CN117252318A - Intelligent networking automobile group machine collaborative carpooling scheduling method and system - Google Patents
Intelligent networking automobile group machine collaborative carpooling scheduling method and system Download PDFInfo
- Publication number
- CN117252318A CN117252318A CN202311258387.6A CN202311258387A CN117252318A CN 117252318 A CN117252318 A CN 117252318A CN 202311258387 A CN202311258387 A CN 202311258387A CN 117252318 A CN117252318 A CN 117252318A
- Authority
- CN
- China
- Prior art keywords
- carpooling
- scheduling
- collaborative
- vehicle
- objective function
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000006855 networking Effects 0.000 title description 2
- 238000005457 optimization Methods 0.000 claims abstract description 34
- 241000879809 Felis margarita Species 0.000 claims abstract description 26
- 238000011161 development Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 36
- 238000004891 communication Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 10
- 230000035945 sensitivity Effects 0.000 claims description 9
- 230000004044 response Effects 0.000 abstract description 2
- 241000282326 Felis catus Species 0.000 description 3
- 241000255581 Drosophila <fruit fly, genus> Species 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- ZINJLDJMHCUBIP-UHFFFAOYSA-N ethametsulfuron-methyl Chemical compound CCOC1=NC(NC)=NC(NC(=O)NS(=O)(=O)C=2C(=CC=CC=2)C(=O)OC)=N1 ZINJLDJMHCUBIP-UHFFFAOYSA-N 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/02—Reservations, e.g. for tickets, services or events
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a method and a system for scheduling intelligent network-connected automobile group machines to cooperatively share automobiles, wherein the method comprises the following steps: acquiring operation vehicle data and passenger order data in a target area; based on the operation vehicle data and the order data, establishing a collaborative carpool scheduling objective function and corresponding constraint conditions by taking the shortest vehicle driving path, the shortest passenger waiting time and the highest carpool success rate as targets; and solving an objective function of collaborative carpooling scheduling by adopting an improved sand cat swarm optimization algorithm to obtain a swarm machine collaborative carpooling scheduling strategy. The invention fully considers factors such as vehicle driving paths, passenger waiting time, car sharing success rate and the like to establish the collaborative car sharing scheduling objective function, improves the exploration stage and the development stage of the sand cat swarm optimization algorithm, solves the objective function of collaborative car sharing scheduling, and obtains the swarm machine collaborative car sharing scheduling strategy so as to better adapt to the diversified car sharing requirements at the present stage, and has the advantages of high response speed and stable and reliable scheduling result.
Description
Technical Field
The invention belongs to the technical field of intelligent network-connected automobile group machine cooperation, and particularly relates to an intelligent network-connected automobile group machine cooperation carpooling scheduling method and system.
Background
The intelligent network-connected automobile is an organic combination of the Internet of vehicles and the intelligent automobile, is provided with advanced devices such as a vehicle-mounted sensor, a controller and an actuator, integrates modern communication and network technology, realizes information exchange sharing of the automobile, people, roads and the background, and is an important component of intelligent traffic. The net car with the car sharing mechanism provides effective assistance for relieving traffic pressure, saving energy and reducing emission. The group machine cooperative carpooling scheduling method is a method for optimizing carpooling scheduling by using a group intelligent or machine learning technology, and the travel demands of a plurality of passengers are integrated and coordinated to reduce the number of vehicles and the travel distance to the greatest extent, so that the carpooling efficiency and the service quality are improved. However, the current research on intelligent network-connected automobile group machine collaborative carpooling scheduling is less, and considered factors are not comprehensive, and often do not meet the actual situation.
The invention patent with publication number of CN110084390A discloses a multi-vehicle collaborative carpool path optimization method based on an improved drosophila algorithm, which aims at the shortest driving distance of all passenger orders to be completed, establishes a multi-vehicle collaborative carpool path optimization mathematical model, and solves the carpool path by using the improved drosophila algorithm. The multi-car carpooling cooperation can be carried out on batches of passengers, but the optimization target is single, and the multi-car carpooling requirement of the current stage cannot be met.
Therefore, a new multi-car collaborative carpool scheduling scheme is needed to better accommodate the current diversified carpool requirements.
Disclosure of Invention
In view of the above, the invention provides an intelligent network-connected automobile group machine collaborative carpooling scheduling method and system, which are used for solving the problem of unreasonable route planning during multi-automobile collaborative carpooling.
The invention discloses a method for scheduling intelligent network-connected automobile group machines to cooperatively pooling, which comprises the following steps:
acquiring operation vehicle data and passenger order data in a target area;
based on the operation vehicle data and the order data, establishing a collaborative carpool scheduling objective function and corresponding constraint conditions by taking the shortest vehicle driving path, the shortest passenger waiting time and the highest carpool success rate as targets;
and solving an objective function of collaborative carpooling scheduling by adopting an improved sand cat swarm optimization algorithm to obtain a swarm machine collaborative carpooling scheduling strategy.
On the basis of the technical scheme, preferably, the operation vehicle data comprises the total number of vehicles participating in operation in a target area, the number of vehicles carrying on a core, a pricing rule and the position of the vehicles before dispatching;
the passenger order data comprises a starting point, an ending point and the number of passengers of each order; and forming a path point set by the starting points and the ending points of all orders.
On the basis of the above technical solution, preferably, the objective of establishing the collaborative carpool scheduling objective function with the shortest vehicle driving path, the least waiting time of passengers and the highest carpool success rate is specifically:
wherein F is an objective function, N is the total number of the route points, P is the total number of passengers, K is the total number of vehicles, N and m respectively represent the route point numbers, indicating whether the vehicle k passes the route points n, m, d nm Representing the distance between the path points N, m, k=1, 2, …, K, n=1, 2, …, N, m=1, 2, …, N; /> Indicating that vehicle k is not going to pick up the p-th passenger; />Representing the waiting time of the passenger when the vehicle is in zone k and the p passenger is received, < >>Estimating according to the distance between the vehicle position before dispatching and the starting point of the order, wherein p=1, 2, … and P; n (N) A 、N s The order quantity in a period of time and the order quantity of successful carpooling are respectively; alpha, beta and gamma are weight coefficients.
On the basis of the above technical solution, preferably, the constraint condition includes:
wherein,the number of passengers in the kth vehicle is represented between the path points n and m, and Q represents the number of passengers on the vehicle; />The ride share rate of the passengers who get on the vehicle at the route point n to get off the vehicle at the route point m is shown.
On the basis of the above technical solution, preferably, the solving the objective function of the collaborative carpooling scheduling by adopting the improved optimization algorithm of the sand cat group specifically includes:
randomly initializing the population position of a sand cat group optimization algorithm, setting the population scale as M and the maximum iteration number as T; taking the objective function as a fitness function, calculating the fitness of each individual in the population, and storing the optimal position;
updating a control parameter R converted between an exploration phase and a development phase;
determining to enter an exploration phase or a development phase according to the magnitude of the control parameter R;
introducing an arithmetic average idea based on a subtraction average optimization algorithm in the exploration stage, and updating the position of an individual according to the current position of the individual, the optimal position and the subtraction average of the population;
in the development stage, on the basis of a random angle, introducing a dominant individual following criterion based on direction judgment, and updating the individual position;
and recalculating the fitness of each individual in the population, and carrying out iterative operation until the maximum iterative times are reached, so as to obtain an optimal solution as a route planning result of each vehicle.
On the basis of the above technical solution, preferably, in the exploring stage, a subtraction average value idea based on a subtraction average optimization algorithm is introduced, and a formula for updating the position of the individual according to the current position of the individual, the optimal position and the subtraction average value of the population is:
wherein X is i (t)、X i (t+1) the position of individual i at the time of the t, t+1 iteration, X b (t) is the current optimal position, v is the "v-" subtraction defined in the subtraction average optimization algorithm, X j (t) is the position of the jth individual at the t-th iteration, j=1, 2, …, M is the total number of individuals, w 1 、w 2 As the weight coefficient, r 1 Sensitivity, r of a sand cat 2 Is [0,1]Random numbers in between.
On the basis of the above technical solution, preferably, in the development stage, on the basis of a random angle, a dominant individual following criterion based on direction judgment is introduced, and the formula for updating the individual position is as follows:
X i (t+1)＝X b (t)-X rnd (t)·cos(θ)·r 1 ·sign(F(X l (t))-F(X r (t))
wherein F is an objective function, θ is a random angle, r 1 Sensitivity of sand cat, X rnd (t) is a random vector, X r (t)、X l (t) each represents X rnd Right and left vectors of (t),is a unit direction vector.
The second aspect of the invention discloses an intelligent network-connected automobile group machine collaborative carpooling dispatching system, which comprises:
and a data acquisition module: the method comprises the steps of acquiring operation vehicle data and passenger order data in a target area;
the target establishment module: the method is used for establishing a collaborative carpooling scheduling objective function and corresponding constraint conditions based on the operation vehicle data and the order data and aiming at the shortest vehicle driving path, the shortest passenger waiting time and the highest carpooling success rate;
scheduling solving module: the method is used for solving the objective function of the collaborative carpooling scheduling by adopting an improved sand cat swarm optimization algorithm to obtain a swarm machine collaborative carpooling scheduling strategy.
In a third aspect of the present invention, an electronic device is disclosed, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete communication with each other through the bus;
the memory stores program instructions executable by the processor which the processor invokes to implement the method according to the first aspect of the invention.
In a fourth aspect of the invention, a computer-readable storage medium is disclosed, storing computer instructions that cause a computer to implement the method according to the first aspect of the invention.
Compared with the prior art, the invention has the following beneficial effects:
1) According to the invention, the factors such as the vehicle driving path, the passenger waiting time, the car sharing success rate and the like are fully considered to establish the collaborative car sharing scheduling objective function, the improved sand cat swarm optimization algorithm is adopted to solve the objective function of collaborative car sharing scheduling, and the obtained swarm machine collaborative car sharing scheduling strategy is better suitable for the current-stage diversified car sharing requirements and has the advantages of high response speed and stable and reliable scheduling result.
2) In the exploration stage of the optimization algorithm of the satay cat group, the arithmetic mean value thought based on the subtraction mean optimization algorithm is introduced, the positions of the individuals are updated according to the current positions of the individuals, the optimal positions and the subtraction mean value of the group, so that information sharing among different individuals can be enhanced, and the situation that local optimal solutions are sunk in early stages in the exploration stage is avoided.
3) In the development stage of the optimization algorithm of the satay cat group, the dominant individual following criterion based on direction judgment is further introduced on the basis of randomly selected attack angles to update the individual positions, so that the randomness of angle selection can be kept, local optimum is avoided, new individuals can keep basic direction judgment capability on the basis of the random angles, the individuals move towards the optimal individual direction, and the algorithm convergence speed is effectively accelerated.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a collaborative carpooling scheduling method of an intelligent network-connected automobile group machine.
Detailed Description
The following description of the embodiments of the present invention will clearly and fully describe the technical aspects of the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
Referring to fig. 1, the invention provides a method for scheduling intelligent network-connected automobile group machines to cooperate with a car pooling, which comprises the following steps:
s1, acquiring operation vehicle data and passenger order data in a target area.
The operating vehicle data generally includes the total number of vehicles available in the target area, the number of vehicles on-board, pricing rules, and the vehicle location before dispatch. Passenger order data typically includes a start point, an end point, a number of passengers, etc. for each order; and collecting the starting points and the ending points of all the current orders to form a path point set.
S2, based on the operation vehicle data and the order data, a collaborative carpooling scheduling objective function and corresponding constraint conditions are established with the aim of the shortest vehicle driving path, the shortest passenger waiting time and the highest carpooling success rate.
To simplify the model for ease of operation, the following assumptions are made prior to establishing the objective function:
(1) when a passenger gets off the vehicle and has residual capacity, a new passenger is allowed to be carried;
(2) waiting at a starting point after a default passenger places an order;
(3) the time for passengers getting on and off is ignored;
(4) all path points are reachable and the distance between each other is known;
(5) the principle of nearby bill taking is followed when no passenger is on the vehicle;
(6) the total number of available operation vehicles in the target area is unchanged within a set time period;
(7) and refreshing the data according to fixed time intervals, and rescheduling.
S21, establishing a collaborative carpooling scheduling objective function.
The vehicle driving path is shortest, the waiting time of passengers is least, the success rate of carpooling is highest, and the expression of the established collaborative carpooling scheduling objective function is as follows:
wherein F is an objective function, N is the total number of the route points, P is the total number of passengers, K is the total number of vehicles, N and m respectively represent the route point numbers, indicating that vehicle k does not pass the waypoints n, m, < > or->Indicating that the vehicle k passes through the route points n, m, d nm Representing the distance between the path points N, m, k=1, 2, …, K, n=1, 2, …, N, m=1, 2, …, N; /> Indicating that vehicle k is not connected to the p-th passenger, < > or->Indicating that vehicle k is to pick up the p-th passenger, < > on>Representing the waiting time of the passenger when the vehicle is in zone k and the p passenger is received, < >>Estimating according to the distance between the vehicle position before dispatching and the starting point of the order, wherein p=1, 2, … and P; n (N) A 、N s The number of orders in a period of time and the success of carpooling are respectivelyOrder quantity; alpha, beta and gamma are weight coefficients.
S22, establishing constraint conditions.
The constraint condition firstly meets the limit of the number of the nuclear passengers of the vehicle, and the number of passengers in each vehicle cannot exceed the number of the nuclear passengers of the vehicle. And each passenger can only be served by one vehicle, and is not allowed to transfer. In addition, for carpooling, the amount spent by passengers carpooling should not exceed the amount spent without carpooling. Travel cost and driver income constraint can be performed based on pricing rules.
The method is based on the restraint of the number of people to be carried, the restraint of the amount spent by the carpooling and the restraint of the transfer impermissible, and the established restraint conditions are as follows:
wherein,the number of passengers in the kth vehicle is represented between the path points n and m, and Q represents the number of passengers on the vehicle; />The ride share rate of the passengers who get on the vehicle at the route point n to get off the vehicle at the route point m is shown.
And S3, solving an objective function of collaborative carpooling scheduling by adopting an improved optimization algorithm of the sand cat group to obtain a group machine collaborative carpooling scheduling strategy.
S31, randomly initializing the population position of the optimization algorithm of the sand cat group, setting the population scale as M and the maximum iteration number as T.
The group-machine collaborative carpooling scheduling of the invention is to plan the driving route of each vehicle when a plurality of vehicles are collaborative carpooling, so that each vehicle passes through a proper path point and is efficiently picked up by each passenger. Because the number of available vehicles is K, the K vehicles need to finish the pickup of P passengers together and are not repeated, so the number range of the passengers [1, P ] can be directly used]Optimization algorithm for boundary pair cat groupRandomly initializing a population of individuals in the population, denoted as X i ＝[x i1 ,x i2 ,…,x iP ]I=1, 2, …, M. At X i The passenger-carrying objects of K vehicles are stored in sequence, and since the start point and the end point of each passenger are fixed, the route of each vehicle can be determined.
S32, calculating the fitness of each individual in the population by taking the objective function as a fitness function, and storing the optimal position.
And substituting the positions of the individuals into the objective function F to calculate fitness values, and arranging the fitness values in ascending order, wherein the minimum value corresponds to the optimal position.
S33, updating the control parameter R of the transition between the exploration phase and the development phase.
The formula of the control parameter R for the transition between the exploration phase and the development phase is:
R＝2r G ·rand(0,1)-r G
wherein T is the current iteration number, T is the maximum iteration number, r G ∈[0,2]Sensitivity of a sand cat, s M As the auditory factor of a salsa, s is preferable M ＝2。
S34, if the I R I is less than or equal to 1, entering an exploration stage.
In the exploration stage, an arithmetic average idea based on a subtraction average optimization algorithm is introduced, and the positions of the individuals are updated according to the current positions of the individuals, the optimal positions and the subtraction average of the groups.
The location update formula of the individual is:
wherein X is i (t)、X i (t+1) the position of individual i at the time of the t, t+1 iteration, X b (t) is the current optimal position, X j (t) is the t th iterationThe j-th individual position, j=1, 2, …, M is the total number of individuals, v is the "v-" subtraction defined in the subtraction average optimization algorithm, w 1 、w 2 As the weight coefficient, r 1 ＝r G Rand (0, 1) is the new sensitivity, r, of a sand cat 2 Is a random number subject to normal distribution.
