CN116805201A - Unmanned aerial vehicle energy supply station deployment method - Google Patents
Unmanned aerial vehicle energy supply station deployment method Download PDFInfo
- Publication number
- CN116805201A CN116805201A CN202310971294.1A CN202310971294A CN116805201A CN 116805201 A CN116805201 A CN 116805201A CN 202310971294 A CN202310971294 A CN 202310971294A CN 116805201 A CN116805201 A CN 116805201A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- energy supply
- area
- station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002068 genetic effect Effects 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 108090000623 proteins and genes Proteins 0.000 claims description 24
- 238000005457 optimization Methods 0.000 claims description 20
- 230000006872 improvement Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 5
- 230000035772 mutation Effects 0.000 claims description 4
- 238000012300 Sequence Analysis Methods 0.000 claims description 3
- 230000001351 cycling effect Effects 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 2
- 239000002699 waste material Substances 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 7
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 230000002354 daily effect Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an energy supply station deployment method of an unmanned aerial vehicle, which comprises the following steps: establishing an analysis model of unmanned aerial vehicle energy supply station deployment; distributing and deciding the batch number required by batch switching of unmanned aerial vehicles in each area; and on the basis of obtaining the distribution of the batch number and the decision result required by the batch switching of the unmanned aerial vehicle in each area, solving an analysis model by using a genetic algorithm to obtain an energy supply station deployment scheme of the unmanned aerial vehicle. According to the method, under the condition that the unmanned aerial vehicle is provided with the edge server, the energy consumption and the charging requirement of the unmanned aerial vehicle are considered. In the deployment and task execution processes, the charging requirements are reasonably met, and the sustainability and stability of unmanned aerial vehicle service are guaranteed. And combining an unmanned aerial vehicle energy supply station and a mobile edge server, learning and analyzing by utilizing historical data, and alternately carrying out service by adopting a plurality of batches of unmanned aerial vehicles in turn, so as to ensure that the area obtains uninterrupted service coverage within a whole period. By optimizing the unmanned aerial vehicle path, the deployment efficiency and the resource utilization rate are improved.
Description
Technical Field
The invention relates to the technical field of replenishment deployment, in particular to an energy replenishment station deployment method of an unmanned aerial vehicle.
Background
Edge computing is one of the future core technologies of intelligent internet of vehicles, which provides high throughput, low latency, mass connected computing services to internet of vehicles users by placing computing power near their network edges. In the 5G and 6G internet of vehicles era, most end-user computing tasks will be undertaken by edge servers deployed on roadside units, base stations, signal lights, cameras, and drones. The edge server is introduced into the mobile environment during mobile edge computing, so that more convenient and flexible computing service is provided for the Internet of vehicles user, wider coverage and higher-density computing resource distribution are realized, and the user can obtain high-quality computing service at any time and any place.
Aiming at the dynamically-changing computing and unloading requirement, the unmanned aerial vehicle is considered to be introduced to be used as a mobile carrier to carry an edge computing server node. Currently, research on mobile edge computing server deployment problems is still in a preliminary stage. While there have been some theoretical studies, many challenges remain in terms of practical deployment. Existing studies mainly consider deployment strategies in an ideal state and path planning of mobile unit edge servers, but in a real situation, deployment strategies may be thoroughly changed due to various problems.
The prior art has the following disadvantages:
1) The energy consumption and charging problems of the unmanned aerial vehicle are not considered, and the importance of energy management is ignored. This may result in the unmanned aerial vehicle exhausting energy during task execution, failing to complete the task or returning to the charging station, affecting service reliability and sustainability.
2) The lack of a specific unmanned aerial vehicle charging plan scheme cannot effectively solve the requirement of unmanned aerial vehicle energy supply. The lack of systematic charging planning may affect overall efficiency.
3) On the premise of optimizing the deployment cost, the specific scheme of the unmanned aerial vehicle charging plan is not comprehensively considered, so that the deployment effect and the cost benefit cannot be considered. This may lead to unreasonable deployment schemes, resulting in wasted resources or poor service.
4) The unmanned aerial vehicle can not keep providing service in the service area in the charging process, so that the continuous service capability of the area in the whole period can not be realized. Service interruption during charging may reduce the user experience, especially for internet of vehicles users who need continuous computing offload services.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an energy supply station deployment method of an unmanned aerial vehicle.
In order to achieve the above purpose, the technical scheme provided by the invention is as follows:
an energy tender station deployment method for an unmanned aerial vehicle, comprising:
establishing an analysis model of unmanned aerial vehicle energy supply station deployment;
distributing and deciding the batch number required by batch switching of unmanned aerial vehicles in each area;
and on the basis of obtaining the distribution of the batch number and the decision result required by the batch switching of the unmanned aerial vehicle in each area, solving an analysis model by using a genetic algorithm to obtain an energy supply station deployment scheme of the unmanned aerial vehicle.
Further, establishing the analysis model includes:
let unmanned aerial vehicle set as U= { U i I=1, …, N, where N is the total number of unmanned aerial vehicles, and the unmanned aerial vehicle energy supply station set is s= { S } i I=1, …, M, where M is the total number of unmanned energy supply stations; deploying a plurality of unmanned aerial vehicles on each path; unmanned aerial vehicle is from unmanned aerial vehicle energy supply station s i Starting and returning to the unmanned energy supply station s at the end of the period i The method comprises the steps of carrying out a first treatment on the surface of the In an area, there are a plurality of known and fixed unmanned travel paths, and initially, an unmanned opportunity is from a certain oneThe unmanned aerial vehicle energy supply station starts and moves to a target position, then flies back to the unmanned aerial vehicle energy supply station from the target position at the end of the period, and the moving path of the unmanned aerial vehicle is as follows
In order to minimize the total distance of all unmanned aerial vehicles, an optimization function is constructed:
while considering several constraints of the optimization problem, as follows:
the distance from a certain unmanned aerial vehicle energy supply station to a target position is represented every time, or the unmanned aerial vehicle returns to a certain unmanned aerial vehicle energy supply station from the target position, wherein the distance cannot exceed the maximum cruising distance K;
the unmanned aerial vehicle completely covers the deployment area, and the service radius of the unmanned aerial vehicle is radius UAV With the unmanned plane as the center of a circle and radius as radius uav The circle of (2) is used as a service area of a single unmanned aerial vehicle, the area is ensured to be covered by all unmanned aerial vehicle service areas in the area, and the area of each area which needs the unmanned aerial vehicle to provide service is area server 。
Further, the allocation and decision of the number of batches required for batch switching of each regional unmanned aerial vehicle comprises:
predicting daily service requests by using a time sequence analysis model according to historical data, and analyzing and predicting daily maximum service request quantity of each area in an unmanned plane scheduling scheme of each area;
performing an allocation strategy of each region;
and carrying out unmanned aerial vehicle batch switching strategies of all areas.
Further, performing an allocation policy for each region, including:
and distributing the unmanned aerial vehicle to each area according to the condition of uneven service request quantity of the area, and simultaneously ensuring that each area can meet the service request based on the predicted demand peak value, so that the waste and surplus of resources are avoided.
Further, performing a lot switching strategy of unmanned aerial vehicles in each area, including:
in each area, in order to ensure that n batches of unmanned aerial vehicles in the area can charge and work in turn and meet service supply of the unmanned aerial vehicles in the whole period, each path of each area is divided, and in each path, unmanned aerial vehicles in the same batch are arranged to work until the energy sources of the unmanned aerial vehicles are nearly exhausted; when the unmanned aerial vehicle energy of a certain batch is nearly exhausted, the unmanned aerial vehicle of the batch is dispatched to return to an unmanned aerial vehicle energy supply station for charging, and meanwhile, the unmanned aerial vehicle of the next batch is dispatched to the paragraph for continuous work; by means of circulation, the unmanned aerial vehicles of all batches on the same path can be guaranteed to be charged and work.
Further, solving the analytical model includes:
rasterizing the map, dividing the map into small grids or cells, and selecting the grids or cells to represent the positions of the unmanned aerial vehicle and the unmanned aerial vehicle energy supply station;
the deployment of the energy supply station and the path optimization of the unmanned aerial vehicle are divided into three loops, namely an innermost loop, a second loop and an outermost loop;
wherein,,
outermost circulation: determining an optimal number of unmanned aerial vehicle energy supply stations;
second layer cycle: calculating the optimal position of the energy supply station;
innermost layer circulation: the path of each energy tender station is optimized.
Further, when the map is rasterized, the position of each grid is represented by using two-dimensional coordinates, and converted into an index value to represent the place on the map, and the accuracy of the original position is maintained, and the maximum deviation distance of the GPS model is selected as the side length of the grid.
Further, the outermost circulation determines an optimal number of unmanned aerial vehicle energy replenishment stations, comprising:
only changing the number of the energy supply stations, setting the change range of the number of the energy supply stations, and executing the change range as a genetic algorithm of a two-layer cycle in which the outermost-layer circulating belt is put into the inner layer, wherein the method is equivalent to simple iteration until the termination condition is met; the termination conditions are: the improvement is small after a plurality of iterations, the number of energy supply stations under a deployment scheme with the minimum total cost is solved, and the calculation formula of the total cost is as follows:
wherein w is 1 、w 2 Is a weight factor, cost all Is the total Cost, cost single Cost and Cost for a single energy supply station per_km For the cost per kilometer of journeyTotal mileage of all unmanned aerial vehicles.
Further, the second tier cycle calculates an optimal location of the energy tender station, comprising:
1) Initializing a population
Randomly generating a set of individuals, each individual representing a location of a plurality of unmanned energy replenishment stations; cycling at the second layer: calculating the optimal position of the energy supply station to generate a set of coordinate sets S location ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 ),…,(x p ,y p ) P=m, M being the number of unmanned energy supply stations;
2) Assessment of fitness
For each individual, i.e., a combination of energy supply stations, the following operations are performed: grouping grids needed to provide computing services into the range of the nearest energy supply station; by this operation, it is ensured that each grid is allocated within the coverage of its nearest energy supply station, in order to provide the required computing services for that grid;
when each individual calculates the fitness, the innermost circulation is required to be called, namely the calculated unmanned aerial vehicle starts from a single supply station, the minimum distance of the supply station is returned after the grid of the service area is serviced, and the fitness of the second circulation is the sum of the minimum distances of all single service paths of the unmanned aerial vehicle energy supply station selected by the individual;
3) Selection of
Selecting part of individuals of the iteration as father according to the fitness value, and selecting two strategies in combination with ranking selection and roulette; firstly, selecting individuals with top fitness values to enter a parent pool by using a ranking selection method; the ranking selection strategy screens out individuals with better performance in the current population, and provides a basis for the next generation of evolution; then, applying a roulette selection strategy to further select the top ranked individuals; in this way, the excellent individual is more likely to become the father of the next generation, and the unmanned aerial vehicle energy supply position combination with the minimum total distance is reserved;
4) Crossover
Performing cross operation on the basis of the selected parent individuals to generate offspring individuals; different crossing modes are adopted, including single-point crossing, multi-point crossing and uniform crossing methods;
(1) single point crossover: selecting a crossing point, cutting two parent individuals at the crossing point, and exchanging the parts after cutting points to generate two child individuals;
(2) multipoint crossing: selecting a plurality of crossing points, exchanging corresponding gene fragments, and generating diversified offspring individuals;
(3) uniform crossing: and selecting a crossing mode based on the probability of the gene loci, randomly generating probability values for each gene locus, and determining whether gene exchange is performed. Generating offspring individuals with a higher diversity;
5) Variation of
Performing mutation operation on offspring individuals, and introducing randomness; by randomly selecting genes or gene loci and changing or replacing the genes or gene loci, the introduction of randomness is helpful to avoid sinking into a local optimal solution, so that the algorithm can be better adapted to the complexity and diversity of the problem;
6) Repeated iteration to find the optimal solution
Iteratively executing the steps 2) to 6), generating a group of individuals, namely the positions of unmanned aerial vehicle energy supply stations, and calculating the fitness of the individuals until the termination condition is met; the termination conditions are: after a certain iteration, the fitness value is larger than the previous fitness value, namely the sum of the distances of the minimum values of the distances of all single service paths of the unmanned aerial vehicle energy supply stations selected by the individuals is larger than the value obtained by the previous iteration, the improvement is not large after repeated iterations, and the positions of a group of unmanned aerial vehicle energy supply stations represented by the individuals with the best fitness are found according to the result of iterative optimization of the genetic algorithm.
Further, the innermost loop optimizes the path of each energy tender station, including:
(1 initializing population
Randomly generating a group of individuals, each individual representing a path of the unmanned aerial vehicle group, i.e. a grid area of service, in order, route uav ＝{g 1 ,g 2 ,g 3 ……g O ......g 1 },g O Numbering grids, the path is a path to and from a single replenishment station, and the starting point and the end point are g 1 That is, the grids where the replenishment station is located, and O is the number of grids covered by the unmanned aerial vehicle service;
(2 evaluation of fitness)
For each individual, calculating that the unmanned aerial vehicle starts from the unmanned aerial vehicle energy supply station to pass through a grid area requiring the unmanned aerial vehicle to provide service and then returns to the starting point, namely returns to the unmanned aerial vehicle energy supply station, wherein the coordinate set of the unmanned aerial vehicle position is U location ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 ),…,(x k ,y k ) I k=n, N being the number of unmanned aerial vehicles; calculating distances using Euclidean distance for representing the sequential passing of Route uav Taking the distance length of the path as the fitness value thereof;
(3 selection)
(4 Cross)
(5 variation)
(6 repeated iteration to find an optimal solution
The steps (2 to (6) are iteratively performed until a termination condition is satisfied, the termination condition being that after a certain iteration the fitness value is greater than the fitness value of the previous time, i.e. the Route is passed in order uav The distance length of the system is larger than the value obtained in the previous iteration, the system is not improved after repeated iterations, and a group of unmanned aerial vehicles represented by individuals with the best adaptability are found according to the result of iterative optimization of the genetic algorithm to provide service for the service area grid to and from a single replenishment station.
Compared with the prior art, the scheme has the following principle and advantages:
1. under the condition that the unmanned aerial vehicle is provided with the edge server, the energy consumption and the charging requirement of the unmanned aerial vehicle are fully considered. The charging requirements are reasonably met in the deployment and task execution processes, so that the sustainability and stability of the unmanned aerial vehicle service are guaranteed.
2. And combining an unmanned aerial vehicle energy supply station and a mobile edge server, learning and analyzing by utilizing historical data, and alternately carrying out service by adopting a plurality of batches of unmanned aerial vehicles in turn, so as to ensure that the area obtains uninterrupted service coverage within a whole period.
3. Genetic algorithm is introduced as a tool for optimizing iteration, so that the total mileage of unmanned aerial vehicle cluster scheduling is minimized, and deployment efficiency and resource utilization rate are improved by optimizing unmanned aerial vehicle paths.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the services required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the figures in the following description are only some embodiments of the present invention, and that other figures can be obtained according to these figures without inventive effort to a person skilled in the art.
FIG. 1 is a schematic flow diagram of an energy supply station deployment method for an unmanned aerial vehicle according to the present invention;
FIG. 2 is a schematic diagram of batch switching of drones in a single zone path (the numbers represent the time sequence of the movement of the drones, i.e., the drones of the previous batch arrive at the drone of the next batch before leaving);
FIG. 3 is a schematic flow diagram of the outermost cycle;
FIG. 4 is a schematic flow diagram of a second layer cycle;
fig. 5 is a schematic diagram of a movement path of the unmanned aerial vehicle in the second-layer cycle;
FIG. 6 is a schematic flow diagram of the innermost cycle;
fig. 7 is a schematic diagram of a path of movement of the drone in the innermost circulation.
Detailed Description
The invention is further illustrated by the following examples:
as shown in fig. 1, the energy supply station deployment method of the unmanned aerial vehicle according to the embodiment includes the following steps:
s1, establishing an analysis model of unmanned aerial vehicle energy supply station deployment;
considering a deployment scheme of multiple paths and multiple unmanned aerial vehicle energy supply stations, let unmanned aerial vehicle set be U= { U i I=1, …, N, where N is the total number of unmanned aerial vehicles, and the unmanned aerial vehicle energy supply station set is s= { S } i I=1, …, M, where M is the total number of unmanned energy replenishment stations. Deploying a number of Unmanned Aerial Vehicles (UAVs) on each path, to simplify the problem, unmanned aerial vehicles from unmanned aerial vehicle energy supply stations s i Starting and returning to the unmanned energy supply station s at the end of the period i . In a larger area there are a number of known and fixed unmanned aerial vehicle travel paths, where initially the unmanned aerial vehicle starts from a certain unmanned aerial vehicle supply station and moves to a target location, and then flies back from that location to the unmanned aerial vehicle supply station at the end of the period, where the unmanned aerial vehicle isThe moving path is It should be noted that the distance from a certain unmanned aerial vehicle energy supply station to a target position each time, or from a target position back to a certain unmanned aerial vehicle energy supply station (possibly a different unmanned aerial vehicle energy supply station), cannot exceed the maximum endurance distance K, since the unmanned aerial vehicle always needs to perform energy supply every day, the unmanned aerial vehicle completely covers the deployment area, assuming that the service radius of the unmanned aerial vehicle is radius uav Unmanned aerial vehicle is used as radius with unmanned aerial vehicle as circle center uav The circle of (2) is used as a service area of a single unmanned aerial vehicle, the area can be covered by all unmanned aerial vehicle service areas in the area, and the area of each area, which needs the unmanned aerial vehicle to provide service, is area server . In order to minimize the total distance of all the drones, the positions of the M drone energy replenishment stations and the service path of the drones need to be determined.
Specifically, an optimization function is adopted to solve an optimization target, and the method comprises the following steps:
while considering several constraints of the optimization problem, as follows:
and establishing a complete deployment scheme for unmanned aerial vehicle energy supply station site selection and unmanned aerial vehicle flight path planning by establishing the analysis model. The optimal scheme adopts three layers of circulation, the outermost circulation determines the number of optimal unmanned aerial vehicle energy supply stations, the middle circulation uses a genetic algorithm to calculate the optimal position of the charging station, and the innermost circulation also uses the genetic algorithm to plan the unmanned aerial vehicle flight path to and from a single charging station. The optimization process starts from the innermost circulation, and the total mileage of the unmanned aerial vehicle is minimized; then circularly changing the positions of the energy supply stations of the unmanned aerial vehicle through a second layer, and finding out the optimal site selection combination of the energy supply stations under the conditions that the positions of the energy supply stations of the unmanned aerial vehicle are different and the number of the energy supply stations is the same; and the outermost layer circulation only changes the number of the energy supply stations to carry out iterative solution. The optimization scheme can greatly improve the economic benefit of edge computing deployment on the premise of completing computing requirements.
The establishment and solution of the above analytical model would face a number of problems:
combination explosion: in a problem, the number of unmanned aerial vehicle sets U and unmanned aerial vehicle energy replenishment station sets S may be large, i.e., N and M may be large values. For each drone, it can start from any one of the energy supply stations and return, which means that there are many possible combinations.
Limiting conditions: there are a number of constraints in the problem. These constraints increase the difficulty of the problem.
Searching the optimal solution is difficult: the objective of the problem is to determine the optimal number of unmanned aerial vehicle energy replenishment stations to achieve the shortest total unmanned aerial vehicle distance in a given service period. This requires searching all possible combinations and calculating the total range of the drone under each combination. The optimization problem is an NP-hard problem, based on the above problems, a heuristic algorithm needs to be used for solution analysis, and the embodiment provides a multi-objective optimization heuristic algorithm based on a genetic algorithm.
S2, distributing and deciding the number of batches required by batch switching of unmanned aerial vehicles in each area;
s2-1, predicting daily service requests by using a time sequence analysis model according to historical data, and analyzing and predicting daily maximum service request quantity of each area in an unmanned aerial vehicle scheduling scheme of each area; for example, a zoneThe set of domains is a= { a i I=1, …, Q }, the daily maximum service request amount per area isThe service time and the service path of the unmanned aerial vehicle need to meet the daily maximum service request quantity of each area, and a certain value cannot be fixed as the calculated service quantity of the unmanned aerial vehicle because the daily maximum service request quantity has certain difference, so that the difference of the service request quantity of each area needs to be obtained from historical data, and reference and limitation are provided for the following unmanned aerial vehicle allocation and switching strategy.
S2-2, carrying out allocation strategies of all areas;
and distributing the unmanned aerial vehicle carrying the edge server to each area according to the condition that the service request quantity of each area is uneven. And a dynamic allocation strategy is adopted, and the batch number of each region is adjusted according to the real-time demand condition. For example, the number of batches is increased during peak demand periods to meet peak demand service requirements. In a relatively free area, the drone is assigned to a larger service request area for service. And setting a threshold value, and when the service request quantity of a certain area exceeds or is close to the threshold value, triggering adjustment of batch times, increasing the batch number of the area, and providing more unmanned aerial vehicle services. According to the dynamic service request quantity of each current area, the batch distribution of the unmanned aerial vehicles is dynamically adjusted, so that the dormancy of an area with excessive service request quantity or one or more batches of unmanned aerial vehicles for energy supply are scheduled, and the service requirements of an area with the service request quantity exceeding or approaching to a threshold value are met. Preventing resource surplus and resource shortage. The allocation policy for each region can be changed according to the service request amount of different time periods, and the batch deployment policy can be adjusted.
S2-3, performing unmanned aerial vehicle batch switching strategies in all areas;
in each area, in order to ensure that n batches of unmanned aerial vehicles in the same area can charge and work in turn and meet service supply of the unmanned aerial vehicle in the whole time period, each path of each area is divided. In each path we arrange for the same batch of unmanned aerial vehicles to work until their energy source is nearly exhausted. When the unmanned aerial vehicle energy of a certain batch is nearly exhausted, the unmanned aerial vehicle of the batch is dispatched to return to the unmanned aerial vehicle energy supply station for charging, and meanwhile, the unmanned aerial vehicle of the next batch is dispatched to the area for continuous operation. Through the cyclic rotation mode, the unmanned aerial vehicle of all batches on same route can be guaranteed to obtain the opportunity of charging and working to ensure the continuous supply of calculation service.
FIG. 2 is a schematic diagram of unmanned lot switching of a single path in an area for illustrating the concept of unmanned lot allocation;
multiple batches of full-energy drones in fig. 2 run alternately. Alternate batches of drones need to be able to reach a designated location to service the area before the first batch fails to service the area, with the next batch of drones arriving before the last batch leaving to ensure that the drones are servicing the area normally uninterrupted. How many batches of drones are specifically needed depends on the drone travel path designed in the historical drone dispatch scheme and it is necessary to ensure that during the process of waiting for the energy-depleted drone batches to be charged, there are still drones able to cover this area.
And S3, solving the analysis model by using a genetic algorithm on the basis of obtaining the distribution of the batch number and the decision result required by the batch switching of the unmanned aerial vehicle in each area, so as to obtain the deployment scheme of the energy supply station of the unmanned aerial vehicle.
The method specifically comprises the following steps:
s3-1, rasterizing a map;
in unmanned aerial vehicle location allocation, one challenge is faced: there are infinite points on the map, direct processing will result in huge computation, and the model has difficulty in handling infinite points. To solve this problem, a discretization strategy is adopted to convert the continuous problem into a discrete problem.
To achieve discretization, the map is divided into small grids and they are selected to represent the positions of the drone and the drone energy replenishment station. Each grid is represented by two-dimensional coordinates and converted to a unique index value to represent a location on the map and maintain the accuracy of the original location. To ensure accuracy, the maximum offset distance of the GPS model is chosen as the side length of the grid. Investigation has shown that civilian GPS positioning distance errors are approximately 15 meters, but offset distances may reach 20 meters or more due to signal strength variations. Thus, 20 meters is used as the side length of the grid. In this way, an infinite number of points can be efficiently processed while maintaining high computational efficiency and model processing power.
S3-2, deploying an energy supply station and optimizing a path of the unmanned aerial vehicle;
iterative ideas and genetic algorithms are used to solve the unmanned aerial vehicle path planning and energy supply station site selection problems. The genetic algorithm is an optimization algorithm based on natural selection and evolution principle, and can be used for searching a better solution in a search space. The execution process of the algorithm is divided into three loops, namely an innermost loop, a second loop and an outermost loop.
Wherein,,
in the innermost loop, genetic algorithms cross and mutate candidate solutions, generate new individuals, and evaluate them. The candidate solution here refers to the path of the drone. By crossover and mutation, a better solution can be obtained, in hopes of finding the optimal solution during evolution.
In the second-tier loop, the genetic algorithm ranks and selects the candidate solutions according to the fitness of the individual (i.e., the value of the total path distance). The higher the fitness the greater the probability that an individual will be selected during the selection process, thus preserving the better solution and eliminating the worse solution.
The outermost loop is the main iterative process of the genetic algorithm. By performing the innermost and second tier loops multiple times, each time a new generation of individuals is generated and a superior solution is selected, the path and the energy tender station location data are gradually optimized. This iterative process will continue until a stop condition is met, such as a certain number of iterations is reached or a satisfactory solution is found.
Through the iterative solution method, the algorithm can find a group of better energy supply station positions, and can use the unmanned aerial vehicle carrying the edge server for providing calculation service for each energy supply station to define an area, so that the total distance can be minimized, and the charging strategy of the unmanned aerial vehicle can be effectively deployed.
In particular, the method comprises the steps of,
as shown in fig. 3, the outermost cycle: determining an optimal number of unmanned aerial vehicle energy supply stations;
only changing the number of the energy supply stations, setting the change range of the number of the energy supply stations, and executing the genetic algorithm as a two-layer circulation of the outermost circulation belt into the inner circulation belt, which is equivalent to simple iteration, until the termination condition is met. The termination conditions are: the improvement is not great after a plurality of iterations, the number of energy supply stations under a deployment scheme with the minimum total cost is solved, and the calculation formula of the total cost is as follows:
w 1 、w 2 is a weight factor, cost all Is the total Cost, cost single Cost and Cost for a single energy supply station per_km For the cost per kilometer of journeyTotal mileage of all unmanned aerial vehicles.
As shown in fig. 4, the second layer loops: calculating an optimal location for an energy tender station, comprising:
1) Initializing a population
Randomly generating a set of individuals, each individual representing a location of a plurality of unmanned energy replenishment stations; cycling at the second layer: calculating the optimal position of the energy supply station to generate a set of coordinate sets S location ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 ),…,(x p ,y p ) P=m, M being the number of unmanned energy supply stations;
2) Assessment of fitness
For each individual (i.e., combination of energy supply stations), the following operations are performed: the grid that needs to provide the computing service is classified as being the nearest energy supply station. By this operation, it is ensured that each grid is allocated to the range covered by the energy replenishment station closest thereto, so as to provide the required computing service for that grid. Such allocation strategies help optimize energy utilization and allocation of computing resources, thereby improving the efficiency and reliability of the overall system;
when each individual calculates the fitness, the innermost circulation is required to be called, namely the calculated unmanned aerial vehicle starts from a single supply station, the minimum distance of the supply station is returned after the grid of the service area is serviced, and the fitness of the second circulation is the sum of the minimum distances of all single service paths of the unmanned aerial vehicle energy supply station selected by the individual;
as shown in fig. 5, the sum of minimum distances of 4 charging stations in the area of the service area after the unmanned aerial vehicle calculated by the innermost circulation starts from a single replenishment station is returned to the replenishment station after the service is performed on the grid of the service area is called as the adaptability of the second-tier circulation.
3) Selection of
Selecting part of individuals of the iteration as father according to the fitness value, and selecting two strategies in combination with ranking selection and roulette; firstly, selecting individuals with top fitness values to enter a parent pool by using a ranking selection method; the ranking selection strategy screens out individuals with better performance in the current population, and provides a basis for the next generation of evolution; then, applying a roulette selection strategy to further select the top ranked individuals; in this way, the excellent individual is more likely to become the father of the next generation, and the unmanned aerial vehicle energy supply position combination with the minimum total distance is reserved;
4) Crossover
Performing cross operation on the basis of the selected parent individuals to generate offspring individuals; different crossing modes are adopted, including single-point crossing, multi-point crossing and uniform crossing methods;
(1) single point crossover: selecting a crossing point, cutting two parent individuals at the crossing point, and exchanging the parts after cutting points to generate two child individuals;
(2) multipoint crossing: selecting a plurality of crossing points, exchanging corresponding gene fragments, and generating diversified offspring individuals;
(3) uniform crossing: selecting a crossing mode based on the probability of the gene loci, randomly generating a probability value for each gene locus, and determining whether to perform gene exchange; generating offspring individuals with a higher diversity;
5) Variation of
Performing mutation operation on offspring individuals, and introducing randomness; by randomly selecting genes or gene loci and changing or replacing the genes or gene loci, the introduction of randomness is helpful to avoid sinking into a local optimal solution, so that the algorithm can be better adapted to the complexity and diversity of the problem;
6) Repeated iteration to find the optimal solution
Iteratively executing the steps 2) to 6), generating a group of individuals, namely the positions of unmanned aerial vehicle energy supply stations, and calculating the fitness of the individuals until the termination condition is met; the termination conditions are: after a certain iteration, the fitness value is larger than the previous fitness value, namely the sum of the distances of the minimum values of the distances of all single service paths of the unmanned aerial vehicle energy supply stations selected by the individuals is larger than the value obtained by the previous iteration, the improvement is not large after repeated iterations, and the positions of a group of unmanned aerial vehicle energy supply stations represented by the individuals with the best fitness are found according to the result of iterative optimization of the genetic algorithm.
As shown in fig. 6, the innermost cycle: optimizing the path of each energy supply station;
(1, initializing population
Randomly generating a group of individuals, each individual representing a path of the unmanned aerial vehicle group, i.e. a grid area of service, in order, route uav ＝{g 1 ,g 2 ,g 3 ……g O ......g 1 },g O Numbering grids, the path is a path to and from a single replenishment station, and the starting point and the end point are g 1 I.e., the grid where the replenishment station is located, O is the number of grids covered by the drone service.
(2, assessing fitness)
For each individual, calculating that the unmanned aerial vehicle starts from the unmanned aerial vehicle energy supply station to pass through a grid area requiring the unmanned aerial vehicle to provide service and then returns to the starting point, namely returns to the unmanned aerial vehicle energy supply station, wherein the coordinate set of the unmanned aerial vehicle position is U location ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 ),…,(x k ,y k ) I k=n, N being the number of drones. Calculating distances using Euclidean distance for representing the sequential passing of Route uav The distance length of the path is taken as the fitness value.
The sum of the distances of paths 1, 2, 3, 4, 5, 6 as shown in fig. 7 serves as the fitness of the innermost loop.
(3 selection)
(4 Cross)
(5 variation)
(6 repeated iteration to find an optimal solution
The steps (2 to (6) are iteratively performed until a termination condition is satisfied, the termination condition being that after a certain iteration the fitness value is greater than the fitness value of the previous time, i.e. the Route is passed in order uav The distance length of the system is larger than the value obtained in the previous iteration, the system is not improved after repeated iterations, and a group of unmanned aerial vehicles represented by individuals with the best adaptability are found according to the result of iterative optimization of the genetic algorithm to provide service for the service area grid to and from a single replenishment station.
The above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, so variations in shape and principles of the present invention should be covered.
Claims (10)
1. An energy tender station deployment method for an unmanned aerial vehicle, comprising:
establishing an analysis model of unmanned aerial vehicle energy supply station deployment;
distributing and deciding the batch number required by batch switching of unmanned aerial vehicles in each area;
and on the basis of obtaining the distribution of the batch number and the decision result required by the batch switching of the unmanned aerial vehicle in each area, solving an analysis model by using a genetic algorithm to obtain an energy supply station deployment scheme of the unmanned aerial vehicle.
2. The unmanned aerial vehicle energy tender station deployment method of claim 1, wherein establishing the analytical model comprises:
let unmanned aerial vehicle set as U= { U i I=1, …, N, where N is the total number of unmanned aerial vehicles, and the unmanned aerial vehicle energy supply station set is s= { S } i I=1, …, M, where M is the total number of unmanned energy supply stations; deploying a plurality of unmanned aerial vehicles on each path; unmanned aerial vehicle is from unmanned aerial vehicle energy supply station s i Starting and returning to the unmanned energy supply station s at the end of the period i The method comprises the steps of carrying out a first treatment on the surface of the In an area, a plurality of known and fixed unmanned aerial vehicle running paths exist, an unmanned aerial vehicle starts from a certain unmanned aerial vehicle energy supply station and moves to a target position at the beginning, then flies back to the unmanned aerial vehicle energy supply station from the position at the end of a period, and the moving path of the unmanned aerial vehicle is as follows
In order to minimize the total distance of all unmanned aerial vehicles, an optimization function is constructed:
while considering several constraints of the optimization problem, as follows:
the distance from a certain unmanned aerial vehicle energy supply station to a target position is represented every time, or the unmanned aerial vehicle returns to a certain unmanned aerial vehicle energy supply station from the target position, wherein the distance cannot exceed the maximum cruising distance K;
the unmanned aerial vehicle completely covers the deployment area, and the service radius of the unmanned aerial vehicle is radius UAV With the unmanned plane as the center of a circle and radius as radius uav The circle of (2) is used as a service area of a single unmanned aerial vehicle, the area is ensured to be covered by all unmanned aerial vehicle service areas in the area, and the area of each area which needs the unmanned aerial vehicle to provide service is erea server 。
3. The energy tender station deployment method of a drone of claim 2, wherein assigning and deciding the number of batches required for each regional drone batch switch comprises:
predicting daily service requests by using a time sequence analysis model according to historical data, and analyzing and predicting daily maximum service request quantity of each area in an unmanned plane scheduling scheme of each area;
performing an allocation strategy of each region;
and carrying out unmanned aerial vehicle batch switching strategies of all areas.
4. A method of deploying an energy tender station for a drone according to claim 3, wherein performing an allocation strategy for each zone comprises:
and distributing the unmanned aerial vehicle to each area according to the condition of uneven service request quantity of the area, and simultaneously ensuring that each area can meet the service request based on the predicted demand peak value, so that the waste and surplus of resources are avoided.
5. A method of unmanned aerial vehicle energy tender station deployment according to claim 3, wherein performing unmanned aerial vehicle lot switching policies for each zone comprises:
in each area, in order to ensure that n batches of unmanned aerial vehicles in the area can charge and work in turn and meet service supply of the unmanned aerial vehicles in the whole period, each path of each area is divided, and in each path, unmanned aerial vehicles in the same batch are arranged to work until the energy sources of the unmanned aerial vehicles are nearly exhausted; when the unmanned aerial vehicle energy of a certain batch is nearly exhausted, the unmanned aerial vehicle of the batch is dispatched to return to an unmanned aerial vehicle energy supply station for charging, and meanwhile, the unmanned aerial vehicle of the next batch is dispatched to the paragraph for continuous work; by means of circulation, the unmanned aerial vehicles of all batches on the same path can be guaranteed to be charged and work.
6. The unmanned aerial vehicle energy tender station deployment method of claim 2, wherein solving the analytical model comprises:
rasterizing the map, dividing the map into small grids or cells, and selecting the grids or cells to represent the positions of the unmanned aerial vehicle and the unmanned aerial vehicle energy supply station;
the deployment of the energy supply station and the path optimization of the unmanned aerial vehicle are divided into three loops, namely an innermost loop, a second loop and an outermost loop;
wherein,,
outermost circulation: determining an optimal number of unmanned aerial vehicle energy supply stations;
second layer cycle: calculating the optimal position of the energy supply station;
innermost layer circulation: the path of each energy tender station is optimized.
7. The energy supply station deployment method of an unmanned aerial vehicle according to claim 6, wherein when the map is rasterized, the position of each grid is represented by using two-dimensional coordinates and converted into an index value to represent a place on the map, and the accuracy of the original position is maintained, and the maximum deviation distance of the GPS model is selected as the side length of the grid.
8. The unmanned aerial vehicle energy tender station deployment method of claim 6, wherein the outermost loop determines an optimal number of unmanned aerial vehicle energy tender stations, comprising:
only changing the number of the energy supply stations, setting the change range of the number of the energy supply stations, and executing the change range as a genetic algorithm of a two-layer cycle in which the outermost-layer circulating belt is put into the inner layer, wherein the method is equivalent to simple iteration until the termination condition is met; the termination conditions are: the improvement is small after a plurality of iterations, the number of energy supply stations under a deployment scheme with the minimum total cost is solved, and the calculation formula of the total cost is as follows:
wherein w is 1 、w 2 Is a weight factor, cost all Is the total Cost, cost single Cost and Cost for a single energy supply station per_km For the cost per kilometer of journeyTotal mileage of all unmanned aerial vehicles.
9. The unmanned aerial vehicle energy tender station deployment method of claim 6, wherein the second tier loop calculates the optimal position of the energy tender station, comprising:
1) Initializing a population
Randomly generating a set of individuals, each individual representing a location of a plurality of unmanned energy replenishment stations; cycling at the second layer: calculating the optimal position of the energy supply station to generate a set of coordinate sets S location ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 ),…,(x p ,y p ) P=m, M being the number of unmanned energy supply stations;
2) Assessment of fitness
For each individual, i.e., a combination of energy supply stations, the following operations are performed: grouping grids needed to provide computing services into the range of the nearest energy supply station; by this operation, it is ensured that each grid is allocated within the coverage of its nearest energy supply station, in order to provide the required computing services for that grid;
when each individual calculates the fitness, the innermost circulation is required to be called, namely the calculated unmanned aerial vehicle starts from a single supply station, the minimum distance of the supply station is returned after the grid of the service area is serviced, and the fitness of the second circulation is the sum of the minimum distances of all single service paths of the unmanned aerial vehicle energy supply station selected by the individual;
3) Selection of
Selecting part of individuals of the iteration as father according to the fitness value, and selecting two strategies in combination with ranking selection and roulette; firstly, selecting individuals with top fitness values to enter a parent pool by using a ranking selection method; the ranking selection strategy screens out individuals with better performance in the current population, and provides a basis for the next generation of evolution; then, applying a roulette selection strategy to further select the top ranked individuals; in this way, the excellent individual is more likely to become the father of the next generation, and the unmanned aerial vehicle energy supply position combination with the minimum total distance is reserved;
4) Crossover
Performing cross operation on the basis of the selected parent individuals to generate offspring individuals; different crossing modes are adopted, including single-point crossing, multi-point crossing and uniform crossing methods;
(1) single point crossover: selecting a crossing point, cutting two parent individuals at the crossing point, and exchanging the parts after cutting points to generate two child individuals;
(2) multipoint crossing: selecting a plurality of crossing points, exchanging corresponding gene fragments, and generating diversified offspring individuals;
(3) uniform crossing: selecting a crossing mode based on the probability of the gene loci, randomly generating a probability value for each gene locus, and determining whether to perform gene exchange; generating offspring individuals with a higher diversity;
5) Variation of
Performing mutation operation on offspring individuals, and introducing randomness; by randomly selecting genes or gene loci and changing or replacing the genes or gene loci, the introduction of randomness is helpful to avoid sinking into a local optimal solution, so that the algorithm can be better adapted to the complexity and diversity of the problem;
6) Repeated iteration to find the optimal solution
Iteratively executing the steps 2) to 6), generating a group of individuals, namely the positions of unmanned aerial vehicle energy supply stations, and calculating the fitness of the individuals until the termination condition is met; the termination conditions are: after a certain iteration, the fitness value is larger than the previous fitness value, namely the sum of the distances of the minimum values of the distances of all single service paths of the unmanned aerial vehicle energy supply stations selected by the individuals is larger than the value obtained by the previous iteration, the improvement is not large after repeated iterations, and the positions of a group of unmanned aerial vehicle energy supply stations represented by the individuals with the best fitness are found according to the result of iterative optimization of the genetic algorithm.
10. The unmanned aerial vehicle energy tender station deployment method of claim 6, wherein the innermost loop optimizes the path of each energy tender station, comprising:
(1 initializing population
Randomly generating a group of individuals, each individual representing a path of the unmanned aerial vehicle group, i.e. a grid area of service, in order, route uav ＝{g 1 ,g 2 ,g 3 ……g O ......g 1 },g O Numbering grids, the path is a path to and from a single replenishment station, and the starting point and the end point are g 1 That is, the grids where the replenishment station is located, and O is the number of grids covered by the unmanned aerial vehicle service;
(2 evaluation of fitness)
For each individual, calculating that the unmanned aerial vehicle starts from the unmanned aerial vehicle energy supply station to pass through a grid area requiring the unmanned aerial vehicle to provide service and then returns to the starting point, namely returns to the unmanned aerial vehicle energy supply station, wherein the coordinate set of the unmanned aerial vehicle position is U location ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 ),…,(x k ,y k )|k＝N}，N is the number of unmanned aerial vehicles; calculating distances using Euclidean distance for representing the sequential passing of Route uav Taking the distance length of the path as the fitness value thereof;
(3 selection)
(4 Cross)
(5 variation)
(6 repeated iteration to find an optimal solution
The steps (2 to (6) are iteratively performed until a termination condition is satisfied, the termination condition being that after a certain iteration the fitness value is greater than the fitness value of the previous time, i.e. the Route is passed in order uav The distance length of the system is larger than the value obtained in the previous iteration, the system is not improved after repeated iterations, and a group of unmanned aerial vehicles represented by individuals with the best adaptability are found according to the result of iterative optimization of the genetic algorithm to provide service for the service area grid to and from a single replenishment station.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310971294.1A CN116805201A (en) | 2023-08-02 | 2023-08-02 | Unmanned aerial vehicle energy supply station deployment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310971294.1A CN116805201A (en) | 2023-08-02 | 2023-08-02 | Unmanned aerial vehicle energy supply station deployment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116805201A true CN116805201A (en) | 2023-09-26 |
Family
ID=88079598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310971294.1A Pending CN116805201A (en) | 2023-08-02 | 2023-08-02 | Unmanned aerial vehicle energy supply station deployment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116805201A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117952285A (en) * | 2024-03-27 | 2024-04-30 | 广东工业大学 | Dynamic scheduling method for unmanned aerial vehicle mobile charging station |
-
2023
- 2023-08-02 CN CN202310971294.1A patent/CN116805201A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117952285A (en) * | 2024-03-27 | 2024-04-30 | 广东工业大学 | Dynamic scheduling method for unmanned aerial vehicle mobile charging station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111862579B (en) | Taxi scheduling method and system based on deep reinforcement learning | |
| CN112016812B (en) | Multi-unmanned aerial vehicle task scheduling method, system and storage medium | |
| Qi et al. | Scalable parallel task scheduling for autonomous driving using multi-task deep reinforcement learning | |
| Rekha et al. | Efficient task allocation approach using genetic algorithm for cloud environment | |
| CN109495945B (en) | Clustering-based cooperative charging method in WSNs | |
| CN113885555A (en) | Multi-machine task allocation method and system for power transmission line dense channel routing inspection | |
| CN116805201A (en) | Unmanned aerial vehicle energy supply station deployment method | |
| Dai et al. | A learning algorithm for real-time service in vehicular networks with mobile-edge computing | |
| Wei et al. | Joint UAV trajectory planning, DAG task scheduling, and service function deployment based on DRL in UAV-empowered edge computing | |
| Tian et al. | Service satisfaction-oriented task offloading and UAV scheduling in UAV-enabled MEC networks | |
| CN102325054A (en) | Self-adaptive adjusting method for hierarchy management of distributed type calculation management platform cluster | |
| Zhou et al. | Design and optimization of solar-powered shared electric autonomous vehicle system for smart cities | |
| Zeng et al. | Joint resource allocation and trajectory optimization in UAV-enabled wirelessly powered MEC for large area | |
| Chen et al. | VarLenMARL: A framework of variable-length time-step multi-agent reinforcement learning for cooperative charging in sensor networks | |
| CN113190342A (en) | Method and system architecture for multi-application fine-grained unloading of cloud-edge cooperative network | |
| CN113139639A (en) | MOMBI-based smart city application-oriented multi-target calculation migration method and device | |
| CN115421885B (en) | Distributed multi-target cloud task scheduling method and device and cloud service system | |
| CN116321189A (en) | Server deployment method based on deep reinforcement learning in edge-oriented computing | |
| CN102523300A (en) | Data-intensive cloud storage model facing intelligent power grid | |
| CN116384706A (en) | Scheduling method and system for ship segmented lightering vehicles | |
| Lu et al. | MOEA/D based UAV swarm deployment for wireless coverage | |
| Chen et al. | Improve the quality of charging services for rechargeable wireless sensor networks by deploying a mobile vehicle with multiple removable chargers | |
| Qi et al. | Cluster-PSO based resource orchestration for multi-task applications in vehicular cloud | |
| CN113810916A (en) | Multi-server mixed deployment architecture and method in 5G/6G edge computing scene | |
| Das et al. | Collaborative data gathering and recharging using multiple mobile vehicles in wireless rechargeable sensor network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |