Unmanned aerial vehicle assisted communication calculation integrated resource allocation method for forest fire fighting

Abstract

The invention provides an unmanned aerial vehicle assisted communication calculation integrated resource allocation method and device for forest fire fighting, and relates to the technical field of communication. The method comprises the following steps: establishing an unmanned aerial vehicle assisted ISCC system scene; according to the established system scene, constructing an unmanned aerial vehicle auxiliary ISCC system model; according to the unmanned aerial vehicle auxiliary ISCC system model, total delay and energy consumption of task completion of the unmanned aerial vehicle auxiliary ISCC system model are determined; according to the total delay and the energy consumption, constructing an optimization target of an unmanned aerial vehicle auxiliary ISCC system model; according to the optimization target, constructing optimization problems of task scheduling and resource allocation in the unmanned aerial vehicle assisted ISCC system model; and modeling an optimization problem as a Markov decision process, and optimizing a task scheduling and resource allocation strategy by adopting a TD3 algorithm to obtain an optimal task scheduling and resource allocation scheme. According to the invention, the real-time monitoring capability of fire behavior can be enhanced, and the fire fighting speed and success rate can be improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and device for allocating resources using unmanned aerial vehicle (UAV) assisted telepathy and computing integration for forest fire fighting. Background Art

[0002] The rapid development of drones marks a new era for the transportation and communication industries. In particular, drones have shown unique advantages in forest fire fighting applications. Drones can be flexibly equipped with a variety of sensors, including communication modules, lidar, and optical cameras. Sensors can collect a large amount of information during a fire. Drones can serve as aerial communication base stations to provide temporary communication networks in disaster areas to ensure smooth communication between rescuers and command centers. In addition, modern drones have powerful onboard computing capabilities and can share computing tasks with other IoT devices. The antennas on drones can also transmit signals to fire targets and receive echoes through radars to achieve accurate wireless perception and positioning. Drone-assisted Integrated Sensing, Computation, and Communication (ISCC) systems are becoming a cutting-edge field in critical tasks such as forest fire fighting. Drones that assist ISCC systems are equipped with high-performance onboard servers for data analysis, advanced communication antennas for instant information transmission, and highly sensitive wireless sensors for environmental monitoring, together forming a wireless platform that performs multiple tasks in a wide range of space. The drone-assisted ISCC system can quickly locate the source of fire, assess the speed and direction of fire spread, and provide critical decision-making support for rescue teams when a fire occurs. At the same time, it can also continuously monitor the fire scene after the fire is controlled to ensure that no fire points are missed and prevent the fire from re-igniting, thereby effectively protecting forest resources and reducing ecological damage. In addition, the drone-assisted ISCC system can also play a role in the daily management of forest fire prevention. Through regular inspections of forest areas, potential fire risk points, such as abnormal temperature rise or illegal activities, can be discovered and reported in a timely manner, so that preventive measures can be taken to avoid fires.

[0003] At present, joint task scheduling and resource allocation in UAV-assisted ISCC systems based on forest fire fighting scenarios is a crucial and challenging problem. Existing methods for joint task scheduling and resource allocation in UAV-assisted ISCC systems include: time division multiple access method, first perception and then offloading protocol method and space division multiple access method; the above methods ignore the mutual interference between task computation offloading and fire target perception; the simultaneous execution of task scheduling and perception may lead to resource competition and performance degradation, affecting the function of the entire system. Summary of the invention

[0004] In order to solve the technical problems of joint task scheduling and resource allocation in the UAV-assisted ISCC system in the forest fire fighting scenario in the prior art, an embodiment of the present invention provides a UAV-assisted telepathic computing integrated resource allocation method and device for forest fire fighting. The technical solution is as follows:

[0005] On the one hand, a method for allocating resources assisted by UAVs and integrated with telepathy and computing for forest fire fighting is provided. The method is implemented by a UAV-assisted integrated with telepathy and computing resource allocation device for forest fire fighting. The method comprises:

[0006] S1. Build a UAV-assisted ISCC system scenario;

[0007] S2. constructing a UAV-assisted ISCC system model according to the UAV-assisted ISCC system scenario;

[0008] S3. Determine the total delay and energy consumption of the UAV-assisted ISCC system model to complete the task according to the UAV-assisted ISCC system model;

[0009] S4. constructing an optimization target of a UAV-assisted ISCC system model according to the total delay and energy consumption;

[0010] S5. According to the optimization goal, construct the optimization problem of task scheduling and resource allocation in the UAV-assisted ISCC system model;

[0011] S6. Model the optimization problem as a Markov decision process, and use the TD3 algorithm to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

[0012] On the other hand, a UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting is provided, and the device is applied to a UAV-assisted telepathic computing integrated resource allocation method for forest fire fighting, and the device comprises:

[0013] The first building unit is used to build the UAV-assisted ISCC system scenario;

[0014] A second construction unit is used to construct a UAV-assisted ISCC system model according to the UAV-assisted ISCC system scenario;

[0015] a determination unit, configured to determine, according to the UAV-assisted ISCC system model, a total delay and energy consumption of the UAV-assisted ISCC system model in completing a task;

[0016] A third construction unit is used to construct an optimization target of the UAV-assisted ISCC system model according to the total delay and energy consumption;

[0017] A fourth construction unit is used to construct an optimization problem of task scheduling and resource allocation in a UAV-assisted ISCC system model according to the optimization target;

[0018] The acquisition unit is used to model the optimization problem as a Markov decision process, and use the TD3 algorithm to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

[0019] On the other hand, a UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting is provided, and the UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting comprises: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned UAV-assisted telepathic computing integrated resource allocation methods for forest fire fighting is implemented.

[0020] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned UAV-assisted synaesthesia-computing integrated resource allocation methods for forest fire fighting.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0022] The embodiment of the present invention first builds a UAV-assisted ISCC system scenario; according to the UAV-assisted ISCC system scenario, a UAV-assisted ISCC system model is constructed; according to the UAV-assisted ISCC system model, the total delay and energy consumption of the UAV-assisted ISCC system model to complete the task are determined; secondly, according to the total delay and energy consumption, the optimization target of the UAV-assisted ISCC system model is constructed; according to the optimization target, the optimization problem of task scheduling and resource allocation in the UAV-assisted ISCC system model is constructed; finally, the optimization problem is modeled as a Markov decision process, and the TD3 algorithm is used to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

[0023] The embodiment of the present invention constructs an optimization model for the applicability of uplink ISCC in processing computationally intensive, data-diverse and delay-sensitive forest firefighting tasks, and can focus on minimizing the weighted sum of the computational offloading penalty index and the perception penalty index, while taking into account a variety of practical operational constraints including feasible flight areas and UAV energy constraints, and can optimize the efficiency and effectiveness of uplink ISCC; the embodiment of the present invention reconstructs the task scheduling and resource allocation problems into a Markov decision process, and uses the TD3 algorithm to process the problems of joint scheduling and resource allocation of tasks in a UAV-assisted ISCC system, which can effectively improve the task processing speed and environmental perception quality; the embodiment of the present invention can provide powerful air support for forest firefighting, enhance the real-time monitoring capability of the fire situation, the data processing speed and the optimal resource allocation, and improve the response speed and success rate of firefighting operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 This is a flow chart of a method for allocating resources using UAV-assisted telepathy and computing integrated with forest firefighting provided by an embodiment of the present invention;

[0026] Figure 2 is a structural schematic diagram of an example scenario of UAV-assisted ISCC provided by an embodiment of the present invention;

[0027] Figure 3 It is a flow chart of a forest fire fighting algorithm based on TD3 provided by an embodiment of the present invention;

[0028] Figure 4 is an iteration diagram of the objective function provided by an embodiment of the present invention;

[0029] Figure 5 is an iterative situation diagram of the cumulative reward item provided by an embodiment of the present invention;

[0030] Figure 6 It is a 2D flight trajectory diagram of a drone in a forest fire fighting scenario provided by an embodiment of the present invention;

[0031] Figure 7 It is a 3D flight trajectory diagram of a drone in a forest fire fighting scenario provided by an embodiment of the present invention;

[0032] Figure 8This is a block diagram of a UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting provided by an embodiment of the present invention;

[0033] Fig. 9 It is a structural schematic diagram of a UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0035] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0036] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0037] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0038] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0039] The embodiment of the present invention provides a method for allocating resources for forest fire fighting with the assistance of UAVs, which can be implemented by a device for allocating resources for forest fire fighting with the assistance of UAVs, which can be a terminal or a server. Figure 1 The flowchart of the method for allocating resources using UAV-assisted telepathy and computing integrated with forest fire fighting is shown in the figure. The processing flow of the method may include the following steps:

[0040] 1. A method for allocating resources using UAV-assisted telepathy and computing for forest firefighting, characterized in that the method comprises:

[0041] S1. Build a UAV-assisted ISCC system scenario.

[0042] Optionally, a drone-assisted ISCC system scenario includes: a base station, an IoT device, a sensing target, and a drone;

[0043] Among them, the base station is used to receive the results of the drone processing computing tasks;

[0044] IoT devices are used to collect environmental information, generate tasks, and send tasks to drones. IoT devices are also used to communicate with drones and coordinate task offloading.

[0045] Among them, the IoT device can generate tasks that need to be processed within the time slot and offload the tasks to the drone; the IoT device is responsible for collecting environmental data, generating tasks, and sending them to the drone. The IoT device can participate in the communication of the drone to coordinate the process of task offloading and result feedback.

[0046] In a feasible implementation, IoT devices can collect environmental information, including temperature, wind speed, humidity, and wind direction. Due to the limited onboard computing and storage capacity of IoT devices, ground-deployed IoT devices need to offload some computing-intensive tasks to drones performing tasks in the area when processing large amounts of environmental monitoring data. Each IoT device is equipped with an omnidirectional antenna to ensure communication with drones in all directions; and each drone is equipped with a directional antenna to more accurately establish a communication link with a specific IoT device or ground control center.

[0047] Perception target, used to provide perception tasks for drones;

[0048] Drones to collect and aggregate information from IoT devices.

[0049] In each time slot, the drone can perform a series of coordinated tasks, including receiving computing tasks from IoT devices, moving to get closer to different IoT devices when necessary, and processing offloaded tasks. After processing, the drone transmits the calculation results to the base station. The drone is also responsible for receiving echo signals from IoT devices, which may contain environmental monitoring data to assist real-time decision-making in forest fire fighting.

[0050] Among them, the drone-assisted ISCC system scenario is the forest fire fighting scenario; in the forest fire fighting scenario, the drone works together with the IoT devices deployed on the ground to collect environmental information quickly and cost-effectively. The collaborative operation method is crucial for the early detection and real-time monitoring of forest fires.

[0051] Among them, the embodiment of the present invention sets a monitoring area of ​​a fixed size, within which the drone and the IoT device jointly perform monitoring tasks; in order to more effectively control and manage, the embodiment of the present invention adopts a time discretization strategy, which divides the entire monitoring time range into multiple equal time periods or time slots corresponding to the duration of a fire event, which helps to achieve continuous tracking and precise control of fire dynamics.

[0052] Among them, the embodiments of the present invention adopt the 5G new generation wireless communication technology and vehicle networking technology; among them, the 5G new generation wireless communication technology has high-speed and low-latency communication capabilities; the vehicle networking technology allows vehicles to communicate directly with other vehicles, pedestrians and infrastructure, etc., and can be used to command and coordinate rescue vehicles, personnel and equipment in forest fire fighting.

[0053] Among them, when the drone performs the task, it continuously transmits directional radar pulse signals to detect fire targets in the forest, including: trees, shrubs, houses and sheds, etc., which are all factors that may affect the fire. In the embodiment of the present invention, the antennas for transmitting and receiving on the drone are set to be separate, which can ensure that the receiving antenna can always be used to receive transmission tasks from sensing echoes and IoT devices. In terms of sensing tasks, the embodiment of the present invention pursues the fairness between maximizing the sensing success rate and fire targets. The drone will tend to visit areas with dense fire targets to improve the sensing success rate; in order to ensure fairness, the drone will also sense fire targets that are less visited; among them, fire targets that are less visited include: fire targets in remote areas: fires located deep in the forest or in the mountains may be less visited and monitored due to their remote geographical location; difficult to reach areas: some difficult to enter or reach areas such as swamps and cliffs may be less visited in fire monitoring due to danger or difficulty in approaching.

[0054] Among them, drones and IoT devices can work closely together within time slots. Drones use computing resources and mobility to support the data processing needs of IoT devices, while IoT devices provide data input and communication interaction with drones, jointly providing support for emergency response tasks such as forest fire fighting.

[0055] In a feasible implementation, multiple drones can be deployed to a specific monitoring area at the beginning of the time slot of a forest fire event; wherein multiple drones are deployed in advance and are ready to deal with any abnormal situation; the drones are set to continuously perform tasks during the entire monitoring cycle and cannot leave the designated monitoring area, and no new drones can be added to the monitoring area during the drone mission; by planning the drones to depart from and eventually return to the docking station, it is convenient for the drones to charge and keep the drones running throughout the mission cycle. The location of the docking station is selected at the edge of the monitoring area, which can maximize the coverage of the drone and enable the drone to quickly respond to emergencies in the area.

[0056] In a feasible implementation, in a drone-assisted ISCC system, drones and IoT devices can interact and perform task offloading through 5G new generation wireless communication technology and vehicle networking technology; in task offloading, each task of the IoT device will be offloaded to at most one drone for processing, and each IoT device can select the most suitable drone to offload tasks from the IoT device based on the drone's computing power, current task load, distance and other factors. In the above manner, drones can serve as mobile edge computing nodes, provide additional computing resources and help IoT devices process data, and can provide more comprehensive data support and decision-making basis for emergency tasks such as forest fire fighting.

[0057] In a feasible implementation, it is assumed that each IoT device collects environmental data at the same sampling rate, but the tasks generated by each IoT device differ in data volume and required computing resources; since the tasks generated by each IoT device are independent of each other, they can be processed in parallel to improve the processing speed; the embodiment of the present invention takes into account the differences in CPU and battery capacity of IoT devices, while drones have the same specifications of CPU and battery capacity, so the embodiment of the present invention reserves the necessary resources for the local task execution of IoT devices and uses the remaining resources for computing offload; wherein, the decision on task scheduling and resource allocation can be made centrally by the cellular base station connected to the drone; the information sharing between the drone and the cellular base station, including the status information of the drone and the nearby IoT devices, is carried out through the 5G new generation wireless communication technology and the Internet of Vehicles technology. The goal of the embodiment of the present invention is to maximize the success rate of computing offload and the fairness between IoT devices. In order to improve the success rate of computing offload, the drone will be more inclined to choose IoT devices with more tasks to be offloaded. At the same time, in order to enable all IoT devices to receive fair services, the embodiment of the present invention introduces a penalty index to encourage drones to visit less visited IoT devices.

[0058] S2. According to the UAV-assisted ISCC system scenario, a UAV-assisted ISCC system model is constructed.

[0059] Among them, according to the UAV-assisted ISCC system model, the location information of the UAV, the location information of the fire target, and the location information of the IoT device in the time slot can be obtained.

[0060] The received signal of the drone includes: the communication signals of all unloaded IoT devices and the perception echo signal emitted by the drone in the time slot and reflected by the fire target. The received signal of the drone is a linear combination of the communication signal and the perception echo signal, which can be expressed by the following formula (1):

[0061] (1)

[0062] in, Indicates time, Indicates whether the IoT device offloads tasks to the drone in time slot tn; assuming that each IoT device can only offload computing tasks to one drone within the acceptable communication distance in each time slot; represents the channel power gain between the IoT device and the drone; Represents the transmission signal of the IoT device in the time slot tn; Indicates whether the UAV senses the fire target in the time slot tn; represents the channel power gain between the IoT device and the fire target; represents the radar pulse signal of the UAV in time slot tn; Indicates the transmission time; represents the round-trip detection time; where and The time is very short and can usually be ignored; is the maximum tolerable offload delay.

[0063] S3. According to the UAV-assisted ISCC system model, determine the total delay and energy consumption of the UAV-assisted ISCC system model to complete the task.

[0064] Optionally, the total delay of the UAV-assisted ISCC system model of S3 to complete the task includes: local delay, transmission delay, and UAV computation delay;

[0065] The total delay is the maximum value between the local calculation delay and the transmission delay plus the drone calculation delay.

[0066] Among them, the local delay is determined by the local computing amount and the computing speed of the IoT device; among them, the local computing amount is the data size of the computing task that is not offloaded to the drone;

[0067] The calculation speed is related to the CPU frequency of the IoT device and the number of CPU cycles required to calculate 1 bit for the computing task of the IoT device.

[0068] Wherein, the transmission delay depends on the amount of data offloaded and the data rate of transmission; wherein, the data rate of transmission is related to the available bandwidth allocated to each IoT device, the transmission power of the IoT device, the channel power gain between the IoT device and the drone, the interference term, and the power of the noise;

[0069] The interference items include inter-user interference and perceived interference of echo signals.

[0070] Among them, the drone computing delay is determined by the amount of offloaded computing and the drone's computing rate.

[0071] The CPU frequency of the drone edge server is set to be evenly distributed to each IoT device whose task is unloaded. The offloaded computational amount is the data size of the computational task unloaded to the drone. The computational speed of the drone is related to the CPU frequency of the drone edge server assigned to the task and the number of CPU cycles required to calculate 1 bit for the task.

[0072] Optionally, the energy consumption of the UAV-assisted ISCC system model of S3 to complete the task includes: the energy consumption of the IoT device and the energy consumption of the UAV;

[0073] Among them, the energy consumption of IoT devices includes: the transmission energy of IoT devices and the computing energy of IoT devices;

[0074] The transmission energy of the IoT device is the product of the transmission power of the IoT device and the transmission delay of the IoT device;

[0075] The computing energy of the IoT device is the product of a constant related to the chip structure of the IoT device, the square of the CPU frequency of the IoT device, and the local computing delay;

[0076] Among them, the energy consumption of the drone includes: mission calculation energy consumption, fire target perception energy consumption and propulsion energy consumption.

[0077] The energy consumption of the drone can be expressed by the following formula (2):

[0078] (2)

[0079] in, represents the energy consumption of the drone; Indicates the energy consumption of task calculation; Indicates the energy consumption of the perceived fire target; It represents the propulsion energy consumption, which is the propulsion energy consumption of the UAV when it is flying or hovering in the air.

[0080] The total number of radar pulses in a time slot is a fixed value. No matter how many fire targets are detected, the UAV only sends one radar pulse to one fire target at a time. The energy consumption of the fire target is the product of the radar pulse power, the radar pulse duration, and the total number of radar pulses of the UAV.

[0081] Among them, the propulsion energy consumption can be expressed as ;in, represents the incremental correction factor for the induced power, Indicates the weight of the drone, represents the air density, Represents the area of ​​the drone's rotor disc.

[0082] Among them, the task computing energy consumption of a single drone is the product of a constant related to the drone chip architecture, the square of the CPU frequency of the drone edge server, and the computing delay. The task computing energy consumption is the sum of the task computing energy consumption of all drones.

[0083] S4. Construct the optimization target of the UAV-assisted ISCC system model based on the total delay and energy consumption;

[0084] Optionally, the optimization objectives of the UAV-assisted ISCC system model of S4 include: calculating an unloading penalty index and a perception penalty index.

[0085] The embodiment of the present invention considers maximizing the fair successful computing offloading and perception ratio under the constraint conditions, and transforms the objective of maximizing the fair successful computing offloading and perception ratio into minimizing the computing offloading and perception penalty by adopting the penalty function method for constraint optimization; wherein the constraint conditions include: feasible area, mobility of the UAV, radar power, transmission power, computing power, offloading ratio and energy; in order to ensure the performance of computing offloading, the computing offloading penalty index is taken as one of the optimization objectives. wherein the computing offloading penalty index can be expressed by the following formula (3):

[0086] (3)

[0087] in, represents the total delay, Indicates the threshold corresponding to the maximum delay, Indicates the successful calculation offloading status of the calculation task, for , Indicates taking the minimum value, Represented as 1 to The sum of whether the IoT device unloads tasks to the drone in the time slot. represents the energy consumption of the computing task, Indicates the threshold corresponding to the maximum energy consumption; 1 means Successfully offloading computational data to drones; It is represented as the penalty index of the computation task at time slot tn-1, Indicates the maximum value of the penalty index.

[0088] The smaller the penalty index, the more timely the computing task is unloaded. The IoT device offloads part of the computing task to the drone, and the rest is calculated locally. In the embodiment of the present invention, local computing tasks and offloaded tasks are generated and executed in parallel.

[0089] The perceived penalty index can be expressed by the following formula (4):

[0090] (4)

[0091] in, represents the perception penalty index of the fire target at time slot tn-1; Indicates the radar pulse duration; Indicates the number of radar pulses; Indicates the threshold corresponding to the maximum delay; Indicates the successful perception state of the fire target, for , represents the radar estimated information rate of the fire target in time slot tn, express a specific threshold value; when Only when this threshold is exceeded can the fire target be considered to be successfully sensed; hour, is 0; when hour, for ,in The index collection of drones that perceive fire targets, represents the index of the drone with the best perceived performance among all the drones served, represents the radar estimated information rate of the UAV sensing the fire target, Indicates the total bandwidth, Indicates the maximum number of orthogonal channels for IoT devices, Represents the available bandwidth allocated to each IoT device; represents the radar pulse power of the UAV, Represents the double-ray round-trip power gain between the UAV and the fire target.

[0092] Among them, since the time when the radar pulse echo arrives at the drone is different, the total perceived interference term of all users only includes the communication interference from all IoT devices. The interference of a single user is the product of the transmission power of the IoT device and the channel power gain between the IoT device and the drone. The total perceived interference is the sum of the perceived interference of all users.

[0093] S5. According to the optimization objectives, the optimization problems of task scheduling and resource allocation in the UAV-assisted ISCC system model are constructed.

[0094] Among them, in the field of forest fire fighting, the design goal of the drone-assisted ISCC system is to minimize the weighted sum of the computational offloading penalty index and the perception penalty index through fine task scheduling and resource allocation. The realization of this goal ensures that during the computational offloading process, the delay and energy consumption are controlled within the preset maximum threshold, while providing equal computational offloading opportunities for all IoT devices to ensure the fairness and energy efficiency of the system. The optimization of the perception penalty index ensures that the information rate of the radar perception task exceeds the minimum threshold, providing a fair execution opportunity for each perception task. In this way, the drone-assisted ISCC system can efficiently support real-time monitoring and rapid response to forest fires, and improve the accuracy of firefighting decisions and the success rate of firefighting operations.

[0095] Among them, in the entire optimization problem, the optimization goal is to minimize the weighted sum of the computational offloading penalty index and the perception penalty index; among them, the optimization problem includes 6 decision variables: The transmission power set of the IoT device is expressed as , UAV radar pulse power set is , the UAV trajectory set is represented as , the uninstallation association indicator set is represented as , the CPU frequency set of IoT devices is expressed as And the IoT offloading ratio set is expressed as .

[0096] Among them, the 11 constraints satisfied by the optimization problem include: the transmission power constraint of the IoT device, the radar pulse power constraint of the drone, the drone boundary constraint, the drone's moving distance constraint in a time slot, the drone's energy constraint, the unloading association indicator constraint, the IoT device's CPU frequency constraint and the IoT device's unloading ratio constraint; Among them, the drone's moving distance constraint in a time slot includes: the drone's moving distance constraint in the X-axis direction in a time slot, the drone's moving distance constraint in the Y-axis direction in a time slot and the drone's moving distance constraint in the Z-axis direction in a time slot; Among them, all drones, IoT devices and time slots must meet the above 11 constraints.

[0097] S6. The optimization problem is modeled as a Markov decision process, and the TD3 algorithm is used to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

[0098] Among them, the TD3 algorithm is obtained by improving the Deep Deterministic Policy Gradient (DDPG) algorithm; the improvements of the TD3 algorithm based on the DDPG algorithm include: (1) Dual Q-network: The TD3 algorithm uses two independent Q-networks to estimate the action value function to reduce the overestimation bias. Specifically, the minimum value of the two Q-networks is selected as the target Q-value, so as to more accurately estimate the true Q-value; (2) Delayed policy update: The TD3 algorithm reduces the update frequency of the policy network, usually updating the policy network once after updating the Q-network several times, thereby reducing the policy network's dependence on unstable Q-value estimation and improving the stability of the algorithm; (3) Target policy smoothing: When calculating the target Q-value, noise is added to the target action to make the target value smoother and reduce the instability caused by sudden changes in the policy.

[0099] Among them, in order to efficiently realize deep reinforcement learning and solve the task scheduling and resource allocation problems of the drone-assisted ISCC system in forest fire fighting, the optimization problem is formalized into a Markov decision process. The Markov decision process consists of four basic elements, including: agent, environment, state, action, strategy and reward.

[0100] Among them, the intelligent agent is an entity responsible for making decisions and taking actions; in an embodiment of the present invention, all cellular base stations within the reach of the drone are set as intelligent agents to determine all variables.

[0101] Among them, the environment includes all external factors that the agent interacts with, constituting the scenario of drone-assisted ISCC; the environment involves the dynamic interaction between drones, IoT devices and perception targets, which work together in the forest fire fighting mission.

[0102] The state describes the current situation of the environment or the environmental conditions in which the agent is located. Each state represents a specific configuration of the environment. In the time slot tn, the state space set contains the positions of all drones, IoT devices and sensing targets, the computational offloading penalty index and computational tasks of all IoT devices, the perception penalty index of all sensing targets, and the energy consumption of all drones. The state space set can be expressed by the following formula (5):

[0103] (5)

[0104] in, represents the state space set; represents the set of drone trajectories; Indicates the location of the IoT device; represents a computational task, The data size of the calculation task is in bits. The number of CPU cycles required to calculate 1 bit for the task, is the maximum tolerable delay, for Any value in , tn is Any value in ; represents the energy consumption of the drone; Indicates the CPU frequency of the drone server.

[0105] Among them, an action is an operation or behavior that an agent can choose to perform in a certain state; the action determines the agent's intervention in the environment. In the time slot tn, the action space set contains the flight distance and radar pulse power of all drones, the unloading rate, the CPU main frequency, the transmission power of the IoT device, and the unloading association indicator. The action space set can be expressed by the following formula (6):

[0106] (6)

[0107] in, represents the action space set; represents the distance the UAV moves in the x direction within the time slot tn; represents the distance the UAV moves in the y direction within the time slot tn; represents the distance the UAV moves in the z direction within the time slot tn; Indicates Radar pulse power of a UAV at time slot tn; Indicates The CPU frequency of each IoT device at time slot tn; Indicates The unloading ratio of IoT devices in time slot tn; Indicates The transmission power of an IoT device in time slot tn; Indicates that in time slot tn Whether the IoT device Unloading mission of a drone.

[0108] Among them, the strategy is the rule or method for the agent to choose actions in different states; the strategy determines how the agent chooses the best action based on the current state. Under a deterministic strategy, for each given state, the agent always chooses the same specific action. Under a stochastic strategy, the agent chooses actions based on a certain probability distribution, which increases flexibility and may explore more state-action pairs. In an embodiment of the present invention, a strategy is defined as the probability of choosing a specific action in a given state.

[0109] Among them, reward is the immediate feedback that the agent gets from the environment after performing an action. Reward is a quantitative indicator used to evaluate the effect of the action performed by the agent. A positive reward usually means that the action is beneficial to the goal, while a negative reward means that the action may be disadvantageous or need to be avoided. The goal of the agent is to maximize the cumulative reward it obtains by learning to select actions, which in the forest fire fighting scenario may mean improving fire fighting efficiency, reducing resource waste or speeding up response time. In the time slot tn, the reward is expressed by the following formula (7):

[0110] (7)

[0111] in, is the proportionality constant, is the weight, is the bias constant; represents the perception penalty index of the fire target at time slot tn; Represents the calculated offloading penalty index at time slot tn.

[0112] Among them, the TD3 algorithm is an online different-policy deep reinforcement learning algorithm for solving continuous control problems, which is improved on the DDPG (Deep Deterministic Policy Gradient, DDPG) algorithm. In essence, the TD3 algorithm incorporates the idea of ​​the Double Q-Learning algorithm into the DDPG algorithm.

[0113] Optionally, S6 uses the TD3 algorithm to optimize the task scheduling and resource allocation strategy in the UAV-assisted ISCC system model, including:

[0114] S61, initializing the policy network, the first Q value network, the second Q value network, the target network of the policy network, the target network of the first Q value network, and the target network of the second Q value network;

[0115] The target network parameters are set to be the same as their corresponding main network parameters.

[0116] S62, sample an action from the environment, execute the action, and obtain the next state and reward;

[0117] S63, storing the tuple of the next state into the experience replay pool;

[0118] S64. Randomly extract a small batch of tuples from the experience replay pool, which can be expressed as ;

[0119] S65. Calculate the target value according to the obtained small batch tuples;

[0120] The formula for calculating the target value can be expressed by the following formula (8):

[0121] (8)

[0122] in, Indicates the next state; The target network represents the policy network; Indicates reward; represents the target value; represents the target network of the first Q value network; represents the target network of the second Q value network; is a discount factor used to balance the relative importance of immediate rewards and future rewards, with a value range between 0 and 1; is the noise added for target policy smoothing.

[0123] S66. Update the parameters of the first Q value network and the parameters of the second Q value network by minimizing the loss function according to the target value;

[0124] Among them, updating the parameters of the first Q value network and the parameters of the second Q value network can be expressed by the following formula (9):

[0125] (9)

[0126] in, represents the loss function of the first Q value network and the second Q value network; M represents the size of the sample or batch, that is, the number of samples drawn from the experience replay buffer in one parameter update. ; Indicates the current state; Indicates action; represents the Q value network, j=1 is the first Q value network; j=2 is the second Q value network.

[0127] S67, updating the parameters of the strategy network every several steps according to the number of times the parameters of the first Q value network and the parameters of the second Q value network are updated;

[0128] The process of updating the parameters of the policy network can be expressed by the following formula (10):

[0129] (10)

[0130] in, Indicates a given state The next action, Represents the objective function of the policy network Parameters The gradient of Represents the policy network parameters The gradient of Represents the gradient of the Q-value network to A.

[0131] S68, updating the parameters of the target network simultaneously according to the parameters of the updated strategy network;

[0132] The target network includes: a target network of the strategy network, a target network of the first Q value network, and a target network of the second Q value network;

[0133] The process of updating the parameters of the target network can be expressed by the following formulas (11) and (12):

[0134] (11)

[0135] (12)

[0136] in, represents the learning rate, represents the parameters of the policy network, represents the parameters of the target policy network, represents the parameters of the j-th target Q network, represents the parameters of the j-th Q network.

[0137] S69, soft updating the target network according to the parameters of the updated target network;

[0138] The process of soft updating the target network can be expressed by the following formulas (13) and (14):

[0139] (13)

[0140] (14)

[0141] in, Indicates the update rate; The target network represents the policy network; represents the policy network; A target network representing the first Q value network and the second Q value network; Represents the first Q value network and the second Q value network.

[0142] S70. Repeat steps S62-S68 until the algorithm reaches a preset convergence value and stops.

[0143] In a feasible implementation, Table 1 shows a joint task scheduling and resource allocation algorithm based on deep reinforcement learning; Figure 3 Shown is a flow chart of the forest fire fighting algorithm based on TD3.

[0144] Table 1

[0145]

[0146] In a feasible implementation, an embodiment of the present invention uses synthetic data to construct a simulation model for a forest fire fighting scenario. On this basis, it will be evaluated whether the algorithm of the proposed drone-assisted ISCC system can achieve the expected results, and ensure that it exhibits efficient task scheduling and resource allocation capabilities in a simulated forest fire environment, which can verify the effectiveness of the algorithm in handling emergency fire fighting tasks. In the context of forest fire fighting, an embodiment of the present invention constructs a smaller-scale simulation scenario, which is set in a rectangular area and deploys three drones to perform auxiliary ISCC tasks, simulating a periodic task and dividing it into TN=100 time slots to facilitate detailed analysis and evaluation of the drone's actions and decisions in each time slot. In order to ensure the safety of drones when performing tasks and avoid collisions with trees or other obstacles on the ground, an embodiment of the present invention sets a safe flight altitude range for all drones. . In the simulation area, 10 IoT devices are deployed to collect key environmental data, such as temperature, humidity, and wind speed. Environmental data is essential for predicting the spread of fire and formulating firefighting strategies. The embodiment of the present invention sets four sensing targets, which may include specific terrain features or potential fire sources that need to be monitored. The location and characteristics of the sensing targets will be considered in detail in the simulation to evaluate the perception capabilities of the drone. The IoT devices and sensing targets are located on the ground, so there are The computing task size is randomly distributed between 20kb and 30kb. The CPU cycles required to process a computing task bit are randomly distributed between 500cyc / bit and 1000cyc / bit. The maximum delay threshold is randomly distributed between 40ms and 60ms. If any computing task fails, it will be assigned a delay of 80ms. Other parameter settings are shown in Table 2.

[0147] Table 2

[0148]

[0149] Among them, in the simulation scenario of forest fire fighting, the change of the objective function was observed through the iterative process, such as Figure 4 As shown in the figure. It can be clearly seen from the figure that after 10,000 iterations, the curve of the objective function value generally shows a trend of first rapidly decreasing and then stabilizing, which further confirms the effectiveness of the proposed algorithm. Specifically, in the first few thousand iterations, the objective function value decreased significantly, indicating that the algorithm can quickly adapt to the specific needs of forest fire fighting scenarios and effectively find better task scheduling and resource allocation strategies. The rapid downward trend shows that the algorithm can learn and understand the environment in a short time, thereby providing an efficient solution for the UAV-assisted ISCC system in forest fire fighting. As the iterations continue, the curve of the objective function value gradually becomes stable, indicating that the algorithm has gradually approached the optimal solution and can maintain this performance level in subsequent iterations. The trend of rapid decrease first and then stabilization verifies the effectiveness and stability of the TD3 algorithm in dealing with the problem of UAV-assisted ISCC system in forest fire fighting task scheduling and resource allocation.

[0150] Among them, Figure 5 The cumulative reward item shows an increasing trend as the number of iterations increases. This phenomenon shows that the strategy of the adopted algorithm is gradually becoming more efficient in the process of continuous learning and self-improvement, thereby improving the performance of task scheduling and resource allocation. In the early stages of iteration, the algorithm may still be exploring effective strategies, but as experience accumulates, it begins to quickly adapt to the complex environment of forest fire fighting and finds more appropriate task allocation and resource utilization methods. As the number of iterations continues to increase, the algorithm shows stronger adaptability and flexibility, and can more accurately predict the development of the fire and respond quickly. The embodiments of the present invention can better handle the computing and perception tasks in the UAV-assisted ISCC system, especially in the changeable and urgent forest fire situations.

[0151] The continuous growth of the cumulative reward can verify the practicality and convergence of the algorithm in synthetic scenarios, providing confidence and basis for applying the algorithm to real-world forest firefighting tasks in the future; through iterative learning and optimization, the algorithm can ensure that the drone can achieve the highest efficiency and effect in both computational offloading and environmental perception when performing firefighting tasks, thus providing strong support for the success of firefighting operations. In order to more intuitively demonstrate the operation of drones in forest firefighting operations, such as Figure 6 and Figure 7The visualization of the drone flight trajectory is simulated in the video, including two-dimensional and three-dimensional views. During the set service time, three drones performed flight operations above the IoT devices in the forest. They played a dual role: on the one hand, they provided computing offload services and assisted in processing large amounts of data from IoT devices; on the other hand, they hovered over multiple sensing target areas that needed to be monitored and performed environmental perception tasks to enhance real-time monitoring of potential fire risks. The drones fully utilized their advantages of mobility and flexibility, and were able to quickly and efficiently transfer between different mission points, ensuring that the IoT devices could transmit data to the drones for processing in a timely manner, while continuously monitoring key areas in the forest. Flexible task scheduling and resource allocation strategies enable drones to quickly respond to the complex and changing situations of forest fires, and to adjust flight paths and monitoring focus in a timely manner to adapt to real-time changes in the fire environment.

[0152] The embodiment of the present invention first builds a UAV-assisted ISCC system scenario; according to the UAV-assisted ISCC system scenario, a UAV-assisted ISCC system model is constructed; according to the UAV-assisted ISCC system model, the total delay and energy consumption of the UAV-assisted ISCC system model to complete the task are determined; secondly, according to the total delay and energy consumption, the optimization target of the UAV-assisted ISCC system model is constructed; according to the optimization target, the optimization problem of task scheduling and resource allocation in the UAV-assisted ISCC system model is constructed; finally, the optimization problem is modeled as a Markov decision process, and the TD3 algorithm is used to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

[0153] The embodiment of the present invention constructs an optimization model for the applicability of uplink ISCC in processing computationally intensive, data-diverse and delay-sensitive forest firefighting tasks, and can focus on minimizing the weighted sum of the computational offloading penalty index and the perception penalty index, while taking into account a variety of practical operational constraints including feasible flight areas and UAV energy constraints, and can optimize the efficiency and effectiveness of uplink ISCC; the embodiment of the present invention reconstructs the task scheduling and resource allocation problems into a Markov decision process, and uses the TD3 algorithm to process the problems of joint scheduling and resource allocation of tasks in a UAV-assisted ISCC system, which can effectively improve the task processing speed and environmental perception quality; the embodiment of the present invention can provide powerful air support for forest firefighting, enhance the real-time monitoring capability of the fire situation, the data processing speed and the optimal resource allocation, and improve the response speed and success rate of firefighting operations.

[0154] Figure 8The invention is a block diagram of a device for allocating resources assisted by UAVs and integrated with telepathy and computing for forest fire fighting according to an exemplary embodiment. The device is used in a method for allocating resources assisted by UAVs and integrated with telepathy and computing for forest fire fighting. Figure 8 The device includes a first construction unit 310, a second construction unit 320, a determination unit 330, a third construction unit 340, a fourth construction unit 350 and an acquisition unit 360. Among them:

[0155] The first construction unit 310 is used to build a UAV-assisted ISCC system scenario;

[0156] A second construction unit 320 is used to construct a UAV-assisted ISCC system model according to the UAV-assisted ISCC system scenario;

[0157] A determination unit 330 is used to determine the total delay and energy consumption of the UAV-assisted ISCC system model to complete the task according to the UAV-assisted ISCC system model;

[0158] A third construction unit 340 is used to construct an optimization target of the UAV-assisted ISCC system model according to the total delay and energy consumption;

[0159] The fourth construction unit 350 is used to construct the optimization problem of task scheduling and resource allocation in the UAV-assisted ISCC system model according to the optimization target;

[0160] The acquisition unit 360 is used to model the optimization problem as a Markov decision process, and use the TD3 algorithm to optimize the task scheduling and resource allocation strategy in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

[0161] Optionally, the drone-assisted ISCC system scenario includes: a base station, an IoT device, a sensing target, and a drone;

[0162] Wherein, the base station is used to receive the result of the drone processing the computing task;

[0163] The IoT device is used to collect environmental information, generate tasks, and send the tasks to the drone; the IoT device is also used to communicate with the drone and coordinate task offloading;

[0164] The sensing target is used to provide a sensing task for the UAV;

[0165] The drone is used to collect and aggregate information from IoT devices.

[0166] Optionally, the total delay of the UAV-assisted ISCC system model to complete the task includes: local delay, transmission delay and UAV calculation delay;

[0167] The local delay is determined by the local computing amount and the computing speed of the IoT device; the local computing amount is the data size of the computing task that is not offloaded to the drone;

[0168] wherein the transmission delay depends on the amount of data unloaded and the data rate of transmission; wherein the data rate of transmission is related to the available bandwidth allocated to each IoT device, the transmission power of the IoT device, the channel power gain between the IoT device and the drone, the interference term, and the power of the noise;

[0169] The calculation delay of the UAV is determined by the amount of offloaded calculations and the calculation rate of the UAV.

[0170] Optionally, the energy consumption of the drone-assisted ISCC system model to complete the task includes: the energy consumption of the IoT device and the energy consumption of the drone;

[0171] Among them, the energy consumption of IoT devices includes: the transmission energy of IoT devices and the computing energy of IoT devices;

[0172] The transmission energy of the IoT device is the product of the transmission power of the IoT device and the transmission delay of the IoT device;

[0173] The computing energy of the IoT device is the product of a constant related to the chip structure of the IoT device, the square of the CPU frequency of the IoT device, and the local computing delay;

[0174] Among them, the energy consumption of the drone includes: mission calculation energy consumption, fire target perception energy consumption and propulsion energy consumption.

[0175] Optionally, the optimization objective of the UAV-assisted ISCC system model includes: calculating an unloading penalty index and a perception penalty index.

[0176] Optionally, the TD3 algorithm is used to optimize the task scheduling and resource allocation strategy in the UAV-assisted ISCC system model, including:

[0177] (1) Initialize the policy network, the first Q value network, the second Q value network, the target network of the policy network, the target network of the first Q value network, and the target network of the second Q value network;

[0178] (2) Sample an action from the environment and execute it to obtain the next state and reward;

[0179] (3) Store the tuple of the next state into the experience replay pool;

[0180] (4) Randomly extract a small batch of tuples from the experience replay pool;

[0181] (5) Calculate the target value based on the obtained mini-batch tuples;

[0182] (6) According to the target value, update the parameters of the first Q value network and the parameters of the second Q value network by minimizing the loss function;

[0183] (7) updating the parameters of the policy network every several steps according to the number of times the parameters of the first Q value network and the parameters of the second Q value network are updated;

[0184] (8) updating the parameters of the target network simultaneously according to the parameters of the updated policy network; wherein the target network includes: a target network of the policy network, a target network of the first Q value network, and a target network of the second Q value network;

[0185] (9) Soft-update the target network according to the parameters of the updated target network;

[0186] (10) Repeat steps (2)-(10) until the algorithm reaches the preset convergence value and stops.

[0187] The embodiment of the present invention first builds a UAV-assisted ISCC system scenario; according to the UAV-assisted ISCC system scenario, a UAV-assisted ISCC system model is constructed; according to the UAV-assisted ISCC system model, the total delay and energy consumption of the UAV-assisted ISCC system model to complete the task are determined; secondly, according to the total delay and energy consumption, the optimization target of the UAV-assisted ISCC system model is constructed; according to the optimization target, the optimization problem of task scheduling and resource allocation in the UAV-assisted ISCC system model is constructed; finally, the optimization problem is modeled as a Markov decision process, and the TD3 algorithm is used to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

[0188] The embodiment of the present invention constructs an optimization model for the applicability of uplink ISCC in processing computationally intensive, data-diverse and delay-sensitive forest firefighting tasks, and can focus on minimizing the weighted sum of the computational offloading penalty index and the perception penalty index, while taking into account a variety of practical operational constraints including feasible flight areas and UAV energy constraints, and can optimize the efficiency and effectiveness of uplink ISCC; the embodiment of the present invention reconstructs the task scheduling and resource allocation problems into a Markov decision process, and uses the TD3 algorithm to process the problems of joint scheduling and resource allocation of tasks in a UAV-assisted ISCC system, which can effectively improve the task processing speed and environmental perception quality; the embodiment of the present invention can provide powerful air support for forest firefighting, enhance the real-time monitoring capability of the fire situation, the data processing speed and the optimal resource allocation, and improve the response speed and success rate of firefighting operations.

[0189] Fig. 9 FIG. 1 is a schematic diagram of a UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting provided by an embodiment of the present invention. Fig. 9 As shown, the UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting may include the above Figure 8 The shown device for allocating resources with integrated telepathy and computing assisted by drones for forest firefighting. Optionally, the device for allocating resources with integrated telepathy and computing assisted by drones for forest firefighting 410 may include a first processor 2001 .

[0190] Optionally, the UAV-assisted telepathic computing integrated resource allocation device 410 for forest fire fighting may also include a memory 2002 and a transceiver 2003 .

[0191] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0192] Combine the following Fig. 9 The components of the UAV-assisted telepathic computing integrated resource allocation device 410 for forest fire fighting are specifically introduced as follows:

[0193] The first processor 2001 is the control center of the UAV-assisted telepathic computing integrated resource allocation device 410 for forest fire fighting, and can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0194] Optionally, the first processor 2001 can execute various functions of the UAV-assisted synaesthesia-computing integrated resource allocation device 410 for forest fire fighting by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0195] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Fig. 9 CPU0 and CPU1 are shown in FIG.

[0196] In a specific implementation, as an embodiment, the UAV-assisted telepathic computing integrated resource allocation device 410 for forest fire fighting may also include multiple processors, such as Fig. 9 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0197] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0198] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently, and may be connected to the first processor 2001 through the interface circuit ( Fig. 9 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0199] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0200] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Fig. 9 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0201] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or can exist independently, and assist the interface circuit ( Fig. 9 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0202] It should be noted that Fig. 9 The structure of the UAV-assisted synaesthesia-computing integrated resource allocation device 410 for forest fire fighting shown in the figure does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0203] In addition, the technical effects of the UAV-assisted telepathic computing integrated resource allocation device 410 for forest fire fighting can refer to the technical effects of the UAV-assisted telepathic computing integrated resource allocation method for forest fire fighting described in the above method embodiment, and will not be repeated here.

[0204] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0205] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0206] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0207] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0208] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0209] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0210] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0211] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0212] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0213] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0214] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0215] If the functions are implemented in the form of software functional units and sold or used as independent products, they 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 the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0216] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A UAV-assisted synaesthesia-computing integrated resource allocation method for forest fire fighting, characterized in that: The method comprises: S1. Build a UAV-assisted ISCC system scenario; S2. constructing a UAV-assisted ISCC system model according to the UAV-assisted ISCC system scenario; S3. Determine the total delay and energy consumption of the UAV-assisted ISCC system model to complete the task according to the UAV-assisted ISCC system model; S4. constructing an optimization target of a UAV-assisted ISCC system model according to the total delay and energy consumption; S5. According to the optimization goal, construct the optimization problem of task scheduling and resource allocation in the UAV-assisted ISCC system model; S6. Model the optimization problem as a Markov decision process, and use the TD3 algorithm to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

2. The method for allocating resources based on UAV-assisted telepathy and computing for forest firefighting according to claim 1 is characterized in that: The UAV-assisted ISCC system scenario includes: base stations, IoT devices, sensing targets, and UAVs; Wherein, the base station is used to receive the result of the drone processing the computing task; The IoT device is used to collect environmental information, generate tasks, and send the tasks to the drone; the IoT device is also used to communicate with the drone and coordinate task offloading; The sensing target is used to provide a sensing task for the UAV; The drone is used to collect and aggregate information from IoT devices.

3. The method for allocating resources based on UAV-assisted telepathy and computing for forest firefighting according to claim 1, characterized in that: The total delay of the UAV-assisted ISCC system model of S3 to complete the task includes: local delay, transmission delay and UAV calculation delay; The local delay is determined by the local computing amount and the computing speed of the IoT device; the local computing amount is the data size of the computing task that is not offloaded to the drone; wherein the transmission delay depends on the amount of data unloaded and the data rate of transmission; wherein the data rate of transmission is related to the available bandwidth allocated to each IoT device, the transmission power of the IoT device, the channel power gain between the IoT device and the drone, the interference term, and the power of the noise; The calculation delay of the UAV is determined by the amount of offloaded calculations and the calculation rate of the UAV.

4. The method for allocating resources based on UAV-assisted telepathy and computing for forest firefighting according to claim 1, characterized in that: The energy consumption of the UAV-assisted ISCC system model of S3 to complete the task includes: the energy consumption of the IoT device and the energy consumption of the UAV; Among them, the energy consumption of IoT devices includes: the transmission energy of IoT devices and the computing energy of IoT devices; The transmission energy of the IoT device is the product of the transmission power of the IoT device and the transmission delay of the IoT device; The computing energy of the IoT device is the product of a constant related to the chip structure of the IoT device, the square of the CPU frequency of the IoT device, and the local computing delay; Among them, the energy consumption of the drone includes: mission calculation energy consumption, fire target perception energy consumption and propulsion energy consumption.

5. The method for allocating resources based on UAV-assisted telepathy and computing for forest firefighting according to claim 1, characterized in that: The optimization objectives of the S4 UAV-assisted ISCC system model include: calculating an unloading penalty index and a perception penalty index.

6. The method for allocating resources based on UAV-assisted telepathy and computing for forest firefighting according to claim 1, characterized in that: The S6 uses the TD3 algorithm to optimize the task scheduling and resource allocation strategy in the UAV-assisted ISCC system model, including: S61, initializing the policy network, the first Q value network, the second Q value network, the target network of the policy network, the target network of the first Q value network, and the target network of the second Q value network; S62, sample an action from the environment, execute the action, and obtain the next state and reward; S63, storing the tuple of the next state into the experience replay pool; S64, randomly extract a small batch of tuples from the experience replay pool; S65. Calculate the target value according to the obtained small batch tuples; S66. Update the parameters of the first Q value network and the parameters of the second Q value network by minimizing the loss function according to the target value; S67, updating the parameters of the strategy network every several steps according to the number of times the parameters of the first Q value network and the parameters of the second Q value network are updated; S68, according to the parameters of the updated policy network, simultaneously update the parameters of the target network; wherein the target network includes: the target network of the policy network, the target network of the first Q value network and the target network of the second Q value network; S69, soft updating the target network according to the parameters of the updated target network; S70. Repeat steps S62-S68 until the algorithm reaches a preset convergence value and stops.

7. A UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting, the UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting is used to implement the UAV-assisted telepathic computing integrated resource allocation method for forest fire fighting as claimed in any one of claims 1 to 6, characterized in that: The device comprises: The first building unit is used to build the UAV-assisted ISCC system scenario; A second construction unit is used to construct a UAV-assisted ISCC system model according to the UAV-assisted ISCC system scenario; a determination unit, configured to determine, according to the UAV-assisted ISCC system model, a total delay and energy consumption of the UAV-assisted ISCC system model in completing a task; A third construction unit is used to construct an optimization target of the UAV-assisted ISCC system model according to the total delay and energy consumption; A fourth construction unit is used to construct an optimization problem of task scheduling and resource allocation in a UAV-assisted ISCC system model according to the optimization target; The acquisition unit is used to model the optimization problem as a Markov decision process, and use the TD3 algorithm to optimize the task scheduling and resource allocation strategies in the UAV-assisted ISCC system model to obtain the optimal task scheduling and resource allocation solution.

8. The UAV-assisted telepathic computing integrated resource allocation device for forest firefighting according to claim 7 is characterized in that: The UAV-assisted ISCC system scenario includes: base stations, IoT devices, sensing targets, and UAVs; Wherein, the base station is used to receive the result of the drone processing the computing task; The IoT device is used to collect environmental information, generate tasks, and send the tasks to the drone; the IoT device is also used to communicate with the drone and coordinate task offloading; The sensing target is used to provide a sensing task for the UAV; The drone is used to collect and aggregate information from IoT devices.

9. A UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting, characterized in that: The UAV-assisted telepathic computing integrated resource allocation device for forest fire fighting includes: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 6.

Images