CN110533279A - For dispatching the method, system and storage medium of cloud logistics platform transport power - Google Patents
For dispatching the method, system and storage medium of cloud logistics platform transport power Download PDFInfo
- Publication number
- CN110533279A CN110533279A CN201910635877.0A CN201910635877A CN110533279A CN 110533279 A CN110533279 A CN 110533279A CN 201910635877 A CN201910635877 A CN 201910635877A CN 110533279 A CN110533279 A CN 110533279A
- Authority
- CN
- China
- Prior art keywords
- chromosome
- cargo
- vehicle
- delivery
- point
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- 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
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Genetics & Genomics (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Embodiment of the present invention provides a kind of for dispatching the method, system and storage medium of cloud logistics platform transport power, belongs to vehicle dispatching problem model and algorithm field.The described method includes: obtaining the type of the collecting and distributing cargo in each Distribution Center；KNN algorithm is used to be clustered to the Distribution Center according to the type to form multiple collecting and distributing centres, wherein each collecting and distributing centre is used for collecting and distributing one kind cargo；Determine the optimal scheduling scheme by cargo from the delivery of cargo point transport to the collecting and distributing centre according to the collecting and distributing centre and corresponding delivery of cargo point respectively using genetic algorithm, wherein the delivery of cargo point is for issuing the cargo.This method, system and storage medium can guarantee the reasonability of scheduling scheme, improve the dispatching efficiency of cloud platform logistics.
Description
Technical field
The present invention relates to vehicle dispatching problem model and algorithm fields, more particularly to one kind for dispatching cloud logistics platform
Method, system and the storage medium of transport power.
Background technique
It is Vehicle Routing Problems in Transport capacity dispatching question essence under cloud logistics platform, is unavoidable in logistics business
Critical issue and the hot issue of domestic and foreign scholars' research.Reasonable vehicle scheduling scheme can be saved for enterprise transport at
This and time, the efficiency of logistics service is improved, promotes competitiveness for enterprise, therefore there is important meaning to the research of the problem
Justice.
Summary of the invention
The purpose of embodiment of the present invention is to provide a kind of for dispatching the method, system and storage of cloud logistics platform transport power
Medium.This method, system and storage medium can guarantee the reasonability of the scheduling scheme of the vehicle of cloud logistics platform, to improve
The dispatching efficiency of vehicle.
To achieve the goals above, embodiment of the present invention provides a kind of method for dispatching cloud logistics platform transport power,
The described method includes:
Obtain the type of the collecting and distributing cargo in each Distribution Center；
The Distribution Center is clustered according to the type using KNN (k-NearestNeighbor, k are neighbouring) algorithm
To form multiple collecting and distributing centres, wherein each collecting and distributing centre is used for collecting and distributing one kind cargo；
It is determined respectively by cargo according to the collecting and distributing centre and corresponding delivery of cargo point from the delivery of cargo point using genetic algorithm
It transports to the optimal scheduling scheme in the collecting and distributing centre, wherein the delivery of cargo point is for issuing the cargo.
On the other hand, the present invention also provides a kind of system for dispatching cloud logistics platform transport power, the system comprises places
Device is managed, the processor is used to execute any of the above-described method.
In another aspect, the storage medium is stored with instruction the present invention also provides a kind of storage medium, described instruction is used for
It is read by a machine so that the machine executes any of the above-described method.
Through the above technical solutions, provided by the present invention for method, system and the storage of dispatching cloud logistics platform transport power
Medium is clustered by using Distribution Center of the KNN clustering method to cargo, to form multiple collecting and distributing centres；Again for each
Analysis of Genetic Algorithms vehicle is respectively adopted from delivery of cargo point by the scheduling scheme of cargo transport to collecting and distributing centre in collecting and distributing centre, ensure that
The reasonability of scheduling scheme improves the dispatching efficiency of vehicle.
The other feature and advantage of embodiment of the present invention will the following detailed description will be given in the detailed implementation section.
Detailed description of the invention
Attached drawing is to further understand for providing to embodiment of the present invention, and constitute part of specification, with
Following specific embodiment is used to explain the present invention embodiment together, but does not constitute the limit to embodiment of the present invention
System.In the accompanying drawings:
Fig. 1 is the flow chart of the method for dispatching cloud logistics platform transport power according to embodiment of the present invention；
Fig. 2 is the stream of the method clustered using KNN algorithm to Distribution Center according to embodiment of the present invention
Cheng Tu；
Fig. 3 is the process of the method that scheduling scheme is determined using genetic algorithm according to embodiment of the present invention
Figure；
Fig. 4 is the flow chart of chromosome coding according to embodiment of the present invention；
Fig. 5 is the flow chart of initialization population according to embodiment of the present invention；
Fig. 6 is the flow chart that crossover operation is carried out to population according to embodiment of the present invention；
Fig. 7 is the flow chart that mutation operation is carried out to population according to embodiment of the present invention；
Fig. 8 is the flow chart of the treatment process of inspection operator according to embodiment of the present invention；And
Fig. 9 is the line chart that the fitness of an exemplary genetic algorithm according to the present invention changes with the number of iterations.
Specific embodiment
It is described in detail below in conjunction with specific embodiment of the attached drawing to embodiment of the present invention.It should be understood that
Embodiment that the specific embodiments described herein are merely illustrative of the invention is not intended to restrict the invention implementation
Mode.
In embodiments of the present invention, in the absence of explanation to the contrary, the noun of locality used such as " upper and lower, top, bottom "
Usually for direction shown in the drawings either for it is vertical, vertically or on gravity direction for each component it is mutual
Positional relationship describes word.
In addition, if relating to the description of " first ", " second " etc. in embodiment of the present invention, it should " first ", " second "
Deng description be used for description purposes only, be not understood to indicate or imply its relative importance or implicitly indicate indicated
The quantity of technical characteristic." first " is defined as a result, the feature of " second " can explicitly or implicitly include at least one and be somebody's turn to do
Feature.It in addition, the technical solution between each embodiment can be combined with each other, but must be with ordinary skill people
Based on member can be realized, this technical solution will be understood that when the combination of technical solution appearance is conflicting or cannot achieve
Combination be not present, also not the present invention claims protection scope within.
It is the method for dispatching cloud logistics platform cloud transport power according to embodiment of the present invention as shown in Figure 1
Flow chart.In Fig. 1, this method may include:
In the step s 100, the type of the collecting and distributing cargo in each Distribution Center is obtained.
In step s 200, KNN algorithm is used to be clustered to Distribution Center according to type to form multiple collecting and distributing centres.Its
In, each collecting and distributing centre is for collecting and distributing a kind of cargo.In the prior art, the subjective environment of logistics platform is generally comprised for sending out
The delivery of cargo point of goods, for be sent to by cargo consolidation and again the Distribution Center of destination and be used for by cargo from the transport of delivery of cargo point to
The vehicle of Distribution Center.In view of the efficiency of scheduling, the general same Distribution Center only can collecting and distributing a kind of cargo, this creates the terminal can
Can there can be the status of multiple Distribution Centers a kind of cargo collecting and distributing simultaneously.It is past in the method for the determination scheduling scheme of the prior art
Past is to be will lead to so directly using Distribution Center as the condition of vehicle dispatching problem when determining scheme, the scale mistake of algorithm
In huge.Therefore, in this embodiment, use KNN algorithm according to the type of the collecting and distributing cargo in each Distribution Center clustered with
The scale of subsequent algorithm can be greatly reduced by forming multiple collecting and distributing centre.It is specific for being clustered using KNN algorithm
Details can be diversified forms known to those skilled in the art.In an example of the invention, which be can be for example
Method shown in Fig. 2.In Fig. 2, this method may include:
In step S210, the data set (type of multiple Distribution Centers and corresponding collecting and distributing cargo) comprising type is carried
Enter in KNN algorithm.
In step S220, the parameter K of KNN algorithm is set.
In step S230, a unselected Distribution Center is randomly selected from data set using as future position.
In step S240, calculate separately future position to each known point distance.It is known that point can indicate by
The Distribution Center of cluster.In this embodiment, it is contemplated that when choosing first Distribution Center, each known point can be to be collected in advance
The multiple Distribution Centers randomly selected in the set of scatterplot are as known point.
In step s 250, calculated distance is sorted in form from small to large.
In step S260, by future position cluster to preceding K in the collecting and distributing centre where corresponding known point.
In step S270, unselected Distribution Center is judged whether there is.
In judgement, there are cluster operation in the case where unselected Distribution Center, illustrated at this time to Distribution Center, there are no complete
At, it is therefore desirable to step S230 is executed again.
In judgement there is no in the case where unselected Distribution Center, illustrate at this time complete to the cluster operation of Distribution Center
At, therefore step S280 can be executed, that is, export multiple collecting and distributing centres for respectively indicating collecting and distributing a kind of cargo.
In step S300, determined respectively by cargo according to collecting and distributing centre and corresponding delivery of cargo point from mentioning using genetic algorithm
Goods point is transported to the optimal scheduling scheme in collecting and distributing centre.Wherein, which can be used for issuing cargo.Preferably
In, for each collecting and distributing centre, the genetic algorithm can be respectively adopted and determine optimal scheduling scheme.Determine the genetic algorithm it
Before, an objective function can be preset, for the objective function, can be those skilled in the art for practical problem to determine
's.In an example of the invention, determine that the detailed process of the objective function can be for example:
First object subfunction is arranged according to formula (1) in step 1,
Wherein, f1For first object subfunction, N is the set of delivery of cargo point, gjFor the goods weight of j-th of delivery of cargo point, M is
The set of schedulable vehicle, QmFor the payload ratings of m-th of vehicle, xmIndicate whether m-th of vehicle takes part in scheduling, in m
In the case that a vehicle participates in scheduling, xm=1, in the case where m-th of vehicle has neither part nor lot in scheduling, xm=0；
The second target subfunction is arranged according to formula (2) in step 2,
Wherein, f2For the second target subfunction, M is the set of schedulable vehicle, ckFor the consolidating of dispatching a car of vehicle of k vehicle
Determine cost,Indicate whether m-th of vehicle is k vehicle, in the case where m-th of vehicle is k vehicle,In m-th of vehicle
In the case where non-k vehicle,N is the set of delivery of cargo point, and N is the set of delivery of cargo point, and c is the every traveling unit distance of vehicle
Cost, dijFor position i to the distance of position j, position includes delivery of cargo point and collecting and distributing centre, xmijIndicate m-th of vehicle whether from
Pick up goods point i to delivery of cargo point j, in the case where m-th of vehicle is from goods point i to delivery of cargo point j, xmij=1, in the non-goods point of m-th of vehicle
In the case where i to delivery of cargo point j, xmij=0；
Third target subfunction is arranged according to formula (3) in step 3,
Wherein, f3For third target subfunction, M is the set of schedulable vehicle, and N is the set of delivery of cargo point, tijFor vehicle
From position i to the running time of position j, xmijM-th of vehicle is indicated whether from delivery of cargo point i to delivery of cargo point j, in m-th of vehicle
In the case where goods point i to delivery of cargo point j, xmij=1, in the case where the non-goods point i of m-th of vehicle to delivery of cargo point j, xmij=0, Ti
For the limitation of delivery availability at the latest for the point i that picks up goods；
Step 4 carries out first object subfunction, the second target subfunction and third target subfunction using formula (4)
Normalized,
Wherein, f' is the function after normalized, and f is the function before normalized；
Objective function is arranged according to formula (5) in step 5,
F=min (λ2f2'-λ1f1'+λ3f3'), (5)
Wherein, F is objective function, λ1、λ2And λ3For preset weight, f1'、f2' and f3' for first after normalized
Target subfunction, the second target subfunction and third target subfunction；
Bound for objective function is arranged according to formula (6-1) to formula (6-8) in step 6.
Wherein, M is the set of schedulable vehicle, and N is the set of delivery of cargo point, gjFor j-th delivery of cargo point goods weight,
xmijIndicate m-th of vehicle whether from delivery of cargo point i to delivery of cargo point j, m-th of vehicle from goods point i to pick up goods point j in the case where,
xmij=1, in the case where the non-goods point i of m-th of vehicle to delivery of cargo point j, QmFor the payload ratings of m-th of vehicle, P is all positions
The set set, position include delivery of cargo point and collecting and distributing centre, PjFor j-th of position；
Wherein, M is the set of schedulable vehicle, and N is the set of delivery of cargo point, xmijIndicate m-th of vehicle whether from delivery of cargo
Point i to the point j, x of picking up goodsmi0Indicate m-th of vehicle whether from delivery of cargo point i to delivery of cargo 0；
Wherein, M is the set of schedulable vehicle, and N is the set of delivery of cargo point, xmijIndicate m-th of vehicle whether from delivery of cargo
Point i to delivery of cargo point j；
Wherein, M is the set of schedulable vehicle, and N is the set of delivery of cargo point, xmirIndicate m-th of vehicle whether from delivery of cargo
Point i to the point r, x of picking up goodsmrjIndicate m-th of vehicle whether from delivery of cargo point r to delivery of cargo point j；
Wherein, M is the set of schedulable vehicle, and N is the set of delivery of cargo point, xmijIndicate m-th of vehicle whether from delivery of cargo
Point i to delivery of cargo point j；
For the detail of the genetic algorithm, it can be diversified forms known to those skilled in the art.Of the invention one
In a example, which can be step for example illustrated in fig. 3.In Fig. 3, which may include:
In step s310, the chromosome of genetic algorithm is encoded.In this example, which is encoded
Detail can be for example shown in Fig. 4.In Fig. 4, for each chromosome, which may include:
In step S311, in the different number of interval range random selection m+n of [1, m+n] to generate a nature
Number string.Wherein, m is the quantity of vehicle, and n is the quantity of delivery of cargo point, and 1 is the number in collecting and distributing centre.In step S311, it is based on
The m is the quantity of vehicle, and n is the quantity of delivery of cargo point, then 1,2,3 ... m of number can indicate to adjust in the natural number string of generation
The vehicle of degree, m+1, m+2, m+3 ... m+n can indicate delivery of cargo point, and number 0 can then indicate collecting and distributing centre.In this example, with
For the quantity of vehicle is 3, the quantity of delivery of cargo point is 6, the natural number string of generation then can be such as are as follows: 1,6,7,8,2,9,3,4,
5。
In step S312, judge whether the first place number of natural number string is located in the interval range of [1, m].
In step S313, in the case where the interval range that the first place number for judging natural number string is located at [1 m] is outer, delete
Except natural number string and again in the different number of interval range random selection m+n of [1, m+n] to generate a natural number string.
In step S314, in the case where the interval range that the first place number for judging natural number string is located at [1 m] is interior, In
The end of natural number string is plus number 0.
In step S315, before the number in interval range for being located at [1, m] in the non-the first number of natural number string
One insertion number 0 is to generate length as the chromosome of 2m+n.For the natural number string shown in the step S311, by step
After the processing of S312 to step S315, the concrete form of the chromosome ultimately generated be can be for example: 1,6,7,8,0,2,9,
0,3,4,5,0, which indicates that scheduling scheme can be as shown in table 1,
Table 1
In step s 320, initialization population and the number of iterations.For the specific value of the number of iterations, to this field people
It should be known for member.In an example of the invention, the initial value of the number of iterations can be such as 0.For first
The detail of beginningization population, the step of can be for example shown in Fig. 5.In Fig. 5, step S320 may include:
In step S321, the number 0 in chromosome is extracted.
In step S322, judge whether the first place number of the chromosome after extracting is located in the interval range of [1, m].
In the case where the digital interval range positioned at [1 m] in first place of the chromosome after judgement is extracted is outer, illustrate at this time
The vehicle of the selection is unsatisfactory for condition, then can encode again to the chromosome of genetic algorithm.
Feelings in step S323, in the digital interval range for being located at [1, m] in the first place of the chromosome after judgement is extracted
Under condition, illustrate that the vehicle of the selection meets condition at this time, then can further judge that any two are located at [1, m] on chromosome
Interval range in number between the total weight of cargo whether be less than or equal to the payload ratings of vehicle.
There are the total weight of the cargo between two numbers in the interval range of [1, m] is big on judging chromosome
In the case where the payload ratings of vehicle, the payload ratings that will lead to vehicle when illustrating this chromosome at this time to vehicle scheduling are difficult
To meet the transportation demand of cargo, therefore the scheduling scheme of this chromosome is unreasonable, then can be again to genetic algorithm
Chromosome is encoded, that is, returns to step S310.
In step S324, any two are located between the number in the interval range of [1, m] on judging chromosome
In the case that the total weight of cargo is less than or equal to the payload ratings of vehicle, illustrate the scheduling scheme that this chromosome indicates at this time
Meet the requirement of vehicle transport, therefore the chromosome can be added in population.
In step S325, judge whether the quantity of the chromosome in population is greater than or equal to preset population scale.
In the case where judging that the quantity of the chromosome in population is less than population scale, illustrate the chromosome generated at this time
Quantity can not constitute population, then can encode again to the chromosome of genetic algorithm, that is, return to step S310.
In step S326, in the case where judging that the quantity of the chromosome in population is greater than or equal to population scale, this
When illustrate that the quantity of the chromosome has been able to constitute population, therefore population can be exported.
In step S330, judge whether the number of iterations reaches preset frequency threshold value.
In step S340, in the case where judging that the number of iterations is not up to frequency threshold value, each dyeing in population is calculated
The fitness of body.Determination for the fitness function can be the objective function that shows using formula (5) to determine, simultaneously
In view of positive the problem of overflowing that may be present, in this example, fitness function can be determined according to formula (7),
Wherein, F ' is fitness function, and F is objective function.
In step S350, selection operation is carried out to population.For the selection operation, can be known to those skilled in the art
Diversified forms.In a preferable example of the invention, selection operation can be carried out to population using roulette method, specifically,
It can be and selection operation is for example carried out to population according to formula (8),
Wherein, FiFor the fitness of i-th chromosome, P (Fi) it is the probability that i-th chromosome is selected.
In step S360, crossover operation is carried out to population.For the crossover operation, can be known to those skilled in the art
Diversified forms.In a preferable example of the invention, which can specifically include step as illustrated in FIG. 6.In
In Fig. 6, which may include:
In step S361, two chromosomes are randomly selected from population and are contaminated as the first parent chromosome and the second parent
Colour solid.
In step S362, from the non-zero number randomly selected in the first parent chromosome on x position, be inserted into
Corresponding position in second parent chromosome is to form new chromosome.In this step, the chromosome 1 and dye to generate at random
For colour solid 2, wherein
The sequence of chromosome 1 can be with are as follows: 1,6,7,8,0,2,9,0,3,4,5,0
The sequence of chromosome 2 can be with are as follows: 1,8,0,2,6,9,7,0,3,5,4,0
When executing crossover operation, can by chromosome 1 4-digit number 8 and ten digits 4 extract, and
The number 8 and number 4 are inserted into the 4th and the tenth of chromosome 2 respectively, to generate chromosome 3, wherein
The sequence of chromosome 3 are as follows: 1,0,2,8,6,9,7,0,3,4,5,0.
In step S363, new chromosome is handled using preset inspection operator and chromosome is added in population.It is right
In the inspection operator, it can be those skilled in the art being actually subjected to solve the problems, such as to determine.Preferably at of the invention one
In example, which may include method as illustrated in FIG. 8.In fig. 8, this method may include:
In step S400, the number 0 in chromosome is extracted.
In step S401, judge whether the first place number of the chromosome after extracting is located in the interval range of [1, m]；
Feelings in step S402, outside the digital interval range for being located at [1, m] in the first place of the chromosome after judgement is extracted
Under condition, the last one first place number for being located at the digital and chromosome in the interval range of [1, m] on chromosome is exchanged with more
New chromosome, and execute step S403.
Feelings in step S403, in the digital interval range for being located at [1, m] in the first place of the chromosome after judgement is extracted
Under condition, judge whether the total weight for the cargo that any two on chromosome are located between the number in the interval range of [1, m] is big
In the payload ratings of vehicle.
In step s 404, any two are located at the digital cargo in the interval range of [1, m] on judging chromosome
Total weight whether be greater than the payload ratings of vehicle in the case where, initialization variation number and variation threshold.
In step S405, two positions are randomly choosed on chromosome, by the number exchange on two positions to update
The chromosome.
In step S406, judge whether variation number is greater than or equal to variation threshold.
In step S 407, in the case where judgement variation number is less than variation threshold, variation number is updated, is being contaminated again
Two positions are randomly choosed on colour solid, by the number exchange on two positions to update chromosome (returning to step S405)；
In step S408, in the case where judgement variation number is greater than or equal to variation threshold, new chromosome is exported
And again extract the number 0 in chromosome, that is, return to step S400.
In step S409, any two are located at the cargo of the number in the interval range of [1, m] on judging chromosome
Total weight be respectively less than or the payload ratings equal to vehicle in the case where, export the chromosome.
In step S364, number of crossings is updated.Wherein, initial number of crossings can be 0.
In step S365, judge whether number of crossings is big or is equal to preset number of crossings threshold value.
In the case where judging that number of crossings is less than number of crossings threshold value, two chromosomes are randomly selected from population again
As the first parent chromosome and the second parent chromosome (returning to step S371)；
In step S366, in the case where judging that number of crossings is greater than or equal to number of crossings threshold value, population is exported.
In step S370, mutation operation is carried out to population.For the detail of the mutation operation, this field can be
Diversified forms known to personnel.In an example of the invention, which can be method for example illustrated in fig. 7.
In Fig. 7, this method may include:
In step S371, a unselected chromosome is randomly selected from population.
It is random to generate variation number and variation threshold in step S372.
In step S373, two positions are randomly choosed on chromosome, by the number exchange on two positions to update
Chromosome.
In step S374, judge whether variation number is greater than or equal to variation threshold.
In the case where judgement variation number is less than variation threshold, variation number is updated, again random choosing on chromosome
Two positions are selected, by the number exchange on two positions to update the chromosome.
In step S375, in the case where judgement variation number is greater than or equal to variation threshold, using shown in Fig. 8
The method for examining operator handles the chromosome, and the chromosome is added in population.
In step S376, judge in population with the presence or absence of unselected chromosome；
In judging population there are in the case where unselected chromosome, randomly selected from population again one not by
The chromosome of selection.
In step S377, in the case where unselected chromosome is not present in judging population, the population is exported.
In step S380, the number of iterations is updated, judges whether the number of iterations reaches frequency threshold value again.
In step S390, in the case where judging that the number of iterations reaches frequency threshold value, the maximum dyeing of fitness is exported
Body is as optimal scheduling scheme.
In an example of the invention, it is applied in the vehicle scheduling work of D company using above-mentioned shown method.
D company is a logistics company on cloud logistics platform, the transport of Main Management vegetable and fruit, the lorry being affiliated under company
There are three types of, specification is 5 tons, 6.2 meters of 4.2 meters of payload ratings, 10 tons of payload ratings of 8 tons and 7.2 meters of payload ratings respectively.At this stage,
D company has saved bit by bit the order in certain period of time and has prepared same arrangement delivery of cargo.
The historical data stored by D company obtains the information (type of coordinate, cargo of delivery of cargo point and Distribution Center
Deng).Distribution Center is clustered using KNN algorithm, to form multiple collecting and distributing centres.
After the completion of cluster, the information of schedulable vehicle is obtained in the historical data, as shown in table 2,
Table 2
The type that delivery of cargo point issues cargo is as shown in table 3,
Table 3
The data in table 2 and table 3 are handled using genetic algorithm.Wherein, it sets the weighted value of genetic algorithm to
0.5,0.25 and 0.25 (λ1、λ2And λ3), population scale 80, crossover probability 30%, mutation probability 50%, frequency threshold value
It is 500 times.
The variation of the fitness for the optimal solution that the genetic algorithm generates is as shown in Figure 9.In Fig. 9, in the genetic algorithm
After the number of iterations reaches 500 times, the value of the fitness of generation gradually restrains, and thus obtains the dyeing for indicating optimal scheduling scheme
The sequence of body is 3,11,27,0,5,19,20,13,0,7,17,12,22,0,4,15,14,0,6,10,26,25,18,0,9,16,
21,24,23,0,2,0,8,0,1,0.
The chromosome is decoded, obtained optimal scheduling scheme is as shown in table 4,
Table 4
On the other hand, the present invention also provides a kind of system for dispatching cloud logistics platform transport power, system includes processor,
The processor can be used for executing any of the above-described method.
In another aspect, the storage medium can store instruction the present invention also provides a kind of storage medium, which can be with
For being read by a machine so that machine executes any of the above-described method.
Through the above technical solutions, provided by the present invention for method, system and the storage of dispatching cloud logistics platform transport power
Medium is clustered by using Distribution Center of the KNN clustering method to cargo, to form multiple collecting and distributing centres；Again for each
Analysis of Genetic Algorithms vehicle is respectively adopted from delivery of cargo point by the scheduling scheme of cargo transport to collecting and distributing centre in collecting and distributing centre, ensure that
The reasonability of scheduling scheme improves the dispatching efficiency of vehicle.
The optional embodiment of example of the present invention is described in detail in conjunction with attached drawing above, still, embodiment of the present invention is not
The detail being limited in above embodiment can be to of the invention real in the range of the technology design of embodiment of the present invention
The technical solution for applying mode carries out a variety of simple variants, these simple variants belong to the protection scope of embodiment of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, it can be combined in any appropriate way.In order to avoid unnecessary repetition, embodiment of the present invention
To various combinations of possible ways, no further explanation will be given.
It will be appreciated by those skilled in the art that realizing that all or part of the steps in above embodiment method is can to lead to
Program is crossed to instruct relevant hardware and complete, which is stored in a storage medium, including some instructions use so that
One (can be single-chip microcontroller, chip etc.) or processor (processor) execute each embodiment the method for the application
All or part of the steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
In addition, any combination can also be carried out between a variety of different embodiments of embodiment of the present invention, as long as its
Without prejudice to the thought of embodiment of the present invention, embodiment of the present invention disclosure of that equally should be considered as.
Claims (10)
1. a kind of method for dispatching cloud logistics platform transport power, which is characterized in that the described method includes:
Obtain the type of the collecting and distributing cargo in each Distribution Center；
KNN algorithm is used to be clustered to the Distribution Center according to the type to form multiple collecting and distributing centres, wherein Mei Gesuo
Collecting and distributing centre is stated for collecting and distributing one kind cargo；
It is determined respectively according to the collecting and distributing centre and corresponding delivery of cargo point using genetic algorithm and transports cargo from the delivery of cargo point
To the optimal scheduling scheme in the collecting and distributing centre, wherein the delivery of cargo point is for issuing the cargo.
2. the method according to claim 1, wherein described use KNN algorithm according to the type to the collection
Scatterplot is clustered to form multiple collecting and distributing centres and include:
It will be loaded into the KNN algorithm comprising the data set of the type；
The parameter K of the KNN algorithm is set；
A unselected Distribution Center is randomly selected from the data set using as future position；
Calculate separately the future position to each known point distance, wherein the known point indicates the collection being clustered
Scatterplot；
By the distance with form sequence from small to large；
By future position cluster into the preceding K collecting and distributing centres apart from where corresponding known point；
Judge whether there is unselected Distribution Center；
It is unselected there are in the case where unselected Distribution Center, randomly selecting one from the data set again in judgement
Distribution Center using as future position；
In judgement there is no in the case where unselected Distribution Center, multiple collecting and distributing centres are exported.
3. the method according to claim 1, wherein described use genetic algorithm respectively according to the collecting and distributing centre
Determine that the optimal scheduling scheme by cargo from the delivery of cargo point transport to the collecting and distributing centre includes: with corresponding delivery of cargo point
According to formula (1), first object subfunction is set,
Wherein, f1For the first object subfunction, N is the set of the delivery of cargo point, gjFor the cargo of j-th of delivery of cargo point
Weight, M are the set of schedulable vehicle, QmFor the payload ratings of m-th of vehicle, xmIndicate whether m-th of vehicle takes part in tune
Degree, in the case where m-th of vehicle participates in scheduling, xm=1, in the case where m-th of vehicle has neither part nor lot in scheduling, xm=0；
According to formula (2), the second target subfunction is set,
Wherein, f2For the second target subfunction, M is the set of schedulable vehicle, ckFor the consolidating of dispatching a car of vehicle of k vehicle
Determine cost,Indicate whether m-th of vehicle is k vehicle, in the case where m-th of vehicle is k vehicle,In m-th of vehicle
In the case where non-k vehicle,N is the set of delivery of cargo point, and N is the set of the delivery of cargo point, and c is the every traveling unit of vehicle
The cost of distance, dijFor position i to the distance of position j, the position includes the delivery of cargo point and the collecting and distributing centre, xmijTable
Show m-th of vehicle whether from delivery of cargo point i to delivery of cargo point j, m-th of vehicle from goods point i to pick up goods point j in the case where, xmij=1,
In the case where the non-goods point i of m-th of vehicle to delivery of cargo point j, xmij=0；
According to formula (3), third target subfunction is set,
Wherein, f3For the third target subfunction, M is the set of schedulable vehicle, and N is the set of the delivery of cargo point, tij
It is vehicle from position i to the running time of position j, xmijM-th of vehicle is indicated whether from delivery of cargo point i to delivery of cargo point j, at m-th
Vehicle from goods point i to delivery of cargo point j in the case where, xmij=1, in the case where the non-goods point i of m-th of vehicle to delivery of cargo point j, xmij=
0, TiFor the limitation of delivery availability at the latest for the point i that picks up goods；
Using formula (4) to the first object subfunction, the second target subfunction and the third target subfunction into
Row normalized,
Wherein, f' is the function after normalized, and f is the function before normalized；
According to formula (5), objective function is set,
F=min (λ2f2'-λ1f1'+λ3f3'), (5)
Wherein, F is the objective function, λ1、λ2And λ3For preset weight, f1'、f2' and f3' it is described after normalized
First object subfunction, the second target subfunction and the third target subfunction；
According to formula (6-1) to formula (6-8), the bound for objective function is set.
Wherein, M is the set of schedulable vehicle, and N is the set of the delivery of cargo point, gjFor the cargo weight of j-th of delivery of cargo point
Amount, xmijM-th of vehicle is indicated whether from delivery of cargo point i to delivery of cargo point j, the case where m-th of vehicle is from goods point i to delivery of cargo point j
Under, xmij=1, in the case where the non-goods point i of m-th of vehicle to delivery of cargo point j, QmFor the payload ratings of m-th of vehicle, P is all
The set of position, the position include the delivery of cargo point and the collecting and distributing centre, PjFor j-th of position；
Wherein, M is the set of schedulable vehicle, and N is the set of the delivery of cargo point, xmijIndicate m-th of vehicle whether from delivery of cargo
Point i to the point j, x of picking up goodsmi0Indicate m-th of vehicle whether from delivery of cargo point i to delivery of cargo 0；
Wherein, M is the set of schedulable vehicle, and N is the set of the delivery of cargo point, xmijIndicate m-th of vehicle whether from delivery of cargo
Point i to delivery of cargo point j；
Wherein, M is the set of schedulable vehicle, and N is the set of the delivery of cargo point, xmirIndicate m-th of vehicle whether from delivery of cargo
Point i to the point r, x of picking up goodsmrjIndicate m-th of vehicle whether from delivery of cargo point r to delivery of cargo point j；
Wherein, M is the set of schedulable vehicle, and N is the set of the delivery of cargo point, xmijIndicate m-th of vehicle whether from delivery of cargo
Point i to delivery of cargo point j；
4. the method according to claim 1, wherein described use genetic algorithm respectively according to the collecting and distributing centre
Determine that the optimal scheduling scheme by cargo from the delivery of cargo point transport to the collecting and distributing centre includes: with corresponding delivery of cargo point
The chromosome of the genetic algorithm is encoded；
Initialization population and the number of iterations；
Judge whether the number of iterations reaches preset frequency threshold value；
In the case where judging that the number of iterations is not up to the frequency threshold value, each chromosome is suitable in calculating population
Response；
Selection operation is carried out to the population；
Crossover operation is carried out to the population；
Mutation operation is carried out to the population；
The number of iterations is updated, judges whether the number of iterations reaches the frequency threshold value again；
In the case where judging that the number of iterations reaches the frequency threshold value, the maximum chromosome conduct of fitness is exported
The optimal scheduling scheme.
5. according to the method described in claim 4, it is characterized in that, the chromosome to the genetic algorithm carries out coding packet
It includes:
In the different number of interval range random selection m+n of [1, m+n] to generate a natural number string, wherein m is described
The quantity of vehicle, n are the quantity of the delivery of cargo point, and 1 is the number in the collecting and distributing centre；
Judge whether the first place number of the natural number string is located in the interval range of [1, m]；
In the case where outside interval range of the first place number for judging the natural number string positioned at [1 m], the natural number is deleted
It goes here and there and again in the different number of interval range random selection m+n of [1, m+n] to generate a natural number string；
In the case where in interval range of the first place number for judging the natural number string positioned at [1 m], in the natural number string
End plus number 0；
The previous position insertion number 0 for the number in interval range for being located at [1, m] in the non-the first number of the natural number string
To generate length as the chromosome of 2m+n.
6. according to the method described in claim 5, it is characterized in that, the initialization population and the number of iterations include:
Number 0 in chromosome is extracted；
Judge whether the first place number of the chromosome after extracting is located in the interval range of [1, m]；
In the case where the digital interval range positioned at [1 m] in first place of the chromosome after judgement is extracted is outer, again to institute
The chromosome for stating genetic algorithm is encoded；
In the case where in the interval range that the first place number of the chromosome after judgement is extracted is located at [1 m], described in judgement
Whether the total weight for the cargo between number that any two are located in the interval range of [1, m] on chromosome is less than or waits
In the payload ratings of the vehicle；
There are the gross weights of the cargo between two numbers in the interval range of [1, m] on judging the chromosome
In the case that amount is greater than the payload ratings of the vehicle, the chromosome of the genetic algorithm is encoded again；
Any two are located at the gross weight of the cargo between the number in the interval range of [1, m] on judging the chromosome
In the case that amount is less than or equal to the payload ratings of the vehicle, the chromosome is added in population；
Judge whether the quantity of the chromosome in the population is greater than or equal to preset population scale；
In the case where judging that the quantity of the chromosome in the population is less than the population scale, again to the genetic algorithm
Chromosome encoded；
In the case where judging that the quantity of the chromosome in the population is greater than or equal to the population scale, described kind is exported
Group.
7. according to the method described in claim 6, which is characterized in that the adaptation for calculating each chromosome in population
Degree includes:
The fitness function is determined according to formula (7),
Wherein, F ' is the fitness function, and F is the objective function；
It is described to include: to population progress selection operation
Selection operation is carried out to the population according to formula (8),
Wherein, FiFor the fitness of i-th chromosome, P (Fi) it is the probability that i-th chromosome is selected；
It is described to include: to population progress crossover operation
Two chromosomes are randomly selected from the population as the first parent chromosome and the second parent chromosome；
The non-zero number on x position is randomly selected from first parent chromosome, is inserted into second parent and is contaminated
Corresponding position in colour solid is to form new chromosome；
Using the new chromosome of preset inspection operator processing and the chromosome is added in the population；
Update number of crossings, wherein the initial number of crossings is 0；
Judge whether the number of crossings is big or is equal to preset number of crossings threshold value；
In the case where judging that the number of crossings is less than the number of crossings threshold value, two are randomly selected from the population again
Chromosome is as the first parent chromosome and the second parent chromosome；
In the case where judging that the number of crossings is greater than or equal to the number of crossings threshold value, the population is exported；
It is described to include: to population progress mutation operation
A unselected chromosome is randomly selected from the population；
It is random to generate variation number and variation threshold；
Two positions are randomly choosed on the chromosome, by the number exchange on described two positions to update the dyeing
Body；
Judge whether the variation number is greater than or equal to the variation threshold；
In the case where judging that the variation number is less than the variation threshold, the variation number is updated, again in the dye
Two positions are randomly choosed on colour solid, by the number exchange on described two positions to update the chromosome；
In the case where judging that the variation number is greater than or equal to the variation threshold, using described in inspection operator processing
Chromosome, and the chromosome is added in the population；
Judge in the population with the presence or absence of unselected chromosome；
There are in the case where unselected chromosome in judging the population, one is randomly selected from the population again
Unselected chromosome；
In the case where unselected chromosome is not present in judging the population, the population is exported.
8. the method according to the description of claim 7 is characterized in that the inspection operator includes:
Number 0 in the chromosome is extracted；
Judge whether the first place number of the chromosome after extracting is located in the interval range of [1, m]；
In the case where the digital interval range positioned at [1 m] in first place of the chromosome after judgement is extracted is outer, by the dye
The last one first place number for being located at the digital and chromosome in the interval range of [1, m] exchanges described to update on colour solid
Chromosome, and judge the cargo that any two on the chromosome are located between the number in the interval range of [1, m]
Whether total weight is greater than the payload ratings of the vehicle；
In the case where in the interval range that the first place number of the chromosome after judgement is extracted is located at [1 m], described in judgement
Whether the total weight for the cargo between number that any two are located in the interval range of [1, m] on chromosome is greater than described
The payload ratings of vehicle；
Any two, which are located at the total weight of the cargo of the number in the interval range of [1, m], on judging the chromosome is
In the case where the no payload ratings greater than the vehicle, initialization variation number and variation threshold；
Two positions are randomly choosed on the chromosome, by the number exchange on described two positions to update the dyeing
Body；
Judge whether the variation number is greater than or equal to the variation threshold；
In the case where judging that the variation number is less than the variation threshold, the variation number is updated, again in the dye
Two positions are randomly choosed on colour solid, by the number exchange on described two positions to update the chromosome；
In the case where judging that the variation number is greater than or equal to the variation threshold, the new chromosome and again is exported
Number 0 in the chromosome is extracted；
On judging the chromosome any two be located in the interval range of [1, m] number the cargo total weight it is equal
In the case where payload ratings less than or equal to the vehicle, the chromosome is exported.
9. a kind of system for dispatching cloud logistics platform transport power, which is characterized in that the system comprises processor, the processing
Device is for executing method as described in any of the claims 1 to 8.
10. a kind of storage medium, which is characterized in that the storage medium is stored with instruction, and described instruction is for being read by a machine
So that the machine executes method as described in any of the claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635877.0A CN110533279B (en) | 2019-07-15 | 2019-07-15 | Method, system and storage medium for scheduling cloud logistics platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635877.0A CN110533279B (en) | 2019-07-15 | 2019-07-15 | Method, system and storage medium for scheduling cloud logistics platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110533279A true CN110533279A (en) | 2019-12-03 |
| CN110533279B CN110533279B (en) | 2023-01-06 |
Family
ID=68660223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910635877.0A Active CN110533279B (en) | 2019-07-15 | 2019-07-15 | Method, system and storage medium for scheduling cloud logistics platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533279B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942271A (en) * | 2019-12-11 | 2020-03-31 | 江苏佳利达国际物流股份有限公司 | Intelligent transportation scheduling management method based on neural network genetic algorithm |
| CN112184099A (en) * | 2020-08-21 | 2021-01-05 | 安徽信息工程学院 | Method for optimizing transportation problem based on K-Means clustering and genetic algorithm |
| CN117350607A (en) * | 2023-09-18 | 2024-01-05 | 嘉兴环洋电商物流服务有限公司 | International logistics transportation path planning system of improved KNN algorithm model |
| CN117350607B (en) * | 2023-09-18 | 2024-06-07 | 嘉兴环洋电商物流服务有限公司 | International logistics transportation path planning system of improved KNN algorithm model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699982A (en) * | 2013-12-26 | 2014-04-02 | 浙江工业大学 | Logistics distribution control method with soft time windows |
| US20180032955A1 (en) * | 2016-08-01 | 2018-02-01 | Sap Se | System and method of minimizing waiting time in vehicle routing and scheduling with narrow time-windows |
| WO2018196525A1 (en) * | 2017-04-27 | 2018-11-01 | 北京京东尚科信息技术有限公司 | Goods handling method and device |
-
2019
- 2019-07-15 CN CN201910635877.0A patent/CN110533279B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699982A (en) * | 2013-12-26 | 2014-04-02 | 浙江工业大学 | Logistics distribution control method with soft time windows |
| US20180032955A1 (en) * | 2016-08-01 | 2018-02-01 | Sap Se | System and method of minimizing waiting time in vehicle routing and scheduling with narrow time-windows |
| WO2018196525A1 (en) * | 2017-04-27 | 2018-11-01 | 北京京东尚科信息技术有限公司 | Goods handling method and device |
Non-Patent Citations (4)
| Title |
|---|
| MAZIN ABEDMOHAMMED等: ""Solving vehicle routing problem by using improved K-nearest neighbor algorithm for best solution"", 《JOURNAL OF COMPUTATIONAL SCIENCE》 * |
| 俞武扬: "时间限制下的应急疏散车辆调度模型", 《电子科技大学学报(社科版)》 * |
| 张雪婷: ""基于 K-Means++和遗传算法的提货车辆路径研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 邢鹏: ""基于云平台的多配送中心车辆调度问题研究"", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942271A (en) * | 2019-12-11 | 2020-03-31 | 江苏佳利达国际物流股份有限公司 | Intelligent transportation scheduling management method based on neural network genetic algorithm |
| CN112184099A (en) * | 2020-08-21 | 2021-01-05 | 安徽信息工程学院 | Method for optimizing transportation problem based on K-Means clustering and genetic algorithm |
| CN117350607A (en) * | 2023-09-18 | 2024-01-05 | 嘉兴环洋电商物流服务有限公司 | International logistics transportation path planning system of improved KNN algorithm model |
| CN117350607B (en) * | 2023-09-18 | 2024-06-07 | 嘉兴环洋电商物流服务有限公司 | International logistics transportation path planning system of improved KNN algorithm model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110533279B (en) | 2023-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921472A (en) | A kind of two stages vehicle and goods matching method of multi-vehicle-type | |
| CN109117993B (en) | Processing method for optimizing vehicle path | |
| Li et al. | A hybrid genetic-simulated annealing algorithm for the location-inventory-routing problem considering returns under E-supply chain environment | |
| CN107766994A (en) | A kind of shared bicycle dispatching method and scheduling system | |
| CN107808215A (en) | A kind of goods yard distribution optimization method applied to the non-traditional layout warehouse of Flying V-types | |
| CN110276698A (en) | Distribution type renewable energy trade decision method based on the study of multiple agent bilayer cooperative reinforcing | |
| CN108764555A (en) | A kind of shared bicycle based on Hadoop parks a site selecting method | |
| CN105929690B (en) | A kind of Flexible Workshop Robust Scheduling method based on decomposition multi-objective Evolutionary Algorithm | |
| CN110046865A (en) | Distributed inventory's dispatching method | |
| CN105676814B (en) | The online Adding medicine control method in digitlization water island based on SFLA SVM | |
| CN110533279A (en) | For dispatching the method, system and storage medium of cloud logistics platform transport power | |
| CN107578197A (en) | The uncertain mix flow vehicles dispatching system optimization of region method of demand | |
| CN104842564B (en) | A kind of 3 D-printing multitask Optimization Scheduling based on NSGA II | |
| CN107292560A (en) | Material storage management method and system | |
| CN107341628B (en) | Hub and spoke type logistics network hub station site selection and distribution method based on probability tabu algorithm | |
| CN113313285B (en) | Multi-constraint vehicle path optimization method, system, storage medium and equipment | |
| Uyan et al. | Comparison of different optimization based land reallocation models | |
| CN110348563A (en) | The semi-supervised training method of neural network, device, server and storage medium | |
| Hou et al. | Stochastic vehicle routing problem with uncertain demand and travel time and simultaneous pickups and deliveries | |
| CN107239853B (en) | Intelligent housekeeper system based on cloud computing and working method thereof | |
| Kumari et al. | Utilizing a hybrid metaheuristic algorithm to solve capacitated vehicle routing problem | |
| CN107633336A (en) | A kind of fused data source statistics equipment, system and method | |
| CN116245346B (en) | Multi-unmanned aerial vehicle task allocation method based on multiple swarm genetic algorithms and local search | |
| Islam et al. | Solving capacitated vehicle routing problem by using heuristic approaches: A case study | |
| Wu et al. | Applications of AI techniques to generation planning and investment |
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 |