Network transmission dynamic power allocation method and system for hydrogen-electric hybrid UAV

Abstract

The present invention discloses a method and system for allocating dynamic power for network transmission of a hydrogen-electric hybrid UAV, which belongs to the technical field of hydrogen-electric hybrid UAVs, and includes: collecting and preprocessing real-time data of status monitoring of a hydrogen-electric hybrid UAV; analyzing characteristic data of status monitoring of a hydrogen-electric hybrid UAV to determine a scheme for allocating dynamic power for network transmission of a hydrogen-electric hybrid UAV; and adjusting and allocating the dynamic power for network transmission of a hydrogen-electric hybrid UAV to optimize energy utilization and communication performance. The present invention solves the problem that the existing method cannot effectively allocate the dynamic power for network transmission of a hydrogen-electric hybrid UAV, resulting in low energy utilization efficiency and an inability to ensure the stability and security of data transmission. The present invention can effectively allocate the dynamic power for network transmission of a hydrogen-electric hybrid UAV, improve the energy utilization efficiency of a hydrogen-electric hybrid UAV, and ensure the stability and security of data transmission, thereby improving communication quality.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen-electric hybrid unmanned aerial vehicles (UAVs), and in particular to a method and system for allocating dynamic power for network transmission of hydrogen-electric hybrid UAVs. Background Art

[0002] Hydrogen-electric hybrid drones are an innovative type of drone that combine two clean energy sources: solar energy and hydrogen. They boast ultra-long flight endurance, are environmentally friendly, and operate in all weather conditions. These drones are primarily powered by a combination of hydrogen fuel cells and battery systems. The fuel cells react hydrogen with oxygen to generate electricity, providing the drone's primary power source. The battery system serves as a supplementary energy source, compensating for the fuel cell's shortcomings under certain conditions.

[0003] When in use, existing hydrogen-electric hybrid drones cannot effectively distribute the dynamic power of network transmission of hydrogen-electric hybrid drones, resulting in low energy utilization efficiency of hydrogen-electric hybrid drones and failure to ensure the stability and security of data transmission. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for allocating dynamic power for network transmission of hydrogen-electric hybrid drones, which can effectively allocate the dynamic power for network transmission of hydrogen-electric hybrid drones, improve the energy utilization efficiency of hydrogen-electric hybrid drones, ensure the stability and security of data transmission, improve communication quality, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for dynamic power allocation for network transmission of a hydrogen-electric hybrid UAV includes:

[0007] Collect energy status monitoring data and communication status monitoring data of hydrogen-electric hybrid UAVs, and determine real-time status monitoring data of hydrogen-electric hybrid UAVs;

[0008] Preprocess the real-time data of hydrogen-electric hybrid UAV status monitoring to determine the characteristic data of hydrogen-electric hybrid UAV status monitoring;

[0009] A dynamic power allocation model for hydrogen-electric hybrid UAV network transmission is established to analyze the characteristic data of hydrogen-electric hybrid UAV status monitoring and determine the dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission;

[0010] According to the dynamic power allocation scheme for network transmission of hydrogen-electric hybrid UAVs, the network transmission dynamic power of hydrogen-electric hybrid UAVs is adjusted and allocated to optimize energy utilization and communication performance;

[0011] Among them, when the lithium battery is low on power, the output power of the hydrogen fuel cell is increased by combining the current total load power with the power regulation coefficient.

[0012] Preferably, determining the real-time data of the hydrogen-electric hybrid UAV status monitoring includes:

[0013] Based on the sensor network, the power, output power and health status of hydrogen fuel cells and lithium batteries are monitored and collected in real time to obtain energy status monitoring data of hydrogen-electric hybrid drones;

[0014] Based on the sensor network, the signal strength, network load and transmission quality of the network transmission communication module are monitored and collected in real time to obtain the communication status monitoring data of the hydrogen-electric hybrid UAV;

[0015] According to the energy status monitoring data and communication status monitoring data of the hydrogen-electric hybrid UAV, the real-time status monitoring data of the hydrogen-electric hybrid UAV is determined.

[0016] Preferably, the real-time data of the hydrogen-electric hybrid UAV status monitoring is preprocessed, including:

[0017] Clean the real-time data of hydrogen-electric hybrid UAV status monitoring to remove the noise data that is useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission;

[0018] Check the real-time data of hydrogen-electric hybrid UAV status monitoring to determine whether there are duplicate values, missing values, and abnormal values in the real-time data that are useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission;

[0019] When there are duplicate values, missing values and outliers in the real-time data of hydrogen-electric hybrid UAV status monitoring that are useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission, the duplicate values, missing values and outliers are directly deleted.

[0020] Preferably, the real-time data of the hydrogen-electric hybrid UAV status monitoring is preprocessed, including:

[0021] Normalize the real-time data of hydrogen-electric hybrid UAV status monitoring to convert it into a unified data format, remove the dimensional differences in the real-time data of hydrogen-electric hybrid UAV status monitoring, and determine the standardized real-time data of hydrogen-electric hybrid UAV status monitoring;

[0022] Feature extraction is performed on the real-time data of hydrogen-electric hybrid UAV status monitoring, and features useful for the dynamic power distribution of hydrogen-electric hybrid UAV network transmission are extracted from the real-time data of hydrogen-electric hybrid UAV status monitoring, and the characteristic data of hydrogen-electric hybrid UAV status monitoring is determined.

[0023] Preferably, a dynamic power allocation model for hydrogen-electric hybrid UAV network transmission is established, including:

[0024] According to the network transmission dynamic power allocation requirements of hydrogen-electric hybrid drones, historical data of hydrogen-electric hybrid drones, including the historical distribution of network transmission dynamic power, is collected. The collected historical data of hydrogen-electric hybrid drones is divided to determine the training set and test set;

[0025] Based on machine learning technology, a training set is used to train the machine learning model, so that the machine learning model can autonomously learn the network transmission dynamic power allocation behavior of the hydrogen-electric hybrid UAV, and determine the network transmission dynamic power allocation model of the hydrogen-electric hybrid UAV based on machine learning;

[0026] Based on the cross-validation method, a test set was used to test the dynamic power allocation model for network transmission of hydrogen-electric hybrid UAVs based on machine learning. The model was evaluated to see whether it can effectively allocate the dynamic power of network transmission of hydrogen-electric hybrid UAVs, and the model test evaluation results were determined.

[0027] According to the model test evaluation results, the parameters of the hydrogen-electric hybrid UAV network transmission dynamic power allocation model based on machine learning are adjusted, and the machine learning-based hydrogen-electric hybrid UAV network transmission dynamic power allocation model after parameter adjustment is continuously optimized to determine the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model.

[0028] Preferably, the analysis of the hydrogen-electric hybrid UAV status monitoring characteristic data includes:

[0029] Obtain the optimal dynamic power allocation model for hydrogen-electric hybrid UAV network transmission, and deploy the optimal dynamic power allocation model in the actual hydrogen-electric hybrid UAV network transmission dynamic power allocation environment;

[0030] The state monitoring characteristic data of the hydrogen-electric hybrid UAV is input into the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model. According to the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model, the state monitoring characteristic data of the hydrogen-electric hybrid UAV is analyzed, and the network transmission dynamic power of the hydrogen-electric hybrid UAV is allocated to determine the hydrogen-electric hybrid UAV network transmission dynamic power allocation plan.

[0031] Preferably, adjusting and allocating the network transmission dynamic power of the hydrogen-electric hybrid UAV includes:

[0032] The output power of hydrogen fuel cells and lithium batteries, as well as the transmission power of network transmission and communication modules, are adjusted according to the dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission. Based on mission priority, power for critical tasks and communications is allocated first to optimize energy utilization and communication performance.

[0033] Among them, according to energy priority, when the lithium battery has sufficient power, it will be used first to supply power, reducing the load of the hydrogen fuel cell; when the lithium battery is insufficient, the output power of the hydrogen fuel cell will be increased, and the lithium battery will be charged at the same time;

[0034] Among them, according to the communication priority, when the network load is high or the signal strength is weak, the transmission power of the communication module is increased to ensure the communication quality; when the network load is low or the signal strength is strong, the transmission power of the communication module is reduced to save energy.

[0035] Preferably, when the lithium battery is low on power, increasing the output power of the hydrogen fuel cell includes:

[0036] When the lithium battery is low on power, the remaining power ratio SOC of the lithium battery corresponding to the moment when the lithium battery is low on power is retrieved, with a range of 0-1;

[0037] Retrieve the adjustment amplitude ratio of the transmission power of the network transmission communication module;

[0038] Wherein, when the adjustment amplitude ratio of the transmission power of the network transmission communication module is positive, it indicates that the transmission power of the network transmission communication module increases; when the adjustment amplitude ratio of the transmission power of the network transmission communication module is negative, it indicates that the transmission power of the network transmission communication module decreases;

[0039] Get the average value of the percentage gradient of power consumption when using lithium battery power supply;

[0040] Obtaining a power regulation coefficient using the adjustment amplitude ratio of the transmission power of the network transmission communication module and the gradient average value of the power consumption percentage;

[0041] Get the current total load power;

[0042] The output power of the hydrogen fuel cell is increased by combining the current total load power with the power regulation coefficient.

[0043] Preferably, increasing the output power of the hydrogen fuel cell by utilizing the current total load power in combination with the power regulation coefficient includes:

[0044] Retrieve the power regulation coefficient;

[0045] The power adjustment coefficient is obtained by the following formula:

[0046]

[0047] Where R represents the power regulation coefficient; P f Indicates the adjustment ratio of the transmission power of the network transmission communication module; E p Indicates the average value of the percentage gradient of power consumption when powered by lithium batteries;

[0048] Comparing the power adjustment coefficient with a preset coefficient threshold;

[0049] When the power regulation coefficient is lower than a preset coefficient threshold, the output power of the hydrogen fuel cell is increased in proportion to (1-SOC)*α; wherein SOC represents the remaining power ratio of the lithium battery; α represents the power regulation coefficient;

[0050] When the power adjustment coefficient is not lower than a preset coefficient threshold, a preset nonlinear corresponding coefficient is retrieved from a database;

[0051] The nonlinear response coefficient is used to adjust the sensitivity of the output power to insufficient power, and the value range of the nonlinear response coefficient is 1.13-1.25;

[0052] The power adjustment coefficient and the current total load power are combined with a nonlinear corresponding coefficient to set the increase ratio of the output power of the hydrogen fuel cell.

