150] P penalty_energy =λ energy max(0,P energy -θ energy ) (28)

[0151] λ energy is the penalty factor for the drone’s energy consumption.

[0152] Communication load P communication It refers to the total amount of data transmitted by the drone in a time slot, including data for communication tasks between the drone and the user equipment, and data for perception tasks between the drone and the target. To avoid communication congestion caused by excessive communication load, the communication load needs to be controlled within a reasonable range. The lower the communication load of the drone, the higher the reward value it receives. The calculation formula is:

[0153]

[0154] Among them, DataRate is the actual data transmission rate of the drone in the current time slot, in bits per second, Time is the duration of the current time slot, in seconds, and MaxDataRate is the maximum data transmission rate supported by the drone communication link under ideal conditions.

[0155] When the communication load P communication Exceeds the preset load threshold θ communication When , the penalty value corresponding to the communication load is:

[0156] P penalty_communication =λ communication max(0,Pcommunication -θ communication ) (30)

[0157] Among them, λ communication is the penalty factor for communication load.

[0158] Rule-based reward value R 规则 (S,A) is expressed as:

[0159]

[0160] Among them, C 规则 The weight of the rule reward or penalty is dynamically adjusted based on the system's reliance on the rule. The rules include the perception duration rule, whereby if the action performed complies with the perception duration rule, a positive reward is awarded, and if it doesn't, a negative reward is awarded.

[0161] In some embodiments, when providing integrated communication and perception services, if the target perception duration (the duration of transmitting signals to the target) is too long, it may lead to resource waste, while if the perception duration is too short, it may result in poor perception performance. Therefore, it is necessary to properly configure the perception duration to ensure reasonable resource utilization and achieve optimal perception performance.

[0162] This embodiment provides a rule-based method for dynamically adjusting perception time. The method determines the demand level of the perception task by calculating the difference ratio based on perception parameters such as the target's moving speed, position estimation error, or mean square error. The method dynamically adjusts the perception duration based on the demand level of the perception task. This method can quickly respond to changes in sensing parameters in a power transmission line detection environment, ensure perception performance, and rationally utilize resources.

[0163] Specifically, define the perception indicator ψ of time slot n n ∈{0,1}, when ψ n =1, it means that the UAV provides communication and perception services in the downlink phase. n =0, indicating that the drone only provides communication services.

[0164] Define the difference ratio r of the perceptual parameters m Characterize the degree of change of the target state between two adjacent perception tasks, expressed as:

[0165]

[0166] Among them, P m-1 is the perception parameter of the m-1th perception, ΔP m= is the difference between the perception parameters detected at the m-1th and mth times. Different types of sensors detect different perception parameters. For example, for a laser displacement sensor, the perception parameter detected is the target's moving speed or position error.

[0167] When the target state changes to a greater extent, the difference ratio r m If the difference ratio is large, a longer perception duration needs to be configured, that is, a longer perception duration needs to be configured to continuously detect perception parameters within the perception duration to prevent target loss or large parameter estimation errors from affecting perception performance. For example, when the difference ratio is large, the target moves faster, and it is necessary to continuously perceive the target's movement speed.

[0168] When the target state changes to a small extent, the difference ratio r m If the difference ratio is small, a smaller perception duration can be configured, that is, a shorter perception duration can be configured to avoid wasting resources. For example, when the difference ratio is small, the error of the target position estimation is small, and there is no need to perceive the target position change for too long.

[0169] Therefore, the required level of perception time can be determined based on the difference ratio. The perception time and perception interval can then be configured based on the difference ratio. Specifically, the perception time rule adjusts the perception time and perception interval based on the degree of target state change between two consecutive perception tasks. The perception interval refers to the time interval between two consecutive perception tasks performed by the drone. The size of the perception interval directly affects the total duration of perception tasks actually performed within a given cycle: a larger perception interval results in fewer perception tasks within the same cycle and a shorter total perception time; a smaller perception interval results in more perception tasks and a longer total perception time. Dynamically adjusting the perception interval ensures optimal resource utilization and avoids unnecessary energy consumption while ensuring perception performance. A smaller difference ratio shortens the required perception time and increases the perception interval; a larger difference ratio increases the required perception time and increases the perception interval. For a given period T, a larger perception interval reduces the total perception time. When the difference ratio is less than a preset state change threshold, the perception interval can be increased; when the difference ratio is greater than the state change threshold, the perception interval can be decreased. For example, the perception interval can be increased or decreased exponentially. By sensing the degree of change in the target's state, the perception interval and duration can be dynamically adjusted to improve perception performance and make rational use of resources.

