CN112101628B - Optimal control combination scheme for taxis of large-scale hub station - Google Patents
Optimal control combination scheme for taxis of large-scale hub station Download PDFInfo
- Publication number
- CN112101628B CN112101628B CN202010831470.8A CN202010831470A CN112101628B CN 112101628 B CN112101628 B CN 112101628B CN 202010831470 A CN202010831470 A CN 202010831470A CN 112101628 B CN112101628 B CN 112101628B
- Authority
- CN
- China
- Prior art keywords
- scheme
- area
- storage
- storage yard
- optimal
- 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.)
- Active
Links
- 230000029305 taxis Effects 0.000 title claims description 25
- 238000011156 evaluation Methods 0.000 claims description 33
- 230000004888 barrier function Effects 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 8
- 230000006698 induction Effects 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 239000002131 composite material Substances 0.000 claims description 5
- 230000008676 import Effects 0.000 claims description 3
- 238000002955 isolation Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
Images
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"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an optimal control combination scheme for a large hub station taxi, which solves the problems that in the prior art, parking in and out is easy to jam and the manual management cost is high. The scheme of the invention can realize intelligent scheduling management of a taxi storage yard, and the optimal combined control scheme of the mouth hardness is obtained by respectively and independently scoring and comprehensively scoring the storage yard scheme, the passing passage scheme and the passenger waiting area scheme, then dividing the supply and demand types of supply and demand data according to different storage yards and different passenger demands and adopting an unsupervised learning automatic clustering K-MEANS algorithm; the clustering center and the optimal combination control scheme pair form a reference library, and the optimal combination control scheme of the reference library is automatically taken out after the clustering center is matched, so that the ordered taxi in-out efficiency is optimal, and meanwhile, the manual management cost is saved.
Description
Technical Field
The invention relates to the field of smart cities, in particular to an optimal control combination scheme for large-scale junction stations taxis, which can recommend that taxis in and out of the junction stations in order.
Background
The method has the advantages that the construction of a large-scale hub station taxi management mode is a necessary trend of modern city development, and intelligent scheduling and control are key points of the large-scale hub station taxi management mode, so that the information bridge of the large-scale hub station taxi and a passenger is opened, the supply and demand balance taxi management mode is constructed, and the optimal taxi control combination scheme is built, and the method has very important significance. At present, the flow of people and the flow of vehicles in a large hub station are large, a taxi management and dispatching area comprises a vehicle storage yard, a vehicle passing channel, a vehicle getting-on area and a passenger waiting area, which are connected with the vehicle storage yard and the vehicle passing channel, wherein the vehicle passing channel, the passenger getting-on area and the passenger waiting area are short for the following, the vehicle storage yard is provided with a plurality of vehicle storage channels at present, the management is basically carried out by relying on manual work and a simple electronic management system, only one channel of the vehicle getting-on area is used for dispatching vehicles in sequence, the passenger waiting area is also only provided with one riding outlet, the phenomenon of disordered congestion can be easily caused when the vehicles get in and out and carry passengers, and the manual management cost is high.
For example, a control system and a control method for a large taxi storage yard disclosed in chinese patent literature, which is disclosed in CN103257618B, wherein a plurality of parallel queuing lanes are provided in the storage yard, and a movable partition rail is provided between two adjacent queuing lanes, characterized in that the front and the tail of each queuing lane are provided with an induction coil, the front and the tail of each queuing lane are provided with an induction automatic rail, the front and the tail of each lane are provided with an alarm lamp alarm bell, and the front and the tail of each queuing lane are provided with an indicator lamp, the control system comprises a monitoring room, the monitoring room is provided with a management workstation, the management workstation is connected with an on-site controller, and the on-site controller is connected with the induction coil, the induction automatic rail, the alarm lamp alarm bell and the indicator lamp. Although the scheme can realize automatic control and reduce managers, the scheme has only one channel for dispatching cars in sequence, the passenger waiting area has only one bus exit, the phenomena of congestion and confusion easily occur when people come in or go out for parking and carrying passengers, and the manual management cost is high.
Disclosure of Invention
The invention aims to solve the problems that the parking in and out is easy to be blocked and the manual management cost is high in the prior art, and provides an optimal control combination scheme for the taxis at the large hub station.
