A forest fire monitoring method based on unmanned aerial vehicle assisted edge computing

Abstract

The application provides a forest fire monitoring method based on unmanned aerial vehicle auxiliary edge calculation, and belongs to the technical field of forest fire detection. The model is constructed by taking the maximum calculation time delay in all unmanned aerial vehicles and the minimum maximum flight energy consumption in the unmanned aerial vehicles as the objective function, and taking the two-dimensional region interval, the unmanned aerial vehicle hovering height interval, the sensor node transmission power interval, the unmanned aerial vehicle allocation to the sensor node calculation resource interval, and the delay threshold as the constraint conditions. The genetic algorithm, the grey wolf algorithm and the sea squirt algorithm are used to update the continuous solution part of the model, the discrete solution part is updated in a random manner, the optimal solution is selected according to the Pareto dominance principle, and the unmanned aerial vehicle hovering position with the minimum flight energy consumption and the minimum time delay is obtained. The calculation efficiency and the transmission efficiency of the sensor node are improved through the unmanned aerial vehicle, and the minimum calculation time delay hovering position is selected to further improve the data calculation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of forest fire detection, and in particular to a forest fire monitoring method based on drone-assisted edge computing. Background Art

[0002] Forest fires can cause severe damage to forest ecosystems, leading to a decrease in forest biomass, reduced productivity, and even casualties among humans and livestock. Therefore, effective forest fire monitoring is crucial for forest management.

[0003] To monitor forest fires in real time, existing technologies deploy multiple sensor nodes throughout the forest. Computational latency of sensor nodes is a key metric, impacting the response time of forest fire monitoring. However, in real-world detection scenarios, sensor nodes have limited computing power and are located far from central computing equipment, resulting in significant computational latency, which can affect fire detection results.

[0004] Therefore, a forest fire detection method that can reduce the computational delay of sensor nodes is needed. Summary of the Invention

[0005] In view of this, the present invention provides a forest fire monitoring method based on drone-assisted edge computing. By utilizing the flexible, mobile, and cost-effective characteristics of drones, drones are used as aerial edge nodes to assist sensor nodes in edge computing, and a hovering position with the minimum computing delay is selected for the drone to further reduce the computing delay of the sensor nodes.

[0006] To this end, the present invention provides the following technical solutions:

[0007] A forest fire monitoring method based on drone-assisted edge computing, comprising:

[0008] Using hovering drone swarms to assist sensor nodes in the forest to perform edge computing;

[0009] The objective function is to minimize the maximum computing delay among all drones and minimize the maximum flight energy consumption among drones;

[0010] The model is constructed with the two-dimensional area interval, the drone hovering height interval, the sensor node transmission power interval, the computing resource interval allocated by the drone to the sensor node, and the delay threshold as constraints.

[0011] The continuous solution part of the model is updated using genetic algorithm, gray wolf algorithm and salp integument algorithm, the discrete solution part of the model is updated using random method and the optimal solution is selected according to the Pareto dominance principle; the hovering position of each UAV with the lowest flight energy consumption and the smallest calculation delay is obtained.

[0012] Furthermore, the objective function:

[0013] F = min{f1, f2}

[0014] in, is the local computation delay of the jth task, is the calculation delay of the UAV of the jth task; f1 is the maximum calculation delay of all sensor nodes; f2 is the maximum flight energy consumption of all UAVs, i is the index of the UAV; E i Indicates the energy consumed by the drone from its initial position to the hovering position.

[0015] Furthermore, the energy consumed by the drone from its initial position to its hovering position is:

[0016]

[0017] in, Indicates the distance from the initial position of the drone to the hovering position.

[0018] Furthermore, the two-dimensional area interval, the drone hovering height interval, the sensor node transmission power interval, the drone allocated computing resource interval to the sensor node, and the delay threshold include:

[0019] L min ≤X i ≤L max

[0020] L min ≤Y i ≤L max

[0021] Z min ≤Z i ≤Z max

[0022]

[0023] TD j ≤T th

[0024] Among them, L min and L max are the lower and upper bounds of the two-dimensional region, Z min and Z max They are the lower and upper bounds of the drone’s hovering height, p min and p max are the lower and upper bounds of the sensor node transmission power, respectively, and f min and f max are the lower and upper bounds of the computing resources allocated by the UAV to the sensor nodes; Tth Indicates the latency threshold.

[0025] Furthermore, the constraints also include:

[0026]

[0027]

[0028] a ij ∈{0, 1}

[0029] Among them, Ca l and Ca u denote the task size of local sensor nodes and UAV calculations, respectively, and a ij Indicates whether the sensor node offloads the computing task to the drone.

[0030] Furthermore, the model input parameters include:

[0031] The three-dimensional position X, Y, Z of the drone and the transmission power p of the sensor node t , the number of drones M, the computing frequency f assigned by drones to each sensor node u , the task size Ca of the local sensor node l , the task size of the UAV calculation Ca u , the number of sensors K and the subordinate relationship a between the UAV and the sensor nodes.

[0032] Furthermore, the updating of the continuous solution part of the model using the genetic algorithm, the gray wolf algorithm and the salp algorithm, the updating of the discrete solution part of the model using a random method, and the selection of the optimal solution according to the Pareto dominance principle include:

[0033] Step 1: Randomly initialize the population and calculate the objective function; a population includes several groups of solutions;

[0034] Step 2: For each solution, a new set of UAV and sensor affiliations is generated, and the objective function is recalculated to obtain the current solution of this step. The solution in step 1 and the current solution of this step are compared according to the Pareto dominance principle. The better solution is used as the solution of this step.

[0035] Step 3: Use the genetic algorithm to update the continuous solution part, recalculate the objective function, and obtain the current solution of this step. Compare the solution in step 2 and the current solution of this step according to the Pareto dominance principle. The better solution is used as the solution of this step.

[0036] Step 4: Determine whether the current number of iterations is greater than 3 / 4 of the total number of iterations. If so, proceed to step 5. Otherwise, proceed to steps 5 and 6 in sequence.

[0037] Step 5: Use the Gray Wolf Algorithm to update the continuous solution part, recalculate the objective function, and obtain the current solution of this step; compare the solution in step 3 and the current solution of this step according to the Pareto dominance principle, and the better solution is used as the solution of this step;

[0038] Step 6: Use the Salp Algorithm to update the continuous solution part and recalculate the objective function to obtain the current solution of this step; compare the solution in step 5 and the current solution of this step according to the Pareto dominance principle, and the better solution is used as the solution of this step;

[0039] Step 7: Update the calculation parameters of the salp algorithm;

[0040] Step 8: Randomly update the discrete solution, obtain the Pareto front and update the archive;

[0041] Step 9: Determine whether the current iteration number is greater than the total iteration number. If so, exit the iteration and obtain the archive. Otherwise, execute steps 2 to 8.

[0042] Furthermore, the solution includes:

[0043]

[0044] Furthermore, the continuous solution part is updated using the gray wolf algorithm:

[0045]

[0046] in, and Respectively represent the three selected leader salps, and is based on the selected leadership salp study, and represents the coefficient vector, and the expression is in is a parameter vector that decreases linearly from 2 to 0 after iteration; and are two randomly generated vectors between (0, 1).

[0047] Furthermore, the continuous solution part is updated using the salp algorithm:

[0048]

[0049] in, and are the global best salp position and the position of the current leader salp in the jth decision variable, ub j and lb j are the upper and lower bounds of the j-th decision variable, respectively.

[0050] Advantages and positive effects of the present invention:

[0051] The present invention uses drones as aerial nodes to assist edge computing of sensor nodes in the forest. The sensor monitoring data is divided into two blocks of data of different sizes, one block is calculated locally by the sensor and the other is calculated by the drone, which reduces the computing delay of the sensor node and improves the efficiency of fire alarm. It has the advantages of flexibility, mobility and cost-effectiveness. The continuous solution part of the model is updated using genetic algorithm, gray wolf algorithm and salp insipid algorithm, and the optimal solution is selected according to the Pareto dominance principle. The drone hovering position with the lowest flight energy consumption and the shortest delay is obtained, which further reduces the computing delay of the sensor node, while reducing the energy consumption of the drone, increasing the endurance of the drone and improving the efficiency of auxiliary computing. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 This is a schematic diagram of a UAV combined with a sensor to detect fire in an embodiment of the present invention;

[0054] Figure 2 This is a flow chart of the model solving method in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0056] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0057] The present invention provides a forest fire monitoring method based on drone-assisted edge computing, such as Figure 1 As shown in the figure, multiple drones provide low-latency edge computing services for ground sensor nodes. To further improve edge computing efficiency, the sensor-monitored task (fire data) can be split into two data blocks of different sizes: one computed locally by the sensor and the other by the drone. The computational latency of the drone-computed task equals the data computation latency + the data transmission latency. However, the computational latency of the sensor node's local computation only involves the data computation latency. The larger of the local and drone computation latencies is used as the computational latency for that sensor node. Furthermore, since drones consume a lot of onboard energy, it is important to minimize their flight energy consumption to improve efficiency.

[0058] Therefore, a multi-objective optimization problem is considered to jointly minimize the maximum computational delay of all sensor nodes and the maximum energy consumption of the UAV. Since this problem is a hybrid multi-objective optimization problem with continuous and discrete solution spaces, an improved multi-objective Salp algorithm is used to solve the model. The algorithm has both continuous and discrete solution update mechanisms to improve the performance of the algorithm.

[0059] Specifically, the present invention constructs a dual-objective optimization problem, which simultaneously minimizes the maximum computing delay among all drones and minimizes the maximum flight energy consumption among drones by adjusting the three-dimensional position of the drone (continuous solution), the transmission power of the sensor nodes (continuous solution), the computing frequency allocated by the drone to each sensor node (continuous solution), the size of the task calculated by the drone (continuous solution), and the subordinate relationship between the drone and the sensor nodes (which sensor is offloaded to which drone, discrete solution).

[0060] S1. Model input parameters include:

[0061] The three-dimensional position X, Y, Z of the drone, the transmission power pt of the sensor node, the number of drones M, and the computing frequency f assigned by the drone to each sensor node u , the task size Ca of the local sensor node l , the task size of the UAV calculation Ca u , the number of sensors K and the subordinate relationship a between the UAV and the sensor node; where the superscript U represents the UAV.

[0062] S2.1 The first target is as follows:

[0063]

[0064] in, is the local computation delay of the jth task, The computation delay for the UAV of the jth task. f1 is the maximum computation delay among all sensor nodes.

[0065] The second goal of S2,2 is as follows:

[0066]

[0067] f2 is the maximum flight energy consumption of all drones, and i is the index of the drone. i It represents the energy consumed by the UAV from its initial position to the hovering position. The expression is:

[0068]

[0069] in, Indicates the distance from the initial position of the drone to the hovering position.

[0070] S3,3 Therefore, the problem is modeled as:

[0071] F = min{f1, f2}

[0072] sL min ≤X i ≤L max

[0073] L min ≤Y i ≤L max

[0074] Z min ≤Z i ≤Z max

[0075]

[0076] a ij ∈{0, 1}

[0077] TD j ≤T th

[0078] where L min and L max are the lower and upper bounds of the two-dimensional region, Z min and Z max are the lower and upper bounds of the UAV hovering height, p min and p max are the lower and upper bounds of the sensor node transmission power, f min and f max are the lower and upper bounds of the UAV allocated computing resources for the sensor node, Ca l and Ca u represent the task size of the local sensor node and the UAV computing, a ij represents whether the sensor node will offload the computing task to the UAV, T th represents the delay threshold.