[0053] The increase ratio of the output power of the hydrogen fuel cell is obtained by the following formula:

[0054]

[0055] Wherein, B represents the increase ratio of the output power of the hydrogen fuel cell; P c Indicates the output power of the hydrogen fuel cell in the current non-increased state; P z Indicates the current total load power; R indicates the power regulation coefficient; SOC indicates the remaining power ratio of the lithium battery; v indicates the nonlinear response coefficient.

[0056] According to another aspect of the present invention, a network transmission dynamic power allocation system for a hydrogen-electric hybrid UAV is provided, which is used to implement the network transmission dynamic power allocation method for the hydrogen-electric hybrid UAV as described above, comprising:

[0057] A data acquisition module is configured to collect status data of the energy system and the communication module in real time based on a sensor network, and obtain real-time data for status monitoring of the hydrogen-electric hybrid UAV;

[0058] A data processing module is configured to pre-process the collected real-time data of the hydrogen-electric hybrid UAV status monitoring and determine characteristic data of the hydrogen-electric hybrid UAV status monitoring;

[0059] a power allocation module configured to analyze characteristic data of the hydrogen-electric hybrid UAV status monitoring and determine a dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission;

[0060] The adjustment and optimization module is configured to adjust the output power of the hydrogen fuel cell and the lithium battery and the transmission power of the network transmission communication module, prioritize the power allocation of key tasks and communications, and optimize energy utilization and communication performance.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] The present invention collects energy status monitoring data and communication status monitoring data of the hydrogen-electric hybrid UAV to determine the real-time status monitoring data of the hydrogen-electric hybrid UAV. By preprocessing the real-time status monitoring data of the hydrogen-electric hybrid UAV, the state monitoring characteristic data of the hydrogen-electric hybrid UAV is determined. A hydrogen-electric hybrid UAV network transmission dynamic power allocation model is established to analyze the hydrogen-electric hybrid UAV state monitoring characteristic data, determine the hydrogen-electric hybrid UAV network transmission dynamic power allocation scheme, and adjust and allocate the network transmission dynamic power of the hydrogen-electric hybrid UAV to optimize energy utilization and communication performance. The network transmission dynamic power of the hydrogen-electric hybrid UAV can be effectively allocated, the energy utilization efficiency of the hydrogen-electric hybrid UAV can be improved, and the stability and security of data transmission can be ensured, thereby improving the communication quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a module diagram of the network transmission dynamic power distribution system of the hydrogen-electric hybrid UAV of the present invention;

[0064] Figure 2 This is a flow chart of the network transmission dynamic power allocation method of the hydrogen-electric hybrid UAV of the present invention. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0066] To address the problem that existing technologies cannot effectively allocate the dynamic power of network transmission for hydrogen-electric hybrid drones, resulting in low energy efficiency for hydrogen-electric hybrid drones and failure to ensure the stability and security of data transmission, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0067] The network transmission dynamic power distribution system of the hydrogen-electric hybrid UAV includes: a data acquisition module, a data processing module, a power distribution module and an adjustment optimization module.

[0068] Among them, the data acquisition module is used to collect the status data of the energy system and communication module in real time based on the sensor network, and obtain the real-time data of the status monitoring of the hydrogen-electric hybrid UAV; the data processing module is used to pre-process the collected real-time data of the status monitoring of the hydrogen-electric hybrid UAV, and determine the characteristic data of the status monitoring of the hydrogen-electric hybrid UAV; the power allocation module is used to analyze the characteristic data of the status monitoring of the hydrogen-electric hybrid UAV, and determine the dynamic power allocation scheme of the network transmission of the hydrogen-electric hybrid UAV; the adjustment and optimization module is used to adjust the output power of the hydrogen fuel cell and lithium battery and the transmission power of the network transmission communication module, give priority to the allocation of power for key tasks and communications, and optimize energy utilization and communication performance.

[0069] Specifically, through the interaction between the data acquisition module, data processing module, power allocation module and adjustment optimization module, the network transmission dynamic power of the hydrogen-electric hybrid drone can be effectively allocated, thereby improving the energy utilization efficiency of the hydrogen-electric hybrid drone, ensuring the stability and security of data transmission, and improving communication quality.

[0070] To better illustrate the dynamic power allocation process for network transmission of a hydrogen-electric hybrid UAV, this embodiment provides a method for dynamic power allocation for network transmission of a hydrogen-electric hybrid UAV. The method is based on the dynamic power allocation system for network transmission of a hydrogen-electric hybrid UAV, and includes:

[0071] Collect energy status monitoring data and communication status monitoring data of hydrogen-electric hybrid UAVs, and determine real-time status monitoring data of hydrogen-electric hybrid UAVs;

[0072] In this embodiment, determining the real-time data of the hydrogen-electric hybrid drone status monitoring includes:

[0073] Based on the sensor network, the power, output power and health status of hydrogen fuel cells and lithium batteries are monitored and collected in real time to obtain energy status monitoring data of hydrogen-electric hybrid drones;

[0074] Specifically, the power level refers to the remaining power of the current hydrogen fuel cell and lithium battery; the output power refers to the power output of the current hydrogen fuel cell and lithium battery; and the health status refers to the temperature, efficiency, life and other parameters of the current hydrogen fuel cell and lithium battery.

[0075] Based on the sensor network, the signal strength, network load and transmission quality of the network transmission communication module are monitored and collected in real time to obtain the communication status monitoring data of the hydrogen-electric hybrid UAV;

[0076] Specifically, signal strength refers to the signal strength of the current communication link; network load refers to data transmission rate, bandwidth utilization, packet loss rate, etc.; transmission quality refers to parameters such as delay, jitter, and bit error rate.

[0077] According to the energy status monitoring data and communication status monitoring data of the hydrogen-electric hybrid UAV, the real-time status monitoring data of the hydrogen-electric hybrid UAV is determined.

[0078] Specifically, hydrogen fuel cells provide continuous and stable power output, suitable for long-term flight; lithium batteries provide instantaneous high-power output to cope with sudden high-load demands; distributing the output power of hydrogen fuel cells and lithium batteries can ensure the stable operation of hydrogen-electric hybrid drones.

[0079] Specifically, the network transmission communication module supports multiple communication protocols, such as 4G / 5G, Wi-Fi, satellite communication, etc., adapts to different network environments, dynamically adjusts the power output of the communication module according to the communication status, and optimizes the communication quality.

[0080] Preprocess the real-time data of hydrogen-electric hybrid UAV status monitoring to determine the characteristic data of hydrogen-electric hybrid UAV status monitoring;

[0081] In this embodiment, the real-time data of the hydrogen-electric hybrid UAV status monitoring is preprocessed, including:

[0082] Clean the real-time data of hydrogen-electric hybrid UAV status monitoring to remove the noise data that is useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission;

[0083] Check the real-time data of hydrogen-electric hybrid UAV status monitoring to determine whether there are duplicate values, missing values, and abnormal values in the real-time data that are useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission;

[0084] When there are duplicate values, missing values and outliers in the real-time data of hydrogen-electric hybrid UAV status monitoring that are useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission, the duplicate values, missing values and outliers are directly deleted.

[0085] In this embodiment, the real-time data of the hydrogen-electric hybrid UAV status monitoring is preprocessed, including:

[0086] Normalize the real-time data of hydrogen-electric hybrid UAV status monitoring to convert it into a unified data format, remove the dimensional differences in the real-time data of hydrogen-electric hybrid UAV status monitoring, and determine the standardized real-time data of hydrogen-electric hybrid UAV status monitoring;

[0087] Feature extraction is performed on the real-time data of hydrogen-electric hybrid UAV status monitoring, and features useful for the dynamic power distribution of hydrogen-electric hybrid UAV network transmission are extracted from the real-time data of hydrogen-electric hybrid UAV status monitoring, and the characteristic data of hydrogen-electric hybrid UAV status monitoring is determined.

[0088] A dynamic power allocation model for hydrogen-electric hybrid UAV network transmission is established to analyze the characteristic data of hydrogen-electric hybrid UAV status monitoring and determine the dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission;

[0089] In this embodiment, a dynamic power allocation model for hydrogen-electric hybrid UAV network transmission is established, including:

[0090] According to the network transmission dynamic power allocation requirements of hydrogen-electric hybrid drones, historical data of hydrogen-electric hybrid drones, including the historical distribution of network transmission dynamic power, is collected. The collected historical data of hydrogen-electric hybrid drones is divided to determine the training set and test set;

[0091] Based on machine learning technology, a training set is used to train the machine learning model, so that the machine learning model can autonomously learn the network transmission dynamic power allocation behavior of the hydrogen-electric hybrid UAV, and determine the network transmission dynamic power allocation model of the hydrogen-electric hybrid UAV based on machine learning;

[0092] Based on the cross-validation method, a test set was used to test the dynamic power allocation model for network transmission of hydrogen-electric hybrid UAVs based on machine learning. The model was evaluated to see whether it can effectively allocate the dynamic power of network transmission of hydrogen-electric hybrid UAVs, and the model test evaluation results were determined.

[0093] According to the model test evaluation results, the parameters of the hydrogen-electric hybrid UAV network transmission dynamic power allocation model based on machine learning are adjusted, and the machine learning-based hydrogen-electric hybrid UAV network transmission dynamic power allocation model after parameter adjustment is continuously optimized to determine the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model.

[0094] In this embodiment, the analysis of the hydrogen-electric hybrid drone status monitoring characteristic data includes:

[0095] Obtain the optimal dynamic power allocation model for hydrogen-electric hybrid UAV network transmission, and deploy the optimal dynamic power allocation model in the actual hydrogen-electric hybrid UAV network transmission dynamic power allocation environment;

[0096] The state monitoring characteristic data of the hydrogen-electric hybrid UAV is input into the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model. According to the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model, the state monitoring characteristic data of the hydrogen-electric hybrid UAV is analyzed, and the network transmission dynamic power of the hydrogen-electric hybrid UAV is allocated to determine the hydrogen-electric hybrid UAV network transmission dynamic power allocation plan.

[0097] According to the dynamic power allocation scheme for network transmission of hydrogen-electric hybrid UAVs, the network transmission dynamic power of hydrogen-electric hybrid UAVs is adjusted and allocated to optimize energy utilization and communication performance.

[0098] In this embodiment, the network transmission dynamic power of the hydrogen-electric hybrid UAV is adjusted and allocated, including:

[0099] The output power of hydrogen fuel cells and lithium batteries, as well as the transmission power of network transmission and communication modules, are adjusted according to the dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission. Based on mission priority, power for critical tasks and communications is allocated first to optimize energy utilization and communication performance.

[0100] Among them, according to energy priority, when the lithium battery has sufficient power, it will be used first to supply power, reducing the load of the hydrogen fuel cell; when the lithium battery is insufficient, the output power of the hydrogen fuel cell will be increased, and the lithium battery will be charged at the same time;

[0101] Among them, according to the communication priority, when the network load is high or the signal strength is weak, the transmission power of the communication module is increased to ensure the communication quality; when the network load is low or the signal strength is strong, the transmission power of the communication module is reduced to save energy.

[0102] Specifically, by dynamically adjusting power distribution, energy utilization efficiency is maximized, the flight time of hydrogen-electric hybrid drones is extended, and the stable operation of the communication module is ensured in different network environments.

[0103] Specifically, when the lithium battery is low on power, the output power of the hydrogen fuel cell is increased, including:

[0104] When the lithium battery is low on power, the remaining power ratio SOC of the lithium battery corresponding to the moment when the lithium battery is low on power is retrieved, with a range of 0-1;

[0105] Retrieve the adjustment amplitude ratio of the transmission power of the network transmission communication module;

[0106] Wherein, when the adjustment amplitude ratio of the transmission power of the network transmission communication module is positive, it indicates that the transmission power of the network transmission communication module increases; when the adjustment amplitude ratio of the transmission power of the network transmission communication module is negative, it indicates that the transmission power of the network transmission communication module decreases;

[0107] Get the average value of the percentage gradient of power consumption when using lithium battery power supply;

[0108] Obtaining a power regulation coefficient using the adjustment amplitude ratio of the transmission power of the network transmission communication module and the gradient average value of the power consumption percentage;

[0109] Get the current total load power;

[0110] The output power of the hydrogen fuel cell is increased by combining the current total load power with the power regulation coefficient.

[0111] The technical effect of the above-mentioned technical solution is that when the lithium battery charge is low, it can dynamically adjust the output power of the hydrogen fuel cell to ensure a continuous and stable supply of system energy. This avoids system downtime or performance degradation caused by lithium battery depletion. By accessing the lithium battery's remaining charge (SOC), the solution accurately understands the current state of the lithium battery and makes appropriate adjustments accordingly. This precise control helps extend the battery life while optimizing overall energy efficiency. The above-mentioned technical solution dynamically adjusts the power of the network transmission communication module based on the transmission power adjustment amplitude ratio. This helps minimize energy consumption while meeting communication needs, especially when the lithium battery charge is low. The gradient average of the power consumption percentage when powered by the lithium battery is used as a factor in determining the power adjustment coefficient. This reflects the system's energy usage over time and helps more intelligently adjust the hydrogen fuel cell output power to suit different workloads and requirements. The above-mentioned technical solution can access the current total load power and combine it with the power adjustment coefficient to increase the hydrogen fuel cell output power. This ensures that the system can flexibly adjust energy supply based on actual load conditions, thereby maintaining optimal performance and efficiency. By comprehensively considering the lithium battery status, network transmission power requirements, power consumption percentage, and system load, this solution achieves efficient energy utilization. This helps reduce energy waste and improve overall system energy efficiency. By dynamically adjusting the hydrogen fuel cell's output power when the lithium battery is low, this solution enhances system stability and ensures normal operation under various operating conditions.

[0112] Specifically, the output power of the hydrogen fuel cell is increased by combining the current total load power with the power regulation coefficient, including:

[0113] Retrieve the power regulation coefficient;

[0114] The power adjustment coefficient is obtained by the following formula:

[0115]

[0116] Where R represents the power regulation coefficient; P fIndicates the adjustment ratio of the transmission power of the network transmission communication module; E p Indicates the average value of the percentage gradient of power consumption when powered by lithium batteries;

[0117] Comparing the power adjustment coefficient with a preset coefficient threshold;

[0118] When the power regulation coefficient is lower than a preset coefficient threshold, the output power of the hydrogen fuel cell is increased in proportion to (1-SOC)*α; wherein SOC represents the remaining power ratio of the lithium battery; α represents the power regulation coefficient;

[0119] When the power adjustment coefficient is not lower than a preset coefficient threshold, a preset nonlinear corresponding coefficient is retrieved from a database;

[0120] The nonlinear response coefficient is used to adjust the sensitivity of the output power to insufficient power, and the value range of the nonlinear response coefficient is 1.13-1.25;

[0121] The power adjustment coefficient and the current total load power are combined with a nonlinear corresponding coefficient to set the increase ratio of the output power of the hydrogen fuel cell.

