CN117669971B - Data-driven electric bus charging station address selection method - Google Patents
Data-driven electric bus charging station address selection method Download PDFInfo
- Publication number
- CN117669971B CN117669971B CN202311691075.4A CN202311691075A CN117669971B CN 117669971 B CN117669971 B CN 117669971B CN 202311691075 A CN202311691075 A CN 202311691075A CN 117669971 B CN117669971 B CN 117669971B
- Authority
- CN
- China
- Prior art keywords
- charging
- charging station
- data
- demand
- bus
- 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
- 238000010187 selection method Methods 0.000 title abstract description 6
- 238000007418 data mining Methods 0.000 claims abstract description 6
- 230000002776 aggregation Effects 0.000 claims description 71
- 238000004220 aggregation Methods 0.000 claims description 71
- 238000000034 method Methods 0.000 claims description 63
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 21
- 230000005484 gravity Effects 0.000 claims description 13
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000009826 distribution Methods 0.000 description 26
- 230000008569 process Effects 0.000 description 22
- 238000011160 research Methods 0.000 description 7
- 238000005192 partition Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 241000588771 Morganella <proteobacterium> Species 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000002803 fossil fuel Substances 0.000 description 2
- 239000005431 greenhouse gas Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000029305 taxis Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention particularly relates to a data-driven electric bus charging station location selection method, which comprises the following steps: rasterizing a target city to generate a target city grid; extracting the OD trip data of the passengers according to the card swiping data of the electric buses; matching the OD travel data of the passengers into a target city grid to generate a city travel network; carrying out community discovery on the urban travel network, and taking communities obtained by division as initial charging service areas; performing data mining on the OD travel data of the passengers to obtain departure shifts and operation mileage of each bus route, and obtaining charging requirements of each bus route according to the departure shifts and the operation mileage; and determining the address of the charging station and the service range of the charging station according to the initial charging service area and the charging requirements of each bus line. The invention comprehensively considers the future and current electric bus charging demands and selects addresses in two stages, thereby improving the prospective and rationality of selecting addresses of electric bus charging stations.
Description
Technical Field
The invention relates to the field of electric bus charging planning and layout, in particular to an electric bus charging station address selection method based on data driving.
Background
The change of the climate conditions caused by the greenhouse gases has an influence on the development of the ecosystem and the socioeconomic performance, and also forms a serious threat to the public health. The daily operation of modern cities consumes a large amount of fossil fuel, most of greenhouse gas emissions come from the inside of the cities, and in the traffic field, many scholars are striving to reduce carbon emissions from the inside of the cities through a green travel mode. In recent years, electric buses are widely popularized and used. Compared with the traditional bus, the electric bus has obvious advantages in noise control and driving stability, has high energy conversion efficiency, can reduce the pollution of the vehicle to the environment in the use process and the dependence on fossil fuel, and can improve the energy structure to a certain extent.
At present, more research is focused on the aspect of charging private cars and taxis, and the arrangement of electric bus charging stations is rarely considered. The uncertainty in the daily running process of private cars and taxis is strong, the time selection and the space selection of charging have great randomness, and the running characteristics of buses are greatly different from those of buses: the bus departure shift is relatively determined, and the bus departure shift is provided with a fixed time window, and is usually charged when waiting for a shift or stopping at night; the line and the stop station are relatively fixed, so that the influence on the operation of the line needs to be considered, and the time loss in the charging process should be reduced as much as possible.
Related studies on electric bus charging facility site selection and optimization can be largely divided into an optimization model and a data-driven class model, with the data-driven class model being the focus of the current study. For example, the existing scheme provides a grid neighbor propagation (AP) clustering algorithm, which searches for the best candidate position of an electric bus charging station under the condition of considering various influencing factors such as land cost, traffic conditions and the like, and provides the extension sequence of the stations based on the result of the candidate position. The influence of charging the electric buses at the bus stops is also researched, and a novel method is provided, so that the bus stop points are clustered while the limit of a power grid is met, and the energy cost is reduced.
Through research on the existing scheme, the applicant finds that the following problems exist in the research on the site selection problem of the charging station: 1) The characteristics of fixed stop points, public operation vehicles and the like of the electric buses compared with private buses are not taken into consideration in the current research generally, the difference of the electric buses in daily operation and charging processes is not reflected, the suitability for charging the buses is poor, and the problem of insufficient site selection rationality of charging stations exists. 2) The existing research provides a layout method based on a static aggregation form of public transportation capacity, but because a public transportation line is greatly influenced by opening a newly built track and the like and has time-varying characteristics, the problem that supply and demand space is not matched under a larger time scale when the charging station is laid out by only considering the current public transportation line and the transportation capacity layout form, so that the prospective of selecting the address of the charging station is poor. Therefore, how to improve the prospective and rationality of the electric bus charging station site selection is a technical problem to be solved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to solve the technical problems that: how to provide an electric bus charging station address selection method based on data driving, the electric bus charging station service area can be divided by taking future demands as foothold points, and meanwhile, the specific address selection of the charging station is performed by considering the transportation capacity and the charging demand aggregation form of the electric bus, namely, the future and current electric bus charging demands can be comprehensively considered and subjected to two-stage address selection, so that the prospective and rationality of the electric bus charging station address selection are improved.
In order to solve the technical problems, the invention adopts the following technical scheme:
An electric bus charging station location method based on data driving comprises the following steps:
S1: rasterizing a target city to generate a target city grid;
S2: extracting corresponding passenger OD trip data according to card swiping data of the electric bus;
s3: matching the OD travel data of the passengers into a target city grid to generate a corresponding city travel network;
s4: carrying out community discovery on the urban travel network, and taking communities obtained by division as initial charging service areas;
S5: performing data mining on the OD travel data of the passengers to obtain departure shifts and operation mileage of each bus route, and obtaining charging requirements of each bus route according to the departure shifts and the operation mileage;
s6: determining the address of a charging station and the service range of the charging station according to the initial charging service area and the charging requirements of each bus line;
The method specifically comprises the following steps:
S601: carrying out cold and hot spot analysis on the charging requirements in each charging service area, and determining hot spot areas and cold spot areas where the charging requirements are gathered;
s602: determining the address of a charging station in each charging service area by using a gravity center method by taking the charging demand as a weight;
S603: repartitioning the service range of the site selection of the charging station by utilizing the Voronoi diagram;
S604: according to the hot spot areas and the cold spot areas which are gathered according to the charging demands and combining with charging station site selection and service ranges thereof, calculating corresponding space gathering degree and demand gathering degree;
S605: judging whether the space aggregation degree and the demand aggregation degree are stable or reach the optimal value: if yes, step S606 is entered, otherwise, the service range of the charging service area is updated according to the newly divided service range of the charging station address selection, and step S601 is returned to carry out the next iteration;
s606: and outputting a corresponding dividing result of the address selection of the charging station and the service range of the charging station.
Preferably, firstly, collecting and counting the starting and ending points of the OD trip data of the passengers; then matching the starting and ending station of resident trip to the corresponding grid in the target city grids; and finally, regarding the starting and ending point of resident travel as a network node, regarding an OD line as a network side, regarding an OD quantity as an edge weight, and generating an urban travel network based on electric bus travel.
Preferably, community discovery is performed by:
s401: initializing, namely dividing each node in the urban travel network into different communities;
s402: for each node, dividing the node into communities where nodes adjacent to the node are located, and calculating module degree change values before and after division: if the module degree change value is zero, abandoning the division; otherwise, the division is accepted;
1) The calculation formula of the modularity is:
Wherein: q represents the modularity of the urban travel network; a represents a tie matrix; a ij represents the weight between nodes i and j, and when the network is an unbiased graph, the weight between all edges can be considered as 1; Representing the sum of the weights of all edges connected to node i; /(I) Representing the sum of the weights of all edges; c i represents the community to which node i is assigned, if two nodes are in the same community, the value of δ (c i,cj) is 1, otherwise it is 0;
2) The calculation formula of the module degree change value is as follows:
ΔQ＝Qf-Qb；
Wherein: Δq represents the amount of change in the module degree Q before and after division, i.e., the module degree change value; q f、Qb represents the module degree Q before and after the change, respectively;
S403: repeating the step S402 until all nodes are accessed once and no update occurs, and generating a corresponding community structure;
S404: reconstructing a city travel network according to the community structure generated in the step S403, and aggregating all nodes in the same community together to form a new node;
s405: and repeating the steps S402 to S404 until the structure of the urban travel network is not changed any more, and taking the communities obtained by division as charging service areas.
Preferably, the charging demand of the bus line is calculated by the following formula:
Demande＝Scale*Mileage Charging method ；
Mileage Charging method ＝Distance First and last station - Charging station ；
Wherein: demand e represents the charging Demand of the bus line; mileage Charging method represents the mileage that the electric bus needs to travel for charging; scale represents the departure shift of a single bus line; distance First and last station - Charging station represents the Euclidean Distance from the head and end of the bus line to the charging station.
Preferably, first and last stations of a bus line are identified, and the first and last stations of the bus line are used as basic space units for cold and hot point analysis; then taking the charging requirement of each bus line as a numerical basis for cold and hot spot analysis; and finally, carrying out hot spot analysis on the aggregation forms of the first and the last stations of each bus line to obtain a hot spot area and a cold spot area with aggregated charging requirements.
Preferably, the cold and hot spot analysis is performed based on the molan index;
Dividing the aggregation forms of the first station and the last station of the bus line into high value aggregation, low value surrounded by high value, low value aggregation and high value surrounded by low value through the Morlan index, and taking the high value aggregation and the low value aggregation as hot spot areas and cold spot areas for charging demand aggregation;
The calculation formula of the Morgan index is described as:
Wherein: i represents a global Morgan index; n represents the number of grids; i and j represent two different grids; w ij represents the spatial weight between two grids, if two grids are adjacent, it is 1, otherwise it is 0; x i and x j are information represented by two grids different from each other, herein referred to as charging demand; An average value of the charging requirements for each grid; i i is the local Morgan index; s i is the standard deviation of the attribute values of all grids, i.e. the standard deviation of the charging demand.
Preferably, the calculation formula of the gravity center method is expressed as:
Wherein: c jlon、Cjlat respectively represents a longitude value and a latitude value of the address of the charging station in the charging service area j; c ilon、Cilat represents the coordinate longitude value and latitude value of the first and last stations i in the charging service area j; demand ei represents the charging Demand of the first and last stations i; m represents the number of first and last stations i in the charging service area j.
Preferably, the calculation formula of the demand concentration is:
Wherein: h represents the demand concentration; d h denotes the charging demand of the hot spot area; d w denotes the total charging demand within the charging station site selection service range.
Preferably, the calculation formula of the space aggregation degree is as follows:
Wherein: s represents the demand concentration degree; dis h represents the average distance of charging station site selection to the hot spot area; dis l represents the average distance of the charging station site to the cold spot area.
Preferably, determining whether the spatial concentration is stable or optimal means that the spatial concentration and the demand concentration obtained by two consecutive calculations are no longer changed or reduced.
Compared with the prior art, the data-driven electric bus charging station address selection method has the following beneficial effects:
The method comprises the steps of extracting the OD travel data of the passengers from the card swiping data of the electric bus, matching the OD travel data of the passengers to a target city grid to generate a city travel network, and finally generating a plurality of charging service areas by carrying out community discovery on the city travel network. According to the invention, the space-time distribution of resident riding demands can be reflected through the passenger OD traveling data, and the passenger traveling OD is always stable under the condition that the urban land property and the industrial gravity center are not changed greatly, namely the data essentially reflect the current and future possible bus route layout, so that the electric bus charging service area (community) is divided by taking the future demands as the landing points through the passenger OD traveling data, and the prospective of electric bus charging station address selection is improved.
According to the invention, on the basis of dividing the charging service areas of the electric buses by taking future demands as foothold points, further analyzing the charging demands of bus lines and performing cold and hot spot analysis, determining hot spot areas and cold spot areas where the charging demands are gathered, then determining the charging station address of each community by using a gravity center method according to the charging demands of each head and tail station, re-dividing the service range of the charging station address by using a Voronoi diagram, finally calculating the space gathering degree and the demand gathering degree to evaluate the rationality of the charging station address selection, and performing iterative address selection of the charging station. On one hand, the invention fully considers the factors of the transportation capacity and the charge demand gathering form of the buses through the charge demand and the cold and hot points of the charge demand gathering of the bus lines, namely, the invention can comprehensively consider and two-stage address selection of the future and current electric bus charge demands, thereby improving the rationality of address selection of the electric bus charging stations. On the other hand, the rationality of the site selection of the charging station can be evaluated from two dimensions of the difference of the distribution of the charging demands in different service areas and the relative time cost of the charging of the buses by calculating the space aggregation degree and the demand aggregation degree; meanwhile, the service range of the charging station address selection is continuously divided again in the charging station iterative address selection process through the Voronoi diagram, so that the rationality of the charging station address selection of the electric bus can be further improved.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings, in which:
FIG. 1 is a logic block diagram of a data-driven electric bus charging station addressing method;
FIG. 2 is a logical block diagram of community discovery;
FIG. 3 is a logic block diagram of iterative addressing of charging stations;
FIG. 4 is a flow chart of iterative site selection of charging stations;
FIG. 5 is a schematic diagram of a community discovery algorithm;
FIG. 6 is an example of a Voronoi diagram;
Fig. 7 is a logic block diagram of a hotspot identification-Voronoi diagram addressing method.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. In the description of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., are directions or positional relationships based on those shown in the drawings, or are directions or positional relationships conventionally put in use of the inventive product, are merely for convenience of describing the present invention and simplifying the description, and are not indicative or implying that the apparatus or element to be referred to must have a specific direction, be constructed and operated in a specific direction, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance. Furthermore, the terms "horizontal," "vertical," and the like do not denote a requirement that the component be absolutely horizontal or overhang, but rather may be slightly inclined. For example, "horizontal" merely means that its direction is more horizontal than "vertical" and does not mean that the structure must be perfectly horizontal, but may be slightly tilted. In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
The following is a further detailed description of the embodiments:
Examples:
in order to better introduce the principle of the technical scheme of the present invention, the following assumptions are made in this embodiment:
1) The electric bus can be charged only before the bus is started at the first and last stops, and the electricity cannot be supplemented along the running path.
2) All electric buses have the same electricity storage performance, namely power batteries with the same capacity.
3) All electric buses have the same power performance, i.e. the time spent by all electric buses is the same under the same running mileage.
4) The number of charging piles in the charging station can meet the charging requirement of buses in a service range, namely, the electric buses have no queuing time loss in the charging process.
5) The urban distribution network can meet the electricity demand of the charging station, namely regional power capacity constraint is not considered.
6) The electric bus can only go to the charging station nearest to the line vehicle for charging, and cannot go to other charging stations under the influence of certain factors.
Meanwhile, the following description is made on some parameters related to the present invention:
1) Considering the operation mileage of a single bus route as the Euclidean distance between the first station and the last station;
mileage operation = Distance head-end station
2) The mileage of the electric bus to the charging station is the Euclidean distance from the first stop to the charging station;
Mileage charge = Distance head end-charging station.
3) Setting the charging requirement as the product of the operation mileage of the bus route and the departure shift;
demande = Scale Mileage charge.
4) The community discovery algorithm is characterized in that part of bus stops are eliminated in the algorithm because a more continuous space area cannot be formed, and the bus stops with the eliminated part are considered to have no great influence on the community discovery result.
5) Because of the difference of the passenger flow of different areas in the city, the invention selects 500m and 500m as the geographic information grids, so that only one bus station can be ensured in the city, and at most only 1 bus station is considered in each geographic information grid.
6) The latitude and longitude information of partial data in the original data set has a larger degree of offset, the partial data is rejected, but the latitude and longitude information of the partial data is found to have a small range of offset, the partial data is difficult to screen, and the partial data is considered to have no larger influence on the final result of the invention.
Based on the above description, the embodiment discloses an electric bus charging station address selecting method based on data driving.
As shown in fig. 1 and 2, a data-driven electric bus charging station location method includes:
S1: rasterizing a target city to generate a target city grid;
S2: extracting corresponding passenger OD trip data according to card swiping data of the electric bus;
In this embodiment, the card swiping data refers to IC card swiping data of passengers taking buses, in which corresponding passenger travel information and bus route information are stored, so that we can determine the positions of individuals and vehicles spatially and temporally. The public transport trip OD of passengers can reflect the current and future public transport line layout to a certain extent, and the charging demand distribution of the public transport system can be identified, so that a new thought is provided for the layout of electric bus charging stations in cities.
S3: matching the OD travel data of the passengers into a target city grid to generate a corresponding city travel network;
s4: carrying out community discovery on the urban travel network, and taking communities obtained by division as initial charging service areas;
S5: performing data mining on the OD travel data of the passengers to obtain departure shifts and operation mileage of each bus route, and obtaining charging requirements of each bus route according to the departure shifts and the operation mileage;
in this embodiment, the passenger OD travel data includes a tag related to a bus route, and all the bus routes in the city can be obtained by screening and de-duplicating the tag.
S6: determining the address of a charging station and the service range of the charging station according to the initial charging service area and the charging requirements of each bus line;
The method specifically comprises the following steps:
S601: carrying out cold and hot spot analysis on the charging requirements in each charging service area, and determining hot spot areas and cold spot areas where the charging requirements are gathered;
s602: determining the address of a charging station in each charging service area by using a gravity center method by taking the charging demand as a weight;
S603: repartitioning the service range of the site selection of the charging station by utilizing the Voronoi diagram;
S604: according to the hot spot areas and the cold spot areas which are gathered according to the charging demands and combining with charging station site selection and service ranges thereof, calculating corresponding space gathering degree and demand gathering degree;
S605: judging whether the space aggregation degree and the demand aggregation degree are stable or reach the optimal value: if yes, step S606 is entered, otherwise, the service range of the charging service area is updated according to the newly divided service range of the charging station address selection, and step S601 is returned to carry out the next iteration;
s606: and outputting a corresponding dividing result of the address selection of the charging station and the service range of the charging station.
The method comprises the steps of extracting the OD travel data of the passengers from the card swiping data of the electric bus, matching the OD travel data of the passengers to a target city grid to generate a city travel network, and finally generating a plurality of charging service areas by carrying out community discovery on the city travel network. According to the invention, the space-time distribution of resident riding demands can be reflected through the passenger OD traveling data, and the passenger traveling OD is always stable under the condition that the urban land property and the industrial gravity center are not changed greatly, namely the data essentially reflect the current and future possible bus route layout, so that the electric bus charging service area (community) is divided by taking the future demands as the landing points through the passenger OD traveling data, and the prospective of electric bus charging station address selection is improved.
According to the invention, on the basis of dividing the charging service areas of the electric buses by taking future demands as foothold points, further analyzing the charging demands of bus lines and performing cold and hot spot analysis, determining hot spot areas and cold spot areas where the charging demands are gathered, then determining the charging station address of each community by using a gravity center method according to the charging demands of each head and tail station, re-dividing the service range of the charging station address by using a Voronoi diagram, finally calculating the space gathering degree and the demand gathering degree to evaluate the rationality of the charging station address selection, and performing iterative address selection of the charging station. On one hand, the invention fully considers the factors of the transportation capacity and the charge demand gathering form of the buses through the charge demand and the cold and hot points of the charge demand gathering of the bus lines, namely, the invention can comprehensively consider and two-stage address selection of the future and current electric bus charge demands, thereby improving the rationality of address selection of the electric bus charging stations. On the other hand, the rationality of the site selection of the charging station can be evaluated from two dimensions of the difference of the distribution of the charging demands in different service areas and the relative time cost of the charging of the buses by calculating the space aggregation degree and the demand aggregation degree; meanwhile, the service range of the charging station address selection is continuously divided again in the charging station iterative address selection process through the Voronoi diagram, so that the rationality of the charging station address selection of the electric bus can be further improved.
In this embodiment, an example analysis is performed by applying 574 ten thousand bus card swiping data in a city in the eastern part of China, the city is divided into 11 charging service areas by using a community discovery model, and address selection is performed in each charging service area. The results show that: in the 11 charging service areas, the demand concentration degree of the 10 charging service areas is increased to a certain extent compared with that of the initial subarea, wherein the demand concentration degree of the 8 charging service areas is more than 0.5, and the charging demands in most of the charging service areas are concentrated in a high-value aggregation area; the space aggregation degree of all the charging service areas is less than 1,7 charging service areas, the space aggregation degree of the whole city is reduced from 0.680 to 0.602 by 11.47%, the space aggregation degree of most charging service areas is reduced, the demand aggregation degree is increased, the structure of the charging service areas is optimized in the site selection process, the time cost of charging buses is relatively reduced, and the technical scheme of the invention has good applicability to site selection of charging stations.
In the specific implementation process, urban rasterization is realized through the existing GIS (geographic information system) software. When the target city is rasterized, the target city is divided into 500 x 500m grids, and at most one bus station exists in each grid.
In the specific implementation process, the OD data of the passengers can be identified and extracted according to specific data generated when the passengers travel by taking the buses as the passengers' OD behaviors, and the corresponding spatial distribution characteristics of the OD data can be further analyzed and identified. The space distribution of the OD is often determined by factors such as urban land property, industry distribution, population aggregation and the like, and is generally stable under a larger time scale, and the space distribution characteristics can reflect travel demands of residents in corresponding areas, namely, the planning demand condition of bus lines under the larger time scale, so that the future bus charging demands are considered by dividing service areas of the charging stations according to the space distribution characteristics.
The invention carries out data cleaning and processing on card swiping data of the electric bus to obtain the OD trip data of passengers.
In this embodiment, the original card swiping data of the electric bus is the IC card swiping data, the ID, time and place of the resident can be displayed by a single piece of data, the latitude and longitude are screened (the latitude and longitude range is the approximate range of the urban administrative district, the time is limited according to the bus running time of the corresponding city, usually, a small amount of data in midnight and early morning is removed), and the resident trip data are obtained by sorting according to the ID and trip time.
Meanwhile, a resident getting-off place is determined by adopting a mode of reconstructing a travel chain, as resident travel is regular, after sorting according to ID and travel time, the times of occurrence of the same ID card in a single day are screened, data (the data are very few) which only occur once and more than four times in the single day are removed, and then the travel chain is reconstructed according to the times of card swiping and the time interval between the data. If an ID appears twice in a single day and the two swipes are long (a few hours apart), then the start of the second swipe is considered to be the end of the first swipe. And reconstructing the row chain in a more refined manner according to the time interval between the data for the data of three times and four times.
In the specific implementation process, firstly, collecting and counting the starting and ending points of the OD travel data of the passengers; then matching the starting and ending station of resident trip to the corresponding grid in the target city grids; and finally, regarding the starting and ending point of resident travel as a network node, regarding an OD line as a network side, regarding an OD quantity as an edge weight, and generating an urban travel network based on electric bus travel.
In this embodiment, the urban travel network is a relatively complex "graph", the OD line refers to travel between two grids in the city, and the urban travel network is an edge; the OD quantity refers to the travel quantity between two grids in the city, and represents the weight of the edge in the city travel network. The specific calculation method is as follows: classifying the starting point and the end point of each trip into the grids according to the longitude and latitude in the obtained resident OD data after the processing, collecting and counting the OD data of which the starting point and the end point are the same grids, wherein the number of the data represents the OD quantity of a specific trip OD, and the connecting line from the starting point grid to the end point grid is the OD line.
In the specific implementation process, division of resident commuting activity areas is an important research content of urban traffic, a macroscopic level is usually based on administrative area planning, control rule units or subjective judgment, due to the difference of land property among administrative areas, the division based on the administrative areas can not accurately reflect resident commuting activity areas, and the main commuting spatial distribution of residents can reflect the spatial distribution of future bus lines to a certain extent. The community is a subgraph comprising nodes and edges, and the connection strength between the nodes in the same community exceeds the connection strength between the nodes in the community.
As shown in fig. 5, the present invention performs community discovery by:
s401: initializing, namely dividing each node in the urban travel network into different communities;
s402: for each node, dividing the node into communities where nodes adjacent to the node are located, and calculating module degree change values before and after division: if the module degree change value is zero, abandoning the division; otherwise, the division is accepted;
1) The calculation formula of the modularity is:
Wherein: q represents the modularity of the urban travel network; a represents a tie matrix; a ij represents the weight between nodes i and j, and when the network is an unbiased graph, the weight between all edges can be considered as 1; Representing the sum of the weights of all edges connected to node i; /(I) Representing the sum of the weights of all edges; c i represents the community to which node i is assigned, if two nodes are in the same community, the value of δ (c i,Cj) is 1, otherwise it is 0;
2) The calculation formula of the module degree change value is as follows:
ΔQ＝Qf-Qb；
Wherein: Δq represents the amount of change in the module degree Q before and after division, i.e., the module degree change value; q f、Qb represents the module degree Q before and after the change, respectively;
S403: repeating the step S402 until all nodes are accessed once and no update occurs, and generating a corresponding community structure;
S404: reconstructing a city travel network according to the community structure generated in the step S403, and aggregating all nodes in the same community together to form a new node;
s405: and repeating the steps S402 to S404 until the structure of the urban travel network is not changed any more, and taking the communities obtained by division as charging service areas.
In the specific implementation process, the public transportation capacity is the departure shift of a single public transportation line in a specific time period, the first and last station space distribution of each line is identified through data mining according to initial card swiping data, and the aggregation characteristics of the transportation capacity are analyzed based on the transportation capacity shift born by each first and last station. The charging demand of the line is further acquired according to the operation mileage and the operation capacity of the line, the charging station is generally arranged in an area close to the head and the tail of the bus line in consideration of daily operation of the bus, and the cold and hot points of the charging demand in each service area are analyzed according to the spatial distribution of the head and the tail of the line and the aggregation characteristics of the charging station are identified. In order to minimize the time cost spent on charging all buses in the service area, the site selection of the charging station should be closer to the circuit station with larger charging demand, and the site selection layout of the charging station is carried out according to the distribution difference of the cold and hot points of the charging demand in different service areas.
In order to reduce the influence of scheduling in the process of bus charging on operation, the charging station is arranged as close to the first and last stations of a bus line as possible. Therefore, the invention firstly identifies the first and the last stations of the bus line and takes the first and the last stations of the bus line as the basic space unit for cold and hot point analysis; then taking the charging requirement of each bus line as a numerical basis for cold and hot spot analysis; and finally, carrying out hot spot analysis on the aggregation forms of the first and the last stations of each bus line to obtain a hot spot area and a cold spot area with aggregated charging requirements.
The primary unit of cold and hot spot analysis is that the electric buses are usually charged after a single operation, and the charging station must be located as close to the first and last stations of the bus route as possible. The basic space unit refers to the smallest analysis unit, the cold and hot spot analysis is performed on the basis of a single grid, and certain specific grids are regarded as the first and last stations of a bus line through data mining, and the single grid is the smallest unit of the cold and hot spot analysis.
Specifically, the charging demand of the bus line is calculated by the following formula:
Demamde＝Scale*Mileage Charging method ；
Mileage Charging method ＝Distance First and last station - Charging station ；
Wherein: demand e represents the charging Demand of the bus line; mileage Charging method represents the mileage that the electric bus needs to travel for charging; scale represents the departure shift of a single bus line; distance First and last station - Charging station represents the Euclidean Distance from the head and end of the bus line to the charging station.
In a specific implementation process, hotspot analysis is generally performed by using spatial autocorrelation, which means that in spatial geographic information, the closer two elements are separated, the larger the spatial relationship weight is, and the closer the association value of the attribute between the two elements is, the property can measure whether the distribution of data in a geographic information system tends to be concentrated or dispersed. The Moran's I is a statistic used for measuring the spatial autocorrelation in space statistics, and the global Moran index is generally used for observing the overall aggregation effect of elements, while the local Moran index is used for measuring the spatial autocorrelation property of a single geographic element and surrounding elements, and the regional property can be further refined by combining the z score.
Specifically, the invention performs cold and hot spot analysis based on the Morlan index;
The global Morand index is indicated between-1 and 1, with less than 0 indicating a negative correlation, greater than 0 indicating a positive correlation, and equal to 0 indicating that the geographic elements within the study area are independent of each other. The local index can be used for describing the average association degree of a single space unit and a peripheral area, and finally the aggregation form of the first and the last stations of the bus route is divided into a High-High (HH), a Low-High (LH), a Low-Low (LL) and a High-Low (HL) by the Moran index, and the High-value aggregation and the Low-value aggregation are used as hot spot areas and cold spot areas for the aggregation of charging demands.
It should be noted that, classifying the first and last stations in the grid (analyzing cold and hot spots) by using the Morlan index can be realized by using the existing maturing means. Specific: the judgment is carried out according to the combination of the value of the local Morganella index and the Z score, wherein the Z score is the local Morganella indexFour combinations exist for measuring the difference between the attribute value of grid i and the average value of all grid attribute values in the region, and according to whether the Z score and the local Morgan index are larger than zero, the first and last stations are finally divided into four categories, if the Z score and the local Morgan index are larger than 0, the stations are divided into high value aggregation, if the Z score is larger than 0 and the local Morgan index is smaller than 0, the stations are divided into high values and are surrounded by low values, and the like.
The calculation formula of the Morgan index is described as:
Wherein: i represents a global Morgan index; n represents the number of grids (in the target city grid); i and j represent two different grids; w ij represents the spatial weight between two grids, if two grids are adjacent, it is 1, otherwise it is 0; x i and x j are information represented by two grids different from each other, herein referred to as charging demand; An average value of the charging requirements for each grid; i i is the local Morgan index; s i is the standard deviation of the attribute values of all grids, i.e. the standard deviation of the charging demand. In the target city grid, only the presence and absence of passengers in the grid, namely the grid with passenger flow, are research objects, all operations on the grids are mentioned on the premise that the passenger flow exists, and because the passenger flow exists, the grids are abstract as bus stations, and the cold and hot spot analysis is used for analyzing the charging requirements, so that the charging requirements of the grids at the non-first and last stations are 0.
In the specific implementation process, the demand concentration degree and the space concentration degree of a new partition are obtained on the basis of repartitioning the service range by utilizing the Voronoi diagram, the hot spot distribution structure and the charging time cost in each service area are uniformly and moderately changed, the difference between the charging station site selection determined by utilizing the gravity center method according to the previous service area partition and the charging station site selection determined by utilizing the existing service range is large, the iteration site selection is conducted by utilizing the gravity center method, and the most preferred site in the iteration process is found according to the integral space concentration degree. And determining the final station address according to the new and old station address ranges when the space aggregation degree change is relatively stable when the final algorithm iteration tends to be stable based on the process of determining the charging station address of the algorithm.
In a data-driven charging station site selection model, the selection of the charging station position is generally performed based on the aggregation form of the vehicle and the charging demand, and the Voronoi diagram can divide the service range of the charging station, and in the site selection process, the time cost change of charging in each service area, the space distribution of the charging demand and the like need to be analyzed. The hot spot analysis can identify hot spots with the collected charging demands, the difference of the collecting conditions of the charging demands in different service areas can be analyzed by combining the space concentration degree and the demand concentration degree on the basis of site selection determination of charging stations, the time cost of charging buses in different service areas in the site selection process can be measured, the optimal charging station position is selected according to the result, and the result of the hot spot analysis can also provide corresponding reference for construction of other electric bus infrastructures.
As shown in fig. 3 and 4, step S6 includes the following steps:
S601: carrying out cold and hot spot analysis on the charging requirements in each charging service area, and determining hot spot areas and cold spot areas where the charging requirements are gathered;
s602: determining the address of a charging station in each charging service area by using a gravity center method by taking the charging demand as a weight;
S603: repartitioning the service range of the site selection of the charging station by utilizing the Voronoi diagram;
In this embodiment, as shown in fig. 6, division of the service range of the charging station is performed using a Voronoi diagram, which is also called a Thiessen polygon or a Dirichlet diagram, which is composed of a set of continuous polygons composed of perpendicular bisectors connecting two adjacent point straight lines. When the initial point is called a generation point, there is only one generation point in any polygon, and the point in the polygon is closest to the generation point in the polygon. The theory of the Voronoi diagram is firstly proposed by Russian mathematics, and is widely applied to the fields of meteorology, physics, urban planning and the like at present along with the continuous development and improvement of the Voronoi diagram.
S604: according to the hot spot areas and the cold spot areas which are gathered according to the charging demands and combining with charging station site selection and service ranges thereof, calculating corresponding space gathering degree and demand gathering degree;
the calculation formula of the demand aggregation degree is as follows:
Wherein: h represents the demand concentration; d h denotes the charging demand of the hot spot area (i.e., the high value aggregate area); the larger the value of the demand concentration, the more concentrated the charging demand in the area is to the high value concentration area, resulting in the addressing of the charging station as a whole being closer to the high value area.
The method comprises the steps that the space distribution of a high-value aggregation area is different from the aggregation degree of a charging requirement of a high-value aggregation area by utilizing the requirement aggregation degree H, the space distribution of the high-value aggregation area is more concentrated and the distance is more short, the distance between the areas is more short, the total distance between a final charging station and the high-value aggregation area is more short, the total time consumed by charging of buses of a corresponding line is less, and the space aggregation degree S is defined to balance the space distribution condition of the high-value aggregation area.
The calculation formula of the space aggregation degree is as follows:
Wherein: s represents the demand concentration degree; dis h represents the average distance of charging station site selection to the hot spot area; dis l represents the average distance of the charging station site to the cold spot area. The smaller the space aggregation degree is, the more concentrated the space distribution of the high value aggregation area in the area is, the more dispersed the distribution of the non-high value aggregation area is, the more favorable the position selection of the charging station is for buses in the high value area, and finally the less the total time cost of charging the buses is.
S605: judging whether the space aggregation degree and the demand aggregation degree are stable or reach the optimal value: if yes, step S606 is entered, otherwise, the service range of the charging service area is updated according to the newly divided service range of the charging station address selection, and step S601 is returned to carry out the next iteration;
In this embodiment, determining whether the spatial aggregation level is stable or optimal means that the spatial aggregation level and the required aggregation level obtained by two consecutive calculations are no longer changed or reduced.
S606: and outputting a corresponding dividing result of the address selection of the charging station and the service range of the charging station.
In the process of site selection and service range division, the distribution structure of charging requirements and the charging time cost in each service area are changed, and the optimal site selection and service area division can be sought in the iterative process by utilizing the space aggregation degree and the requirement aggregation degree obtained by hot spot identification.
With reference to fig. 7, on the basis of community discovery partition and initial charging station address selection determination, the Voronoi diagram is utilized to divide the service range of the charging station, modify the original community discovery partition, and ensure that the time cost spent for charging the bus is relatively less according to the result of hot spot identification.
S606: and outputting a corresponding dividing result of the address selection of the charging station and the service range of the charging station.
In the specific implementation process, the daily operation of the bus is provided with a relatively fixed line, the charging requirement of the bus can be obtained through the operation line and the departure shift, and compared with a private car, the space distribution condition of the charging requirement of the bus can be analyzed by utilizing the space autocorrelation, and further, the difference of different service areas can be analyzed by utilizing the space aggregation degree and the requirement aggregation degree and used as the basis for measuring the site selection quality.
The calculation formula of the gravity center method is expressed as:
Wherein: c jlon、Cjlat respectively represents a longitude value and a latitude value of the address of the charging station in the charging service area j; c ilon、Cilat represents the coordinate longitude value and latitude value of the first and last stations i in the charging service area; demand ei represents the charging Demand of the first and last stations i; m represents the number of first and last stations i in the charging service area.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the technical solution, and those skilled in the art should understand that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the present invention, and all such modifications and equivalents are included in the scope of the claims.
Claims (8)
1. A data-driven electric bus charging station location method, comprising:
S1: rasterizing a target city to generate a target city grid;
S2: extracting corresponding passenger OD trip data according to card swiping data of the electric bus;
s3: matching the OD travel data of the passengers into a target city grid to generate a corresponding city travel network;
s4: carrying out community discovery on the urban travel network, and taking communities obtained by division as initial charging service areas;
S5: performing data mining on the OD travel data of the passengers to obtain departure shifts and operation mileage of each bus route, and obtaining charging requirements of each bus route according to the departure shifts and the operation mileage;
s6: determining the address of a charging station and the service range of the charging station according to the initial charging service area and the charging requirements of each bus line;
The method specifically comprises the following steps:
S601: carrying out cold and hot spot analysis on the charging requirements in each charging service area, and determining hot spot areas and cold spot areas where the charging requirements are gathered;
s602: determining the address of a charging station in each charging service area by using a gravity center method by taking the charging demand as a weight;
S603: repartitioning the service range of the site selection of the charging station by utilizing the Voronoi diagram;
S604: according to the hot spot areas and the cold spot areas which are gathered according to the charging demands and combining with charging station site selection and service ranges thereof, calculating corresponding space gathering degree and demand gathering degree;
In step S604, the calculation formula of the demand aggregation level is:
Wherein: h represents the demand concentration; d h denotes the charging demand of the hot spot area; d w denotes the total charging demand within the charging station site selection service range;
the calculation formula of the space aggregation degree is as follows:
Wherein: s represents the demand concentration degree; dis h represents the average distance of charging station site selection to the hot spot area; dis l represents the average distance from the charging station site to the cold spot area;
S605: judging whether the space aggregation degree and the demand aggregation degree are stable or reach the optimal value: if yes, step S606 is entered, otherwise, the service range of the charging service area is updated according to the newly divided service range of the charging station address selection, and step S601 is returned to carry out the next iteration;
s606: and outputting a corresponding dividing result of the address selection of the charging station and the service range of the charging station.
2. The data-driven electric bus charging station location method of claim 1, wherein: in step S3, firstly, collecting and counting starting and ending points of the OD travel data of the passengers; then matching the starting and ending station of resident trip to the corresponding grid in the target city grids; and finally, regarding the starting and ending point of resident travel as a network node, regarding an OD line as a network side, regarding an OD quantity as an edge weight, and generating an urban travel network based on electric bus travel.
3. The data-driven electric bus charging station location method of claim 1, wherein: in step S4, community discovery is performed by:
s401: initializing, namely dividing each node in the urban travel network into different communities;
s402: for each node, dividing the node into communities where nodes adjacent to the node are located, and calculating module degree change values before and after division: if the module degree change value is zero, abandoning the division; otherwise, the division is accepted;
1) The calculation formula of the modularity is:
Wherein: q represents the modularity of the urban travel network; a represents a tie matrix; a ij represents the weight between nodes i and j, and when the network is an unbiased graph, the weight between all edges can be considered as 1; Representing the sum of the weights of all edges connected to node i; /(I) Representing the sum of the weights of all edges; c i represents the community to which node i is assigned, if two nodes are in the same community, the value of δ (c i,cj) is 1, otherwise it is 0;
2) The calculation formula of the module degree change value is as follows:
ΔQ＝Qf-Qb；
Wherein: Δq represents the amount of change in the module degree Q before and after division, i.e., the module degree change value; q f、Qb represents the module degree Q before and after the change, respectively;
S403: repeating the step S402 until all nodes are accessed once and no update occurs, and generating a corresponding community structure;
S404: reconstructing a city travel network according to the community structure generated in the step S403, and aggregating all nodes in the same community together to form a new node;
s405: and repeating the steps S402 to S404 until the structure of the urban travel network is not changed any more, and taking the communities obtained by division as charging service areas.
4. The data-driven electric bus charging station location method of claim 1, wherein: in step S5, the charging requirement of the bus line is calculated according to the following formula:
Demande＝Scale*Mileage Charging method ；
Mileage Charging method ＝Distance First and last station - Charging station ；
Wherein: demand e represents the charging Demand of the bus line; mileage Charging method represents the mileage that the electric bus needs to travel for charging; scale represents the departure shift of a single bus line; distance First and last station - Charging station represents the Euclidean Distance from the head and end of the bus line to the charging station.
5. The data-driven electric bus charging station location method of claim 1, wherein: in step S601, first, the first and the last stations of the bus line are identified, and the first and the last stations of the bus line are used as basic space units for analyzing cold and hot points; then taking the charging requirement of each bus line as a numerical basis for cold and hot spot analysis; and finally, carrying out hot spot analysis on the aggregation forms of the first and the last stations of each bus line to obtain a hot spot area and a cold spot area with aggregated charging requirements.
6. The data-driven electric bus charging station locating method of claim 5, wherein: in step S601, cold and hot spot analysis is performed based on the molan index;
Dividing the aggregation forms of the first station and the last station of the bus line into high value aggregation, low value surrounded by high value, low value aggregation and high value surrounded by low value through the Morlan index, and taking the high value aggregation and the low value aggregation as hot spot areas and cold spot areas for charging demand aggregation;
The calculation formula of the Morgan index is described as:
Wherein: i represents a global Morgan index; n represents the number of grids; i and j represent two different grids; w ij represents the spatial weight between two grids, if two grids are adjacent, it is 1, otherwise it is 0; x i and x j are information represented by two grids different from each other, herein referred to as charging demand; An average value of the charging requirements for each grid; i i is the local Morgan index; s i is the standard deviation of the attribute values of all grids, i.e. the standard deviation of the charging demand.
7. The data-driven electric bus charging station location method of claim 1, wherein: in step S602, the calculation formula of the gravity center method is expressed as:
Wherein: c jlon、Cjlat respectively represents a longitude value and a latitude value of the address of the charging station in the charging service area j; c ilon、Cilat represents the coordinate longitude value and latitude value of the first and last stations i in the charging service area j; demand ei represents the charging Demand of the first and last stations i; m represents the number of first and last stations i in the charging service area j.
8. The data-driven electric bus charging station location method of claim 1, wherein: in step S605, determining whether the spatial aggregation level is stable or optimal means that the spatial aggregation level and the demand aggregation level obtained by two consecutive calculations are no longer changed or reduced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311691075.4A CN117669971B (en) | 2023-12-11 | 2023-12-11 | Data-driven electric bus charging station address selection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311691075.4A CN117669971B (en) | 2023-12-11 | 2023-12-11 | Data-driven electric bus charging station address selection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117669971A CN117669971A (en) | 2024-03-08 |
| CN117669971B true CN117669971B (en) | 2024-06-25 |
Family
ID=90086164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311691075.4A Active CN117669971B (en) | 2023-12-11 | 2023-12-11 | Data-driven electric bus charging station address selection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117669971B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107248007A (en) * | 2017-06-02 | 2017-10-13 | 武汉大学 | The rural residential area intelligent optimization collocation method that a kind of double-deck domain is oriented to |
| CN110705793A (en) * | 2019-10-08 | 2020-01-17 | 北京工商大学 | Fresh food electricity commercial warehouse site selection system and method under community structure |
| CN111523930A (en) * | 2020-04-17 | 2020-08-11 | 国网上海市电力公司 | Planning method for site selection and service range division of urban electric taxi charging station |
| CN112950109B (en) * | 2021-01-28 | 2022-05-17 | 浙江大学 | Complex network-based associated article storage position optimization method |
| CN114297809A (en) * | 2021-12-20 | 2022-04-08 | 上海电机学院 | Electric vehicle charging station site selection and volume fixing method |
| CN115034501A (en) * | 2022-06-29 | 2022-09-09 | 国网河南省电力公司许昌供电公司 | Electric vehicle charging station site selection and volume fixing method |
-
2023
- 2023-12-11 CN CN202311691075.4A patent/CN117669971B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| A novel fast-charging stations locational planning model for electric bus transit system;Xiaomei wu等;《Energy》;20210601;全文 * |
| 站城一体化背景下的铁路客运站选址方法研究;翁雨琳;《中国优秀硕士论文集》;20220515;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117669971A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Helmus et al. | A data driven typology of electric vehicle user types and charging sessions | |
| CN109493119B (en) | POI data-based urban business center identification method and system | |
| CN105825310A (en) | Taxi passenger-searching path recommendation method based on information entropy | |
| CN107729938B (en) | Rail station classification method based on bus connection radiation zone characteristics | |
| Zhang et al. | Green travel mobility of dockless bike-sharing based on trip data in big cities: A spatial network analysis | |
| CN110836675B (en) | Decision tree-based automatic driving search decision method | |
| CN111523714B (en) | Site selection layout method and device for electric power charging station | |
| Wang et al. | Taxi trajectory data based fast-charging facility planning for urban electric taxi systems | |
| CN113222271B (en) | Medium and small airport site selection layout method under comprehensive transportation system | |
| Zhang et al. | An auxiliary optimization method for complex public transit route network based on link prediction | |
| CN114048920A (en) | Site selection layout method, device, equipment and storage medium for charging facility construction | |
| CN114548811A (en) | Airport accessibility detection method and device, electronic equipment and storage medium | |
| CN116542709A (en) | Electric vehicle charging station planning analysis method based on traffic situation awareness | |
| CN117196197A (en) | Public transportation site layout optimization method | |
| CN114723596A (en) | Urban functional area identification method based on multi-source traffic travel data and theme model | |
| Bao et al. | Spatiotemporal clustering analysis of shared electric vehicles based on trajectory data for sustainable urban governance | |
| Zhang et al. | A multi-objective site selection of electric vehicle charging station based on NSGA-II | |
| Lai et al. | Data-driven flexible vehicle scheduling and route optimization | |
| CN117669971B (en) | Data-driven electric bus charging station address selection method | |
| CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure | |
| Yue et al. | Classification and determinants of high-speed rail stations using multi-source data: A case study in Jiangsu Province, China | |
| CN110533215A (en) | A kind of taxi of cruising based on GPS data seeks objective behavior prediction method | |
| Zhou et al. | Refined taxi demand prediction with ST-Vec | |
| Tian et al. | A SITING URBAN TAXI STATIONS MODEL BASED ON SPATIAL-TEMPORAL ORIGIN-DESTINATION DATA | |
| Regal et al. | Defining urban logistics profile zones in South American metropolis by combining functional and spatial clustering techniques |
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 |