[0079] S3, solving the model by algorithm, combining Figure 1 The solving method in the application is further described:

[0080] Step 1: randomly initialize a population (a population is composed of a plurality of groups of solutions, and an example of a solution is shown below), and calculate the objective function: F = min{f1, f2}.

[0081] The solution formula is:

[0082]

[0083] Where X, Y, and Z are the three-dimensional positions of the UAV, M represents the number of UAVs, pt is the transmission power of the UAV, and K is the number of sensors.

[0084] Step 2: regenerate a group of UAV and sensor affiliation for each solution, recalculate the objective function, and obtain a new solution compared with the solution of step 1, and take the better one as the solution of step 2; (whether better follows the Pareto dominance principle).

[0085] Step 3: update the continuous solution part by using the genetic algorithm, recalculate the objective function, and obtain the current solution, compared with the solution of step 2, take the better one as the solution of step 3 (whether better follows the Pareto dominance principle).

[0086] Step 4: judge whether the current iteration number is greater than 3 / 4 of the total iteration number, if yes, execute step 5, otherwise, sequentially execute step 5 and step 6.

[0087] Step 5: the continuous solution part is updated by using the grey wolf algorithm, the objective function is recalculated, the current solution is compared with the solution of step 3, and the better one is taken as the solution of step 5 (whether better or not follows the Pareto dominance principle).

[0088]

[0089] wherein, and respectively represent three selected leader Ciona intestinalis, and are learned according to the selected leader Ciona intestinalis, and represent a coefficient vector, and the expression is wherein is a parameter vector, and is linearly reduced from 2 to 0 after iteration; and are two vectors randomly generated between (0, 1).

[0090] Step 6: the continuous solution part is updated by using the Ciona intestinalis algorithm,

[0091]

[0092] wherein, and respectively represent the global best Ciona intestinalis position and the position of the current leader Ciona intestinalis in the jth decision variable, ub j and lb j respectively represent the upper limit and the lower limit of the jth decision variable. The objective function is recalculated, compared with the solution of step 5, and the better one is taken as the solution of step 6 (whether better or not follows the Pareto dominance principle).

[0093] Step 7: the calculation parameters of the Ciona intestinalis algorithm are updated;

[0094] Step 8: the discrete solution is randomly updated, the Pareto front is obtained, and the archive is updated;

[0095] Step 9: whether the current iteration number is greater than the total iteration number is judged, if yes, the iteration is exited, the archive is obtained, and if not, steps 2-8 are executed.

[0096] The unmanned aerial vehicle hovering position is constructed as a multi-objective optimization problem, and the continuous solution updating mechanism including the crossover operation of the genetic algorithm and the updating operation of the grey wolf algorithm is used to obtain the optimal calculation efficiency of the unmanned aerial vehicle hovering position, so that the forest fire can be effectively monitored.

[0097] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions recorded in the above embodiments can be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A forest fire monitoring method based on drone-assisted edge computing, characterized in that: include: Using hovering drone swarms to assist sensor nodes in the forest to perform edge computing; The objective function is to minimize the maximum computing delay among all drones and minimize the maximum flight energy consumption among drones; The model is constructed with the two-dimensional area interval, the drone hovering height interval, the sensor node transmission power interval, the computing resource interval allocated by the drone to the sensor node, and the delay threshold as constraints. The continuous solution part of the model is updated using a genetic algorithm, a gray wolf algorithm, and a salp algorithm, the discrete solution part of the model is updated in a random manner, and the optimal solution is selected according to the Pareto dominance principle: Step 1: Randomly initialize a population and calculate an objective function; a population includes several groups of solutions; Step 2: For each solution, a new set of UAV and sensor affiliations is generated, and the objective function is recalculated to obtain the current solution of this step. The solution in step 1 and the current solution of this step are compared according to the Pareto dominance principle. The better solution is used as the solution of this step. Step 3: Use the genetic algorithm to update the continuous solution part, recalculate the objective function, and obtain the current solution of this step. Compare the solution in step 2 with the current solution of this step according to the Pareto dominance principle. The better solution is used as the solution of this step. Step 4: Determine whether the current number of iterations is greater than 3 / 4 of the total number of iterations. If so, proceed to step 5. Otherwise, proceed to steps 5 and 6 in sequence. Step 5: Use the Gray Wolf Algorithm to update the continuous solution part, recalculate the objective function, and obtain the current solution of this step; compare the solution in step 3 and the current solution of this step according to the Pareto dominance principle, and the better solution is used as the solution of this step; Step 6: Use the Salp Algorithm to update the continuous solution part and recalculate the objective function to obtain the current solution of this step; compare the solution in step 5 and the current solution of this step according to the Pareto dominance principle, and the better solution is used as the solution of this step; Step 7: Update the calculation parameters of the salp algorithm; Step 8: Randomly update the discrete solution, obtain the Pareto front and update the archive; Step 9: Determine whether the current iteration number is greater than the total iteration number. If so, exit the iteration and obtain the archive. Otherwise, execute steps 2 to 8. Obtain the hovering position of each drone with the lowest flight energy consumption and the smallest calculation delay.

2. The forest fire monitoring method based on drone-assisted edge computing according to claim 1, characterized in that: The objective function: in, ; ; ; For the j The local computation latency of each task, For the j The calculation delay of the drone for each mission; is the maximum computational delay among all sensor nodes; It is the largest flight energy consumption among all drones. Index of drones; Indicates the energy consumed by the drone from its initial position to the hovering position.

3. The forest fire monitoring method based on drone-assisted edge computing according to claim 2 is characterized in that: The energy consumed by the drone from its initial position to its hovering position: in, Indicates the distance from the initial position of the drone to the hovering position.

4. The forest fire monitoring method based on drone-assisted edge computing according to claim 1, characterized in that: The two-dimensional area interval, the drone hovering height interval, the sensor node transmission power interval, the drone allocated computing resource interval to the sensor node, and the delay threshold include: in, and are the lower and upper bounds of the two-dimensional region, and They are the lower and upper bounds of the drone’s hovering height, and are the lower and upper bounds of the sensor node transmission power, and are the lower and upper bounds of the computing resources allocated by the UAV to the sensor nodes; Indicates the latency threshold.

5. The forest fire monitoring method based on drone-assisted edge computing according to claim 1, characterized in that: The constraints also include: in, and denote the task sizes of local sensor nodes and UAV calculations, Indicates whether the sensor node offloads the computing task to the drone.

6. The forest fire monitoring method based on drone-assisted edge computing according to claim 1, characterized in that: The model input parameters include: The three-dimensional position of the drone X , Y , Z , the transmission power of the sensor node , the number of drones M、 The computing frequency allocated to each sensor node by the drone , the task size of the local sensor node , the size of the UAV calculation task , the number of sensors And the subordinate relationship between drones and sensor nodes .

7. The forest fire monitoring method based on drone-assisted edge computing according to claim 1, characterized in that: The solution includes: 。 8. The forest fire monitoring method based on drone-assisted edge computing according to claim 1, characterized in that: The gray wolf algorithm is used to update the continuous solution part: in, 、 and Respectively represent the three selected leader salps, 、 and is based on the selected leadership salp study, and represents the coefficient vector, and the expression is , ,in is a parameter vector that decreases linearly from 2 to 0 after iteration; and are two randomly generated vectors between (0, 1).

9. The forest fire monitoring method based on drone-assisted edge computing according to claim 1, characterized in that: The continuous solution part is updated using the salp algorithm: in, and are the global best salp position and the current leader salp position in The position of the decision variable, and They are upper and lower bounds for the decision variables.

Images