Unmanned aerial vehicle assisted emergency communication network system and performance optimization method

Abstract

The invention discloses an unmanned aerial vehicle assisted emergency communication network performance optimization method and system. The method covers communication link optimization based on environment perception, information is collected through multiple sensors, an environment model is established by applying a machine learning algorithm, and the flight attitude and the communication frequency are dynamically adjusted according to the environment model. The distributed resource allocation utilizes a distributed algorithm and a game theory, takes a utility function Ui = w1Qi + w2Ri-w3Ei as a decision basis, and reaches Nash equilibrium through an iterative game; efficient energy management improves endurance by means of devices such as a solar panel and a wind energy collector in combination with an intelligent algorithm and an energy sharing mechanism. The system comprises a plurality of unmanned aerial vehicles equipped with various modules and corresponding control modules. The stability, the resource utilization rate and the cruising ability of the emergency communication network are effectively improved, and powerful communication guarantee is provided for emergency rescue.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an unmanned aerial vehicle-assisted emergency communication network system and a performance optimization method. Background Art

[0002] When natural disasters such as earthquakes, floods, and mudslides, as well as emergencies such as terrorist attacks and major traffic accidents occur, ground communication infrastructure often suffers serious damage. According to relevant statistics, in the 2019 typhoon disaster in Japan, more than 70% of base stations could not work normally due to strong winds, heavy rains and floods; during the California wildfires in the United States in 2020, about 80% of communication lines in the affected areas were interrupted due to fires and infrastructure damage. This communication interruption greatly hinders the development of emergency rescue work. Rescuers are unable to obtain on-site information and coordinate rescue operations in a timely manner, which seriously affects the rescue efficiency and the safety of life and property of the affected people.

[0003] As an emerging emergency communication means, drone communication emergency self-organizing network technology builds a communication network through a group of drones, and communicates with each other in a collaborative manner, becoming a powerful solution to make up for the shortcomings of ground communication equipment in special environments. However, the technology has exposed many performance problems in practical applications. In complex urban environments, buildings are dense and irregularly laid out, and the communication signals between drone nodes are easily affected by the obstruction, reflection and scattering of buildings. For example, in areas with high-rise buildings in cities, the signal attenuation can reach more than 30dB, resulting in unstable communication links, a significant increase in packet loss rate, and a serious decline in communication quality. In severe weather conditions, such as heavy rain, dust, and dense fog, communication signals will also be severely interfered with. Taking heavy rain weather as an example, the attenuation of millimeter-wave communication signals by raindrops can reach more than 10dB per kilometer, seriously affecting the reliability of communication.

[0004] When drones need to be deployed on a large scale to cover a large emergency area, how to efficiently manage and dispatch numerous drone nodes and achieve reasonable allocation of network resources becomes a key problem. The traditional centralized resource allocation method, due to the need for a large amount of information interaction and complex calculations, will cause serious communication delays and computing burdens in large-scale networks, and cannot meet the real-time requirements of emergency communications. In addition, drones themselves have limited energy, and their endurance faces severe challenges in complex environments. Emergency rescue scenes often last for a long time, while drones usually have a short battery life on a single charge. Generally, consumer-grade drones only have a battery life of 20-30 minutes, and even professional-grade drones mostly do not exceed 2 hours. How to ensure the energy supply of drones during long-term emergency missions and extend their battery life is an important issue that needs to be solved to improve the performance of emergency communication networks. Summary of the invention

[0005] The object of the present invention is to provide an unmanned aerial vehicle (UAV)-assisted emergency communication network system and a performance optimization method, which can comprehensively improve communication stability, resource allocation efficiency and UAV endurance through innovative technical means, ensure that the emergency communication network can operate efficiently and reliably in complex and extreme emergency environments, and provide a solid communication guarantee for rescue operations, so as to solve the problems of poor communication stability, unreasonable resource allocation and insufficient endurance existing in the UAV-assisted emergency communication network in the prior art.

[0006] To achieve the above object, the present invention is implemented by the following technical solutions: A method for optimizing the performance of a UAV-assisted emergency communication network, comprising the following steps:

[0007] Step S1, a communication link optimization step based on environmental perception:

[0008] Each UAV is equipped with a radar sensor, a vision sensor and an environmental monitoring sensor;

[0009] Using machine learning algorithms, an environmental model is established based on the position and distance data of surrounding obstacles detected by the radar sensor, the building and terrain feature data identified by the vision sensor, and the meteorological parameter data detected by the environmental monitoring sensor. Among them, a deep neural network is used to process visual image data to identify obstacles and terrain, and a regression model is used to analyze the relationship between meteorological parameters and signal attenuation;

[0010] According to the environmental model, the flight attitude and communication frequency of the UAV are dynamically adjusted. When blocked by buildings, the flight height or angle is adjusted, and the communication frequency is selected according to the influence of the environment on signal attenuation;

[0011] Step S2, a distributed resource allocation step:

[0012] A distributed algorithm is used to achieve resource allocation among UAV nodes, and each node makes an independent decision based on its own and surrounding node resource information;

[0013] Introducing the idea of game theory, the resource allocation problem is modeled as a non-cooperative game, and the node maximizes the utility function U i = w1Q i + w2R i - w3E i , where U i is the utility of the i-th UAV node, Q i is the communication quality index, R i is the data transmission rate, E i is the energy consumption, and w1, w2, and w3 are weight coefficients adjusted according to actual needs to make resource allocation decisions;

[0014] Through multiple iterative games, the UAV nodes reach a Nash equilibrium state to achieve reasonable resource allocation;

[0015] Step S3, Energy-efficient management step:

[0016] Configure energy collection devices such as solar panels and wind energy collectors for the drone;

[0017] Adopt an intelligent energy management algorithm. According to the battery power of the drone, task requirements, and environmental energy collection situation, adjust the flight strategy and communication mode of the drone. When the battery power is low and the energy collection is sufficient, reduce the flight speed, increase the energy collection efficiency, and reduce the communication power; when the battery power is sufficient and the task is urgent, increase the flight speed and communication power;

[0018] Build an energy sharing mechanism between drones. The drone with more power transmits energy to the drone with less power through wireless energy transmission technology.

[0019] Further as an improvement of the technical solution of the present invention, in the communication link optimization step based on environmental perception, the radar sensor is a high-precision lidar sensor with a resolution of centimeter level.

[0020] Further as an improvement of the technical solution of the present invention, in the communication link optimization step based on environmental perception, the vision sensor processes visual image data using deep learning algorithms.

[0021] Further as an improvement of the technical solution of the present invention, in the distributed resource allocation step, each drone node records and shares its own resource information through blockchain technology.

[0022] Further as an improvement of the technical solution of the present invention, in the energy-efficient management step, the solar panel uses high-efficiency single-crystalline silicon material and has an adaptive angle adjustment function.

[0023] Further as an improvement of the technical solution of the present invention, in the energy-efficient management step, the wireless energy transmission technology is magnetic resonance wireless energy transmission technology.

[0024] Further as an improvement of the technical solution of the present invention, a drone-assisted emergency communication network system includes:

[0025] Multiple drones, each drone is equipped with a radar sensor, a vision sensor, an environmental monitoring sensor, an energy collection device, and a wireless energy transmission module;

[0026] A calculation unit that establishes an environmental model based on the environmental information obtained by the sensor and generates a flight attitude adjustment instruction and a communication frequency adjustment instruction;

[0027] A flight control module connected to the calculation unit;

[0028] A communication module connected to the calculation unit to achieve communication between drone nodes;

[0029] The energy management module controls the flight strategy, communication mode, and energy sharing operation of the drone according to the battery power, task requirements, and environmental energy harvesting situation.

[0030] As a further improvement of the technical solution of the present invention, the computing unit adopts edge computing technology.

[0031] As a further improvement of the technical solution of the present invention, the energy harvesting device includes a solar panel installed on the top of the drone and a wind energy collector installed at a suitable position on the drone's wing or fuselage.

[0032] As a further improvement of the technical solution of the present invention, the system adopts a distributed algorithm to achieve resource allocation among drone nodes, and constructs a non-cooperative game model for resource allocation based on the idea of game theory.

[0033] The present invention has the following beneficial effects:

[0034] The intelligent dynamic environment adaptation communication link technology can perceive complex environment changes in real time and accurately. By synergistically optimizing the flight attitude and communication frequency, it can effectively reduce the signal interruption probability by more than 80%, greatly improve the stability and reliability of the communication link, and ensure unobstructed emergency communication.

[0035] The distributed resource collaborative allocation mechanism based on blockchain and game theory, with the help of the trusted resource sharing of blockchain and the accurate resource allocation of multi-dimensional utility game, can achieve a more than 30% improvement in network resource utilization rate, significantly optimize the overall network performance, and meet the communication requirements of diverse and high-priority services in emergency communication.

[0036] The energy guarantee system with multi-energy complementation and intelligent scheduling can extend the endurance time of the drone by more than 50% through composite energy harvesting, dynamic energy management, and energy sharing among drones, greatly enhancing the continuous operation ability of the emergency communication network and enabling it to work stably in long-term and high-intensity emergency rescue tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, purposes, and advantages of the present invention will become more obvious:

[0038] Figure 1 It is a flowchart of a method for optimizing the performance of an emergency communication network assisted by a drone according to the present invention;

[0039] Figure 2 It is a schematic diagram of the architecture of an emergency communication network system assisted by a drone according to the present invention;

[0040] Figure 3Schematic diagram of the emergency self-organizing network application of an emergency communication network system assisted by an unmanned aerial vehicle according to the present invention. Specific implementation manners

[0041] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. Here, the schematic embodiments and descriptions of the present invention are used to explain the present invention, but do not limit the present invention.

[0042] It should be noted that all directional indications (such as up, down, left, right, front, back, upper end, lower end, top, bottom...) in the embodiments of the present invention are only used to explain the relative position relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0043] In the present invention, unless otherwise clearly defined and limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meaning of the above terms in the present invention can be understood according to specific circumstances.

[0044] In addition, in the present invention, descriptions such as "first" and "second" are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0045] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0046] Refer to Figure 1 , a method for optimizing the performance of an emergency communication network assisted by an unmanned aerial vehicle, including the following steps:

[0047] Step S1, a communication link optimization step based on environmental perception:

[0048] Each unmanned aerial vehicle is equipped with a radar sensor, a vision sensor, and an environmental monitoring sensor;

[0049] Using machine learning algorithms, an environmental model is established based on the position and distance data of surrounding obstacles detected by radar sensors, the building and terrain feature data recognized by vision sensors, and the meteorological parameter data detected by environmental monitoring sensors. Among them, a deep neural network is used to process visual image data to identify obstacles and terrain, and a regression model is used to analyze the relationship between meteorological parameters and signal attenuation;

[0050] According to the environmental model, the flight attitude and communication frequency of the UAV are dynamically adjusted. When blocked by buildings, the flight height or angle is adjusted, and the communication frequency is selected according to the impact of the environment on signal attenuation;

[0051] Step S2, Distributed resource allocation step:

[0052] A distributed algorithm is used to realize resource allocation among UAV nodes, and each node makes independent decisions based on its own and surrounding node resource information;

[0053] Introduce the idea of game theory, model the resource allocation problem as a non - cooperative game, and the node maximizes the utility function U i =w1Q i +w2R i -w3E i , where U i is the utility of the i - th UAV node, Q i is the communication quality index, R i is the data transmission rate, E i is the energy consumption, and w1, w2, w3 are weight coefficients adjusted according to actual needs to make resource allocation decisions;

[0054] Through multiple iterative games, a Nash equilibrium state is achieved among UAV nodes to realize reasonable resource allocation;

[0055] Step S3, Energy - efficient management step:

[0056] Configure energy - harvesting devices such as solar panels and wind energy collectors for the UAV;

[0057] Adopt an intelligent energy management algorithm. According to the battery power of the UAV, task requirements, and environmental energy - harvesting situation, adjust the flight strategy and communication mode of the UAV. When the battery power is low and the energy - harvesting is sufficient, reduce the flight speed, increase the energy - harvesting efficiency, and reduce the communication power; when the battery power is sufficient and the task is urgent, increase the flight speed and communication power;

[0058] Construct an energy - sharing mechanism among UAVs. The UAV with more power transmits energy to the UAV with less power through wireless energy transfer technology.

[0059] It should be noted that in the solution of this embodiment:

[0060] Intelligent dynamic environment - adapted communication link technology

[0061] Multi-source heterogeneous sensor fusion perception: Each UAV is equipped with multi-source heterogeneous sensors, including high-resolution lidar sensors, high-definition cameras with deep learning vision recognition capabilities, and high-precision meteorological environment monitoring sensors. With its high resolution and real-time detection capabilities, the lidar sensor can accurately obtain the three-dimensional position information of surrounding obstacles, with a resolution of up to centimeter level. The vision sensor uses advanced deep learning algorithms to quickly identify complex building structures, terrain features, and moving obstacles, with an identification accuracy rate exceeding 95%. The meteorological sensor can real-time monitor environmental parameters such as wind speed, wind direction, humidity, rainfall intensity, and dust concentration, providing comprehensive and accurate data support for subsequent environmental modeling.

[0062] Real-time adaptive environmental modeling: Based on the massive data collected by sensors, edge computing technology is used to build a real-time environmental model locally on the UAV. The spatio-temporal graph convolutional neural network (ST-GCN) is used to jointly process lidar and visual image data, which can dynamically and accurately depict the topological structure and obstacle distribution of the surrounding environment. At the same time, a method combining multiple linear regression and time series analysis is used to deeply explore the complex relationship between meteorological parameters and communication signal attenuation, and a precise signal attenuation prediction model is established.

[0063] Dual-drive collaborative communication link optimization: In terms of flight attitude adjustment, when the environmental model identifies a communication occlusion risk ahead, the UAV flight control module, based on the model prediction results, calculates the optimal flight adjustment plan within milliseconds through an intelligent path planning algorithm, and quickly adjusts the flight height, angle, and route to avoid the occlusion area and ensure the physical smoothness of the communication link. In terms of communication frequency switching, the communication module, based on the signal attenuation prediction model, combines the interference situation of the current communication frequency band, and uses intelligent spectrum sensing and switching technology to complete the dynamic switching of the communication frequency within a few microseconds, selects the optimal communication frequency band, effectively reduces signal interference, improves communication quality, and ensures that the communication rate is stable at a high level.

[0064] Distributed resource collaborative allocation mechanism based on blockchain and game theory

[0065] Blockchain-enabled trustworthy resource sharing: Build a UAV resource information sharing platform based on the consortium blockchain, and each UAV is used as a node in the blockchain network. The UAV encrypts its real-time resource status, including information such as battery power, remaining communication bandwidth, and computing resources, through encryption algorithms, and records it in the distributed ledger in the form of blockchain transactions. The immutable feature of the blockchain ensures the authenticity and credibility of the resource information. Each UAV node can obtain the whole network resource information in real time and securely, providing a reliable data basis for resource allocation decisions.

[0066] Multi - dimensional Utility Game - based Resource Allocation: Introduce a game - theory model to construct the resource allocation problem among UAV nodes as a multi - dimensional utility game. Each node makes resource allocation decisions with the goal of maximizing its own comprehensive utility function. The comprehensive utility function U i Comprehensively consider the communication quality Q i , data transmission rate R i , energy consumption E i and resource allocation fairness F i and other factors, that is, U i = w1Q i + w2R i - w3E i + w4F i . Among them, w1, w2, w3, and w4 are weight coefficients dynamically adjusted according to the priority and real - time requirements of emergency communication tasks. For example, in the task of transmitting emergency rescue command information, the weights w1 and w2 corresponding to the communication quality Q i and data transmission rate R i can be increased to ensure the efficient transmission of key information.

[0067] Achieve Equilibrium through Adaptive Iterative Optimization: Based on the local resource status and the obtained network - wide resource information, UAV nodes perform multiple iterative games through a distributed algorithm. In each iteration, the node dynamically adjusts its own resource allocation plan according to the resource allocation strategies of other nodes, gradually approaching the Nash equilibrium state. At the same time, an adaptive learning mechanism is introduced, and the node can automatically adjust its own decision - making parameters according to the game results and task execution feedback, accelerating convergence to the optimal resource allocation state, realizing the efficient and reasonable allocation of network resources, and improving the overall network performance.

[0068] Energy Guarantee System with Multi - energy Complementary and Intelligent Scheduling

[0069] Integration of Composite Energy Harvesting Module: Design an integrated composite energy harvesting module for UAVs, integrating high - efficiency solar panels, micro - wind turbines, and new vibration energy harvesters. The solar panels are made of high - efficiency single - crystal silicon materials, with a photoelectric conversion efficiency exceeding 25%, and have an adaptive angle adjustment function, which can adjust the lighting angle in real - time according to the sun's position to maximize the solar energy collection efficiency. The micro - wind turbines are optimized in aerodynamics and can generate electricity stably in a low - wind - speed (≥2m / s) environment, with an output power of up to dozens of watts. The vibration energy harvester utilizes the body vibration during the flight of the UAV to convert mechanical energy into electrical energy through piezoelectric materials, realizing multi - energy complementary harvesting and effectively improving the energy harvesting efficiency.

[0070] Dynamic Programming-based Energy Intelligent Management: Develop an energy management system based on dynamic programming algorithms. According to the real-time battery power of the UAV, the urgency of task requirements, and the environmental energy harvesting situation, formulate an optimal energy allocation and usage strategy. When the battery power is lower than the set threshold and the environmental energy harvesting is sufficient, the system optimizes the flight trajectory and speed to reduce flight power consumption. At the same time, it improves the working efficiency of the energy harvesting device. For example, reducing the flight speed by 30% can increase the energy harvesting efficiency by 20%, and appropriately reduce the communication power to maintain critical communication functions. When the battery power is sufficient and an emergency communication task is faced, the system gives priority to ensuring communication and flight performance and reasonably allocates energy resources.

[0071] Directional Beam-based Wireless Energy Sharing Network: Construct an energy sharing network among UAVs based on directional beam wireless energy transmission technology. When some UAVs have a relatively large amount of remaining battery power while some have insufficient power, the UAVs with sufficient power transmit high-energy-density wireless energy beams through directional antennas and accurately transmit them to the UAVs with insufficient power. Beamforming and tracking technologies are adopted to ensure the efficiency and accuracy of energy transmission, and the transmission efficiency can reach more than 70%. Through this energy sharing mechanism, the endurance of the entire emergency communication network is significantly improved, and the continuous working time of the network is extended.

[0072] Specifically, in the communication link optimization step based on environmental perception in the solution of this embodiment, the radar sensor is a high-precision lidar sensor with a resolution at the centimeter level.

[0073] Specifically, in the communication link optimization step based on environmental perception in the solution of this embodiment, the vision sensor processes visual image data using deep learning algorithms.

[0074] Specifically, in the distributed resource allocation step in the solution of this embodiment, each UAV node records and shares its own resource information through blockchain technology.

[0075] Specifically, in the energy efficient management step in the solution of this embodiment, the solar panel uses high-efficiency monocrystalline silicon material and has an adaptive angle adjustment function.

[0076] Specifically, in the energy efficient management step in the solution of this embodiment, the wireless energy transmission technology is magnetic resonance wireless energy transmission technology.

[0077] Refer to Figure 2 and Figure 3 , specifically, in the solution of this embodiment, a UAV-assisted emergency communication network system includes:

[0078] Multiple UAVs, each UAV is equipped with a radar sensor, a vision sensor, an environmental monitoring sensor, an energy harvesting device, and a wireless energy transmission module;

[0079] A computing unit that establishes an environmental model based on environmental information obtained by sensors and generates flight attitude adjustment instructions and communication frequency adjustment instructions;

[0080] A flight control module connected to the computing unit;

[0081] A communication module connected to the computing unit to enable communication between UAV nodes;

[0082] An energy management module that controls the UAV flight strategy, communication mode, and energy sharing operation according to the battery power, mission requirements, and environmental energy harvesting situation.

[0083] Specifically, in the solution of this embodiment, the computing unit adopts edge computing technology.

[0084] Specifically, in the solution of this embodiment, the energy harvesting device includes a solar panel installed on the top of the UAV and a wind energy collector installed at a suitable position on the UAV wing or fuselage.

[0085] Specifically, in the solution of this embodiment, the system adopts a distributed algorithm to implement resource allocation between UAV nodes and constructs a non - cooperative game model for resource allocation based on game theory.

[0086] Embodiment:

[0087] A method for optimizing the performance of an emergency communication network assisted by UAVs, and its specific implementation steps include:

[0088] Implementation of environmental perception and communication link optimization

[0089] Before the UAV takes off, calibrate and initialize the radar sensor, vision sensor, and environmental monitoring sensor. Taking the lidar sensor as an example, calibrate its distance through a standard reflector to ensure measurement accuracy. For the vision sensor, use an image dataset with known features for parameter calibration to improve recognition accuracy.

[0090] During the UAV flight, the sensors collect data in real - time. The lidar sensor emits laser beams at a frequency of N times per second, and the calculation formula for obtaining the distance d to the obstacle is: d = c×t / 2, where c is the speed of light and t is the laser round - trip time. The vision sensor captures images at a frame rate of f and processes the images using deep learning algorithms to identify features such as buildings and terrain. The environmental monitoring sensor monitors meteorological parameters such as wind speed v, humidity h, and rainfall intensity r in real - time.

[0091] The collected data is transmitted to the computing unit carried by the drone, and a machine learning algorithm is used to establish an environmental model. When establishing a regression model for the relationship between signal attenuation and meteorological parameters, it is assumed that there is a linear relationship between signal attenuation S and wind speed v, humidity h, and rainfall intensity r, which can be expressed as: S = a1v + a2h + a3r + b, where a1, a2, and a3 are regression coefficients and b is a constant term. These parameter values are determined through training with a large amount of historical data.

[0092] According to the environmental model, the flight control module and communication module of the drone work together. When the lidar detects that the distance to an obstacle ahead is less than the safety threshold d safe , the flight control module calculates and adjusts the angle θ according to the obstacle avoidance algorithm. The formula is: θ = arctan((y obs - y uav ) / (x obs - x uav )) + Δθ, where (x obs , y obs ) are the coordinates of the obstacle, (x uav , y uav ) are the coordinates of the drone, and Δθ is the adjustment offset. The communication module selects the optimal communication frequency f opt according to the signal attenuation model and the current frequency band interference situation. For example, by calculating the signal-to-noise ratio SNR at different frequencies, SNR = P signal / P noise , where P signal is the signal power and P noise is the noise power, and the frequency with the maximum SNR is selected as f opt .

[0093] Implementation of distributed resource allocation

[0094] After each drone starts, it broadcasts its own resource information (such as battery power E and communication bandwidth B) to the surrounding nodes, and the broadcast radius is R. When the surrounding nodes receive the information, they judge whether the information is valid according to the relationship between signal strength I and distance d, I = P / (4πd 2 ) where P is the transmission power).

[0095] The drone calculates the utility function U i = w1Q i + w2R i - w3E i according to the received information and its own resource status. The communication quality Q i can be measured by the bit error rate BER, Q i = 1 - BER. The data transmission rate R i is calculated according to the current communication bandwidth and link status. Assuming the link capacity is C, R i= C × α, where α is the utilization factor. The energy consumption E i is calculated based on the flight power P of the unmanned aerial vehicle flight and the communication power P comm as well as the time t. E i = (P flight + P comm ) × t. The coefficients w1, w2, and w3 are dynamically adjusted according to the task priority. For example, in the task of transmitting emergency rescue command information, w1 = 0.5, w2 = 0.4, and w3 = 0.1.

[0096] Information interaction and utility calculation are continuously carried out among the unmanned aerial vehicle nodes. In each iteration, node i adjusts its own resource allocation according to the resource allocation strategies of other nodes. Assume that the bandwidth allocated by node j for communication is B j，comm , and node i adjusts its own communication bandwidth according to the competition relationship and its own requirements The formula is: where β is the adjustment factor. After multiple iterations, the Nash equilibrium state is gradually reached, and the reasonable allocation of network resources is achieved.

[0097] Implementation of energy-efficient management

[0098] In the design stage of the unmanned aerial vehicle, solar panels and wind energy collectors are reasonably installed according to the size and flight characteristics of the unmanned aerial vehicle. The area of the solar panel is A solar , and its power generation P solar The calculation formula is: P solar = η solar × A solar × I solar , where η solar is the photoelectric conversion efficiency, and I solar is the solar radiation intensity. The wind energy collector is designed according to aerodynamics, and its power generation P wind is proportional to the cube of the wind speed v where ρ is the air density, A wind is the windward area of the wind energy collector, and η wind is the wind energy conversion efficiency.

[0099] During the flight of the unmanned aerial vehicle, the energy collection device collects environmental energy in real time and stores it in the battery. The energy management algorithm dynamically adjusts the parameters of the unmanned aerial vehicle according to the battery power E battery , the task requirements, and the environmental energy collection situation. When the battery power is lower than the threshold E thresh and the solar radiation intensity I solar is greater than a certain value, the flight speed v new is reduced. According to the relationship between the flight power consumption and the speed P flight ∝ v 3, reducing the flight speed can reduce power consumption while increasing the solar energy collection efficiency. Assuming that the reduction ratio of the flight speed is γ and the increase ratio of the solar energy collection efficiency is δ, the adjusted flight speed v new = v × (1 - γ), and the solar energy collection efficiency becomes The communication power is also appropriately adjusted according to the battery power and the urgency of the task.

[0100] When it is detected that the battery power of some drones is lower than E low , while there are drones with battery power higher than E high around, the drones with sufficient power activate the wireless energy transmission module. Taking magnetic resonance wireless energy transmission as an example, the transmission power P transfer is related to factors such as the transmission distance d, and the quality factors Q1 and Q2 of the transmitting coil and the receiving coil. Among them, P transmit is the transmitting power, k is the coupling coefficient, ω is the angular frequency, L1 and L2 are the coil inductances, and R1 and R2 are the coil resistances. The drones with sufficient power transmit energy to the drones with insufficient power to improve their endurance.

[0101] Implementation case:

[0102] Taking the emergency communication scenario after an earthquake as an example, in the earthquake-stricken area, most of the ground communication facilities are paralyzed. The rescue department quickly dispatched 10 drones equipped with the technology of the present invention to form an emergency communication network. After the drones took off, through the environmental perception system, it was found that there were a large number of collapsed buildings in some areas, seriously affecting the communication link. The lidar sensor detected that the distance to the obstacle ahead was less than the safety threshold, and the flight control module adjusted the flight altitude according to the obstacle avoidance algorithm. The communication module selected the optimal communication frequency according to the signal attenuation model, successfully avoided the occlusion, and established a stable communication link. In terms of resource allocation, each drone node reasonably allocated communication bandwidth and battery power through multiple iterative games according to its own resources and the needs of surrounding nodes. For example, Node 1 calculated according to the utility function and increased its own communication bandwidth allocation, improving the transmission rate of important rescue command information. At the same time, the energy-efficient management mechanism came into play, and the drones used solar panels and wind energy collectors to collect energy. When the battery power of some drones was lower than the threshold, the drones with sufficient power transmitted energy to them through wireless energy transmission technology. Through these measures, the entire emergency communication network continued to operate for 12 hours, providing strong communication support for the rescue work and successfully completing the rescue task.

[0103] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0104] The intelligent dynamic environment adaptation communication link technology can perceive complex environment changes in real time and accurately. Through the collaborative optimization of flight attitude and communication frequency, it can effectively reduce the signal interruption probability by more than 80%, greatly improve the stability and reliability of the communication link, and ensure the unobstructed emergency communication.

[0105] The distributed resource collaborative allocation mechanism based on blockchain and game theory, with the help of the trusted resource sharing of blockchain and the accurate resource allocation of multi-dimensional utility game, can achieve a network resource utilization rate increase of more than 30%, significantly optimize the overall network performance, and meet the communication needs of diverse and high-priority services in emergency communication.

[0106] The energy guarantee system with multi-energy complementation and intelligent scheduling can extend the UAV endurance time by more than 50% through composite energy harvesting, dynamic energy management, and energy sharing among UAVs, greatly enhancing the continuous operation ability of the emergency communication network and enabling it to work stably in long-term and high-intensity emergency rescue tasks.

[0107] The above has introduced the technical solutions provided by the embodiments of the present invention in detail. Specific examples are used in this article to elaborate on the principles and implementation manners of the embodiments of the present invention. The descriptions of the above embodiments are only applicable to help understand the principles of the embodiments of the present invention; at the same time, for those of ordinary skill in the art, according to the embodiments of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for optimizing the performance of an unmanned aerial vehicle (UAV)-assisted emergency communication network, characterized in that, It includes the following steps: Step S1, Communication link optimization step based on environmental perception: Each drone is equipped with a radar sensor, a vision sensor, and an environmental monitoring sensor; Using machine learning algorithms, an environmental model is established based on the position and distance data of surrounding obstacles detected by the radar sensor, the building and terrain feature data identified by the vision sensor, and the meteorological parameter data detected by the environmental monitoring sensor. Among them, a deep neural network is used to process visual image data to identify obstacles and terrain, and a regression model is used to analyze the relationship between meteorological parameters and signal attenuation; According to the environmental model, dynamically adjust the flight attitude and communication frequency of the drone. When blocked by a building, adjust the flight height or angle, and select the communication frequency according to the impact of the environment on signal attenuation; Step S2, Distributed resource allocation step: Adopt a distributed algorithm to realize resource allocation among drone nodes, and each node makes independent decisions based on its own and surrounding node resource information; Introduce the idea of game theory, model the resource allocation problem as a non - cooperative game, and the nodes maximize the utility function U i = w1Q i + w2R i - w3E i , where U i is the utility of the i - th drone node, Q i is the communication quality index, R i is the data transmission rate, E i is the energy consumption, and w1, w2, w3 are weight coefficients adjusted according to actual needs to make resource allocation decisions; Through multiple iterative games, a Nash equilibrium state is reached among drone nodes to achieve reasonable resource allocation; Step S3, Energy-efficient management step: Configure energy collection devices such as solar panels and wind energy collectors for the drone; Adopt an intelligent energy management algorithm. According to the battery power of the drone, task requirements, and environmental energy collection situation, adjust the flight strategy and communication mode of the drone. When the battery power is low and the energy collection is sufficient, reduce the flight speed, increase the energy collection efficiency, and reduce the communication power; when the battery power is sufficient and the task is urgent, increase the flight speed and communication power; Build an energy sharing mechanism between drones. Drones with more power transmit energy to drones with less power through wireless energy transmission technology.

2. The method for optimizing the performance of an unmanned aerial vehicle-assisted emergency communication network according to claim 1, wherein: In the communication link optimization step based on environmental perception, the radar sensor is a high-precision lidar sensor with a resolution of centimeter level.

3. The method for optimizing the performance of an emergency communication network assisted by an unmanned aerial vehicle according to claim 1, wherein: In the communication link optimization step based on environmental perception, the vision sensor uses deep learning algorithms to process visual image data.

4. The method for optimizing the performance of an emergency communication network assisted by an unmanned aerial vehicle according to claim 1, wherein: In the distributed resource allocation step, each drone node records and shares its own resource information through blockchain technology.

5. The method for optimizing the performance of an unmanned aerial vehicle-assisted emergency communication network according to claim 1, wherein: In the energy-efficient management step, the solar panel uses high-efficiency monocrystalline silicon materials.

6. The method for optimizing the performance of an emergency communication network assisted by a drone according to claim 1, wherein: In the energy-efficient management step, the wireless energy transmission technology is magnetic resonance wireless energy transmission technology.

7. An unmanned aerial vehicle-assisted emergency communication network system, characterized in that, It includes: Multiple drones, each drone carrying a radar sensor, a vision sensor, an environmental monitoring sensor, an energy collection device, and a wireless energy transmission module; A calculation unit that establishes an environmental model based on the environmental information obtained by the sensor and generates flight attitude adjustment instructions and communication frequency adjustment instructions; A flight control module connected to the calculation unit; A communication module connected to the calculation unit to realize communication between drone nodes; An energy management module that controls the flight strategy, communication mode, and energy sharing operation of the drone according to the battery power, task requirements, and environmental energy collection situation.

8. The UAV-assisted emergency communication network system according to claim 7, characterized in that: The calculation unit adopts edge computing technology.

9. An emergency communication network system assisted by a drone according to claim 7, characterized in that: The energy collection device includes a solar panel installed on the top of the drone and a wind energy collector installed at a suitable position on the drone wing or fuselage.

10. An unmanned aerial vehicle-assisted emergency communication network system according to claim 7, characterized in that: The system adopts a distributed algorithm to realize resource allocation among drone nodes and constructs a non-cooperative game model for resource allocation based on game theory.

Images