[0170] In some implementations, the sensing duration and sensing interval are adjusted in time slots, by setting the sensing indicator ψ nThe perception duration and interval are adjusted based on the difference ratio. For example, setting multiple consecutive perception indicator values to 0 and fewer perception indicator values to 1 can increase the perception interval and reduce the perception time. Thus, the perception indicator values can be adjusted based on the difference ratio to achieve the purpose of adjusting the perception duration and interval.

[0171] In some embodiments, considering that the continuous increase or decrease of the perception interval may cause the tracking target to be lost or the new target to be not detected, a maximum threshold Δmax and a minimum threshold Δmin of the perception interval are set to ensure that the perception interval can be adjusted within a reasonable range.

[0172] like Figure 4 As shown, in some embodiments, the training process of the perception strategy configuration model includes: randomly initializing the parameters θ of the main network (i.e., the Q network) and the parameters θ' of the target network. According to the defined perception duration rule, a perception strategy sample is generated (including that when the target state changes greatly, the perception duration is longer, and when the target state changes slightly, the perception duration is shorter), and the perception strategy sample is used as the initial strategy sample of the experience pool. Various state variables such as wind speed, humidity, transmission line vibration frequency, and drone energy consumption, as well as characteristics such as the difficulty, priority, and data collection requirements of the perception task are obtained from the historical detection data of the transmission line, and training samples are generated based on the obtained data.

[0173] Execute an exploration and exploitation strategy, randomly exploring the environment and balancing exploration and exploitation with an ∈-greedy strategy. Initially, prioritize actions that conform to the perception duration rule and increase rewards for rule consistency. This reduces the instability associated with random exploration. Each executed state-action-reward-next-state sample (S, A, R, S′) is stored in the experience pool.

[0174] Randomly sample state-action pairs from the experience pool and calculate the priority of each sample through the temporal difference (TD) error. The calculation method is:

[0175]

[0176] Among them, R is the immediate reward obtained after taking action A in the current state, that is, the reward value fed back to the agent by the environment, γ is the discount factor, and A′ is the action that may be taken in the next state S′.

[0177] According to the priority of each sample, high-priority samples with a priority higher than the preset priority threshold are determined, and the high-priority samples are used to update the network parameters to improve training efficiency.

[0178] The parameters of the main network are updated using the following loss function:

[0179]

[0180] Regularly synchronize the parameters θ of the main network to the parameters θ′ of the target network to ensure the stability of the training process. As the training progresses, gradually reduce the weight C of the rule in the reward function. 规则 , making the model rely more on its own learning ability, and gradually transitioning from rule inspiration to complete intelligent optimization.

[0181] After training, the trained Q network is deployed on the UAV as a perception strategy configuration model. The UAV obtains the current state based on the real-time perceived environmental parameters and line parameters combined with the UAV energy consumption parameters and system parameters. The current state is input into the perception strategy configuration model, and the model outputs the action, that is, the optimal perception strategy suitable for the current state. The UAV detects the transmission line based on the perception strategy, which can rationally utilize resources, ensure the system performance of the UAV in different environments, and improve the accuracy and adaptability of transmission line detection.

[0182] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied in a distributed scenario and performed by multiple devices working together. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the method.

[0183] It should be noted that the foregoing description of this specification is based on specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0184] like Figure 5 As shown, the embodiment of the present application also provides an adaptive synaesthesia integrated transmission line monitoring device based on a drone, comprising:

[0185] An acquisition module is used to obtain environmental parameters and line parameters perceived by the drone's sensors based on the constructed drone communication perception system model;

[0186] The perception strategy configuration module is used to take environmental parameters, line parameters, drone energy consumption parameters, and system parameters of the communication perception system as the current state, input the current state into a pre-built perception strategy configuration model, and the perception strategy configuration model outputs the perception strategy for drone power transmission line detection.

[0187] In some embodiments, the perception strategy includes the perception duration, perception accuracy, sampling frequency, and sampling power of the drone; the perception strategy configuration model is implemented based on a deep Q network, and the reward function of the perception strategy configuration model is constructed according to preset perception duration, perception accuracy, drone energy consumption, and drone communication load reward rules.

[0188] In some embodiments, the reward function is:

[0189] R(S,A)=R 基础 (S,A)+R 规则 (S,A) (23)

[0190] R 基础 (S, A) = α·P accuracy -β·P energy -γ·P communication -δ·P penalty (twenty four)

[0191] Among them, R 基础 (S, A) is the multi-target reward, P accuracy is the perception accuracy, P energy is the energy consumption of the UAV, P communication is the communication load of the UAV, P penalty is a penalty term. When one or more of the perception accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the penalty term takes the corresponding penalty value. α, β, γ, and δ are weight coefficients. 规则 (S, A) is the rule-based reward value. When the executed action is consistent with the preset rule, a positive reward value is obtained. When the executed action is inconsistent with the preset rule, a negative reward value is obtained.

[0192] In some embodiments, the perception strategy configuration module is used to determine when the perception accuracy is lower than a preset accuracy threshold θ accuracy When , the penalty value corresponding to the perception accuracy is:

[0193] P penalty_accuracy =λ accuracy max(0,θ accuracy -P accuracy ) (26)

[0194] When the energy consumption of the drone exceeds the preset energy consumption threshold θ energy When , the penalty value corresponding to the drone energy consumption is:

[0195] P penalty_energy =λ energy max(0,P energy -θ energy) (28)

[0196] When the communication load exceeds the preset load threshold θ communication When , the penalty value corresponding to the communication load is:

[0197] P penalty_communication =λ communication max(0,P communication -θ communication ) (30)

[0198] Among them, λ accuracy is the penalty factor of perceptual accuracy, λ energy is the penalty factor for the UAV’s energy consumption, λ communication is the penalty factor for communication load.

[0199] In some embodiments, the preset rules include a perception duration rule, and the perception duration rule includes adjusting the perception duration according to a degree of change in the target state between two adjacent perception tasks.

[0200] In some embodiments, the perception strategy configuration module is used to adjust the perception duration by setting the value of the perception indicator; wherein, when the value of the perception indicator is a first value, the drone provides communication and perception services in the downlink phase, and when the value of the perception indicator is a second value, the drone only provides communication services.

[0201] For the convenience of description, the above devices are described as being functionally divided into various modules. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0202] The apparatus of the above embodiment is used to implement the corresponding method in the above embodiment and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0203] Figure 6 10 is a schematic diagram showing a more specific hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other within the device via the bus 1050.

[0204] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0205] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0206] The input / output interface 1030 is used to connect input / output modules to implement information input and output. The input / output modules can be configured as components within the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0207] The communication interface 1040 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WiFi, Bluetooth, etc.).

[0208] The bus 1050 comprises a path for transmitting information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0209] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0210] The electronic devices of the above embodiments are used to implement the corresponding methods in the above embodiments and have the beneficial effects of the corresponding method embodiments, which will not be described in detail here.

[0211] The computer-readable media of this embodiment include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0212] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples. Within the scope of the present disclosure, the above embodiments or technical features in different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0213] In addition, to simplify the description and discussion, and in order not to make the embodiment of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the accompanying drawings provided. In addition, the device can be shown in the form of a block diagram to avoid making the embodiment of the present application difficult to understand, and this also takes into account the following fact, that is, the details of the implementation method of these block diagram devices are highly dependent on the platform to be implemented in the embodiment of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). When specific details (for example, circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiment of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0214] Although the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art based on the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0215] The embodiments of the present application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of this disclosure.

Claims

1. The adaptive synaesthesia integrated transmission line monitoring method based on UAV is characterized by: include: Based on the constructed UAV communication perception system model, the environmental parameters and line parameters perceived by the UAV’s sensors are obtained; Taking the environmental parameters, the line parameters, the UAV energy consumption parameters, and the system parameters of the communication perception system as the current state, the current state is input into a pre-built perception strategy configuration model, and the perception strategy configuration model outputs the perception strategy for UAV power transmission line detection.

2. The method according to claim 1, characterized in that The perception strategy includes the drone's perception duration, perception accuracy, sampling frequency, and sampling power; the perception strategy configuration model is implemented based on a deep Q network, and the reward function of the perception strategy configuration model is constructed according to preset perception duration, perception accuracy, drone energy consumption, and drone communication load reward rules.

3. The method according to claim 2, characterized in that The reward function is: R(S,A)=R 基础 (S,A)+R 规则 (S,A) (23) R 基础 (S,A)=α·P accuracy -β·P energy -γ·P communication -δ·P penalty (24) Among them, R 基础 (S, A) is the multi-target reward, P accuracy is the perception accuracy, P energy is the energy consumption of the UAV, P communication is the communication load of the UAV, P penalty is a penalty term. When one or more of the sensing accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the penalty term is set to the corresponding penalty value. α, β, γ, and δ are weight coefficients. 规则 (S, A) is the rule-based reward value. When the executed action is consistent with the preset rule, a positive reward value is obtained. When the executed action is inconsistent with the preset rule, a negative reward value is obtained.

4. The method according to claim 3, characterized in that When one or more of the sensing accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the penalty item is set to the corresponding penalty value, including: When the perception accuracy is lower than the preset accuracy threshold θ accuracy When , the penalty value corresponding to the perception accuracy is: P penalty_accuracy =λ accuracy ·max(0,θ accuracy -P accuracy ) (26) When the energy consumption of the drone exceeds the preset energy consumption threshold θ energy When , the penalty value corresponding to the drone energy consumption is: P penalty_energy =λ energy ·max(0,P energy -θ energy ) (28) When the communication load exceeds the preset load threshold θ communication When , the penalty value corresponding to the communication load is: P penalty_communication =λ communication ·max(0,P communication -θ communication ) (30) Among them, λ accuracy is the penalty factor of perceptual accuracy, λ energy is the penalty factor for the UAV’s energy consumption, λ communication is the penalty factor for communication load.

5. The method according to claim 3, characterized in that The preset rules include a perception duration rule, and the perception duration rule includes adjusting the perception duration according to a degree of change in the target state between two adjacent perception tasks.

6. The method according to claim 5, characterized in that The adjusting of the perception duration includes: The perception duration is adjusted by setting the value of the perception indicator; when the value of the perception indicator is a first value, the drone provides communication and perception services in the downlink phase, and when the value of the perception indicator is a second value, the drone only provides communication services.

7. The adaptive synaesthesia integrated transmission line monitoring device based on drone is characterized by: include: An acquisition module is used to obtain environmental parameters and line parameters perceived by the drone's sensors based on the constructed drone communication perception system model; The perception strategy configuration module is used to take the environmental parameters, the line parameters, the UAV energy consumption parameters, and the system parameters of the communication perception system as the current state, input the current state into a pre-built perception strategy configuration model, and the perception strategy configuration model outputs the perception strategy for UAV power transmission line detection.

8. The device according to claim 7, characterized in that The perception strategy includes the drone's perception duration, perception accuracy, sampling frequency, and sampling power; the perception strategy configuration model is implemented based on a deep Q network, and the reward function of the perception strategy configuration model is constructed according to preset perception duration, perception accuracy, drone energy consumption, and drone communication load reward rules.

9. The device according to claim 8, characterized in that The reward function is: R(S,A)=R 基础 (S,A)+R 规则 (S,A) (23) R 基础 (S,A)=α·P accuracy -β·P energy -γ·P communication -δ·P penalty (24) Among them, R 基础 (S, A) is the multi-target reward, P accuracy is the perception accuracy, P energy is the energy consumption of the UAV, P communication is the communication load of the UAV, P penalty is a penalty term. When one or more of the sensing accuracy, drone energy consumption, and communication load meet the corresponding penalty rules, the penalty term is set to the corresponding penalty value. α, β, γ, and δ are weight coefficients. 规则 (S, A) is the rule-based reward value. When the executed action is consistent with the preset rule, a positive reward value is obtained. When the executed action is inconsistent with the preset rule, a negative reward value is obtained.

10. The device according to claim 9, characterized in that The perception strategy configuration module is used to determine when the perception accuracy is lower than the preset accuracy threshold θ accuracy When , the penalty value corresponding to the perception accuracy is: P penalty_accuracy =λ accuracy ·max(0,θ accuracy -P accuracy ) (26) When the energy consumption of the drone exceeds the preset energy consumption threshold θ energy When , the penalty value corresponding to the drone energy consumption is: P penalty_energy =λ energy ·max(0,P energy -θ energy ) (28) When the communication load exceeds the preset load threshold θ communication When , the penalty value corresponding to the communication load is: P penalty_communication =λ communication ·max(0,P communication -θ communication ) (30) Among them, λ accuracy is the penalty factor of perceptual accuracy, λ energy is the penalty factor for the UAV’s energy consumption, λ communication is the penalty factor for communication load.

11. The device according to claim 9, characterized in that The preset rules include a perception duration rule, and the perception duration rule includes adjusting the perception duration according to a degree of change in the target state between two adjacent perception tasks.

12. The device according to claim 11, characterized in that The perception strategy configuration module is used to adjust the perception duration by setting the value of the perception indicator; wherein, when the value of the perception indicator is a first value, the drone provides communication and perception services in the downlink phase, and when the value of the perception indicator is a second value, the drone only provides communication services.

13. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 6.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

Images