In order to achieve the purpose, the invention adopts the following technical scheme:
an optimal control combination scheme for taxis of a large hub station comprises the following steps:
s1, traffic organization optimization of four control areas, namely a storage yard, a traffic passage, a boarding area and a passenger waiting area;
s2, optimizing logic control processes of three control areas, namely a storage yard, a traffic passage and a boarding area, and control schemes of all areas;
s3, manually selecting a combination of a storage yard storage scheme, a passing lane scheme and a boarding area control scheme according to supply and demand conditions of a storage yard and a passenger waiting area in video monitoring, and simultaneously scoring and comprehensively scoring each area;
s4, automatically clustering N types of supply and demand types according to unsupervised learning after a certain amount of taxi supply and passenger waiting area demand data of the storage yard are accumulated in the step S3, wherein N is the number of clusters, each type of supply and demand type is matched with the respective optimal scheme combination according to the comprehensive score in the step S3, and the combination pair of the cluster center and the optimal scheme is a reference library;
and S5, matching corresponding supply and demand types under different storage yard storage supply and different passenger demands, and automatically taking out the optimal combination control scheme in the reference library.
Preferably, the S1 includes the following steps:
s11, adding equipment to the storage yard channel in the control area, wherein the equipment comprises an inlet/outlet gateway, an inlet/outlet light control assembly, inlet sensing equipment and outlet queuing detection equipment;
s12, the passing passage additional equipment comprises a passage waiting area entrance and exit gate and license plate recognition equipment, and the passenger area additional equipment comprises an entrance control lamp assembly, entrance queuing detection equipment and exit license plate recognition equipment;
s13, the passenger waiting area additional equipment comprises import and export counter equipment.
Preferably, the passenger waiting area comprises a queuing isolation facility, a plurality of automatic induction doors, movable railings, an entrance and a love channel.
Preferably, the S2 includes the following steps:
s21, a storage yard, a passing lane and a boarding area are logically controlled in the following steps that the storage yard is responsible for storing vehicles and outputting the vehicles to the passing lane, the passing lane is responsible for storing the vehicles passing through the storage yard and releasing the vehicles to the boarding area, and vehicle requests are sent to the passing lane when empty parking spaces appear at all points of the boarding area;
s22, the storage yard channel comprises two storage schemes, wherein in the first scheme, storage is carried out in turn from small to large according to the number of the channel, in the second scheme, three channels closest to the outlet are selected as priority storage channels, and storage is carried out in turn from small to large according to the number of the channels when the three priority storage channels are full;
s23, the vehicle passing channel comprises three control schemes, namely, a scheme I that an entrance barrier and an exit barrier are fully opened without limiting vehicle passing, a scheme II that the entrance barrier is normally opened, the exit barrier releases vehicles according to a plurality of batches of vehicles requested by a passenger area to open the barriers, and closes the barriers after releasing is completed;
s24, the boarding area comprises two boarding points, namely an area A and an area B, wherein the area A is far away from the vehicle passing channel and is provided with a special buffer area lane;
s25, wherein two rows of boarding passages are arranged in the boarding area A and the boarding area B and respectively correspond to the passages A1, A2, B1, B2, A1 and B1 which are close to passengers for boarding, the passages A2 and B2 which are far away from the passengers for boarding, 6 parking spaces are arranged in each row, and 6 vehicles can be stored in the buffer area B3 in the area B; for the safety of passengers getting on the vehicle, the precondition that the passengers are allowed to get on by A2 is that the passengers are on A1 and the passengers are not on A2, and the precondition that the passengers are allowed to get on by B2 is that the passengers are on B1 and the passengers are not on B2;
s26, the passenger getting-on area B requests vehicles from the passing lane, and the scheme comprises two request schemes, namely, a scheme I that B3 directly requests the passing lane, a scheme B1 that B2 directly requests the vehicles from B3, and a scheme II that B1 and B2 directly request the passing lane.
Preferably, the S3 includes the following steps:
s31, selecting a storage scheme, a traffic passage scheme and a boarding area scheme of the storage yard by workers according to supply and demand conditions of the storage area and a passenger waiting area in video monitoring;
and S32, after the scheme is selected, issuing the selected scheme and running the selected scheme for a period, wherein the period duration is 15 minutes, and after the period is finished, calculating three control areas of a parking lot storage scheme, a passing lane scheme and a passenger waiting area to respectively score and comprehensively score according to a storage lot evaluation rule, a passing lane scoring rule, a passenger waiting area scoring rule and a comprehensive scoring rule.
Preferably, the parking lot scoring rule is as follows:
wherein ST1 is the average waiting time of the driver in the storage yard in the period as the storage yard evaluation index, ST0 is the upper limit of the tolerance of the driver waiting time, the value is usually 120 minutes, SCORE1 is the evaluation SCORE of the storage yard, and SCORE1 is more than or equal to 0 and less than or equal to 10;
the scoring rule of the vehicle passing channel is as follows:
wherein AV1 is the average speed of the taxi in the period as the evaluation index of the passing lane, AV0 is the speed limit of the passing lane, the value is usually 40km/h, SCORE2 is the evaluation SCORE of the passing lane, and SCORE2 is not less than 0 and not more than 10;
the scoring rule of the passenger waiting area is as follows:
wherein CT1 is the passenger waiting area evaluation index and is the average waiting time of passengers in the period, CT0 is the passenger waiting time tolerance upper limit, the value is usually 30 minutes, SCORE3 is the evaluation SCORE of the passenger waiting area, SCORE3 is more than or equal to 0 and less than or equal to 10;
SCORE1, SCORE2, and SCORE3 are used to calculate a composite SCORE value SCORE.
Preferably, the calculation method of the composite score comprises the following steps:
SCORE＝a1*SCORE1+a2*SCORE2+a3*SCORE3,
wherein a1 is the evaluation weight of the storage yard, a2 is the evaluation weight of the passing lane, a3 is the evaluation weight of the passenger waiting area, SCORE is the comprehensive evaluation SCORE, and SCORE is more than or equal to 0 and less than or equal to 10.
Preferably, the S4 includes the following steps:
s41, nine supply and demand types can be divided according to the number of the storage areas and the passenger waiting areas after the supply and demand data of a certain number of the storage areas and the passenger waiting areas are accumulated in the S3;
s42, obtaining a specific division rule by adopting an unsupervised learning automatic clustering K-MEANS algorithm, inputting the number of taxis in a storage yard and the queuing number of passenger waiting areas by the clustering algorithm, inputting nine clustering numbers, automatically generating nine supply and demand types, and obtaining a two-dimensional clustering center (si, ci) of each type of clustering cluster, wherein si represents the number of taxis in the storage yard, and ci represents the queuing number of passenger waiting areas;
s43, selecting an optimal comprehensive score value for each cluster center, wherein the cluster center corresponds to the cluster with the comprehensive score values corresponding to all samples, and the highest comprehensive score value in each cluster is selected as the score value corresponding to each cluster center, according to the step (1-3), each optimal comprehensive score value corresponds to an optimal combination control scheme, the scheme is the optimal combination control scheme corresponding to the cluster center, and the cluster center and the optimal combination control scheme form a reference library.
Preferably, the S5 includes the following steps:
s51, under the conditions of new different storage yard storage supply and different passenger demands, when the realtime (S0, c0) is equal to the realtime (100,25), calculating the two-dimensional cluster center (si, ci) nearest distance dis of each cluster in the realtime (S0, c0) to S4, wherein the dis calculation formula is as follows:
wherein si represents the number of taxis in the storage yard, ci represents the queuing number of the passenger waiting area, and the real-time (s0, c0) represents the number of taxis in the storage yard and the queuing number of the passenger waiting area;
and S52, automatically taking out the combined control scheme corresponding to the supply and demand type in the reference library after matching the cluster center.
Therefore, the invention has the following beneficial effects:
1. the scheme of the invention can realize intelligent scheduling management of a taxi storage yard, and the method comprises the steps of performing individual scoring and comprehensive scoring on the storage yard scheme, the vehicle passing passage scheme and the passenger waiting area scheme, dividing supply and demand types of supply and demand data according to the number of vehicles supplied to different storage yards and different passenger demands, and obtaining an optimal combined control scheme by adopting an unsupervised learning automatic clustering K-MEANS algorithm;
2. and forming a reference library by the clustering center and the optimal combination control scheme pair, and automatically taking out the optimal combination control scheme of the reference library after matching the clustering center.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention is further described with reference to the following detailed description and accompanying drawings.
An optimal control combination scheme for taxis at a large hub station, as shown in fig. 1, comprises the following steps:
s1, traffic organization optimization of four control areas, namely a storage yard, a traffic passage, a boarding area and a passenger waiting area;
s2, optimizing logic control processes of three control areas, namely a storage yard, a traffic passage and a boarding area, and control schemes of all areas;
s3, manually selecting a combination of a storage yard storage scheme, a passing lane scheme and a boarding area control scheme according to supply and demand conditions of a storage yard and a passenger waiting area in video monitoring, and simultaneously scoring and comprehensively scoring each area;
s4, automatically clustering N types of supply and demand types according to unsupervised learning after a certain amount of taxi supply and passenger waiting area demand data of the storage yard are accumulated in the step S3, wherein N is the number of clusters, each type of supply and demand type is matched with the respective optimal scheme combination according to the comprehensive score in the step S3, and the combination pair of the cluster center and the optimal scheme is a reference library;
and S5, matching corresponding supply and demand types under different storage yard storage supply and different passenger demands, and automatically taking out the optimal combination control scheme in the reference library.
Preferably, the S1 includes the following steps:
s11, adding equipment to the storage yard channel in the control area, wherein the equipment comprises an inlet/outlet road gate, an inlet/outlet light control assembly, inlet sensing equipment and outlet queuing detection equipment;
s12, the passing passage additional equipment comprises a passage waiting area entrance and exit gate and license plate recognition equipment, and the passenger area additional equipment comprises an entrance control lamp assembly, entrance queuing detection equipment and exit license plate recognition equipment;
s13, the passenger waiting area additional equipment comprises import and export counter equipment.
The passenger waiting area comprises a queuing isolation facility, a plurality of automatic induction doors, movable railings, entrances and love channels.
Preferably, the S2 includes the following steps:
s21, a storage yard, a passing lane and a boarding area are logically controlled in the following steps that the storage yard is responsible for storing vehicles and outputting the vehicles to the passing lane, the passing lane is responsible for storing the vehicles passing through the storage yard and releasing the vehicles to the boarding area, and vehicle requests are sent to the passing lane when empty parking spaces appear at all points of the boarding area;
s22, the storage yard channels comprise two storage schemes, wherein in the first scheme, storage is sequentially and alternately circulated from small to large according to the channel numbers, in the second scheme, three channels closest to the outlet are selected as priority storage channels, and storage is sequentially and alternately circulated from small to large according to the channel numbers under the condition that the three priority storage channels are fully arranged;
s23, the vehicle passing channel comprises three control schemes, namely, a scheme I that an inlet barrier gate and an outlet barrier gate are fully opened without limiting vehicle passing, a scheme II that the inlet barrier gate is normally opened, the outlet barrier gate requests vehicles to release the vehicles for opening in batches according to the passenger area, and closes the vehicle after releasing is completed;
s24, the boarding area comprises two boarding points, namely an area A and an area B, wherein the area A is far away from the vehicle passing channel and is provided with a special buffer area lane;
s25, wherein the A area and the B area of the passenger getting-on area have two rows of passenger getting-on channels which respectively correspond to A1, A2 and B1, B2, A1 and B1 are channels close to passengers getting on the bus, A2 and B2 are channels far away from the passengers getting on the bus, each row has 6 parking spaces, and the B area buffer B3 can store 6 cars; for the safety of passengers getting on the vehicle, the precondition that the passengers are allowed to get on by A2 is that the passengers are on A1 and the passengers are not on A2, and the precondition that the passengers are allowed to get on by B2 is that the passengers are on B1 and the passengers are not on B2;
s26, the passenger getting-on area B requests vehicles from the passing lane, and the scheme comprises two request schemes, namely, a scheme I that B3 directly requests the passing lane, a scheme B1 that B2 directly requests the vehicles from B3, and a scheme II that B1 and B2 directly request the passing lane.
Preferably, the S3 includes the following steps:
s31, selecting a storage scheme, a passing lane scheme and a boarding area scheme of the storage area according to supply and demand conditions of the storage area and the passenger waiting area in video monitoring by workers;
and S32, after the scheme is selected, issuing the selected scheme and running the selected scheme for a period, wherein the period duration is 15 minutes, and after the period is finished, calculating three control areas of a parking lot storage scheme, a passing lane scheme and a passenger waiting area to respectively score and comprehensively score according to a storage lot evaluation rule, a passing lane scoring rule, a passenger waiting area scoring rule and a comprehensive scoring rule.
Preferably, the parking lot scoring rule is as follows:
wherein ST1 is the average waiting time of the driver in the storage yard in the period as the storage yard evaluation index, ST0 is the upper limit of the tolerance of the driver waiting time, the value is usually 120 minutes, SCORE1 is the evaluation SCORE of the storage yard, and SCORE1 is more than or equal to 0 and less than or equal to 10;
the scoring rule of the vehicle passing channel is as follows:
wherein AV1 is the average speed of the taxi in the period as the evaluation index of the passing lane, AV0 is the speed limit of the passing lane, the value is usually 40km/h, SCORE2 is the evaluation SCORE of the passing lane, and SCORE2 is not less than 0 and not more than 10;
the scoring rule of the passenger waiting area is as follows:
wherein CT1 is the passenger waiting area evaluation index and is the average waiting time of passengers in the period, CT0 is the passenger waiting time tolerance upper limit, the value is usually 30 minutes, SCORE3 is the evaluation SCORE of the passenger waiting area, SCORE3 is more than or equal to 0 and less than or equal to 10;
SCORE1, SCORE2, and SCORE3 are used to calculate a composite SCORE value SCORE.
Preferably, the calculation method of the composite score comprises the following steps:
SCORE＝a1*SCORE1+a2*SCORE2+a3*SCORE3,
wherein a1 is the evaluation weight of the storage yard, the value is 0.2, a2 is the evaluation weight of the passing lane, the value is 0.2, a3 is the evaluation weight of the passenger waiting area, the value is 0.6, SCORE is the comprehensive evaluation SCORE, and SCORE is not less than 0 and not more than 10.
Preferably, the S4 includes the following steps:
s41, nine supply and demand types can be divided according to the number of the storage areas and the passenger waiting areas after the supply and demand data of a certain number of the storage areas and the passenger waiting areas are accumulated in the S3;
s42, obtaining a specific division rule by adopting an unsupervised learning automatic clustering K-MEANS algorithm, inputting the number of taxis in a storage yard and the queuing number of passenger waiting areas by the clustering algorithm, inputting nine clustering numbers, automatically generating nine supply and demand types, and obtaining a two-dimensional clustering center (si, ci) of each type of clustering cluster, wherein si represents the number of taxis in the storage yard, and ci represents the queuing number of passenger waiting areas;
s43, selecting an optimal comprehensive score value for each cluster center, wherein the cluster center corresponds to the cluster with the comprehensive score values corresponding to all samples, and the highest comprehensive score value in each cluster is selected as the score value corresponding to each cluster center, according to the step (1-3), each optimal comprehensive score value corresponds to an optimal combination control scheme, the scheme is the optimal combination control scheme corresponding to the cluster center, and the cluster center and the optimal combination control scheme form a reference library.
The clustering centers and the optimal combination control scheme pair form a reference library, and part of data reference libraries are shown in the following table.
Table 1
Preferably, the S5 includes the following steps:
s51, under the conditions of new different storage yard storage supply and different passenger demands, when the realtime (S0, c0) is equal to the realtime (100,25), calculating the two-dimensional cluster center (si, ci) nearest distance dis of each cluster in the realtime (S0, c0) to S4, wherein the dis calculation formula is as follows:
wherein si represents the number of taxis in the storage yard, ci represents the queuing number of the passenger waiting area, and the real-time (s0, c0) represents the number of taxis in the storage yard and the queuing number of the passenger waiting area;
and S52, automatically taking out the combined control scheme with the reference library supply and demand type being type 3 after the cluster center is matched.
The scheme of the invention can realize intelligent scheduling management of a taxi storage yard, and the optimal combined control scheme is obtained by respectively and independently scoring and comprehensively scoring the storage yard scheme, the passing lane scheme and the passenger waiting area scheme, then dividing supply and demand types of supply and demand data according to the number of vehicles supplied by different storage yards and different passenger demands and adopting an unsupervised learning automatic clustering K-MEANS algorithm; the clustering center and the optimal combination control scheme pair form a reference library, and the optimal combination control scheme of the reference library is automatically taken out after the clustering center is matched, so that the ordered taxi in-out efficiency is optimal, and meanwhile, the manual management cost is saved.
The above embodiments are described in detail for the purpose of further illustrating the present invention and should not be construed as limiting the scope of the present invention, and the skilled engineer can make insubstantial modifications and variations of the present invention based on the above disclosure.
Claims (6)
1. An optimal control combination scheme for taxis of a large hub station is characterized by comprising the following steps:
s1, traffic organization optimization of four control areas, namely a storage yard, a traffic passage, a boarding area and a passenger waiting area;
s2, optimizing logic control processes of three control areas, namely a storage yard, a traffic passage and a boarding area, and control schemes of all areas;
s3, manually selecting a combination of a storage yard storage scheme, a passing lane scheme and a boarding area control scheme according to supply and demand conditions of a storage yard and a passenger waiting area in video monitoring, and simultaneously scoring and comprehensively scoring each area;
s4, automatically clustering N types of supply and demand types according to unsupervised learning after a certain amount of taxi supply and passenger waiting area demand data of the storage yard are accumulated in the step S3, wherein N is the number of clusters, each type of supply and demand type is matched with the respective optimal scheme combination according to the comprehensive score in the step S3, and the combination pair of the cluster center and the optimal scheme is a reference library;
s5, matching corresponding supply and demand types under different storage supply of the storage yard and different passenger demands, and automatically taking out the optimal combination control scheme in the reference library;
the S2 includes the steps of:
s21, a storage yard, a passing lane and a boarding area are logically controlled in the following steps that the storage yard is responsible for storing vehicles and outputting the vehicles to the passing lane, the passing lane is responsible for storing the vehicles passing through the storage yard and releasing the vehicles to the boarding area, and vehicle requests are sent to the passing lane when empty parking spaces appear at all points of the boarding area;
s22, the storage yard channel comprises two storage schemes, wherein in the first scheme, storage is carried out in turn from small to large according to the number of the channel, in the second scheme, three channels closest to the outlet are selected as priority storage channels, and storage is carried out in turn from small to large according to the number of the channels when the three priority storage channels are full;
s23, the vehicle passing channel comprises three control schemes, namely, a scheme I that an inlet barrier gate and an outlet barrier gate are fully opened without limiting vehicle passing, a scheme II that the inlet barrier gate is normally opened, the outlet barrier gate requests vehicles to release the vehicles for opening in batches according to the passenger area, and closes the vehicle after releasing is completed;
s24, the boarding area comprises two boarding points, namely an area A and an area B, wherein the area A enters from the passing channel and is free of a buffer lane, the area B is far from the passing channel and is provided with a special buffer lane, and the special buffer lane has three state control schemes, namely, a scheme I, an area A is opened, an area B is opened, a scheme II, an area A is opened, an area B is closed, a scheme III, an area A is closed and an area B is opened;
s25, wherein two rows of boarding passages are arranged in the boarding area A and the boarding area B and respectively correspond to the passages A1, A2, B1, B2, A1 and B1 which are close to passengers for boarding, the passages A2 and B2 which are far away from the passengers for boarding, 6 parking spaces are arranged in each row, and 6 vehicles can be stored in the buffer area B3 in the area B; for the safety of passengers getting on the bus, the A2 allows passengers to be taken on the premise that the A1 has the bus and the A2 does not have the bus, and the B2 allows passengers to be taken on the premise that the B1 has the bus and the B2 does not have the bus;
s26, the passenger getting-on area B requests vehicles from the passing lane, and the scheme comprises two request schemes, namely, a scheme I that B3 directly requests the passing lane, a scheme B1 that B2 directly requests the vehicles from B3, and a scheme II that B1 and B2 directly request the passing lane;
the S3 includes the steps of:
s31, selecting a storage scheme, a passing lane scheme and a boarding area scheme of the storage area according to supply and demand conditions of the storage area and the passenger waiting area in video monitoring by workers;
s32, after the scheme is selected, issuing the scheme to run for a period, wherein the period duration is 15 minutes, and after the period is finished, calculating three control areas of a parking lot storage scheme, a passing lane scheme and a passenger waiting area to respectively score and comprehensively score according to a storage lot evaluation rule, a passing lane scoring rule, a passenger waiting area scoring rule and a comprehensive scoring rule;
the parking lot scoring rule is as follows:
wherein ST1 is the average waiting time of the driver in the storage yard in the period as the storage yard evaluation index, ST0 is the upper limit of the tolerance of the waiting time of the driver, SCORE1 is the evaluation SCORE of the storage yard, SCORE1 is more than or equal to 0 and less than or equal to 10;
the scoring rule of the vehicle passing channel is as follows:
wherein AV1 is the average speed of the taxi in the period as the evaluation index of the passing lane, AV0 is the speed limit of the passing lane, SCORE2 is the evaluation SCORE of the passing lane, and SCORE2 is more than or equal to 0 and less than or equal to 10;
the scoring rule of the passenger waiting area is as follows:
wherein the CT1 is the passenger waiting area evaluation index and is the average waiting time of passengers in the period, the CT0 is the passenger waiting time tolerance upper limit, the SCORE3 is the evaluation SCORE of the passenger waiting area, and the SCORE3 is not less than 0 and not more than 10;
SCORE1, SCORE2, and SCORE3 are used to calculate a composite SCORE value SCORE.
2. The optimal control combination scheme for taxis at large hub stations according to claim 1, wherein the step S1 comprises the steps of:
s11, adding equipment to the storage yard channel in the control area, wherein the equipment comprises an inlet/outlet gateway, an inlet/outlet light control assembly, inlet sensing equipment and outlet queuing detection equipment;
s12, the passing passage additional equipment comprises a passage waiting area entrance and exit gate and license plate recognition equipment, and the passenger area additional equipment comprises an entrance control lamp assembly, entrance queuing detection equipment and exit license plate recognition equipment;
s13, the passenger waiting area additional equipment comprises import and export counter equipment.
3. The optimal control combination scheme for taxis at large hub stations according to claim 2, wherein the passenger waiting area comprises queuing isolation facilities, a plurality of automatic induction doors, movable railings, entrances and love lanes.
4. The optimal control combination scheme for taxis at large hub stations according to claim 3, wherein the calculation method of the comprehensive score is as follows:
SCORE＝a1*SCORE1+a2*SCORE2+a3*SCORE3,
wherein a1 is the evaluation weight of the storage yard, a2 is the evaluation weight of the passing lane, a3 is the evaluation weight of the passenger waiting area, SCORE is the comprehensive evaluation SCORE, and SCORE is more than or equal to 0 and less than or equal to 10.
5. The optimal control combination scheme for taxis at large hub stations according to claim 1, wherein the step S4 comprises the steps of:
s41, nine supply and demand types can be divided according to the number of the storage areas and the passenger waiting areas after the supply and demand data of a certain number of the storage areas and the passenger waiting areas are accumulated in the S3;
s42, obtaining a specific division rule by adopting an unsupervised learning automatic clustering K-MEANS algorithm, inputting the number of taxis in a storage yard and the queuing number of passenger waiting areas by the clustering algorithm, inputting nine clustering numbers, automatically generating nine supply and demand types, and obtaining a two-dimensional clustering center (si, ci) of each type of clustering cluster, wherein si represents the number of taxis in the storage yard, and ci represents the queuing number of passenger waiting areas;
s43, selecting an optimal comprehensive score value for each cluster center, wherein the cluster center corresponds to the cluster with the comprehensive score values corresponding to all samples, and the highest comprehensive score value in each cluster is selected as the score value corresponding to each cluster center, according to the step (1-3), each optimal comprehensive score value corresponds to an optimal combination control scheme, the scheme is the optimal combination control scheme corresponding to the cluster center, and the cluster center and the optimal combination control scheme form a reference library.
6. The optimal control combination scheme for taxis at large hub stations according to claim 1, wherein the step S5 comprises the steps of:
s51, under the conditions of new different storage yard storage supply and different passenger demands, when the realtime (S0, c0) is equal to the realtime (100,25), calculating the two-dimensional cluster center (si, ci) nearest distance dis of each cluster in the realtime (S0, c0) to S4, wherein the dis calculation formula is as follows:
wherein si representsThe number of taxis in the storage yard, ci represents the queuing number of the passenger waiting area, and the realtime (s0, c0) represents the real-time number of the taxis in the storage yard and the queuing number of the passenger waiting area;
and S52, automatically taking out the combined control scheme corresponding to the supply and demand type in the reference library after matching the cluster center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010831470.8A CN112101628B (en) | 2020-08-18 | 2020-08-18 | Optimal control combination scheme for taxis of large-scale hub station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010831470.8A CN112101628B (en) | 2020-08-18 | 2020-08-18 | Optimal control combination scheme for taxis of large-scale hub station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112101628A CN112101628A (en) | 2020-12-18 |
| CN112101628B true CN112101628B (en) | 2022-09-16 |
Family
ID=73753130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010831470.8A Active CN112101628B (en) | 2020-08-18 | 2020-08-18 | Optimal control combination scheme for taxis of large-scale hub station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101628B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115329417B (en) * | 2022-03-30 | 2024-06-07 | 西南交通大学 | Pivot column flow graph compiling method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2768578A1 (en) * | 2012-02-16 | 2013-08-16 | Trapeze Software Inc. | Method and system for adjusting a demand-response transit schedule |
| CN107832882A (en) * | 2017-11-03 | 2018-03-23 | 上海交通大学 | A kind of taxi based on markov decision process seeks objective policy recommendation method |
| CN110175788A (en) * | 2019-05-31 | 2019-08-27 | 国网上海市电力公司 | A kind of smart city energy cloud platform |
| CN111133447A (en) * | 2018-02-18 | 2020-05-08 | 辉达公司 | Object detection and detection confidence suitable for autonomous driving |
| EP3660757A1 (en) * | 2018-11-29 | 2020-06-03 | HERE Global B.V. | Method and apparatus for booking of a shared vehicle |
-
2020
- 2020-08-18 CN CN202010831470.8A patent/CN112101628B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2768578A1 (en) * | 2012-02-16 | 2013-08-16 | Trapeze Software Inc. | Method and system for adjusting a demand-response transit schedule |
| CN107832882A (en) * | 2017-11-03 | 2018-03-23 | 上海交通大学 | A kind of taxi based on markov decision process seeks objective policy recommendation method |
| CN111133447A (en) * | 2018-02-18 | 2020-05-08 | 辉达公司 | Object detection and detection confidence suitable for autonomous driving |
| EP3660757A1 (en) * | 2018-11-29 | 2020-06-03 | HERE Global B.V. | Method and apparatus for booking of a shared vehicle |
| CN110175788A (en) * | 2019-05-31 | 2019-08-27 | 国网上海市电力公司 | A kind of smart city energy cloud platform |
Non-Patent Citations (2)
| Title |
|---|
| 基于灰色加权关联度的城市轨道交通与常规公交协调方案优选研究;周静;《公路与汽运》;20130725(第04期);第55-57+68页 * |
| 考虑轨迹相似度的综合客运枢纽出租车合乘方法研究;吴玥琳等;《交通运输系统工程与信息》;20200415(第02期);第192-199页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112101628A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119835B (en) | Bus dynamic departure scheduling optimization method based on interval calculation | |
| CN109887267B (en) | Conventional public transportation adjusting method for common line segment of rail transit | |
| CN111340289B (en) | Genetic algorithm-based bus departure and speed adjustment optimization method and system | |
| CN109886491A (en) | A kind of routine bus system two stages Optimization Scheduling of magnanimity operation data driving | |
| CN110751366A (en) | Method for calculating running capacity matching degree of main railway and urban rail transit | |
| CN110942411A (en) | Subway station passenger flow grading alarm method based on regional linkage | |
| CN102110368A (en) | System and method for automatically checking vehicles evading toll fee by changing license plates on highways | |
| CN114141030B (en) | Post-accident highway traffic flow induction method under heterogeneous driving requirements | |
| CN112101628B (en) | Optimal control combination scheme for taxis of large-scale hub station | |
| CN111401643B (en) | Urban rail transit passenger flow loop self-adaptive intelligent train scheduling method | |
| CN108665140A (en) | A kind of inter-city passenger rail Passenger Transport Hub traffic connection System Assessment Method | |
| CN112861420B (en) | Mesoscopic traffic simulation model construction method oriented to mixed traffic flow operation scene | |
| CN113988371B (en) | Urban rail transit cross-station stop-start scheme optimization method based on passenger flow direct | |
| CN109979186B (en) | Bus parking position real-time distribution method based on GPS system | |
| CN113257007B (en) | Signal control method and system for intersection to share automatic driving lane | |
| CN114707709A (en) | Safety early warning method and system for comprehensive passenger transport hub of railway | |
| CN106683432A (en) | Intersection traffic signal lamp driving control system of intelligent electronic police | |
| CN114841415A (en) | Urban rail transit passenger flow prediction and multistage transportation organization method during large-scale activities | |
| CN115860594A (en) | Simulation system and method applied to intelligent bus scheduling | |
| KR102150723B1 (en) | Automatic ticket selling and checking system for railway train | |
| CN117576929B (en) | Vehicle speed and signal collaborative optimization method considering intersection of different public transport planes | |
| CN117094506A (en) | Subway transfer station passenger flow bottleneck control method based on platform congestion degree | |
| CN101550667A (en) | Control method of integrated setting of on-board and off-board stop station of bus and taxi | |
| CN115440073A (en) | Quick emergency personnel vehicle scheduling system in wisdom city | |
| Deng et al. | Digital twin modeling for demand responsive transit |
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 | ||
| CB02 | Change of applicant information |
Address after: 310053 23-25, 2 building, 352 BINKANG Road, Binjiang District, Hangzhou, Zhejiang. Applicant after: Zhejiang zhongkong Information Industry Co.,Ltd. Address before: 310053 23-25, 2 building, 352 BINKANG Road, Binjiang District, Hangzhou, Zhejiang. Applicant before: ZHEJIANG SUPCON INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |