Unmanned aerial vehicle charging path planning method based on hybrid artificial bee colony and ant colony algorithm

Abstract

The invention discloses an unmanned aerial vehicle charging path planning method based on a hybrid artificial bee colony and ant colony algorithm, and belongs to the technical field of unmanned aerial vehicles, and the method comprises the steps: 1, carrying out the mathematical modeling based on all basic data of a selected scene; 2, determining the scale of a charging scene according to the number of all to-be-charged sensor nodes in the selected scene; wherein when the number of sensor nodes is less than 500, the positions of hovering points of the unmanned aerial vehicle, the flight path of the unmanned aerial vehicle and the number of hovering points are optimized based on a hybrid artificial bee colony and ant colony algorithm, and the total energy consumption of the unmanned aerial vehicle is minimized; when the number of the sensor nodes is greater than 500, optimizing the positions of hovering points of the unmanned aerial vehicle, the flight path of the unmanned aerial vehicle and the number of hovering points based on an improved non-dominated genetic algorithm, and minimizing the total energy consumption of the unmanned aerial vehicle; and step 3, the unmanned aerial vehicle performs charging and data acquisition on the sensor node through the calculated optimal path and the optimal hovering point. Charging path planning can be carried out for different to-be-charged scenes.

Description

Technical Field

[0001] The present invention relates to a method for planning the charging path of an unmanned aerial vehicle based on a hybrid artificial bee colony and ant colony algorithm, belonging to the technical field of unmanned aerial vehicles. Background Art

[0002] A wireless sensor network (WSN) is a wireless network composed of a large number of stationary or mobile sensors in a self-organizing and multi-hop manner, which collaboratively senses, collects, processes, and transmits information about the sensed objects within the geographical area covered by the network, and finally sends this information to the owner of the network.

[0003] In recent years, wireless sensor networks (WSNs) have been ubiquitous in fields such as commerce, detection, and healthcare. It is a network system composed of a large number of distributed micro-sensor nodes, and the sensor nodes in this system often have sensing capabilities and communication capabilities. However, restricted by the size and cost of sensors, energy replenishment has become a key issue determining the operating time of the entire system. Energy replenishment is to supply energy to the nodes in the wireless sensor network. In theory, it can infinitely extend the network life, so it has attracted a large amount of research. Currently, the most advanced and reliable method is to achieve it through wireless energy transfer technology.

[0004] The traditional artificial bee colony algorithm is mainly applicable to optimization problems in continuous spaces, while the traditional ant colony algorithm is good at discrete combinatorial optimization problems. We combine the two to break through the limitations of the original algorithms in solving the joint optimization of UAV scheduling and trajectory problems, and introduce corresponding improvement strategies. After improvement, a hybrid artificial bee colony and ant colony algorithm (HABC-ACO) is proposed. Compared with the traditional algorithms, it not only adapts to the change of the solution dimension during the iteration process, but also speeds up the convergence rate of the algorithm. However, due to the single-solution property of the algorithm, it performs slightly inadequately when dealing with large-scale problems. For this, new solutions are also proposed, and new optimization objectives are introduced subsequently to improve the performance of the entire wireless rechargeable sensor network. Aiming at the mismatch problem of the traditional NSGA-II algorithm when facing the joint optimization of UAV scheduling and trajectory problems in large-scale scenarios, a series of improvement strategies are introduced into the algorithm, including an adaptive population dimension mechanism, an adversarial elimination strategy, a PMX factor is introduced during the crossover process, and a 2-OPT factor and a cross-path improvement mechanism are introduced during the mutation process. Through these improvements, an improved non-dominated genetic algorithm (IMNSGA-II) is proposed. Compared with the original NSGA-II algorithm, it significantly improves the global search ability and solution accuracy of the algorithm. Summary of the Invention

[0005] The present invention designs and develops a method for path planning of UAV charging based on a hybrid artificial bee colony and ant colony algorithm, which can perform path planning for different charging scenarios and improve the wireless charging efficiency of UAVs.

[0006] The technical solution provided by the present invention is as follows: A method for path planning of UAV charging based on a hybrid artificial bee colony and ant colony algorithm, comprising: Step 1: Based on the number and positions of sensor nodes and the basic power data required by sensor nodes in a selected scenario, perform mathematical modeling of the scenario according to the environmental parameters, UAV power parameters, and corresponding charging parameters of the application scenario. Step 2: Determine the scale of the charging scenario according to the number of all sensor nodes to be charged in the selected scenario. Among them, when the number of sensor nodes is less than 500, it is a small-scale scenario; Based on the hybrid artificial bee colony and ant colony algorithm, optimize the UAV hovering point positions, UAV flight trajectories, and the number of hovering points to minimize the total energy consumption of the UAV. When the number of sensor nodes is greater than 500, it is a large-scale scenario; Based on the improved non-dominated genetic algorithm, optimize the UAV hovering point positions, UAV flight trajectories, and the number of hovering points to minimize the total energy consumption of the UAV. Step 3: The UAV charges and collects data from sensor nodes through the calculated optimal path and optimal hovering points.

[0007] Preferably, in the method for path planning of UAV charging based on the hybrid artificial bee colony and ant colony algorithm, the hybrid artificial bee colony and ant colony algorithm includes: Step a1: Initialize the relevant parameters of the hybrid artificial bee colony and ant colony algorithm; Randomly generate a set of hovering positions to form a total set , and each set contains hovering points, , , and initialize them; Step a2: The employed bees perturb each coordinate to obtain a new set of hovering points for each set of hovering points and add them to the total set , such that ; Step a3: Enter the inner loop, and use the ant colony to complete a loop for each set of hovering points to update the pheromone concentration of each edge; When the number of inner loop iterations is reached, each set of hovering points selects the Hamiltonian circuit with the largest total pheromone concentration as the optimal path, otherwise, it will continue to enter the inner loop; Step a4: Calculate the total energy consumption, fitness function, and retention probability of each hovering point set. The hovering point sets retained according to the probability form a new total set and the number of sets ; Select the total energy consumption of the hovering set with the largest retention probability, denoted as ; Set the optimal solution of the energy consumption in the current situation as ; When , after updating the optimal solution, if the outer loop count is reached, output the global optimal solution; When , if the outer loop count is reached, directly output the global optimal solution; If the loop count is not reached, continue to return to step a2 and reset the inner loop count; Step a5: Output the optimal result and the calculation ends.

[0008] Preferably, the improved non-dominated genetic algorithm includes: Step b1: Initialize the population, parameters, and hovering position set; Step b2: Generate a new hovering position set based on the adaptive population dimension mechanism and the adversarial elimination strategy, and set the number of generations , the maximum number of generations , the population size ; Step b3: After performing non-dominated sorting and crowding degree calculation selection on the initial population, generate the first-generation population; Perform a crossover operation with PMX factor improvement on the first-generation population to generate a crossover sub-population; Step b4: Perform a mutation operation with 2-OPT factor and crossover path improvement mechanism improvement on the first-generation population to generate a mutant population; Step b5: Merge the first-generation population, crossover sub-population, and mutant population into a set, and perform non-dominated sorting and crowding degree calculation on the elements in the set, and then perform truncation, Step b6: When , output the global optimal solution; When , return to the crossover operation step until the global optimal solution is output.

[0009] Preferably, the step a3 includes: Enter the inner loop, for each and , , use the ant colony algorithm to generate the optimal path of ; Set each ant as , , from a random starting point Start and select the next hover point The probability is: ; Where, For any ant, is the total number of ants, For the set of all remaining points, 、 is the heuristic factor weight, For two points 、 The pheromone concentration between the edges, For two points 、 The pheromone concentration between the edges, for 、 The reciprocal of the distance between two points, for 、 The reciprocal of the distance between two points; All ants return to their starting point After that, update the information concentration , pheromone enhancement is ; Where, It's an ant The total length of the path, Add weight to pheromones; Update pheromone matrix ; If the inner cycle is reached , select the pheromone concentration and the largest Hamiltonian circuit as Go to the next step, otherwise return to this step.

[0010] Preferably, The calculation formula of the fitness is: ; The calculation formula of the retention probability is: ; Where, is the total energy consumption, is the traversal index of all individuals in the population, and its value range is , representing the total number of individual, is the size of the population after merging.

[0011] Advantages of the present invention: The method for charging path planning of WRSNS drones based on the hybrid artificial bee colony and ant colony algorithm provided by the present invention can apply different optimization methods to different scale scenarios to minimize the total energy consumption of drone charging, shorten the charging time, and improve the charging efficiency.

[0012] The traditional artificial bee colony algorithm and the traditional ant colony algorithm are combined to break through the limitations of the original algorithms in solving the joint optimization of drone scheduling and trajectory problems. It not only adapts to the dimension of the solution in the iterative process but also speeds up the convergence rate of the algorithm.

[0013] The improved non-dominated genetic algorithm introduces an adaptive population mechanism, an adversarial resolution strategy, and a PMX factor in the crossover process, and a 2-OPT factor and a cross-path improvement mechanism in the mutation process. Through these improvements, the global search ability and solution accuracy of the algorithm are significantly improved.

[0014] In this method, based on the adaptive population mechanism, the diversity index of this method remains at 0.18 - 0.35 in the later stage of iteration, which can effectively avoid the problem of premature convergence. Especially when dealing with heterogeneous node distributions, compared with traditional algorithms, it can significantly reduce the standard deviation of charging efficiency, showing superior robustness and scene adaptability.

[0015] In the intelligent agricultural monitoring system, using this method can shorten the total flight distance of the drone, reduce the charging task completion time, and at the same time can reduce the peak energy consumption and reduce the inefficiencies in path planning. In disaster emergencies, it can cover the optimal charging path of the monitored area within seconds. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of a drone-assisted wireless rechargeable sensor network according to the present invention.

[0017] Figure 2 It is a flowchart of an algorithm for charging path planning of a drone-assisted wireless rechargeable sensor network based on multi-objective optimization according to the present invention.

[0018] Figure 3 It is a schematic diagram of the optimization results of the hovering points and trajectory points of the drone when the number of ground sensor nodes is 300 according to the present invention.

[0019] Figure 4 It is a comparison chart of the fitness function values of different algorithms when the number of ground sensor nodes is 100 according to the present invention.

[0020] Figure 5 It is a schematic diagram of the optimization results of the hovering points and trajectory of the drone when the sensor node scale is 500 using the IMNSGA-II algorithm according to the present invention.

[0021] Figure 6 This is a diagram showing the effect of the hovering points and trajectories of the UAV when the sensor node scale is 500 using the IMNSGA-II algorithm described in the present invention.

[0022] Figure 7 This is a schematic diagram showing the optimization results of the hovering points and trajectories of the UAV when the sensor node scale is 1000 using the IMNSGA-II algorithm described in the present invention.

[0023] Figure 8 This is a diagram showing the effect of the hovering points and trajectories of the UAV when the sensor node scale is 1000 using the IMNSGA-II algorithm described in the present invention.

[0024] Figure 9 This is a schematic diagram showing the optimization results of the hovering points and trajectories of the UAV when the sensor node scale is 1500 using the IMNSGA-II algorithm described in the present invention.

[0025] Figure 10 This is a diagram showing the effect of the hovering points and trajectories of the UAV when the sensor node scale is 1500 using the IMNSGA-II algorithm described in the present invention.

[0026] Figure 11 This is a comparison diagram for validating the effectiveness of the improved algorithm and the existing algorithm described in the present invention. Detailed implementation manners

[0027] The following further elaborates on the present invention in conjunction with the accompanying drawings, enabling those skilled in the art to implement it based on the description in the specification.

[0028] As Figures 1-11 shown, the present invention provides a method for UAV charging path planning based on a hybrid artificial bee colony and ant colony algorithm. By using the hybrid artificial bee colony and ant colony algorithms and an improved non-dominated genetic algorithm, charging path planning is performed for different charging scenarios to improve the wireless charging efficiency of the UAV, including: Step 1: Based on all the basic data of the selected scenario, mathematical modeling is performed according to the environmental parameters of the application scenario, the power parameters of the UAV, and the corresponding charging parameters. Among them, the basic data includes: the number and positions of sensor nodes, and the electrical energy required by the sensor nodes. The power parameters of the UAV include: the transmission power of the charging UAV, the propulsion speed, and the charging parameters include: the charging energy consumption, the effective charging distance. Step 2: Determine the scale of the charging scenario according to the number of all the sensor nodes to be charged in the selected scenario. Among them, when the number of sensor nodes is less than 500, it is a small-scale scenario. Optimizing the UAV hovering point positions, UAV flight trajectories, and the number of hovering points based on a hybrid artificial bee colony and ant colony algorithm to minimize the total energy consumption of the UAV, including: Step a1: Initialize the relevant parameters of the hybrid artificial bee colony and ant colony algorithms; Randomly generate sets of hovering positions to form the total set , and each set contains hovering points, , , and initialize them; Step a2: The employed bees perturb each coordinate to obtain a new set of hovering points for each set of hovering points and add them to the total set , such that ; Step a3: Enter the inner loop, use the ant colony to complete a circuit for each set of hovering points, and update the pheromone concentration of each edge; When the number of inner loop iterations is reached, each set of hovering points selects the Hamiltonian circuit with the largest total pheromone concentration as the optimal path, otherwise, continue to enter the inner loop; Step a4: Calculate the total energy consumption, fitness function, and retention probability of each set of hovering points. The sets of hovering points retained according to the probability form a new total set and the number of sets ; Select the total energy consumption of the hovering set with the largest retention probability, denoted as ; Set the optimal solution of the energy consumption in the current situation as ; When , after updating the optimal solution, if the number of outer loop iterations is reached, output the global optimal solution; When , if the number of outer loop iterations is reached, directly output the global optimal solution; If the number of loop iterations is not reached, continue to return to step a2 and reset the number of inner loop iterations; Step a5: Output the optimal result and the calculation ends.

[0029] When the number of sensor nodes is greater than 500, it is a large-scale scenario; Optimizing the UAV hovering point positions, UAV flight trajectories, and the number of hovering points based on an improved non-dominated genetic algorithm to minimize the total energy consumption of the UAV, including: Step b1: Initialize the population, parameters, and the set of hovering positions; Step b2: Generate a new set of hovering positions based on the adaptive population dimension mechanism and the adversarial elimination strategy, and set the number of generations , the maximum number of generations , population size ; Step b3: After performing non-dominated sorting and crowding degree calculation on the initial population, generate the first-generation population , and set ; Perform a crossover operation with improved PMX factor on the first-generation population to generate a crossover sub-population; Step b4: Perform a mutation operation with improved 2-OPT factor and crossover path improvement mechanism on the first-generation population to generate a mutated population; Step b5: Merge the first-generation population, crossover sub-population, and mutated population into a set, and perform truncation after non-dominated sorting and crowding degree calculation on the elements in the set; Step b6: When , output the global optimal solution; When , return to the crossover operation step until the global optimal solution is output.

[0030] Step Three: The drone charges the sensor nodes and collects data through the calculated optimal path and optimal hovering points.

[0031] Step 1: Determine the number of sensor nodes , the positions of the sensor nodes and the flight altitude of the drone .

[0032] Step 2: Calculate the charging power transmission efficiency between the drone and the nodes , data transmission rate and the energy consumption of the drone .

[0033] (a) The distance between the node and the drone at any moment :

[0034] Among them, is the three-dimensional coordinate of the sensor node , is the coordinate of the drone at any moment; (b) Charging power transmission efficiency : ; Among them, is the transmission power of the drone, is the receiving power of the node, , , are all relevant constants of the charging drone.

[0035] (c) Data transfer rate between the node and the UAV ; ; Among them, is the system bandwidth, is the UAV transmission power, is the channel gain, is the white noise power, is the distance between the node and the UAV at any moment at any time.

[0036] Define as the amount of data, then the data transfer time is: ; (d) Total energy consumption of the UAV during the charging cycle :

[0037]

[0038]

[0039]

[0040] Among them, is the UAV charging energy consumption, is the energy collected by all nodes, is each node the required electrical energy. and are the UAV flight energy consumption and hovering energy consumption respectively, and are the flight power and hovering power respectively, and are the flight time and hovering time respectively. The propulsion power of the UAV is calculated as follows: ; Among them, and are two constants, which are the blade profile power and induced power of the UAV in the hovering state respectively, is the rotor blade speed, is the time when the speed of the UAV, is the average rotor induced speed during hovering, and are the fuselage drag ratio and rotor solidity respectively, and are the air density and the rotor disk area respectively. When the propulsion speed of the UAV is , the propulsion power ; when the propulsion speed of the UAV is 0, i.e., hovering, the hovering power .

[0041] The hovering time of the UAV at the hovering point is , where is a binary variable representing the th sensor node can be connected to the UAV at the th hovering point. If the UAV can be connected to the th hovering point with the th node, then , otherwise it is 0. is the data transmission time from the sensor nodes to the UAV at the th hovering point. The total hovering time of the UAV can be expressed as: , then the hovering energy consumption is . From the above, the total energy consumption of the UAV during the entire charging cycle is: .

[0042] Step 3: For small-scale and large-scale scenarios, construct different optimization problems and adopt different solutions, as follows: (a) For small-scale scenarios, the objective function is designed as follows:

[0043]

[0044]

[0045]

[0046]

[0047] Among them, is the total energy consumption under the optimization objective, represents the coordinates of the th hovering point, represents the distance between the th hovering point and the th hovering point, is a binary variable indicating and whether there is a trajectory between them, is the total number of hovering points, is the total energy received by the sensor node, and the objective function represents minimizing the total hovering energy consumption of the UAV at all hovering points. The fewer the number of hovering points and the more appropriate their positions, the smaller the hovering energy consumption.

[0048] The objective function represents minimizing the total flight energy consumption of the UAV between hovering points. The UAV flies at a constant speed, and the shorter the total length of the trajectory, the smaller the flight energy consumption. The objective function is the charging energy consumption in Step 2. Based on these objective functions, the hovering point positions, the UAV flight trajectory, and the number of hovering points are optimized by the Hybrid Artificial Bee Colony and Ant Colony Optimization (HABC-ACO) to minimize the total energy consumption of the UAV, that is, the sum of the hovering energy consumption, the flight energy consumption, and the charging energy consumption.

[0049] The specific calculation process is as follows: (i) Initialize the maximum number of outer loop iterations , the maximum number of inner loop iterations , the range of the number of hovering points , initialize the size of the bee colony , the triggering threshold of the scout bee ; the number of ants , the pheromone evaporation coefficient , the pheromone enhancement weight , the heuristic factor weight ; ; randomly generate sets of hovering positions to form the set , each set contains hovering points, ; ; initialize the pheromone concentration of the edges between every two points of each to the same value, ; ; (ii) Enter the outer loop. For each coordinate of each set , perturb to generate a new coordinate , obtain the new set of hovering positions and , update and through the adversarial elimination strategy to ensure that they meet the requirements, and add them to . Finally, the number of elements in ; (iii) Enter the inner loop. For each and , The optimal path is generated using the Ant Colony Optimization (ACO) algorithm . The specific process is as follows: Each ant , starting from a random starting point , , selects the next hovering point with a probability of ; where , is the reciprocal of the distance between points and , is the reciprocal of the distance between points and , is the set of all remaining points. After all ants return to their own starting points , the pheromone concentration is updated, and the pheromone is enhanced to , where is the total path length of ant . The pheromone matrix is updated; if the inner loop is reached, the Hamiltonian cycle with the highest pheromone concentration is selected as and transferred to (iv), otherwise return to (iii); (iv) For each , the total energy consumption is calculated according to the optimal path , and the fitness is calculated. Whether to retain is selected with a probability of to form and , and the maximum is selected and denoted as , let , and . If , then record , , . If is retained continuously times, the scout bee randomly resets its coordinates and ensures that and meet the requirements; update , ; if the outer loop is reached, then go to (v), otherwise return to (ii); ( ) Output , , The calculation is completed.

[0050] (b) For large-scale scenarios, the objective function is designed as follows:

[0051]

[0052]

[0053]

[0054]

[0055] Similar to the representation of small-scale scenarios, is the total hovering energy consumption, is the total flight energy consumption, is the total charging energy consumption, is the energy utilization rate of the UAV, is the total energy received by the sensor node, is the total energy transmitted by the UAV. The total objective function optimizes the hovering point position, the UAV flight trajectory, and the number of hovering points through the IMNSGA-II algorithm to minimize the total energy consumption of the UAV, that is, the sum of the hovering energy consumption, flight energy consumption, and charging energy consumption, and to maximize the energy utilization rate of the UAV. The specific calculation process is as follows: (i) Parameter and population initialization, initialize the maximum number of hovering point iterations and set the number of evolution generations , the maximum number of evolution generations , the population size , the crossover ratio , the mutation ratio , the mutation rate coefficient , the hovering position set and the number of hovering points ; (ii) Apply the adaptive population dimension mechanism to obtain the updated hovering position set and the number of hovering points at this time , and make and meet the requirements through the adversarial elimination strategy, and iterate times, and then generate the initial population in the form of a structure; (iii) After performing the selection operations of non-dominated sorting and crowding degree calculation on the initial population, generate the first-generation population and set ; (iv) For the population Perform crossover operation with PMX operator to generate crossover sub-population ; (v) Perform mutation operation on the population with 2-OPT factor and cross-path reduction mechanism to generate mutant sub-population ; (vi) Fuse the populations , , into a set . After non-dominated sorting and crowding degree calculation on the elements in , perform truncation, retain the first individuals, and assign the individuals in the set at this time to ; (vii) If , output the result; otherwise then, and go to (iv); (viii) Output the global optimal path , the lowest total energy consumption , and the maximum system efficiency .

[0056] Step 4: The UAV charges and collects data from the sensor nodes through the calculated optimal path and optimal hovering points.

[0057] Example 1 To verify the effectiveness of IMSA in solving problems, a comparative experiment was conducted when the number of sensor nodes was 100. The comparative algorithms selected were Genetic Algorithm (GA), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Simulated Annealing (SA). Figure 4 shows the comparison results, where the abscissa represents the number of experimental iterations and the ordinate represents the global total energy consumption. It can be seen from Figure 4 that the HABC-ACO algorithm has a smaller fitness function value and a faster convergence speed compared with other algorithms.

[0058] Example 2

[0059] Although the improved algorithm has achieved a great improvement in convergence performance, it is also necessary to ensure the stability of the algorithm. To eliminate randomness, the IMSA algorithm and other comparative algorithms were each calculated 50 times under different scenarios. Table 1 compares the maximum value, minimum value, mean value, and standard deviation of each algorithm (Note: The data in the table are all divided by )。

[0060] Table 1 Numerical Comparison of Each Algorithm

[0061] It can be seen from Table 1 that HABC-ACO has better stability compared with other algorithms. After 50 experimental results, all the data of the algorithm are optimal, which means that the algorithm has excellent stability in scenarios of different scales.

[0062] Example 3 In order to verify the operation time of the proposed HABC-ACO algorithm in scenarios of different scales, the IMNSGA-II algorithm provided by the present invention is compared with the HABC-ACO algorithm to prove the advantages of the HABC-ACO algorithm in small-scale scenarios and the advantages of the IMNSGA-II algorithm in large-scale scenarios.

[0063] To eliminate random errors, the data in the table are all the averages after 50 calculation results.

[0064] Table 2 Comparison of Operation Times of Two Improved Algorithms under Different Scale Conditions

[0065] It can be seen from Table 2 that the HABC-ACO algorithm has less operation time in small-scale scenarios, which means that the algorithm is more suitable for small-scale scenarios. As the number of nodes increases, the time required for the algorithm to complete iteration increases greatly, while the IMNSGA-II algorithm performs more strongly in large-scale scenarios. Therefore, the IMNSGA-II algorithm is applied in large-scale scenarios.

[0066] Example 4 As Figures 5-10 shown, it shows the two-dimensional and three-dimensional effects of the movement trajectories of the hovering point sets of the UAV when the sensor node scales are 500, 1000, and 1500 respectively. It can be seen from the figure that as the node scale increases, the scale of the hovering points also increases, but the optimization result of the algorithm for complex paths is still efficient. The paths of the UAVs do not cross, which proves that the optimization of the algorithm for the problem is very effective.

[0067] Example 5 In order to verify the effectiveness of this algorithm in multi-objective problems, comparative tests were conducted when the number of nodes was 500, 1000, and 1500. The comparative algorithms used were NSGA-II (Nondominated Sorting Genetic Algorithm II), NSGA-III (Nondominated Sorting Genetic Algorithm III), MOPSO (Multi-Objective Particle Swarm Optimization), and MOALO (Multi-Objective Antlion Optimization). Table 3 shows the results of the two objectives after optimization (Note: The data in the table are divided by ), and The lower the two values, the more effective the improvement. As can be seen from Table 3, the IMNSGA-II algorithm has a better performance in the two objectives. and Each has the best results.

[0068] Table 3 Multi-objective optimization results of the algorithm in different scenarios

[0069] Example 6 In order to verify whether the performance of the algorithm in solving problems is significantly improved after adding improvement points, 500 nodes are taken as an example.

[0070] like Figure 11 As shown, the horizontal axis represents the number of algorithm iterations, and the vertical axis represents + Calculation results. IMNSGA-II is the algorithm proposed in this paper; IMPROVE indicates that the proposed improvements were introduced in the 150th iteration; NSGA-II represents the unmodified algorithm. The graph shows that the algorithm converges significantly faster after the improvements are introduced, ultimately converging to a result similar to IMNSGA-III, effectively demonstrating the effectiveness of the improvements.

[0071] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the description and implementation methods. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

Claims

1. A method for path planning of UAV charging based on a hybrid artificial bee colony and ant colony algorithm, characterized in that, Including: Step 1: Based on the number and positions of sensor nodes in the selected scenario, and the basic power data required by the sensor nodes, perform mathematical modeling of the scenario according to the environmental parameters, UAV power parameters, and corresponding charging parameters of the application scenario; Step 2: Determine the scale of the charging scenario according to the number of all sensor nodes to be charged in the selected scenario; Among them, when the number of sensor nodes is less than 500, it is a small-scale scenario; Based on the hybrid artificial bee colony and ant colony algorithm, optimize the UAV hovering point positions, UAV flight trajectories, and the number of hovering points to minimize the total energy consumption of the UAV; When the number of sensor nodes is greater than 500, it is a large-scale scenario; Based on the improved non-dominated genetic algorithm, optimize the UAV hovering point positions, UAV flight trajectories, and the number of hovering points to minimize the total energy consumption of the UAV; Step 3: The UAV charges and collects data from the sensor nodes through the calculated optimal path and optimal hovering points.

2. The method for planning the charging path of an unmanned aerial vehicle based on the hybrid artificial bee colony ant colony algorithm according to claim 1, wherein, The hybrid artificial bee colony and ant colony algorithm includes: Step a1: Initialize the relevant parameters of the hybrid artificial bee colony and ant colony algorithm; Random generation A set of hover positions forms the total set Each set Contains Hover points And Initialize them Step a2: The employed bees perturb each coordinate to obtain a new set of hovering points for each set of hovering points and add them to the total set , such that ; Step a3: Enter the inner loop, and use the ant colony to complete a loop for each set of hovering points, and update the pheromone concentration of each edge; When the number of inner loop iterations is reached, each set of hovering points selects the Hamiltonian cycle with the largest total pheromone concentration as the optimal path, otherwise, continue to enter the inner loop; Step a4: Calculate the total energy consumption, fitness function, and retention probability of each hovering point set. The hovering point sets retained according to the probability form a new total set and the number of sets ; Select the total energy consumption of the hovering set with the largest retention probability, denoted as ; Set the optimal solution of the energy consumption in the current situation as ; When After updating the optimal solution, if the outer loop count is reached, output the global optimal solution; When If the number of outer loop iterations is reached, directly output the global optimal solution; If the number of loop iterations is not reached, then continue to return to Step a2 and reset the number of inner loop iterations; Step a5: Output the optimal result and the calculation ends.

3. The method for planning the charging path of an unmanned aerial vehicle based on the hybrid artificial bee colony and ant colony algorithm according to claim 2, wherein The improved non-dominated genetic algorithm based on includes: Step b1: Initialize the population, parameters, and set of hovering positions; Step b2: Generate a new set of hovering positions based on the adaptive population dimension mechanism and the adversarial elimination strategy, and set the number of generations of evolution , the maximum number of generations of evolution , the population size ; Step b3: After performing non-dominated sorting and crowding degree calculation selection on the initial population, generate the first-generation population; Perform a crossover operation with PMX factor improvement on the first-generation population to generate a crossover sub-population; Step b4: Perform a mutation operation with 2-OPT factor and crossover path improvement mechanism improvement on the first-generation population to generate a mutant population; Step b5: Merge the first-generation population, crossover sub-population, and mutant population into a set, and perform non-dominated sorting and crowding degree calculation on the elements in the set, and then perform truncation, Step b6, when is satisfied, output the globally optimal solution; When returns to the crossover operation steps until the global optimal solution is output.

4. The method for path planning of UAV charging based on the hybrid artificial bee colony and ant colony algorithm according to claim 2 or 3, characterized in that The said Step a3 includes: Enter the inner loop, for each and , , use the ant colony algorithm to generate the optimal path ; Set each ant as , , starting from a random starting point and the probability of selecting the next hovering point is as follows: ; In the formula, represents any one ant, represents the total number of ants, represents the set of all the remaining points, , is the weight of the heuristic factor, is the pheromone concentration of the edge between two points , ; is the pheromone concentration of the edge between two points , ; is , the reciprocal of the distance between two points is , the reciprocal of the distance between two points; All ants return to their own starting points After that, update the information concentration , and the pheromone is enhanced to ; In the formula, is the total path length of the ants , and is the pheromone enhancement weight; Update pheromone matrix ; If the inner loop is reached , select the pheromone concentration and the largest Hamiltonian cycle as and go to the next step, otherwise return to this step.

5. The method for UAV charging path planning based on the hybrid artificial bee colony and ant colony algorithm according to claim 4, characterized in that, The calculation formula for the fitness is as follows: ; The calculation formula for the retention probability is as follows: ; In the formula, is the total energy consumption, is the traversal index of all individuals in the population, and its value range is , representing that there are individuals in the population, represents the size of the merged population.

Images