X i (t)-vX j (t) redefined "v-" subtraction operation for the subtraction average optimization algorithm, satisfying:
wherein F is an objective function, sign is a sign function,the dimension is P, which is a vector of random numbers generated from the set 1, 2.
In the invention, the idea of subtracting the average value based on the subtracting average optimization algorithm is introduced in the exploration stage of the sand cat swarm optimization algorithm, and when the individual position is updated, the factors such as the v-subtraction arithmetic average value among the current position, the optimal position and each search agent of the swarm of the individual are comprehensively used, so that the information sharing among different individuals can be enhanced, the situation that the local optimal solution is sunk in early in the exploration stage is avoided, and the global searching capability is enhanced.
And S35, if |R| >1, entering a development stage.
In the development stage, assuming that the sensitivity range of the sand cat is a circle, randomly selecting an angle theta for each sand cat by using a roulette method, and introducing a dominant individual following criterion based on direction judgment on the basis of the random angle theta to update the individual position.
The formula for performing individual location update is:
X i (t+1)＝X b (t)-X rnd (t)·cos(θ)·r 1 ·sign(F(X l (t))-F(X r (t))
wherein F is an objective function, r 1 For sensitivity, X rnd (t) is a random vector, X rnd (t)＝|rand(0,1)·X b (t)-X i (t)|，X r (t)、X l (t) each represents X rnd Right and left vectors of (t),is a unit direction vector.
The original optimization algorithm of the sand cat group is to generate a random position by utilizing the optimal position and the current position in the development stage, then, the sensitivity range of the sand cat is assumed to be a circle, an angle theta is randomly selected for each sand cat by using a roulette method, and the hunting object search is carried out according to the direction of the random angle theta, wherein the random position can originally ensure that the sand cat is close to the hunting object, and the random angle can avoid the algorithm from sinking into local optimum. However, the primary task in the development stage is to quickly find the global optimal solution, and when the search is actually performed, the situation that the randomness is too strong and the progress of finding the global optimal solution is dragged slowly is found, so that the actual effect is not ideal.
The invention aims at the problem, further introduces a dominant individual following criterion based on direction judgment on the basis of keeping a randomly selected attack angle, namely, after the direction of selecting a random angle theta, judging whether the optimal position is at the left side or the right side of the current direction, and following the direction of the dominant individual, thereby not only keeping the randomness of tracking angle selection and avoiding local optimization, but also keeping the basic direction judging capability of a new individual on the basis of the random angle, leading the individual to move towards the optimal individual direction, and effectively accelerating the algorithm convergence speed, and further taking the optimizing speed and the solution quality into consideration.
S36, returning to the step S32, recalculating the fitness of each individual in the population, carrying out iterative operation until the maximum iterative times T are reached, and outputting an optimal solution.
And the optimal solution sequentially stores the passenger numbers carried by the K vehicles, and the K vehicles are scheduled according to the corresponding passenger numbers, so that the group-machine collaborative carpooling scheduling strategy is obtained.
Corresponding to the embodiment of the method, the invention also provides an intelligent network-connected automobile group machine collaborative carpooling scheduling system, which comprises the following steps:
and a data acquisition module: the method comprises the steps of acquiring operation vehicle data and passenger order data in a target area;
the target establishment module: the method is used for establishing a collaborative carpooling scheduling objective function and corresponding constraint conditions by taking the shortest vehicle driving path, the shortest passenger waiting time, the highest carpooling success rate and the smallest travel cost as targets based on the operation vehicle data and the order data;
scheduling solving module: the method is used for solving the objective function of the collaborative carpooling scheduling by adopting an improved sand cat swarm optimization algorithm to obtain a swarm machine collaborative carpooling scheduling strategy.
The system embodiments and the method embodiments are in one-to-one correspondence, and the brief description of the system embodiments is just to refer to the method embodiments.
The invention also discloses an electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus; the processor, the memory and the communication interface complete communication with each other through the bus; the memory stores program instructions executable by the processor that the processor invokes to implement the aforementioned methods of the present invention.
The invention also discloses a computer readable storage medium storing computer instructions for causing a computer to implement all or part of the steps of the methods of the embodiments of the invention. The storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, i.e., may be distributed over a plurality of network elements. One of ordinary skill in the art may select some or all of the modules according to actual needs without performing any inventive effort to achieve the objectives of the present embodiment.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. An intelligent network-connected automobile group machine collaborative carpooling scheduling method is characterized by comprising the following steps:
acquiring operation vehicle data and passenger order data in a target area;
based on the operation vehicle data and the order data, establishing a collaborative carpool scheduling objective function and corresponding constraint conditions by taking the shortest vehicle driving path, the shortest passenger waiting time and the highest carpool success rate as targets;
and solving an objective function of collaborative carpooling scheduling by adopting an improved sand cat swarm optimization algorithm to obtain a swarm machine collaborative carpooling scheduling strategy.
2. The intelligent network-connected automobile group machine collaborative carpooling scheduling method according to claim 1, wherein the operation vehicle data comprises the total number of vehicles participating in operation, the number of vehicles carrying a check, the pricing rule and the vehicle position before dispatching a bill in a target area;
the passenger order data comprises a starting point, an ending point and the number of passengers of each order; and forming a path point set by the starting points and the ending points of all orders.
3. The intelligent network-connected automobile group machine collaborative carpooling scheduling method according to claim 2, wherein the building of the collaborative carpooling scheduling objective function with the goals of the shortest vehicle driving path, the least passenger waiting time and the highest carpooling success rate is specifically as follows:
wherein F is an objective function, N is the total number of the route points, P is the total number of passengers, K is the total number of vehicles, N and m respectively represent the route point numbers, indicating whether the vehicle k passes through the route points n, m; d, d nm Representing the distance between the path points N, m, k=1, 2, …, K, n=1, 2, …, N, m=1, 2, …, N; /> Indicating whether vehicle k is to pick up the p-th passenger, < > or not>Representing the waiting time of the passenger when the vehicle is in zone k and the p passenger is received, < >>Estimating according to the distance between the vehicle position before dispatching and the starting point of the order, wherein p=1, 2, … and P; n (N) A 、N s The order quantity in a period of time and the order quantity of successful carpooling are respectively; alpha, beta and gamma are weight coefficients.
4. The intelligent network-connected automobile group machine collaborative carpooling scheduling method according to claim 3, wherein the constraint conditions include:
s.t.
wherein,the number of passengers in the kth vehicle is represented between the path points n and m, and Q represents the number of passengers on the vehicle; />The ride share rate of the passengers who get on the vehicle at the route point n to get off the vehicle at the route point m is shown.
5. The intelligent network-connected automobile swarm machine collaborative carpooling scheduling method according to claim 1, wherein the method for solving the objective function of collaborative carpooling scheduling by adopting the improved sand cat swarm optimization algorithm specifically comprises the following steps:
randomly initializing the population position of a sand cat group optimization algorithm, setting the population scale as M and the maximum iteration number as T; taking the objective function as a fitness function, calculating the fitness of each individual in the population, and storing the optimal position;
updating a control parameter R converted between an exploration phase and a development phase;
determining to enter an exploration phase or a development phase according to the magnitude of the control parameter R;
introducing an arithmetic average idea based on a subtraction average optimization algorithm in the exploration stage, and updating the position of an individual according to the current position of the individual, the optimal position and the subtraction average of the population;
in the development stage, on the basis of a random angle, introducing a dominant individual following criterion based on direction judgment, and updating the individual position;
and recalculating the fitness of each individual in the population, and carrying out iterative operation until the maximum iterative times are reached.
6. The intelligent network-connected automobile swarm machine collaborative carpooling scheduling method according to claim 5, wherein in the exploration phase, a subtraction average value idea based on a subtraction average optimization algorithm is introduced, and a formula for updating the position of an individual according to the current position of the individual, the optimal position and the subtraction average value of the swarm is as follows:
wherein X is i (t)、X i (t+1) the position of individual i at the time of the t, t+1 iteration, X b (t) is the current optimal position, v is the "v-" subtraction defined in the subtraction average optimization algorithm, X j (t) is the position of the jth individual at the t-th iteration, j=1, 2, …, M is the total number of individuals, w 1 、w 2 As the weight coefficient, r 1 Sensitivity, r of a sand cat 2 Is [0,1]Random numbers in between.
7. The intelligent network-connected automobile group machine collaborative carpooling scheduling method according to claim 6, wherein in the development stage, on the basis of a random angle, a dominant individual following criterion based on direction judgment is introduced, and an individual position updating formula is as follows:
X i (t+1)＝X b (t)-X rnd (t)·cos(θ)·r 1 ·sign(F(X l (t))-F(X r (t))
wherein F is an objective function, θ is a random angle, r 1 For sensitivity, X rnd (t) is a random vector, X r (t)、X l (t) each represents X rnd Right and left vectors of (t),is a unit direction vector.
8. An intelligent network-connected automobile group machine collaborative carpooling scheduling system, which is characterized by comprising:
and a data acquisition module: the method comprises the steps of acquiring operation vehicle data and passenger order data in a target area;
the target establishment module: the method is used for establishing a collaborative carpooling scheduling objective function and corresponding constraint conditions based on the operation vehicle data and the order data and aiming at the shortest vehicle driving path, the shortest passenger waiting time and the highest carpooling success rate;
scheduling solving module: the method is used for solving the objective function of the collaborative carpooling scheduling by adopting an improved sand cat swarm optimization algorithm to obtain a swarm machine collaborative carpooling scheduling strategy.
9. An electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete communication with each other through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to implement the method of any of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a computer to implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311258387.6A CN117252318B (en) | 2023-09-26 | 2023-09-26 | Intelligent networking automobile group machine collaborative carpooling scheduling method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311258387.6A CN117252318B (en) | 2023-09-26 | 2023-09-26 | Intelligent networking automobile group machine collaborative carpooling scheduling method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117252318A true CN117252318A (en) | 2023-12-19 |
| CN117252318B CN117252318B (en) | 2024-04-09 |
Family
ID=89130977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311258387.6A Active CN117252318B (en) | 2023-09-26 | 2023-09-26 | Intelligent networking automobile group machine collaborative carpooling scheduling method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117252318B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117610437A (en) * | 2024-01-24 | 2024-02-27 | 青岛理工大学 | Prediction method and device for evacuation high-risk area of underground station in flood scene |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105489002A (en) * | 2016-01-05 | 2016-04-13 | 深圳大学 | Intelligent matching and route optimization-base carpooling method and system |
| US20190026671A1 (en) * | 2017-07-20 | 2019-01-24 | DTA International FZCO | Device, System, and Method for Optimizing Taxi Dispatch Requests |
| CN110084390A (en) * | 2019-03-26 | 2019-08-02 | 河南科技学院 | A kind of more vehicles collaboration share-car method for optimizing route based on modified drosophila algorithm |
| US20200058044A1 (en) * | 2017-03-27 | 2020-02-20 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for carpooling |
| CN111178724A (en) * | 2019-12-23 | 2020-05-19 | 华南理工大学 | Carpooling scheduling method based on evolution algorithm |
| WO2020199524A1 (en) * | 2019-04-02 | 2020-10-08 | 长安大学 | Method for matching ride-sharing travellers based on network representation learning |
| CN112613663A (en) * | 2020-12-25 | 2021-04-06 | 环球车享汽车租赁有限公司 | Shared vehicle scheduling method, computing device, and computer-readable storage medium |
| CN116468219A (en) * | 2023-03-21 | 2023-07-21 | 北京工业大学 | Method for matching taxi sharing schedule by junction station |
-
2023
- 2023-09-26 CN CN202311258387.6A patent/CN117252318B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105489002A (en) * | 2016-01-05 | 2016-04-13 | 深圳大学 | Intelligent matching and route optimization-base carpooling method and system |
| US20200058044A1 (en) * | 2017-03-27 | 2020-02-20 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for carpooling |
| US20190026671A1 (en) * | 2017-07-20 | 2019-01-24 | DTA International FZCO | Device, System, and Method for Optimizing Taxi Dispatch Requests |
| CN110084390A (en) * | 2019-03-26 | 2019-08-02 | 河南科技学院 | A kind of more vehicles collaboration share-car method for optimizing route based on modified drosophila algorithm |
| WO2020199524A1 (en) * | 2019-04-02 | 2020-10-08 | 长安大学 | Method for matching ride-sharing travellers based on network representation learning |
| CN111178724A (en) * | 2019-12-23 | 2020-05-19 | 华南理工大学 | Carpooling scheduling method based on evolution algorithm |
| CN112613663A (en) * | 2020-12-25 | 2021-04-06 | 环球车享汽车租赁有限公司 | Shared vehicle scheduling method, computing device, and computer-readable storage medium |
| CN116468219A (en) * | 2023-03-21 | 2023-07-21 | 北京工业大学 | Method for matching taxi sharing schedule by junction station |
Non-Patent Citations (3)
| Title |
|---|
| DI WU等: "Sand Cat Swarm Optimization: a nature-inspired algorithm to solve global optimization problems Engineering with Computers", 《ENGINEERING WITH COMPUTERS》, vol. 39, no. 4, 11 April 2022 (2022-04-11), pages 2627 - 2651 * |
| 何胜学;赵惠光;: "基于路径优化模式的出租车合乘调度", 长沙理工大学学报(自然科学版), no. 03, 28 September 2018 (2018-09-28) * |
| 蔡文广等: "基于概率路由的出租车共乘调度算法", 《计算 机应用研究》, 22 August 2023 (2023-08-22) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117610437A (en) * | 2024-01-24 | 2024-02-27 | 青岛理工大学 | Prediction method and device for evacuation high-risk area of underground station in flood scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117252318B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194575B (en) | Vehicle autonomous scheduling method for processing express adding and pickup requirements | |
| CN117252318B (en) | Intelligent networking automobile group machine collaborative carpooling scheduling method and system | |
| CN110110903B (en) | Neural evolution-based distribution vehicle path planning method | |
| Shi et al. | Memory-based ant colony system approach for multi-source data associated dynamic electric vehicle dispatch optimization | |
| CN110570656B (en) | Method and device for customizing public transport line | |
| EP3772026A1 (en) | Method and system for routing a plurality of vehicles | |
| CN114119159A (en) | Network taxi appointment real-time order matching and idle vehicle scheduling method and system | |
| CN112097783B (en) | Electric taxi charging navigation path planning method based on deep reinforcement learning | |
| CN113415288A (en) | Sectional type longitudinal vehicle speed planning method, device, equipment and storage medium | |
| CN111580526B (en) | Cooperative driving method for fixed vehicle formation scene | |
| CN115146946A (en) | Automobile charging facility selection and planning method based on multi-source data | |
| Haliem et al. | A distributed model-free ride-sharing algorithm with pricing using deep reinforcement learning | |
| Oda et al. | Distributed fleet control with maximum entropy deep reinforcement learning | |
| CN117093009B (en) | Logistics AGV trolley navigation control method and system based on machine vision | |
| JP7040571B2 (en) | Learning device and model learning system | |
| US20220277246A1 (en) | Method for Coordinating an Autonomous Vehicle Fleet, and Vehicle Fleet Coordination System | |
| WO2021031636A1 (en) | Real-time order travel vehicle-based real-time order assignment method and apparatus | |
| Castagna et al. | Demand-responsive rebalancing zone generation for reinforcement learning-based on-demand mobility | |
| CN113222248B (en) | Automatic taxi-driving charging pile selection method | |
| CN114925911A (en) | Self-adaptive dynamic scheduling method and system based on accurate passenger flow prediction of unmanned bus | |
| CN112561104A (en) | Vehicle sharing service order dispatching method and system based on reinforcement learning | |
| Dziubany et al. | Optimization of a cpss-based flexible transportation system | |
| EP3772028A1 (en) | Method and system for routing a plurality of vehicles using a neural network | |
| CN112750298A (en) | Truck formation dynamic resource allocation method based on SMDP and DRL | |
| Xiao et al. | A reinforcement-learning-based bus scheduling model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |