Resource allocation method and device for multi-load unmanned aerial vehicle system, equipment and medium
By generating configuration files and resource allocation models, resources are dynamically scheduled, solving the compatibility and reliability issues of multi-payload UAV systems, achieving efficient resource allocation and fault response, and improving the system's robustness and mission success rate.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING MATARNET TECH
- Filing Date
- 2025-11-27
- Publication Date
- 2026-04-28
AI Technical Summary
Existing multi-payload unmanned aerial vehicle (UAV) systems suffer from high complexity in hardware design and software adaptation, lack of flexibility in resource allocation strategies, and lack of real-time fault perception and dynamic reconfiguration capabilities, resulting in poor compatibility, low efficiency, and low reliability.
By generating configuration files, configuring based on FPGA and software-defined communication protocol stacks, combining resource allocation models and monitoring system status, dynamically scheduling resources, identifying anomalies and executing fault-tolerant strategies, rapid compatibility and adaptation to heterogeneous payload devices can be achieved.
It improves the efficiency and reliability of resource allocation, and enhances the system's robustness and task success rate in complex environments.
Smart Images
Figure CN121940306A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a resource allocation method, apparatus, equipment, and medium for a multi-payload UAV system. Background Technology
[0002] With the widespread application of intelligent unmanned systems such as drones and unmanned vehicles in fields such as surveying, inspection, and disaster relief, multi-payload integration has become a key technology to improve their functional diversity and mission adaptability.
[0003] However, existing technologies face significant challenges in achieving multi-payload integration. First, different payload devices typically employ heterogeneous hardware interfaces, communication protocols, and power supply standards, leading to high complexity and cost in hardware design and software adaptation. Second, traditional multi-payload systems often use fixed resource allocation strategies, lacking flexible resource scheduling mechanisms when facing complex tasks requiring real-time switching or parallel driving of multiple payloads, easily resulting in resource contention or low utilization. Furthermore, existing systems largely rely on static protection strategies to address electromagnetic interference, mechanical vibration, and payload failures, generally lacking real-time fault detection and dynamic reconfiguration capabilities, which severely restricts the system's reliability and robustness in complex environments. Summary of the Invention
[0004] This invention provides a resource allocation method, apparatus, device, and medium for multi-payload unmanned aerial vehicle (UAV) systems, which addresses the shortcomings of existing resource allocation methods for multi-payload UAV systems, such as poor compatibility, low efficiency, and low reliability.
[0005] This invention provides a resource allocation method for a multi-payload unmanned aerial vehicle (UAV) system, comprising: Based on multiple interface types and communication protocols of multiple payload devices, a configuration file is generated. Based on the configuration file, the field-programmable gate array (FPGA) and communication protocol stack of the multi-payload UAV system are configured. The communication protocol stack is defined by software. Obtain the system resource status and the operating status of the multiple load devices, and determine the task requirements associated with the multiple load devices; The system resource status, operating status, and task requirements are input into the resource allocation model to obtain the resource allocation strategies corresponding to the multiple load devices output by the resource allocation model. The resource allocation model is trained based on the system resource status samples, the operating status samples and task requirement samples of the multiple load device samples, and the resource allocation strategy labels corresponding to the multiple load device samples.
[0006] In some embodiments, after obtaining the resource allocation strategies corresponding to the plurality of load devices output by the resource allocation model, the method further includes: Based on the resource allocation strategy, the system resources are dynamically scheduled; The multiple payload devices and the multi-payload UAV system are monitored to obtain monitoring data, and abnormal states are identified based on the monitoring data. Based on the abnormal state, a fault tolerance strategy is determined from a pre-built fault response knowledge base and then executed.
[0007] In some embodiments, implementing the fault tolerance strategy includes at least one of the following: The configuration file is updated to obtain an updated configuration file. Based on the updated configuration file, the FPGA and the communication protocol stack are reconfigured. The resource allocation strategy is adjusted to obtain the adjusted resource allocation strategy.
[0008] In some embodiments, the system resources include computing resources, communication resources, and power supply resources; the dynamic scheduling of system resources includes: Based on the Time Division Multiple Access (TDMA) scheduling algorithm, communication resources are dynamically scheduled. Dynamic Voltage and Frequency Scaling (DVFS) technology is used to dynamically schedule power supply resources.
[0009] In some embodiments, the resource allocation model includes a feature extraction layer, a feature fusion layer, and a decision layer; the feature extraction layer is used to extract features from the system resource state to obtain system resource state features, extract features from the operating state to obtain operating state features, and extract features from the task requirements to obtain task requirement features; the feature fusion layer is used to fuse the system resource state features, operating state features, and task requirement features to obtain fused features; the decision layer is used to make allocation decisions for system resources based on the fused features to obtain the resource allocation strategy.
[0010] In some embodiments, before generating the configuration file based on multiple interface types and multiple communication protocols of multiple payload devices, the method further includes: Construct a first digital twin model corresponding to the multiple payload devices, and construct a second digital twin model corresponding to the multi-payload unmanned aerial vehicle system; Based on the first digital twin model and the second digital twin model, the compatibility of the multiple payload devices with the multi-payload UAV system is simulated and verified. If the verification is successful, a configuration file is generated.
[0011] In some embodiments, the resource allocation model is trained based on the following steps: Obtain system resource status samples and multiple load device samples' operational status samples, and determine the task requirement samples associated with the multiple load device samples; Determine the resource allocation strategy labels corresponding to the multiple payload device samples; Using the system resource status samples, operation status samples, and task requirement samples as training samples, and the resource allocation strategy labels corresponding to the multiple load device samples as sample labels, an initial resource allocation model is trained. After training, the resource allocation model is obtained.
[0012] The present invention also provides a resource allocation device for a multi-payload unmanned aerial vehicle system, comprising: The configuration unit is used to generate a configuration file based on multiple interface types and multiple communication protocols of multiple payload devices, and to configure the field-programmable gate array (FPGA) and communication protocol stack of the multi-payload UAV system based on the configuration file. The communication protocol stack is defined by software. The acquisition unit is used to acquire the system resource status and the operating status of the multiple load devices, and to determine the task requirements associated with the multiple load devices. The decision unit is used to input the system resource status, operating status and task requirements into the resource allocation model to obtain the resource allocation strategy corresponding to the multiple load devices output by the resource allocation model; the resource allocation model is trained based on the system resource status sample and the operating status sample and task requirement sample of the multiple load devices, as well as the resource allocation strategy label corresponding to the multiple load devices.
[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the resource allocation method of any of the above-described multi-payload unmanned aerial vehicle systems.
[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the resource allocation method of any of the above-described multi-payload unmanned aerial vehicle systems.
[0015] The resource allocation method, apparatus, device, and medium for multi-payload unmanned aerial vehicle (UAV) systems provided by this invention generate configuration files based on multiple interface types and communication protocols of multiple payload devices. Based on these configuration files, the field-programmable gate array (FPGA) and software-defined communication protocol stack of the multi-payload UAV system are configured, combining the versatility of hardware with the flexibility of software to achieve rapid compatibility and adaptation to heterogeneous payload devices. By acquiring the system resource status and the operating status of multiple payload devices, the task requirements associated with these payload devices are determined. The system resource status, operating status, and task requirements are input into a resource allocation model to obtain the resource allocation strategy corresponding to the multiple payload devices output by the model, thereby improving the efficiency and reliability of resource allocation. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating the resource allocation method for a multi-payload unmanned aerial vehicle system provided in an embodiment of the present invention.
[0018] Figure 2 This is a flowchart illustrating the training process of the resource allocation model provided in this embodiment of the invention.
[0019] Figure 3 This is a schematic diagram of the structure of the resource allocation device for the multi-payload unmanned aerial vehicle system provided in an embodiment of the present invention.
[0020] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation
[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0022] The terms "first," "second," etc., used in this invention are used to distinguish similar objects, not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, in this invention, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0023] In this embodiment of the invention, the multi-payload unmanned aerial vehicle (UAV) system includes at least: an UAV platform, multiple payload devices, a payload integration and management system, and a ground control system; the UAV platform is the flight carrier of the entire system, and the UAV platform includes at least: an airframe structure, a power system, a flight control system, and a navigation system. To meet the requirements of multiple payloads, the UAV platform usually needs to have sufficient load capacity, endurance, and standardized physical mounting interfaces.
[0024] Optionally, multiple payload devices can be categorized into various types, such as sensing and detection payload devices, communication payload devices, operational / execution payload devices, and special-purpose payload devices. Sensing and detection payload devices are used to collect environmental information, such as visible light cameras, infrared thermal imaging cameras, lidar, and hyperspectral / multispectral cameras. Communication payload devices are used for data transmission or network coverage, such as communication relay equipment, satellite communication terminals, and 4G / 5G communication modules. Operational / execution payload devices are used to perform physical operations, such as material delivery devices, spraying equipment, robotic arms, and searchlights. Special-purpose payload devices are used in specific industries, such as gas detectors and magnetic anomaly detectors.
[0025] The payload integration and management system connects the UAV platform with multiple payload devices. This system comprises at least a hardware layer, a software layer, and a control layer. The hardware layer includes a multi-functional hardware interface, a power management unit, and an FPGA for flexible interface protocol conversion. The software and control layer includes device drivers, a communication protocol stack, and a resource allocation and scheduling module. This module dynamically manages and allocates computing, communication, and power resources.
[0026] It should be noted that operators can use the ground control system for mission planning, flight status monitoring, and real-time remote control, as well as control of various payload devices, and receive, display, and process data transmitted back from each payload device.
[0027] Figure 1 This is a flowchart illustrating a resource allocation method for a multi-payload unmanned aerial vehicle (UAV) system provided in an embodiment of the present invention. Figure 1As shown, the method includes the following steps: step 110, step 120, and step 130. This method flow is merely one possible implementation of the present invention.
[0028] Step 110: Based on multiple interface types and communication protocols of multiple payload devices, generate configuration files. Based on the configuration files, configure the FPGA and communication protocol stack of the multi-payload UAV system. The communication protocol stack is software-defined.
[0029] Among them, a Field Programmable Gate Array (FPGA) is a semiconductor device whose hardware logic can be reprogrammed after deployment. By programming the dynamic logic units of the FPGA, the system can dynamically generate different physical interfaces such as Universal Asynchronous Receiver / Transmitter (UART), Controller Area Network (CAN), and Universal Serial Bus (USB) to adapt to the hardware requirements of different payload devices and achieve plug-and-play functionality at the hardware level.
[0030] It should be noted that the communication protocol processing and conversion functions are implemented in software, rather than being embedded in the hardware. This allows the system to flexibly support and convert multiple communication protocols. When a payload device using a specific communication protocol is connected, the system only needs to load the corresponding software module to enable communication.
[0031] Optionally, the FPGA can be reprogrammed based on the hardware interface information in the configuration file. For example, if the payload device requires a CAN interface, the logic unit inside the FPGA can be configured as a CAN controller and connected to the corresponding physical pin.
[0032] Optionally, based on the communication protocol information in the configuration file, the corresponding communication protocol stack is loaded and run at the software level. For example, if the payload device uses the RS-232 protocol, the corresponding parsing and encapsulation program is started through the communication protocol stack to achieve transparent protocol conversion.
[0033] Step 120: Obtain the system resource status and the operating status of multiple load devices, and determine the task requirements associated with multiple load devices.
[0034] Among them, system resource status refers to the status of the core public resources currently available in the multi-payload UAV system, such as the usage status of the system's computing resources, communication resources, and energy; operational status refers to the real-time working status of each payload device, such as whether the camera is recording, sensor temperature, LiDAR data output rate, and whether the device has fault codes; mission requirements refer to the functional and performance requirements proposed for each payload device in order to complete a specific mission. Mission requirements also include priorities. For example, in reconnaissance missions, the requirement for high-definition video transmission has the highest priority.
[0035] Step 130: Input the system resource status, operating status and task requirements into the resource allocation model to obtain the resource allocation strategies corresponding to multiple load devices output by the resource allocation model; the resource allocation model is trained based on the system resource status samples and the operating status samples, task requirement samples and resource allocation strategy labels corresponding to multiple load device samples.
[0036] The resource allocation strategy clarifies how to allocate limited system resources to multiple payload devices at the current moment. For example, 10Mbps bandwidth might be allocated to camera A, 2W of power to sensor B, while heterogeneous computing units are used to accelerate the processing of data from camera A.
[0037] In some embodiments, the resource allocation model includes a feature extraction layer, a feature fusion layer, and a decision layer. The feature extraction layer is used to extract features from the system resource status to obtain system resource status features, extract features from the operating status to obtain operating status features, and extract features from the task requirements to obtain task requirement features. The feature fusion layer is used to fuse the system resource status features, operating status features, and task requirement features to obtain fused features. The decision layer is used to make allocation decisions for system resources based on the fused features to obtain a resource allocation strategy.
[0038] In this embodiment of the invention, a configuration file is generated based on multiple interface types and communication protocols of multiple payload devices. Based on the configuration file, the field-programmable gate array (FPGA) and software-defined communication protocol stack of the multi-payload UAV system are configured, combining the versatility of hardware with the flexibility of software, thus achieving rapid compatibility and adaptation to heterogeneous payload devices. By acquiring the system resource status and the operating status of multiple payload devices, the task requirements associated with multiple payload devices are determined. The system resource status, operating status, and task requirements are input into the resource allocation model to obtain the resource allocation strategy corresponding to multiple payload devices output by the resource allocation model, thereby improving the efficiency and reliability of resource allocation.
[0039] In some embodiments, after obtaining the resource allocation strategies corresponding to multiple load devices output by the resource allocation model, the method further includes: Based on resource allocation strategies, system resources are dynamically scheduled; Monitoring multiple payload devices and multi-payload UAV systems to obtain monitoring data, and identifying abnormal states based on the monitoring data; Based on the abnormal state, the fault tolerance strategy is determined from the pre-built fault response knowledge base and then executed.
[0040] Monitoring data refers to the raw data collected by the system during operation through various sensors and software probes, used to determine the system's health status. Monitoring data includes not only the status of the payload equipment itself, but also performance data after the system performs resource scheduling, such as the actual bit error rate of the communication link, packet loss rate, actual temperature of the payload processor, and fluctuations in the system's total power consumption. Abnormal states refer to system behaviors or states that deviate from normal expectations, such as excessively high temperature, communication interruption, sudden increase in power consumption, or excessive data processing latency. For example, if monitoring data shows a camera temperature of 90℃, while the preset safety threshold is 85℃, the system will identify an abnormal state of excessively high camera temperature.
[0041] The fault response knowledge base is built based on equipment manuals, expert experience data, a large amount of experimental test data, and historical data; the fault tolerance strategy is a specific action plan used to correct anomalies, restore system stability, or ensure that core tasks are not affected.
[0042] In this embodiment of the invention, by monitoring multiple payload devices and multi-payload UAV systems, abnormal states are identified. Based on the abnormal states, fault tolerance strategies are determined from a pre-built fault response knowledge base and executed. This greatly improves the robustness and reliability of the system and ensures the success rate of core tasks.
[0043] In some embodiments, a fault tolerance strategy is implemented, including at least one of the following: Update the configuration file to obtain the updated configuration file, and reconfigure the FPGA and communication protocol stack based on the updated configuration file; The resource allocation strategy is adjusted to obtain the adjusted resource allocation strategy.
[0044] Optionally, implementing fault-tolerant strategies may also include isolating abnormal load devices.
[0045] In this embodiment of the invention, by updating the configuration file and reconfiguring the FPGA and communication protocol stack based on the updated configuration file, it is ensured that information and instructions can flow stably between the system and the payload; by adjusting the resource allocation strategy, it is ensured that the system can make optimal resource allocation decisions under abnormal conditions.
[0046] In some embodiments, system resources include computing resources, communication resources, and power supply resources; dynamic scheduling of system resources includes: Based on the Time Division Multiple Access (TDMA) scheduling algorithm, communication resources are dynamically scheduled. Dynamic Voltage Frequency Scaling (DVFS) technology is used to dynamically schedule power supply resources.
[0047] Time Division Multiple Access (TDMA) is a channel multiplexing technology. Its core idea is to divide time into multiple small segments, or time slots, and then allocate these time slots to different users according to certain rules. Dynamic Voltage and Frequency Scaling (DVFS) is a mainstream low-power technology widely used in modern processors. Its basic principle is that the processor's power consumption is proportional to the square of its operating voltage and its operating frequency. When the processor is not under heavy load, power consumption can be significantly reduced by simultaneously lowering its operating voltage and frequency; when high performance is required, it can be switched back to a high voltage and high frequency state.
[0048] In this embodiment of the invention, the communication resources are dynamically scheduled based on the Time Division Multiple Access (TDMA) scheduling algorithm, which is highly flexible and can provide guaranteed bandwidth for high-priority critical payloads. The communication quality is not affected by burst data from other non-critical payloads, ensuring smooth communication for core tasks. The Dynamic Voltage and Frequency Adjustment (DVFS) technology is used to dynamically schedule power supply resources, which can significantly extend the battery life, reduce system heat dissipation, improve stability, and achieve refined energy management.
[0049] In some embodiments, before generating the configuration file, based on multiple interface types and multiple communication protocols of multiple payload devices, the following steps are also included: Construct a first digital twin model corresponding to multiple payload devices, and construct a second digital twin model corresponding to the multi-payload unmanned aerial vehicle system; Based on the first and second digital twin models, the compatibility of multiple payload devices with the multi-payload UAV system is simulated and verified. If the verification is successful, a configuration file is generated.
[0050] It should be noted that a digital twin model is a digital copy of a physical entity that is completely corresponding to the physical entity in virtual space. It not only includes the geometry and physical properties of the physical entity, but also simulates the entity's behavior, functions, states and communication interfaces.
[0051] The first digital twin model refers to a digital twin model built separately for each payload device, which accurately describes all the key characteristics of the payload device, such as interface characteristics, communication protocols, functions, performance, and behavior patterns.
[0052] The second digital twin model refers to the digital twin model built for the multi-payload unmanned aerial vehicle system itself. The second digital twin model includes a virtual FPGA, a virtual communication protocol stack, and a virtual resource pool.
[0053] Optionally, in a computer simulation environment, one or more first digital twin models are inserted into the second digital twin model, and a simulation program is run to perform compatibility simulation verification.
[0054] In this embodiment of the invention, a first digital twin model corresponding to multiple payload devices is constructed, and a second digital twin model corresponding to the multi-payload UAV system is constructed. Based on the first and second digital twin models, the compatibility between the multiple payload devices and the multi-payload UAV system is simulated and verified. If the verification is successful, a configuration file is generated, which improves the security of the system, significantly improves the efficiency of system integration and development, and reduces costs.
[0055] Figure 2 This is a flowchart illustrating the training process of the resource allocation model provided in an embodiment of the present invention. Figure 2 As shown, in some embodiments, the resource allocation model is trained based on the following steps: Step 210: Obtain system resource status samples and running status samples of multiple load device samples, and determine the task requirement samples associated with the multiple load device samples; Step 220: Determine the resource allocation strategy labels corresponding to multiple payload device samples; Step 230: Using system resource status samples, running status samples, and task requirement samples as training samples, and resource allocation strategy labels corresponding to multiple load device samples as sample labels, train the initial resource allocation model. After training, the resource allocation model is obtained.
[0056] Optionally, the initial resource allocation model includes an initial feature extraction layer, an initial feature fusion layer, and an initial decision layer. The initial feature extraction layer is used to extract features from system resource state samples to obtain system resource state feature samples, to extract features from operating state samples to obtain operating state feature samples, and to extract features from task requirement samples to obtain task requirement feature samples. The initial feature fusion layer is used to fuse system resource state feature samples, operating state feature samples, and task requirement feature samples to obtain fused feature samples. The initial decision layer is used to obtain a predicted resource allocation strategy based on the fused feature samples.
[0057] Optionally, based on the predicted resource allocation strategy and the resource allocation strategy label, a loss function value is calculated, and based on the loss function value, the parameters of the initial resource allocation model are iteratively optimized to obtain the resource allocation model.
[0058] In this embodiment of the invention, system resource status samples, running status samples, and task requirement samples are used as training samples, and resource allocation strategy labels corresponding to multiple load device samples are used as sample labels to train an initial resource allocation model. After training, a resource allocation model is obtained, which improves the robustness of the resource allocation model.
[0059] The resource allocation device for a multi-payload unmanned aerial vehicle (UAV) system provided in the embodiments of the present invention is described below. The resource allocation device for a multi-payload UAV system described below can be referred to in correspondence with the resource allocation method for a multi-payload UAV system described above.
[0060] Figure 3 This is a schematic diagram of the structure of the resource allocation device for a multi-payload unmanned aerial vehicle system provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the resource allocation device 300 of the multi-payload unmanned aerial vehicle system includes: Configuration unit 310 is used to generate configuration files based on multiple interface types and multiple communication protocols of multiple payload devices. Based on the configuration files, the field programmable gate array (FPGA) and communication protocol stack of the multi-payload UAV system are configured. The communication protocol stack is defined by software. The acquisition unit 320 is used to acquire the system resource status and the operating status of multiple load devices, and to determine the task requirements associated with the multiple load devices; The decision unit 330 is used to input the system resource status, operating status and task requirements into the resource allocation model to obtain the resource allocation strategies corresponding to multiple load devices output by the resource allocation model. The resource allocation model is trained based on the system resource status sample and the operating status sample, task requirement sample and resource allocation strategy label corresponding to multiple load device samples.
[0061] Optionally, the resource allocation device for the multi-payload unmanned aerial vehicle system also includes: The scheduling unit is used to dynamically schedule system resources based on resource allocation strategies. Anomaly identification unit is used to monitor multiple payload devices and multi-payload UAV systems, obtain monitoring data, and identify abnormal states based on the monitoring data; The fault-tolerant unit is used to determine and execute fault-tolerant strategies based on abnormal states from a pre-built fault response knowledge base.
[0062] Optionally, a fault-tolerance strategy is implemented, including at least one of the following: Update the configuration file to obtain the updated configuration file, and reconfigure the FPGA and communication protocol stack based on the updated configuration file; The resource allocation strategy is adjusted to obtain the adjusted resource allocation strategy.
[0063] Optionally, system resources include computing resources, communication resources, and power supply resources; dynamic scheduling of system resources includes: Based on the Time Division Multiple Access (TDMA) scheduling algorithm, communication resources are dynamically scheduled. Dynamic Voltage Frequency Scaling (DVFS) technology is used to dynamically schedule power supply resources.
[0064] Optionally, the resource allocation model includes a feature extraction layer, a feature fusion layer, and a decision layer. The feature extraction layer is used to extract features from the system resource status to obtain system resource status features, extract features from the operating status to obtain operating status features, and extract features from the task requirements to obtain task requirement features. The feature fusion layer is used to fuse the system resource status features, operating status features, and task requirement features to obtain fused features. The decision layer is used to make allocation decisions for system resources based on the fused features to obtain a resource allocation strategy.
[0065] Optionally, the resource allocation device for the multi-payload unmanned aerial vehicle system also includes: The building unit is used to build a first digital twin model corresponding to multiple payload devices and a second digital twin model corresponding to a multi-payload unmanned aerial vehicle system. The simulation verification unit is used to perform simulation verification of the compatibility between multiple payload devices and multi-payload UAV systems based on the first digital twin model and the second digital twin model. If the verification is successful, a configuration file is generated.
[0066] Optionally, the resource allocation model is trained based on the following steps: Obtain system resource status samples and running status samples of multiple load devices, and determine the task requirement samples associated with multiple load device samples; Determine the resource allocation strategy labels corresponding to multiple payload device samples; The initial resource allocation model is trained using system resource status samples, operation status samples, and task requirement samples, and resource allocation strategy labels corresponding to multiple load device samples are used as sample labels. After training, the resource allocation model is obtained.
[0067] It should be noted that the resource allocation device for the multi-payload unmanned aerial vehicle system provided in this embodiment of the invention can implement all the method steps implemented in the above-mentioned resource allocation method embodiment of the multi-payload unmanned aerial vehicle system, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.
[0068] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 4As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a resource allocation method for a multi-payload UAV system. This method includes: generating a configuration file based on multiple interface types and multiple communication protocols of multiple payload devices; configuring the field-programmable gate array (FPGA) and communication protocol stack of the multi-payload UAV system based on the configuration file, wherein the communication protocol stack is software-defined; acquiring the system resource status and the operating status of multiple payload devices, and determining the task requirements associated with multiple payload devices; inputting the system resource status, operating status, and task requirements into a resource allocation model to obtain the resource allocation strategy corresponding to multiple payload devices output by the resource allocation model; the resource allocation model is trained based on system resource status samples, operating status samples and task requirement samples of multiple payload devices, and resource allocation strategy labels corresponding to multiple payload device samples.
[0069] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0070] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform the resource allocation method for a multi-payload unmanned aerial vehicle (UAV) system provided by the above-described methods. The method includes: generating a configuration file based on multiple interface types and multiple communication protocols of multiple payload devices; configuring the field-programmable gate array (FPGA) and communication protocol stack of the multi-payload UAV system based on the configuration file, wherein the communication protocol stack is software-defined; acquiring the system resource status and the operating status of multiple payload devices, and determining the task requirements associated with the multiple payload devices; inputting the system resource status, operating status, and task requirements into a resource allocation model to obtain the resource allocation strategy corresponding to the multiple payload devices output by the resource allocation model; wherein the resource allocation model is trained based on system resource status samples, operating status samples and task requirement samples of multiple payload devices, and resource allocation strategy labels corresponding to the multiple payload device samples.
[0071] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0072] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A resource allocation method for a multi-payload unmanned aerial vehicle (UAV) system, characterized in that, include: Based on multiple interface types and communication protocols of multiple payload devices, a configuration file is generated. Based on the configuration file, the field-programmable gate array (FPGA) and communication protocol stack of the multi-payload UAV system are configured. The communication protocol stack is defined by software. Obtain the system resource status and the operating status of the multiple load devices, and determine the task requirements associated with the multiple load devices; The system resource status, operating status, and task requirements are input into the resource allocation model to obtain the resource allocation strategies corresponding to the multiple load devices output by the resource allocation model. The resource allocation model is trained based on the system resource status samples, the operating status samples and task requirement samples of the multiple load device samples, and the resource allocation strategy labels corresponding to the multiple load device samples.
2. The resource allocation method for a multi-payload unmanned aerial vehicle system according to claim 1, characterized in that, After obtaining the resource allocation strategies corresponding to the multiple load devices output by the resource allocation model, the method further includes: Based on the resource allocation strategy, the system resources are dynamically scheduled; The multiple payload devices and the multi-payload UAV system are monitored to obtain monitoring data, and abnormal states are identified based on the monitoring data. Based on the abnormal state, a fault tolerance strategy is determined from a pre-built fault response knowledge base and then executed.
3. The resource allocation method for a multi-payload unmanned aerial vehicle system according to claim 2, characterized in that, The execution of the fault tolerance strategy includes at least one of the following: The configuration file is updated to obtain an updated configuration file. Based on the updated configuration file, the FPGA and the communication protocol stack are reconfigured. The resource allocation strategy is adjusted to obtain the adjusted resource allocation strategy.
4. The resource allocation method for a multi-payload unmanned aerial vehicle system according to claim 2, characterized in that, The system resources include computing resources, communication resources, and power supply resources; The dynamic scheduling of system resources includes: The communication resources are dynamically scheduled based on the Time Division Multiple Access (TDMA) scheduling algorithm. Dynamic Voltage Frequency Scaling (DVFS) technology is used to dynamically schedule the power supply resources.
5. The resource allocation method for a multi-payload unmanned aerial vehicle system according to claim 1, characterized in that, The resource allocation model includes a feature extraction layer, a feature fusion layer, and a decision layer. The feature extraction layer is used to extract features from the system resource status to obtain system resource status features, extract features from the operating status to obtain operating status features, and extract features from the task requirements to obtain task requirement features. The feature fusion layer is used to fuse the system resource status features, operating status features, and task requirement features to obtain fused features. The decision layer is used to make allocation decisions for system resources based on the fused features to obtain the resource allocation strategy.
6. The resource allocation method for a multi-payload unmanned aerial vehicle system according to claim 1, characterized in that, Before generating the configuration file, based on multiple interface types and multiple communication protocols of multiple payload devices, the following is also included: Construct a first digital twin model corresponding to the multiple payload devices, and construct a second digital twin model corresponding to the multi-payload unmanned aerial vehicle system; Based on the first digital twin model and the second digital twin model, the compatibility of the multiple payload devices with the multi-payload UAV system is simulated and verified. If the verification is successful, a configuration file is generated.
7. The resource allocation method for a multi-payload unmanned aerial vehicle system according to claim 1, characterized in that, The resource allocation model is trained based on the following steps: Obtain system resource status samples and multiple load device samples' operational status samples, and determine the task requirement samples associated with the multiple load device samples; Determine the resource allocation strategy labels corresponding to the multiple payload device samples; Using the system resource status samples, operation status samples, and task requirement samples as training samples, and the resource allocation strategy labels corresponding to the multiple load device samples as sample labels, an initial resource allocation model is trained. After training, the resource allocation model is obtained.
8. A resource allocation device for a multi-payload unmanned aerial vehicle (UAV) system, characterized in that, include: The configuration unit is used to generate a configuration file based on multiple interface types and multiple communication protocols of multiple payload devices, and to configure the field-programmable gate array (FPGA) and communication protocol stack of the multi-payload UAV system based on the configuration file. The communication protocol stack is defined by software. The acquisition unit is used to acquire the system resource status and the operating status of the multiple load devices, and to determine the task requirements associated with the multiple load devices. The decision unit is used to input the system resource status, operating status and task requirements into the resource allocation model to obtain the resource allocation strategy corresponding to the multiple load devices output by the resource allocation model; the resource allocation model is trained based on the system resource status sample and the operating status sample and task requirement sample of the multiple load devices, as well as the resource allocation strategy label corresponding to the multiple load devices.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the resource allocation method for the multi-payload unmanned aerial vehicle system as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the resource allocation method for the multi-payload unmanned aerial vehicle system as described in any one of claims 1 to 7.