[0122] The increase ratio of the output power of the hydrogen fuel cell is obtained by the following formula:

[0123]

[0124] Wherein, B represents the increase ratio of the output power of the hydrogen fuel cell; P c Indicates the output power of the hydrogen fuel cell in the current non-increased state; P z Indicates the current total load power; R indicates the power regulation coefficient; SOC indicates the remaining power ratio of the lithium battery; v indicates the nonlinear response coefficient.

[0125] The technical solution described above achieves the following: By calculating a power regulation coefficient based on factors such as the transmission power adjustment ratio of the network transmission communication module and the average gradient of the percentage of power consumption when powered by the lithium battery, the hydrogen fuel cell output power is dynamically adjusted. This system can rationally allocate power based on different system states (such as the lithium battery charge level and the power demand of the communication module), improving energy efficiency and avoiding energy waste. When the lithium battery charge is low, different strategies are used to adjust the hydrogen fuel cell output power based on the comparison between the power regulation coefficient and a preset threshold. This hierarchical control approach ensures stable system operation under different operating conditions, avoids system failures caused by sudden power changes, and improves the stability and reliability of the entire energy supply system. By using a nonlinear response coefficient to adjust the output power sensitivity to power shortages, the hydrogen fuel cell can quickly and accurately respond to changes in power demand when the lithium battery charge is low, promptly increasing output power to meet load requirements and improving system responsiveness.

[0126] At the same time, in the above technical solution The power regulation coefficient combines the transmission power adjustment ratio of the network transmission communication module and the average power consumption percentage gradient when powered by lithium batteries. The transmission power adjustment ratio of the network transmission communication module reflects changes in the power demand of the communication module. An increase in the power demand of the communication module may indicate a change in the overall system load, requiring adjustment of the hydrogen fuel cell output power. The average power consumption percentage gradient when powered by lithium batteries reflects the changing trend of power consumption when powered by lithium batteries. A large power consumption gradient indicates rapid lithium battery power depletion, requiring advance planning of hydrogen fuel cell power output. The combined calculation of these two factors is used to measure the degree to which the current system state requires hydrogen fuel cell power regulation.

[0127] This formula comprehensively considers the hydrogen fuel cell output power in its unused state, the current total load power, the power regulation coefficient, the remaining charge percentage of the lithium battery, and the nonlinear response coefficient. By combining these parameters, an appropriate increase ratio for the hydrogen fuel cell output power is calculated to meet the system power demand. When the lithium battery charge is low, the increase ratio calculated using this formula can precisely increase the hydrogen fuel cell output power based on factors such as the actual system load, the current hydrogen fuel cell power, the power regulation coefficient, and the nonlinear response coefficient to meet the load demand and avoid power under- or over-supply. Properly controlling the hydrogen fuel cell output power can reduce excessive discharge of the lithium battery when the charge is low. Excessive discharge accelerates lithium battery aging. By appropriately increasing the hydrogen fuel cell power, the depth of discharge (DOD) of the lithium battery can be reduced, extending its service life and reducing battery replacement costs. Effectively increasing the hydrogen fuel cell output power when the lithium battery charge is low ensures continuous and stable system operation, improves the overall energy system's endurance, and meets the needs of long-term equipment operation. This is particularly suitable for applications with high endurance requirements, such as mobile power banks and electric vehicles.

[0128] Furthermore, the solution dynamically adjusts the output power of the hydrogen fuel cell based on the current total load power and the power regulation coefficient. This dynamic response mechanism ensures that the system can rapidly adjust energy supply in response to varying load demands, thereby maintaining system stability and performance. By introducing the power regulation coefficient, the solution enables more precise control of the hydrogen fuel cell's output power. This precise regulation helps reduce energy waste and improve energy efficiency. Furthermore, power adjustment based on the remaining charge (SOC) of the lithium battery further ensures the rational allocation and use of energy. When the power regulation coefficient is at least a preset threshold, the solution uses a nonlinear response coefficient to adjust the sensitivity of the output power to battery power shortages. This nonlinear regulation mechanism enables more flexible adjustment of the hydrogen fuel cell's output power in response to low lithium battery power, thereby maintaining system stability and performance. Furthermore, the range of the nonlinear response coefficient (1.13-1.25) ensures appropriate and rational regulation. By using parameters such as the preset coefficient threshold and the nonlinear response coefficient, the solution achieves intelligent and automated power regulation. This intelligent regulation mechanism reduces the need for manual intervention and improves system reliability and stability. Parameters in this solution, such as the power regulation coefficient and nonlinear response coefficient, can be adjusted and optimized based on actual needs. This scalability and flexibility enable the solution to adapt to diverse application scenarios and load requirements. By comprehensively considering factors such as the current total load power, the power regulation coefficient, the remaining charge percentage of the lithium battery, and the nonlinear response coefficient, the solution optimizes the output power of the hydrogen fuel cell, thereby improving the overall performance and energy efficiency of the system.

[0129] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0130] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for dynamic power allocation for network transmission of a hydrogen-electric hybrid UAV, characterized in that: include: Collect energy status monitoring data and communication status monitoring data of hydrogen-electric hybrid UAVs, and determine real-time status monitoring data of hydrogen-electric hybrid UAVs; Preprocess the real-time data of hydrogen-electric hybrid UAV status monitoring to determine the characteristic data of hydrogen-electric hybrid UAV status monitoring; A dynamic power allocation model for hydrogen-electric hybrid UAV network transmission is established to analyze the characteristic data of hydrogen-electric hybrid UAV status monitoring and determine the dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission; According to the dynamic power allocation scheme for network transmission of hydrogen-electric hybrid UAVs, the network transmission dynamic power of hydrogen-electric hybrid UAVs is adjusted and allocated to optimize energy utilization and communication performance; Adjust and allocate the network transmission dynamic power of hydrogen-electric hybrid drones, including: The output power of hydrogen fuel cells and lithium batteries, as well as the transmission power of network transmission and communication modules, are adjusted according to the dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission. Based on mission priority, power for critical tasks and communications is allocated first to optimize energy utilization and communication performance. Among them, according to energy priority, when the lithium battery has sufficient power, it will be used first to supply power, reducing the load of the hydrogen fuel cell; when the lithium battery is insufficient, the output power of the hydrogen fuel cell will be increased, and the lithium battery will be charged at the same time; Among them, according to the communication priority, when the network load is high or the signal strength is weak, the transmission power of the communication module is increased to ensure the communication quality; when the network load is low or the signal strength is strong, the transmission power of the communication module is reduced to save energy; Among them, when the lithium battery is low on power, the output power of the hydrogen fuel cell is increased by combining the current total load power with the power regulation coefficient, including: Retrieve the power regulation coefficient; The power adjustment coefficient is obtained by the following formula: Where R represents the power regulation coefficient; P f Indicates the adjustment ratio of the transmission power of the network transmission communication module; E p Indicates the average value of the percentage gradient of power consumption when powered by lithium batteries; Comparing the power adjustment coefficient with a preset coefficient threshold; When the power regulation coefficient is lower than a preset coefficient threshold, the output power of the hydrogen fuel cell is increased in proportion to (1-SOC)*α; wherein SOC represents the remaining power ratio of the lithium battery; α represents the power regulation coefficient; When the power adjustment coefficient is not lower than a preset coefficient threshold, a preset nonlinear corresponding coefficient is retrieved from a database; The nonlinear response coefficient is used to adjust the sensitivity of the output power to insufficient power, and the value range of the nonlinear response coefficient is 1.13-1.25; The power adjustment coefficient and the current total load power are combined with a nonlinear corresponding coefficient to set the increase ratio of the output power of the hydrogen fuel cell; The increase ratio of the output power of the hydrogen fuel cell is obtained by the following formula: Wherein, B represents the increase ratio of the output power of the hydrogen fuel cell; P c Indicates the output power of the hydrogen fuel cell in the current non-increased state; P z Indicates the current total load power; R indicates the power regulation coefficient; SOC indicates the remaining power ratio of the lithium battery; v indicates the nonlinear response coefficient.

2. The method for network transmission dynamic power allocation of a hydrogen-electric hybrid UAV according to claim 1, characterized in that: Determine the real-time status monitoring data of hydrogen-electric hybrid drones, including: Based on the sensor network, the power, output power and health status of hydrogen fuel cells and lithium batteries are monitored and collected in real time to obtain energy status monitoring data of hydrogen-electric hybrid drones; Based on the sensor network, the signal strength, network load and transmission quality of the network transmission communication module are monitored and collected in real time to obtain the communication status monitoring data of the hydrogen-electric hybrid UAV; According to the energy status monitoring data and communication status monitoring data of the hydrogen-electric hybrid UAV, the real-time status monitoring data of the hydrogen-electric hybrid UAV is determined.

3. The method for network transmission dynamic power allocation of a hydrogen-electric hybrid UAV according to claim 1, characterized in that: Preprocessing of real-time data of hydrogen-electric hybrid drone status monitoring, including: Clean the real-time data of hydrogen-electric hybrid UAV status monitoring to remove the noise data that is useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission; Check the real-time data of hydrogen-electric hybrid UAV status monitoring to determine whether there are duplicate values, missing values, and abnormal values in the real-time data that are useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission; When there are duplicate values, missing values and outliers in the real-time data of hydrogen-electric hybrid UAV status monitoring that are useless for the dynamic power allocation of hydrogen-electric hybrid UAV network transmission, the duplicate values, missing values and outliers are directly deleted.

4. The method for network transmission dynamic power allocation of a hydrogen-electric hybrid UAV according to claim 3, characterized in that: Preprocessing of real-time data of hydrogen-electric hybrid drone status monitoring, including: Normalize the real-time data of hydrogen-electric hybrid UAV status monitoring to convert it into a unified data format, remove the dimensional differences in the real-time data of hydrogen-electric hybrid UAV status monitoring, and determine the standardized real-time data of hydrogen-electric hybrid UAV status monitoring; Feature extraction is performed on the real-time data of hydrogen-electric hybrid UAV status monitoring, and features useful for the dynamic power distribution of hydrogen-electric hybrid UAV network transmission are extracted from the real-time data of hydrogen-electric hybrid UAV status monitoring, and the characteristic data of hydrogen-electric hybrid UAV status monitoring is determined.

5. The method for network transmission dynamic power allocation of a hydrogen-electric hybrid UAV according to claim 1, characterized in that: Establish a dynamic power allocation model for hydrogen-electric hybrid UAV network transmission, including: According to the network transmission dynamic power allocation requirements of hydrogen-electric hybrid drones, historical data of hydrogen-electric hybrid drones, including the historical distribution of network transmission dynamic power, is collected. The collected historical data of hydrogen-electric hybrid drones is divided to determine the training set and test set; Based on machine learning technology, a training set is used to train the machine learning model, so that the machine learning model can autonomously learn the network transmission dynamic power allocation behavior of the hydrogen-electric hybrid UAV, and determine the network transmission dynamic power allocation model of the hydrogen-electric hybrid UAV based on machine learning; Based on the cross-validation method, a test set was used to test the dynamic power allocation model for network transmission of hydrogen-electric hybrid UAVs based on machine learning. The model was evaluated to see whether it can effectively allocate the dynamic power of network transmission of hydrogen-electric hybrid UAVs, and the model test evaluation results were determined. According to the model test evaluation results, the parameters of the hydrogen-electric hybrid UAV network transmission dynamic power allocation model based on machine learning are adjusted, and the machine learning-based hydrogen-electric hybrid UAV network transmission dynamic power allocation model after parameter adjustment is continuously optimized to determine the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model.

6. The method for network transmission dynamic power allocation of a hydrogen-electric hybrid UAV according to claim 5, characterized in that: Analysis of hydrogen-electric hybrid drone status monitoring characteristic data, including: Obtain the optimal dynamic power allocation model for hydrogen-electric hybrid UAV network transmission, and deploy the optimal dynamic power allocation model in the actual hydrogen-electric hybrid UAV network transmission dynamic power allocation environment; The state monitoring characteristic data of the hydrogen-electric hybrid UAV is input into the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model. According to the optimal hydrogen-electric hybrid UAV network transmission dynamic power allocation model, the state monitoring characteristic data of the hydrogen-electric hybrid UAV is analyzed, and the network transmission dynamic power of the hydrogen-electric hybrid UAV is allocated to determine the hydrogen-electric hybrid UAV network transmission dynamic power allocation plan.

7. The method for network transmission dynamic power allocation of a hydrogen-electric hybrid UAV according to claim 1, characterized in that: When the lithium battery is low on power, the output power of the hydrogen fuel cell is increased, including: When the lithium battery is low on power, the remaining power ratio SOC of the lithium battery corresponding to the moment when the lithium battery is low on power is retrieved, with a range of 0-1; Retrieve the adjustment amplitude ratio of the transmission power of the network transmission communication module; Wherein, when the adjustment amplitude ratio of the transmission power of the network transmission communication module is positive, it indicates that the transmission power of the network transmission communication module increases; when the adjustment amplitude ratio of the transmission power of the network transmission communication module is negative, it indicates that the transmission power of the network transmission communication module decreases; Get the average value of the percentage gradient of power consumption when using lithium battery power supply; Obtaining a power regulation coefficient using the adjustment amplitude ratio of the transmission power of the network transmission communication module and the gradient average value of the power consumption percentage; Get the current total load power; The output power of the hydrogen fuel cell is increased by combining the current total load power with the power regulation coefficient.

8. A network transmission dynamic power allocation system for a hydrogen-electric hybrid UAV, used to implement the network transmission dynamic power allocation method for a hydrogen-electric hybrid UAV as claimed in claim 1, characterized in that: include: A data acquisition module is configured to collect status data of the energy system and the communication module in real time based on a sensor network, and obtain real-time data for status monitoring of the hydrogen-electric hybrid UAV; A data processing module is configured to pre-process the collected real-time data of the hydrogen-electric hybrid UAV status monitoring and determine characteristic data of the hydrogen-electric hybrid UAV status monitoring; a power allocation module configured to analyze characteristic data of the hydrogen-electric hybrid UAV status monitoring and determine a dynamic power allocation scheme for hydrogen-electric hybrid UAV network transmission; The adjustment and optimization module is configured to adjust the output power of the hydrogen fuel cell and the lithium battery and the transmission power of the network transmission communication module, prioritize the power allocation of key tasks and communications, and optimize energy utilization and communication performance.

Images