Low-altitude edge network fault-tolerant task migration and dnn adaptive segmentation method

Abstract

The application discloses a low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method, which comprises the following steps: constructing a multi-unmanned aerial vehicle (UAV) assisted mobile edge computing (MEC) system, performing DNN task division through a DNN adaptive division strategy; constructing a fault migration model to migrate the unfinished DNN tasks on the failed UAV to normal UAVs; reconstructing the minimum weighted energy consumption problem of the multi-UAV assisted MEC system into a Markov decision process, learning an optimal strategy through interaction with the environment; constructing a DKSAC-PER joint optimization framework, optimizing transmission power through a Dirichlet transformation, performing calculation resource allocation optimization through a Lagrange multiplier method, calculating the reward value of the current step through a SAC-PER algorithm and updating network parameters, and solving a complex mixed decision space. The application can autonomously adjust the flight trajectories of the remaining UAVs and redistribute the calculation load, greatly improving the survival ability of the system in a harsh environment.

Description

Technical Field

[0001] This invention relates to the field of mobile edge computing technology, and in particular to a fault-resistant task migration and DNN adaptive segmentation method for low-altitude edge networks. Background Technology

[0002] With the development of the low-altitude economy, the improvement of low-altitude intelligent network infrastructure, and the continuous advancement of 6G technology, tasks based on deep neural networks (DNNs) are widely used in various industries. However, such tasks are usually computationally intensive and latency-sensitive, and their high computational load and low latency requirements pose significant challenges to the limited computing power and battery life of mobile devices (MDs).

[0003] To address the insufficient computing power of mobile devices, DNN network segmentation technology has been proposed. Leveraging the hierarchical structure of DNN models, they are divided into multiple parts. The computationally intensive deep networks are partially offloaded through deployed edge servers, with only a small amount of computation remaining locally. In complex urban or wilderness environments, the channel link between ground users and base stations is easily blocked by buildings or obstacles, leading to non-line-of-sight (NOS) transmission. As a key aerial node in low-altitude intelligent networks, unmanned aerial vehicles (UAVs), with their flexible deployment and NOS transmission capabilities, can act as aerial MEC servers to solve this problem.

[0004] However, drones may malfunction and leave the service network during missions due to factors such as battery depletion, communication interruption, hardware failure, and severe weather. This unexpected drone exit disrupts ongoing communication and computing tasks, leading to incomplete DNN inference and a sharp decline in performance, thus affecting the overall service continuity and mission completion rate of the low-altitude intelligent network. Furthermore, existing technologies largely focus on task offloading, trajectory optimization, and resource allocation, with less consideration given to robust design in the event of drone exit, and a lack of research on dynamic migration and reallocation strategies for DNN tasks after drone exit. Summary of the Invention

[0005] The problem this invention aims to solve is to provide a fault-tolerant task migration and DNN adaptive segmentation method for low-altitude edge networks. This method combines adaptive DNN segmentation and a failed UAV task migration mechanism to increase the system's fault tolerance. It uses the weighted energy consumption in a multi-UAV assisted MEC system as a performance indicator to achieve joint optimization of DNN partitioning decisions, computational task migration, UAV computational resource allocation, and UAV trajectories. Furthermore, it reconstructs the weighted energy consumption minimization problem in a multi-UAV assisted MEC system as a Markov decision process. The method integrates the Tinkelbach transform, Lagrange multiplier method, and a soft actor-commentator algorithm with priority experience replay through the DKSAC-PER joint optimization framework to efficiently solve complex hybrid decision spaces.

[0006] This invention adopts the following technical solution: a method for fault-resistant task transfer and DNN adaptive segmentation in low-altitude edge networks, comprising the following steps:

[0007] Step 1: Construct a multi-UAV assisted MEC system, consisting of a ground mobile device layer and an airborne UAV edge layer. The positions of the UAVs and mobile devices are modeled using a three-dimensional Cartesian coordinate system.

[0008] Step 2: Treat the computing tasks generated by each mobile device in the multi-UAV assisted MEC system as DNN inference tasks, use weighted energy consumption as the performance index, and divide the DNN tasks through a DNN adaptive partitioning strategy.

[0009] Step 3: Construct a fault migration model. By defining UAV state variables and task migration decision variables, the unfinished DNN tasks on the failed UAV are migrated to the normal UAV.

[0010] Step 4: Reconstruct the weighted energy consumption minimization problem of the multi-UAV assisted MEC system into a Markov decision process, map the complex dynamic environment into the observation space of the reinforcement learning agent, and learn the optimal strategy through interaction with the environment.

[0011] Step 5: Construct the DKSAC-PER joint optimization framework to solve the hybrid decision space, including:

[0012] Step 5.1: Optimize the transmission power through the Tinkelbach transform. Introduce auxiliary variables to transform the non-convex problem into a convex optimization problem. Alternately update the transmission power and auxiliary variables until convergence is achieved, and obtain the optimal transmission power.

[0013] Step 5.2: Optimize the allocation of computing resources using the Lagrange multiplier method, introduce time delay constraints and UAV computing capacity constraints, derive the closed-form solution of the optimal computing resource allocation using KKT conditions, and determine the optimal computing resource allocation scheme.

[0014] Step 5.3: Calculate the reward value of the current step and update the network parameters using the SAC-PER algorithm to solve the complex mixed decision space;

[0015] Step 6: Embed the optimization of transmission power into each step of reinforcement learning training. The current association strategy, segmentation decision and trajectory optimization action are given by the Actor network. The value of the action is evaluated by the Critic network. A priority experience replay mechanism is introduced to improve sample efficiency. A weighted energy consumption minimization joint optimization strategy that can adaptively cope with dynamic environment and equipment failure is obtained.

[0016] The results are further applied to mobile edge computing networks assisted by multiple drones, especially in scenarios where drones fail due to power depletion or hardware malfunction. Task migration and adaptive DNN segmentation are used to ensure the continuity of DNN inference tasks and the robustness of the system.

[0017] As a preferred embodiment, in step 1, the multi-UAV assisted MEC system includes A drone equipped with a MEC server and A ground mobile device (MD) in this environment will complete the entire flight cycle. Divided into equal intervals There are 3 equal-sized time slots, each with a length of 1. The positions of drones and mobile devices are modeled using a three-dimensional Cartesian coordinate system.

[0018] Each ground mobile device generates a DNN-based computation task in each time slot. A mobile user can only be served by one UAV in the same time slot, while a UAV can serve multiple ground mobile devices in the same time slot. The computation task generated by each mobile device is a DNN inference task.

[0019] As a preferred embodiment, in step 2, the DNN adaptive partitioning strategy is based on There are k types of DNN models, where the k-th type of DNN model contains Layer, user set as Introducing DNN to partition decision variables The task is divided into two parts: Level 1 to Level 2. The layer is calculated locally, the first Layer to the first The layer is unloaded to the drone for computation.

[0020] As a preferred embodiment, in step 3, the fault migration model defines the UAV state variables. and task migration decision variables The unfinished DNN tasks on the failed drones are migrated to normal drones to ensure the integrity of the DNN tasks.

[0021] Furthermore, when At that time, it indicates that the drone In the time slot Normal operation, task migration is prohibited at this time; when The time indicates drone If a time slot fails (malfunctions), task migration is permitted.

[0022] If and only if At that time, mobile devices Unprocessed DNN task layers will be migrated to normal drones. Process it.

[0023] use Indicates the target drone The state when At that time, it indicates the target drone. The malfunction prevents the mission from being transferred to the failed drone; when At that time, it indicates the target drone. Normal, mission migration to target drone is permitted. .

[0024] As a preferred approach, in step 4, the system needs to acquire environmental status information in real time, including the task attributes of mobile devices, channel status, the three-dimensional position of the UAV, remaining battery power, and fault status indications. The weighted energy consumption minimization problem of the multi-UAV assisted MEC system is reconstructed as a Markov decision process for modeling, which is used to map the complex dynamic environment into the observation space of the reinforcement learning agent, enabling it to learn the optimal strategy through continuous interaction with the environment.

[0025] Furthermore, the Markov decision process is composed of quadruples. Composition, state space Includes: task size, UAV-MD correlation metrics, migration variables, UAV acceleration, UAV speed, and UAV position information; motion space. Define a hybrid action space, including discrete variables (DNN partitioning decision). UAV-MD association Task migration ) and continuous variables (UAV acceleration) ); reward function The design incorporates weighted total energy consumption and introduces penalties for collisions, boundary violations, timeouts, and speed and acceleration violations.

[0026] As a preferred embodiment, the DKSAC-PER joint optimization framework described in step 5 consists of three coupled steps: transmission power optimization based on the Tinkelbach transform, computational resource allocation optimization based on the Lagrange multiplier method, and joint optimization of UAV-MD correlation factors, task migration, DNN segmentation decision, and UAV trajectory based on the SAC-PER architecture.

[0027] In step 5.1, under the determined Markov decision, the Tinkelbach transform technique is applied to optimize the transmission power. With the goal of minimizing energy consumption, auxiliary variables are introduced to transform the non-convex problem into a convex optimization problem. The objective function is set and the transmission power and auxiliary variables are updated alternately until convergence is achieved, and the globally optimal transmission power solution is obtained. This greatly reduces the action space dimension of the deep reinforcement learning algorithm and improves the convergence accuracy.

[0028] In step 5.2, based on the transmission power determined in step 5.1, a Lagrangian function for computing resource allocation is constructed, and time delay constraints and UAV computing capacity constraints are introduced. The closed-form solution for optimal computing resource allocation is derived using the Karush-Kuhn-Tucker Conditions, and the optimal computing resource allocation scheme that satisfies the time delay and capacity constraints is obtained.

[0029] In step 5.3, based on the transmission power determined in step 5.1 and the computing resource allocation scheme determined in step 5.2, the optimized power is obtained through the SAC-PER algorithm. and computing resource frequency Substitute the environment into the calculation, calculate the reward value for the current step, optimize the remaining variables using a soft actor-critic network with priority experience replay, and update the network parameters. During training, calculate sample priority based on temporal difference error, prioritize sampling samples with large temporal difference errors, and correct bias using importance sampling weights.

[0030] As a preferred approach, in step 6, the optimization of transmission power and the optimization of computational resource allocation are embedded into each step of reinforcement learning training.

[0031] After the Actor network provides the current association strategy, segmentation decision, and trajectory optimization, these variables are fixed, and actions such as DNN partitioning, UAV-MD association, task migration, and UAV trajectory control are output. The Critic network evaluates the value of the actions and introduces maximum entropy to enhance the exploration capability and prevent getting trapped in local optima. Finally, it outputs the converged Actor network parameters and the corresponding optimal joint control strategy after iterative training. This guides the UAV MEC system to perform DNN task segmentation, mobile device association, task migration, and UAV trajectory planning in each time slot, so as to minimize the weighted energy consumption of the system while meeting the time delay constraints and ensuring fault robustness.

[0032] Compared with the prior art, the present invention, employing the above technical solution, has the following technical effects:

[0033] 1. This invention introduces a fault-aware task migration mechanism. When the system detects that a drone has failed due to power depletion or hardware malfunction, it can adaptively migrate unfinished DNN tasks originally offloaded to the failed drone to other available drones. Simulation experiments show that in dynamic scenarios where drones fail, this invention can autonomously adjust the flight trajectories of the remaining drones and reallocate the computational load, ensuring the continuous execution of DNN inference tasks, avoiding complete service interruption due to single-point failures, and greatly improving the system's survivability in harsh environments.

[0034] 2. The DKSAC-PER joint optimization framework proposed in this invention decouples the complex mixed-integer nonlinear programming problem. On the one hand, it obtains the optimal solutions for transmission power and computational resources through the Tinkelbach transform and the Lagrange multiplier method, respectively, avoiding blind searching in the continuous high-dimensional action space by deep reinforcement learning. On the other hand, it proposes a priority experience replay mechanism based on the SAC algorithm, which assigns higher sampling priority to samples with larger temporal difference errors, enabling the agent to focus more on learning high-value experiences.

[0035] 3. The DKSAC-PER joint optimization framework constructed in this invention effectively overcomes the problems of service interruption, high energy consumption, and slow convergence speed of deep reinforcement learning algorithms in low-altitude edge networks and abnormal drone exit scenarios by jointly optimizing UAV-MD association, task migration, DNN segmentation, UAV trajectory, computing resource allocation, and transmission power.

[0036] 4. This invention uses an adaptive DNN partitioning strategy to dynamically determine the split point between local and edge processing of DNN tasks based on channel conditions and computing power, thus avoiding the resource waste caused by traditional "all offloading" or "random partitioning". Attached Figure Description

[0037] Figure 1 This is a schematic diagram of the multi-UAV assisted MEC system architecture of the present invention;

[0038] Figure 2 This is a flowchart of the SAC-PER algorithm of the present invention;

[0039] Figure 3 This is a flowchart of the DKSAC-PER algorithm of the present invention;

[0040] Figure 4This diagram illustrates a comparison of the convergence performance of the DKSAC-PER algorithm used in this invention with the stochastic ensemble double-Q learning algorithm and the soft actor-critic algorithm under the system model of this invention.

[0041] Figure 5 This is a schematic diagram illustrating the optimization of three-dimensional flight trajectories of multiple UAVs under dynamic fault scenarios in an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the application will be further described in detail below with reference to the accompanying drawings. The described embodiments are only a part of the embodiments involved in this invention. All non-innovative embodiments based on these embodiments by other researchers in the art are within the protection scope of this invention. Furthermore, the step numbers in the embodiments of this invention are only set for ease of explanation and do not limit the order of the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0043] In one embodiment of the present invention, a method for fault-resistant task migration and DNN adaptive segmentation in low-altitude edge networks specifically includes the following steps:

[0044] (a) Constructing a multi-UAV assisted MEC system model;

[0045] like Figure 1 As shown, the multi-UAV assisted MEC system consists of a ground-based mobile device layer and an airborne UAV edge layer, including... A drone (UAV) equipped with a MEC server and Each ground mobile device (MD) generates a DNN-based computational task in each time slot.

[0046] For ease of processing, this embodiment will cover the entire flight cycle. Divided into equal intervals There are 1 time slot, and the length of each time slot is 1. The positions of the UAV and MD are modeled using a three-dimensional Cartesian coordinate system. In the... The first time slot, the first The horizontal position of each MD is represented as , No. The position of each UAV is represented as The superscript T indicates transpose.

[0047] The movement of MD follows a Gauss-Markov model, and its velocity... and direction The update formula is:

[0048] ;

[0049] ;

[0050] in, and These represent the average velocity and direction, respectively. , This represents the degree of memory retention. This represents the random fluctuation of the speed update of the i-th mobile device during movement, following a mean and variance of [values ​​to be filled in]. Gaussian distribution; This represents the random fluctuation of the azimuth update of the i-th mobile device during motion engineering, following a mean and variance of [values ​​to be filled in]. The Gaussian distribution.

[0051] The trajectory of a UAV is affected by its flight speed and acceleration The control, and its position update formula is:

[0052] ;

[0053] Meanwhile, to ensure flight safety, the distance between any two drones must meet safety constraints:

[0054] ;

[0055] in, Indicates a collection of drones. Represents a set of time slots. Indicates time slot drones Location, Indicates time slot drones Location, This is a preset safe distance.

[0056] (ii) Dividing DNN tasks

[0057] To achieve flexible allocation of computational load, this embodiment employs a DNN adaptive partitioning strategy. Assume there are... K There are k types of DNN models, where the k-th type of DNN model contains Layer, let the user set of the k-th class DNN model be . ,in .

[0058] Introducing DNN to partition decision variables The task is divided into two parts: Level 1 to Level 2. The layer is calculated locally, the first Layer to the first The computational load of each layer of the DNN is offloaded to the UAV. (FLOPs) and output data volume (bits) are determined by the following formula based on the layer type (convolutional layer or fully connected layer):

[0059] ;

[0060] ;

[0061] in, Indicates the first A collection of convolutional layers in a DNN-like model. Indicates the first The collection of fully connected layers in a DNN-like model. Represents a convolutional layer Input the height of the feature map, Represents a convolutional layer Input the width of the feature map. Represents a convolutional layer Number of input channels, Represents a convolutional layer The number of output channels, Represents a convolutional layer The size of the convolution kernel, Represents a convolutional layer One-dimensional input size, Represents a convolutional layer One-dimensional output size, Memory usage per unit of data.

[0062] (III) Constructing a fault migration model

[0063] This embodiment introduces a binary variable to address potential drone malfunctions (such as battery depletion or hardware failure). This indicates the status of the drone.

[0064] If the first If a UAV malfunctions, the system activates the task migration mechanism:

[0065] ;

[0066] ;

[0067] Among them, when At that time, it indicates that the drone In the time slot Normal operation, task migration is prohibited at this time; when The time indicates drone If a time slot fails (malfunctions), task migration is permitted.

[0068] Denotes the task decision transition variable if and only if At that time, mobile devices Unprocessed DNN task layers will be migrated to normal UAV. Process it.

[0069] Indicates the target drone The state when At that time, it indicates the target drone. The malfunction prevents the mission from being transferred to the failed drone; when At that time, it indicates the target drone. Normal, mission migration to target drone is permitted. .

[0070] (iv) Markov Decision Process

[0071] To address the joint optimization problem in dynamic environments, this embodiment reconstructs the weighted energy consumption minimization problem of a multi-UAV assisted MEC system into a Markov Decision Process (MDP), consisting of quadruples. constitute.

[0072] state space In time slots ,state DNN tasks involving MD UAV flight speed UAV location MD-UAV transmission rate UAV inter-transmission rate and UAV remaining energy .

[0073] Action space :action It includes both discrete and continuous variables, specifically DNN partitioning decisions. UAV-MD correlation index Task migration decision and UAV flight acceleration .

[0074] reward function The objective is to maximize the cumulative reward, which means minimizing the system's weighted total energy consumption while satisfying constraints. The reward function is defined as the negative of the weighted total energy consumption minus multiple penalties.

[0075] ;

[0076] in, This represents the system's weighted total energy consumption. This represents the collision avoidance penalty function for drones. This represents the function that penalizes task timeouts. This represents the function that penalizes drones for crossing boundaries. This represents the penalty function for exceeding the maximum acceleration limit for the drone. This represents the maximum speed exceeding the limit penalty function.

[0077] Let be the state transition probability function, representing the system's state transition probability in the current time slot. In a state And perform the action Then, transition to the next state. The probability of.

[0078] (V) DKSAC-PER Hybrid Optimization Framework

[0079] To address the high dimensionality and convergence difficulties arising from mixed variables (discrete and continuous) in the action space, this embodiment proposes the DKSAC-PER algorithm framework, which decouples the optimization problem into the following three sub-problems:

[0080] 1. Transmission Power Optimization (Dinkelbach Transform): This problem aims to minimize energy consumption. It is a non-convex fractional programming problem, and the objective function is expressed as:

[0081] ;

[0082] in, The optimization objective is to seek the optimal. To minimize the function value, Indicates the UAV-MD correlation factor. Indicates mobile device Transmission power, Indicates the amount of data to be transmitted. Indicates channel bandwidth. Indicates channel gain. Indicates noise power. Indicates the minimum feasible transmission power. This indicates the maximum transmission power.

[0083] To solve the above-mentioned score problem, auxiliary variables are introduced. By using the Tinkelbach transform, the non-convex fractional programming power minimization problem is transformed into a subtractive parametric convex problem. The transformed objective function is expressed as:

[0084] .

[0085] 2. Computational resource allocation optimization (Lagrange multiplier method): Based on the given power and policy, construct the Lagrange function:

[0086] ;

[0087] in, Indicates in time slot drones Assigned to mobile devices The frequency of computational resources is the optimization variable in this formula; These are the Lagrange multipliers corresponding to the delay constraints, used to relax mobile devices. Maximum computational delay constraint; These are Lagrange multipliers corresponding to capacity constraints, used to relax unmanned aerial vehicles (UAVs). Maximum computational capacity constraint; Indicates mobile device In the time slot The latency limit for internal tasks to be processed on the drone; Indicates drone Maximum computing resource capacity; This represents the energy consumption coefficient parameter. ,in, This represents the effective capacitance coefficient of the CPU. This indicates the computational workload of the unloading task:

[0088] ;

[0089] in, Indicates the CPU's processing power. Indicates mobile device The DNN model The computational workload required for each layer Indicates mobile device The total number of layers in the DNN model.

[0090] Further utilize the KKT conditions to obtain the optimal computation frequency that satisfies the time delay constraint. The closed-form solution, based on the resource coordination state With capacity The relationship between them allows for adaptive adjustment of allocation strategies.

[0091] 3. Joint Strategy Optimization (SAC-PER):

[0092] The SAC-PER algorithm flow in this embodiment is as follows: Figure 2 As shown, it consists of three parts: the UAV MEC environment, the priority experience replay buffer, and the SAC agent.

[0093] In complex environments including drone failures, this architecture feeds back the optimized power and resource allocation results to the SAC agent, using the PER mechanism to filter high-value samples and drive the Actor-Critic network to continuously iterate. On one hand, the architecture updates the policy network (Actor) parameters by minimizing KL divergence to balance exploration and exploitation; on the other hand, it optimizes the critic network (Critic) based on Bellman residuals, including the main DNN, target DNN, critic 1, critic 2, etc., and uses a soft update mechanism to synchronize the target network parameters and ensure training stability. Finally, it outputs an optimal joint control strategy that can adaptively cope with drone failures and dynamic environments.

[0094] (vi) DKSAC-PER Algorithm Architecture

[0095] In the DKSAC-PER algorithm architecture described in this embodiment, the processing flow is as follows: Figure 3 As shown, the system first performs system initialization, and then enters a loop iteration process.

[0096] In each iteration: First, the current state is acquired, and actions are generated through the actor network. Next, based on the current state and the generated actions, transmission power and resource allocation are optimized sequentially to determine continuous control variables. Then, actions are executed and rewards are calculated to obtain environmental feedback. Finally, the network parameters are updated using the calculated rewards and experience samples. After the network update, the system performs parameter fusion and determines whether the training termination condition is met. If the termination condition is not met, the system returns to the "acquire current state" step for the next iteration. If the termination condition is met, training ends and the optimal policy is output to minimize the weighted energy consumption of the multi-UAV assisted MEC system.

[0097] Specifically, the temporal difference error for each sample is calculated. :

[0098] ;

[0099] in, Indicates the agent's state and perform actions Then, the feedback reward value obtained from the environment; This represents the discount factor, used to balance the weights of current rewards and future long-term rewards; The estimated future value is based on the target network's prediction of the state at the next time step. and actions Value estimation; The value of the current prediction is based on the current network's understanding of the current state. and Value estimate.

[0100] According to priority Non-uniform sampling is used to make the agent learn from experiences with large prediction errors first.

[0101] in, This indicates the sampling priority of the i-th sample in the experience pool; It represents a very small positive constant, used to prevent the sampling probability from becoming 0 when the time difference error is 0; Indicates the first The larger the absolute value of the temporal difference error of a sample, the higher the contribution of that sample to the model update. This represents the priority adjustment factor, with a value range of [value range missing]. Used to control the strength of priority, when This is considered uniform sampling.

[0102] Furthermore, the loss function of the Actor network incorporates policy entropy to encourage exploration:

[0103] ;

[0104] in, This represents the loss function of the Actor network, and the parameters of the Actor network are updated by minimizing this value. ; This represents the Q-value of the i-th Critic network output. Let be the expectation operator, representing the state sampled from the experience replay buffer. The expected value. Indicates according to the current strategy In state Actions obtained by downsampling The mathematical expectation, This indicates that according to the current Actor network policy Generate Actions . It is an adaptive temperature coefficient.

[0105] Simulation experiments show that the DKSAC-PER algorithm architecture proposed in this invention has significant advantages in handling fault-resistant task transfer and DNN adaptive segmentation tasks in multi-UAV assisted MEC systems. Figure 4 As shown, compared with the random ensemble double Q learning algorithm and the soft actor-critic algorithm, the method of this invention has a faster convergence speed (approximately 20k steps to converge) and can achieve the lowest average weighted energy consumption under different numbers of MDs and different transmission power constraints, proving its robustness and efficiency in dynamic fault environments.

[0106] In this embodiment of the invention, the optimization of three-dimensional flight trajectories of multiple UAVs under dynamic fault scenarios is performed, such as... Figure 5 As shown, in dynamic scenarios where drones malfunction, the method of this invention can autonomously adjust the flight trajectory of the remaining drones and redistribute the computational load, ensuring the continuous execution of DNN inference tasks, avoiding complete service interruption due to single point of failure, and greatly improving the system's survivability in harsh environments.

[0107] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A fault-resistant task transfer and DNN adaptive segmentation method for low-altitude edge networks, characterized in that, Includes the following steps: Step 1: Construct a multi-UAV assisted MEC system, consisting of a ground mobile device layer and an airborne UAV edge layer. The positions of the UAVs and mobile devices are modeled using a three-dimensional Cartesian coordinate system. Step 2: Treat the computing tasks generated by each mobile device in the multi-UAV assisted MEC system as DNN inference tasks, use weighted energy consumption as the performance index, and divide the DNN tasks through a DNN adaptive partitioning strategy. Step 3: Construct a fault migration model. By defining UAV state variables and task migration decision variables, the unfinished DNN tasks on the failed UAV are migrated to the normal UAV. Step 4: Reconstruct the weighted energy consumption minimization problem of the multi-UAV assisted MEC system into a Markov decision process, map the complex dynamic environment into the observation space of the reinforcement learning agent, and learn the optimal strategy through interaction with the environment. Step 5: Construct the DKSAC-PER joint optimization framework to solve the hybrid decision space, including: Step 5.1: Optimize the transmission power through the Tinkelbach transform. Introduce auxiliary variables to transform the non-convex problem into a convex optimization problem. Alternately update the transmission power and auxiliary variables until convergence is achieved, and obtain the optimal transmission power. Step 5.2: Optimize the allocation of computing resources using the Lagrange multiplier method, introduce time delay constraints and UAV computing capacity constraints, derive the closed-form solution of the optimal computing resource allocation using KKT conditions, and determine the optimal computing resource allocation scheme. Step 5.3: Calculate the reward value of the current step and update the network parameters using the SAC-PER algorithm to solve the complex mixed decision space; Step 6: Embed the optimization of transmission power into each step of reinforcement learning training. The current association strategy, segmentation decision and trajectory optimization action are given through the Actor network. The value of the action is evaluated through the Critic network. A priority experience replay mechanism is introduced to improve sample efficiency. A weighted energy consumption minimization joint optimization strategy that can adaptively cope with dynamic environment and equipment failure is obtained.

2. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 1, characterized in that, The multi-UAV assisted MEC system includes A drone equipped with a MEC server and A ground-based mobile device will cover the entire flight cycle. Divided into equal intervals There are 1 time slot, and the length of each time slot is 1. Each ground mobile device generates a DNN-based computational task in each time slot.

3. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 2, characterized in that, The positions of the UAV and mobile devices are modeled using a three-dimensional Cartesian coordinate system, as follows: The movement of the mobile device follows a Gauss-Markov model, the first... Mobile device time slots speed and direction The updated formula is: ； ； in, and These represent the average velocity and direction, respectively. , This represents the coefficient of memory retention. This represents the random fluctuation of the speed update of the i-th mobile device during movement, following a mean and variance of [values ​​to be filled in]. Gaussian distribution; This represents the random fluctuation of the azimuth update of the i-th mobile device during motion engineering, following a mean and variance of [values ​​to be filled in]. Gaussian distribution; No. The trajectory of a drone is affected by its flight speed. and acceleration The control and position update formula is as follows: ； The distance between any two drones satisfies the following safety constraint: ； in, Indicates a collection of drones. Represents a set of time slots. , They represent time slots respectively. drones , Location, This is a preset safe distance.

4. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 3, characterized in that, The DNN adaptive partitioning strategy is based on There are k types of DNN models, and the k-th type of DNN model contains Layer, user set as Introducing DNN to partition decision variables The task is divided into two parts: Level 1 to Level 2. The layer is calculated locally, the first Layer to the first Layer offload to drone computing; The computational cost of each layer of a DNN and output data volume The layer type is determined by the following formula: ； ； in, Indicates the first A collection of convolutional layers in a DNN-like model. Indicates the first The collection of fully connected layers in a DNN-like model. Represents a convolutional layer Input the height of the feature map, Represents a convolutional layer Input the width of the feature map. , Representing convolutional layers Number of input channels and number of output channels Represents a convolutional layer The size of the convolution kernel, , Representing convolutional layers One-dimensional input size and one-dimensional output size, Memory usage per unit of data.

5. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 3, characterized in that, The fault migration model introduces binary variables. Indicates the drone's status, when At that time, it indicates that the drone In the time slot In case of a failure, activate task migration: ； ； in, Represents a set of mobile devices. Denotes the task decision transition variable if and only if At that time, mobile devices Unprocessed DNN task layers were migrated to normal drones. Process it; Indicates the target drone The state when At that time, it indicates the target drone. The malfunction prevents the mission from being transferred to the failed drone; when At that time, it indicates the target drone. Normal, mission migration to target drone is permitted. .

6. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 5, characterized in that, The Markov decision process is composed of quadruples. constitute: For state space: in time slot ,state DNN tasks including mobile devices The flight speed of drones drone location Mobile device-drone transmission rate Inter-UAV transmission rate and the remaining energy of the drone ; For action space: in time slots ,action Includes both discrete and continuous variables, specifically: DNN partitioning decision. Drone-Mobile Device Correlation Indicators Task decision transfer variables and drone flight acceleration ; The reward function is defined as the negative of the weighted total energy consumption minus multiple penalties: ； in, This represents the system's weighted total energy consumption. This represents the collision avoidance penalty function for drones. This represents the function that penalizes task timeouts. This represents the function that penalizes drones for crossing boundaries. This represents the penalty function for exceeding the maximum acceleration limit for the drone. This represents the maximum speed exceeding the limit penalty function; Let be the state transition probability function, representing the system's state transition probability in the current time slot. In a state And perform the action Then, transition to the next state. The probability of.

7. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 6, characterized in that, The transmission power can be optimized using the Tinkelbach transform, as follows: With the goal of minimizing energy consumption, transmission power optimization is treated as a non-convex fractional programming problem, and the objective function is expressed as: ； in, The optimization objective is to seek the optimal transmission power. Minimize the function value; Indicates the drone-mobile device association factor. Indicates mobile device Transmission power, Indicates the amount of data to be transmitted. Indicates channel bandwidth. Indicates channel gain. Indicates noise power. Indicates the minimum feasible transmission power. Indicates the maximum transmission power; Introducing auxiliary variables The power minimization problem in non-convex fractional programming form is transformed into a parameterized convex problem in subtraction form using the Tinkelbach transform. The transformed objective function is: 。 8. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 7, characterized in that, The Lagrange multiplier method is used to optimize computational resource allocation, as follows: Based on the given power and policy, construct the Lagrange function: ； in, Indicates in time slot drones Assigned to mobile devices The frequency of computing resources; These are the Lagrange multipliers corresponding to the delay constraints, used to relax mobile devices. Maximum computational delay constraint; These are Lagrange multipliers corresponding to capacity constraints, used to relax unmanned aerial vehicles (UAVs). Maximum computational capacity constraint; This represents the energy consumption coefficient parameter; Indicates mobile device In the time slot The latency limit for internal tasks to be processed on the drone; Indicates drone Maximum computing resource capacity; This indicates the computational workload of the unloading task; The optimal computational frequency that satisfies the time delay constraint is obtained using the KKT conditions. The closed-form solution, based on the resource coordination state With capacity The relationship between them allows for adaptive adjustment of allocation strategies.

9. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 8, characterized in that, The optimized power is obtained through the SAC-PER algorithm. and computing resource frequency Substitute the environment, calculate the reward value for the current step, and use a soft actor-critic network with priority experience replay to optimize the remaining variables, including: mobile device association decisions, task migration decisions, DNN segmentation decisions, and drone flight trajectories, to complete the joint optimization.

10. The low-altitude edge network fault-resistant task migration and DNN adaptive segmentation method according to claim 6, characterized in that, In the DKSAC-PER joint optimization framework, the agent outputs the action distribution through the Actor network, the Critic network evaluates the action value, and a priority experience replay mechanism is introduced to improve sample efficiency, as follows: Calculate the temporal difference error for each sample. : ； in, Indicates the agent's state Next action The feedback reward value obtained from the environment afterwards; This represents the discount factor, used to balance the weights of current rewards and future long-term rewards; The estimated future value is based on the target network's prediction of the state at the next time step. and actions Value estimation; The value of the current prediction is based on the current network's understanding of the current state. and Value estimation; According to priority Non-uniform sampling is used to allow the agent to learn from experiences with large prediction errors first. The loss function of the Actor network encourages exploration by incorporating policy entropy. ； in, Indicates the first in the experience pool Sampling priority of each sample This represents a very small positive constant to prevent the sampling probability from being 0. Indicates the first The temporal difference error of each sample, Indicates the priority adjustment factor; The loss function of the Actor network is defined by minimizing... Update the parameters of the Actor network ; This represents the Q-value of the output of the i-th Critic network; Let be the expectation operator, representing the state sampled from the experience replay buffer. Expected value; Indicates according to the current strategy In state Actions obtained by downsampling The mathematical expectation; It is an adaptive temperature coefficient.

Images