Partition layout method and device for automobile charging pile group

Abstract

The present application provides a zoning layout method and device for a group of automobile charging piles, which relates to the field of data processing technology, including: dividing regional grids based on the layout area of ​​charging piles; setting decision variables, making planning and layout decisions for regional grids by training a 0-1 planning model, and determining the first charging pile layout, wherein the decision variables include a first decision variable based on vehicle flow and a second decision variable based on parking volume; using the first charging pile layout as a reference, identifying non-deterministic settings, and performing optimization iterations to determine the second charging pile layout; integrating the first charging pile layout with the second charging pile layout to determine the distribution layout result of the charging pile group. The present application solves the technical problem that the existing method for layout of automobile charging piles has a single reference factor when making decisions, resulting in uneven layout of charging piles and waste of resources, and achieves the technical effect of improving the scientificity and rationality of the layout of charging piles.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for zoning and arranging a group of automobile charging piles. Background Art

[0002] As an infrastructure for electric vehicles to supplement electricity, the rationality of the layout of car charging piles directly affects the charging convenience and user experience of electric vehicle users. Existing car charging pile layout methods are mostly considered from the perspective of macro-geographical areas or simple distance factors. For example, charging piles are laid out according to administrative divisions or equidistant divisions. This layout method does not fully consider the differences in road section types. The traffic flow and parking characteristics of different road sections (such as main roads and branch roads) are completely different, making the layout of charging piles out of touch with actual needs. Secondly, when making layout decisions, factors such as traffic flow or parking volume are often considered alone, which cannot fully reflect complex charging needs and ignores the coordination of the overall layout, which can easily lead to excessive layout in high-traffic areas where parking is inconvenient or insufficient layout in areas where parking is convenient but traffic flow is small. Summary of the invention

[0003] The present application provides a zoning layout method and device for a group of automobile charging piles, which solves the technical problem that the existing automobile charging pile layout method has a single reference factor when making decisions, resulting in uneven charging pile layout and waste of resources, and achieves the technical effect of improving the scientificity and rationality of the charging pile layout.

[0004] In view of the above problems, on the one hand, the present application provides a zoning layout method for a group of automobile charging piles, the method comprising: for a charging pile layout area, dividing the regional grid based on a preset range, wherein the road section type is used as a division constraint; setting decision variables, and making planning and layout decisions for the regional grid by training a 0-1 planning model to determine a first charging pile layout, wherein the decision variables include a first decision variable based on vehicle flow and a second decision variable based on parking volume; taking the first charging pile layout as a reference, identifying non-determined settings, and performing optimization iterations to determine a second charging pile layout, wherein the non-determined settings are adjustable layouts to be optimized; integrating the first charging pile layout with the second charging pile layout to determine the distribution layout result of the charging pile group.

[0005] On the other hand, the present application also provides a zoning layout device for a group of automobile charging piles, the device comprising: a regional grid division module, the regional grid division module is used to divide the regional grid based on a preset range for the charging pile layout area, wherein the road section type is used as the division constraint; a first planning and layout module, the first planning and layout module is used to set decision variables, and make planning and layout decisions for the regional grid by training a 0-1 planning model to determine the first charging pile layout, wherein the decision variables include a first decision variable based on vehicle flow and a second decision variable based on parking volume; a second planning and layout module, the second planning and layout module is used to identify non-determined settings based on the first charging pile layout, and perform optimization iteration to determine the second charging pile layout, wherein the non-determined settings are adjustable layouts to be optimized; a distribution layout module, the distribution layout module is used to integrate the first charging pile layout and the second charging pile layout to determine the distribution layout results of the charging pile group.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] For the charging pile layout area, the regional grid is divided based on the preset range. By introducing the road section type as a division constraint and combining the regional grid method to refine the overall layout area, it is helpful to accurately identify the charging demand characteristics of different areas and provide a basis for subsequent decision-making. The two key decision variables of vehicle flow and parking volume are set, and the planning and layout decisions are made for the regional grid by training the 0-1 planning model. The first charging pile layout including the locations where charging piles must be set and cannot be set is preliminarily determined, laying a framework foundation for the overall layout. Based on the first charging pile layout as a benchmark, the non-determined settings are identified, and optimization iterations are performed to further improve the rationality of the layout to adapt to the complex and changeable actual situation. Finally, the second charging pile layout is determined to achieve global optimization in local adjustments. The first charging pile layout and the second charging pile layout are integrated to determine the distribution layout results of the charging pile group, which not only retains the stability of the layout, but also takes into account the differences between regions, forming a scientific and reasonable charging pile distribution plan.

[0008] In summary, this application establishes a preliminary layout framework through regional grid division and multi-dimensional decision variables, combines the optimization iteration of flexible regions to determine the local optimization layout, and finally integrates the two layout results to determine the final distribution layout result. This scheme comprehensively considers multiple factors such as road section type, traffic flow, parking volume, etc., takes into account the accuracy, flexibility and overallness of the layout, realizes the scientific and reasonable layout of the charging pile group, effectively reduces the uneven distribution and waste of charging piles, thereby improving the convenience of electric vehicle charging and the utilization efficiency of charging pile resources.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of a method for zoning a group of vehicle charging piles provided in an embodiment of the present application.

[0011] Figure 2 A schematic diagram of the process of training a 0-1 planning model in the zoning layout method of a vehicle charging pile group provided in an embodiment of the present application.

[0012] Figure 3 A schematic diagram of the structure of a zoning layout device for a group of automobile charging piles provided in an embodiment of the present application.

[0013] Explanation of reference numerals: regional grid division module 10 , first planning and layout module 20 , second planning and layout module 30 , distribution layout module 40 . DETAILED DESCRIPTION

[0014] The embodiments of the present application provide a zoning layout method and device for a group of automobile charging piles, thereby solving the technical problem that the existing automobile charging pile layout method has a single reference factor when making decisions, resulting in uneven charging pile layout and waste of resources, thereby achieving the technical effect of improving the scientificity and rationality of the charging pile layout.

[0015] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a partition layout method for a vehicle charging pile group, the method comprising:

[0016] Step S1: For the charging pile layout area, divide the area into grids based on a preset range, wherein the road section type is used as a division constraint.

[0017] Specifically, the charging pile layout area refers to the geographical area where the charging piles are planned to be laid out, which can be a city, an urban area or a specific functional area (such as a commercial area, residential area, etc.). The preset range is a pre-set spatial range boundary, which is used to determine the size or boundary of the regional grid. For example, it can be set as a circular range with a radius of 5 kilometers centered on a certain landmark, or a square range with a side length of 10 kilometers. Road section types include main roads, secondary roads, branch roads or highways, and different road section types have different requirements for charging piles.

[0018] Determine the area where the charging piles are to be laid out, and then divide the area into small grids according to the preset range to form a regional grid, which is convenient for targeted analysis and planning. In the division process, the road section type is used as the division constraint. For example, when dividing the grid, the part containing the main road is divided into one type of grid, and the area with more branches is divided into another type of grid. Classify and label different grids. For example, in an area dominated by business, it can be divided into 5 grids, 2 of which are main road areas.

[0019] By dividing the regional grid, the overall layout area can be refined, providing a benchmark analysis geographical framework for subsequent layout decisions, facilitating the accurate identification of charging demand characteristics in different regions and improving the accuracy of charging pile layout.

[0020] Step S2: setting decision variables, making planning and layout decisions for the regional grid by training a 0-1 planning model, and determining the first charging pile layout, wherein the decision variables include a first decision variable based on vehicle flow and a second decision variable based on parking volume.

[0021] Specifically, decision variables are variables in the planning model that are used to represent factors that affect layout decisions. Decision variables include a first decision variable related to traffic flow and a second decision variable related to parking volume. The 0-1 planning model is a special linear planning model in which the variable value can only be 0 or 1. 0 means not performing a certain operation (such as not setting up a charging pile in a certain grid), and 1 means performing a certain operation (such as setting up a charging pile in a certain grid).

[0022] According to the grid division in step S1, the traffic flow and parking volume data of each grid are collected. These data can be obtained through traffic sensors or statistical reports. Then, two decision variables are defined: a first decision variable reflecting the traffic flow and a second decision variable reflecting the parking volume. By training the 0-1 planning model, planning layout decisions are made to determine whether charging piles are set in each grid, forming the first charging pile layout. The first charging pile layout contains the grid location information where charging piles must be set and the location information of charging piles that do not require equipment.

[0023] This step quantifies the two key factors of vehicle flow and parking volume, and uses the 0-1 planning model to preliminarily determine the approximate layout plan of charging piles, providing an overall layout framework for the reasonable layout of charging piles.

[0024] Step S3: Taking the first charging pile layout as a reference, identifying non-determined settings, and performing optimization iteration to determine a second charging pile layout, wherein the non-determined settings are adjustable layouts to be optimized.

[0025] Specifically, the non-determined settings are those locations in the preliminary layout that can be flexibly adjusted, not fixed charging pile points. Using the first charging pile layout result in step S2 as a benchmark, identify those grids that can be adjusted. For example, although the traffic flow and parking volume data of some regional grids show that charging piles can be set up, there are actually some other factors (such as large-scale construction nearby) that require reconsidering the layout. Through optimization algorithms (such as genetic algorithms or particle swarm optimization), these grids are adjusted and iterated to balance the integrity and flexibility of the charging pile layout, and generate a second charging pile layout.

[0026] This step, based on the determination of some positions that must be set and those that cannot be set, conducts in-depth analysis and optimization of the adjustable layout to be optimized, which can further improve the rationality of the layout, adapt to complex and changing actual conditions, and ensure the overall nature of the layout.

[0027] Step S4: integrating the first charging pile layout and the second charging pile layout to determine the distribution layout result of the charging pile group.

[0028] Specifically, the first charging pile layout obtained in step S2 and the second charging pile layout obtained in step S3 are merged, duplicates are removed and a layout diagram is formed to obtain the final distribution layout result of the charging pile group. By integrating the above two layout results, the preliminary decision of the first layout and the optimization results of the second layout are fully utilized to obtain a comprehensive and integrated charging pile group distribution layout plan, making the final layout result more scientific and reasonable.

[0029] Furthermore, setting the decision variables in step S2 also includes:

[0030] Set the decision variables: ; .

[0031] in, is the first decision variable, Refers to Charging points to The traffic flow at each charging demand point, Refers to the high flow threshold, Refers to the low flow threshold; is the second decision variable, Refers to Charging points to The parking volume of charging demand points, is the high parking volume threshold,

[0032] is a low parking volume threshold; Refers to the charging pile settings. It means that no charging pile is set up. and This is an undefined setting.

[0033] Specifically, the high flow threshold The upper limit of vehicle flow. If the value exceeds this limit, it means that charging piles need to be set up in this area first. The lower limit of vehicle flow. If the value is lower than this, it means that there is no need to install charging piles in this area. High parking volume threshold The upper limit of parking volume. If the value exceeds this limit, it indicates that charging piles need to be set up first. This is the lower limit of parking volume. If the value is lower than this, it means that there is no need to set up charging piles.

[0034] Collect the traffic flow and parking volume data of each regional grid. For each regional grid, determine the value of the first decision variable corresponding to the regional grid according to the set high flow threshold and low flow threshold. When the traffic flow is greater than the high flow threshold, the first decision variable is 1, and the charging pile must be set; if the traffic flow is less than the low flow threshold, the first decision variable is 0, and the charging pile does not need to be set; when the traffic flow is between the high flow threshold and the low flow threshold, the first decision variable is an uncertain setting. , the setting status of the charging pile cannot be determined directly and needs to be adjusted through further optimization decisions.

[0035] At the same time, for each regional grid, the second decision variable value corresponding to the regional grid is determined according to the set high parking volume threshold and low parking volume threshold. Similarly, when the parking volume is greater than the high parking volume threshold, the second decision variable is 1, and charging piles must be set; if the parking volume is less than the low parking volume threshold, the second decision variable is 0, and charging piles do not need to be set; when the parking volume is between the high parking volume threshold and the low parking volume threshold, the second decision variable is an undetermined setting. , the setting status of the charging pile cannot be determined directly and needs to be adjusted through further optimization decisions.

[0036] Further, such as Figure 2 As shown, the training of the 0-1 planning model in step S2 also includes:

[0037] Step S21: In combination with the regional grid, calling periodic historical data records, wherein the historical data records include vehicle flow records and parking records.

[0038] Step S22: Based on the first decision logic of the first decision variable, supervise and train the first planning unit based on the vehicle flow record.

[0039] Step S23: Based on the second decision logic of the second decision variable, supervise and train a second planning unit based on the parking record.

[0040] Step S24: Integrate the first planning unit and the second planning unit to generate the 0-1 planning model.

[0041] Specifically, based on the divided regional grids, the historical data records of vehicle flow and parking volume related to each regional grid are retrieved. Vehicle flow records can be obtained from the database of the traffic management department. These vehicle flow data are obtained through long-term monitoring by sensors installed on the road (such as induction coils, radar speed meters, etc.). Parking records can be collected from the management systems of various parking lots. These management systems will record information such as the entry and exit time and parking duration of each vehicle, so that the parking volume in different periods can be counted.

[0042] Using the first decision variable set above The decision logic of the first planning unit is used to supervise the training of the historical data in the traffic flow records. The training process includes: first, the historical data in the traffic flow records are labeled according to the decision logic of the first decision variable to obtain the labeled historical data. A supervised learning model is constructed based on algorithms such as logistic regression, support vector machine or decision tree. The labeled historical data is divided into a certain proportion (such as 80% as a training set and 20% as a test set), and the training set data is used to continuously adjust the parameters in the supervised learning model according to the above decision logic, and then the test set data is used to verify the prediction effect of the adjusted model, and it is continuously iterated until the supervised learning model can make accurate decisions according to the first decision logic when processing traffic flow data. At this time, the output model is the first planning unit.

[0043] Using the first decision variable set above The decision logic of the second planning unit is trained using a supervised learning model (such as logistic regression). The specific training process of the second planning unit is similar to that of the first planning unit and will not be elaborated here.

[0044] The first planning unit and the second planning unit are integrated to generate the final 0-1 planning model. This planning model will consider two factors, traffic flow and parking volume, to determine whether each area needs to install charging piles. The output value of the planning model is 0 or 1, indicating whether each regional grid should be equipped with charging piles. 1 means that the regional grid must be equipped with charging piles, and 0 means that the regional grid does not need to be equipped with charging piles.

[0045] By combining historical data and decision variables based on vehicle flow and parking volume, two independent planning units are trained and combined to generate a comprehensive 0-1 planning model. Through this planning model, it is possible to determine whether to install charging piles in different regional grids and make decisions on the layout of charging piles for the entire region, which can not only improve the accuracy of the layout of charging piles, but also better meet the actual needs of different regions.

[0046] Furthermore, step S24 further includes:

[0047] Step S241: Determine a first plan and a second plan by identifying outputs of the first planning unit and the second planning unit.

[0048] Step S242: Mapping the first plan and the second plan to determine a plurality of pairs of charging points, wherein a pair of charging points mapped from the first plan and the second plan is a pair of charging points.

[0049] Step S243: traverse the multiple pairs of charging points. If the distance between the mapped charging point pairs is less than the preset interval, the center position of the distance is used as the planned charging point. If the distance between the mapped charging point pairs is greater than the preset interval, the mapped charging point pairs are used as the planned charging points, wherein the preset interval is the interval constraint condition for the charging pile layout.

[0050] Specifically, the traffic volume data of each regional grid is input into the first planning unit, and the first planning unit outputs a decision value (0 or 1) on whether to install a charging pile. Similarly, the parking volume data of each regional grid is input into the second planning unit, and the second planning unit outputs a decision value (0 or 1) on whether to install a charging pile. The outputs of the first planning unit and the second planning unit are identified to determine the regional grids (i.e., the first plan) that need to install charging piles, and the regional grids (i.e., the second plan) that the second planning unit determines need to install charging piles.

[0051] Map the decision results of the first plan and the second plan, find the areas in the two plans that are relatively close or repeatedly recommended to install charging piles, and determine them as mapped charging point pairs. For example, three potential charging point locations A, B, and C on a certain road are determined in the first plan, and three potential charging point locations A', B', and C' on the same road or adjacent roads are determined in the second plan. According to the proximity of geographic coordinates or the correspondence between regional grids, A and A', B and B', and C and C' are mapped to charging point pairs (A, A'), (B, B'), and (C, C'), respectively, and these charging point pairs constitute multiple pairs of charging points.

[0052] Traverse the determined multiple pairs of charging points, calculate the distance between each pair of charging points, and compare them with the preset interval. Among them, the preset interval is the distance limit set when the charging pile is laid out, which is used to control the minimum spacing between charging piles. This interval usually takes into account factors such as road traffic conditions, the distribution of parking spaces, and the installation space of charging piles. If the distance between two charging points in a mapped charging point pair is less than the preset interval, then the two charging points are merged into a planned charging point, and the center position of the distance between the two charging points is used as the new charging point position. This can avoid charging piles being too concentrated in one area, resulting in a waste of resources. If the distance between two charging points in a mapped charging point pair is greater than the preset interval, the two charging points are respectively determined as planned charging points.

[0053] By mapping and optimizing the charging pile locations generated by the first planning unit and the second planning unit, identifying and merging charging points that are too close, while maintaining the independence of charging points that are farther away, more space and spacing optimization are added to the layout of charging piles to avoid excessive concentration of charging piles, thereby improving the rationality of the charging pile layout and the utilization rate of charging pile resources.

[0054] Furthermore, step S1 of the embodiment of the present application further includes:

[0055] Step S11: for the road section type, set a preset range of area division and determine a grid standard, wherein the grid standard corresponds to the road section type one by one.

[0056] Step S12: for the charging pile layout area, perform road section type identification and grid standard matching, and divide and determine the regional grid.

[0057] Specifically, the grid standard refers to the specific standards set for each road section type when dividing the regional grid, including the size, shape, location of the grid, and the number of charging piles that should be included in each grid. The grid standard is adjusted according to the road section type to adapt to different charging needs.

[0058] Before regional grid division, different preset ranges and grid standards are first set for different types of road sections. For example, for main road sections, due to their large traffic volume and wide service range, the preset range may be a larger area, such as a range of 2 to 3 kilometers on each side with the main road as the center, and a grid standard of 1 kilometer square grid; for secondary road sections, the preset range may be relatively small, such as a range of 0.5 to 1 kilometer on each side with the secondary road as the center, and a square grid of 0.5 kilometers on each side. These grid standards are in a one-to-one correspondence with road section types, that is, one road section type corresponds to a specific grid division standard.

[0059] When dividing the regional grid, first identify the road section types within the charging pile layout area and determine the specific types of all road sections within the layout area. The identification process can use the road data of the transportation department, or analyze the traffic flow data and road width data of the road to identify the road section type. Then, match the identified road section type with the determined grid standard, apply the corresponding grid standard to divide each type of road section, and determine the final regional grid.

[0060] In this way, the grid division of each area is customized according to the type of road section, which can better reflect the charging demand characteristics of each area, so that more reasonable and detailed decisions can be made in the subsequent charging pile layout planning.

[0061] Furthermore, step S3 of the embodiment of the present application also includes:

[0062] Step S31: constructing an optimization space based on the first charging pile layout, wherein the optimization space is based on the regional grid.

[0063] Step S32: In combination with the interval constraint condition, iterative optimization is performed in the optimization space until a convergence condition is met, and the second charging pile layout is determined.

[0064] Specifically, on the basis of the first charging pile layout, an optimization space is built with the regional grid as an area with an undetermined range. The optimization space represents the possible adjustment range of the charging pile layout, that is, the area where the charging pile can be adjusted or optimized. In the optimization space, iterative optimization is performed according to the interval constraint (i.e., the preset interval increased in step S243), and the layout position of the charging pile is continuously adjusted until the convergence condition is met, that is, a stable charging pile layout that meets the design objectives is found. The optimization result is determined as the second charging pile layout. The convergence condition can be that the objective function has no obvious improvement in several consecutive iterations, or the maximum number of iterations is reached.

[0065] Through iterative optimization, based on the first charging pile layout, the layout of the regional grids where it is not determined whether to set up charging piles can be optimized, so as to achieve accurate layout decisions in the entire charging pile layout area.

[0066] Furthermore, step S32 further includes:

[0067] Step S321: Determine an initialization layout based on the optimization space and the spacing constraint.

[0068] Step S322: traverse the initialization layout, perform two-step optimization, and determine a first optimized layout set, wherein the two-step optimization includes global migration and selective migration.

[0069] Step S323: Based on the initialization layout and the first optimized layout set, randomly select a layout solution and perform secondary iterative optimization until the convergence condition is met, and select the layout with the highest fitness as the second charging pile layout.

[0070] Specifically, in the optimization space, an initial layout of charging piles is determined based on the distance relationship with the charging piles in the adjacent grids and the boundary of the optimization space. This initial layout is the starting point for iterative optimization. For example, by calculating the distance between each grid center and the center of other grids where charging piles have been set up, it is decided whether to initialize the charging piles in the grid according to the spacing constraint.

[0071] For each charging pile position in the initial layout, a two-step optimization operation is performed, including global migration and selective migration. In the global migration process, a random search algorithm can be used in combination with the objective function to find a possible better position in the entire optimization space, and the charging pile positions in multiple areas can be adjusted simultaneously to improve the overall layout effect. In the optimization process, the corresponding fitness function can be set as the objective function according to the specific optimization goal, such as minimizing the sum of the distances from all users to the nearest charging pile, or maximizing the coverage of the charging pile, etc.

[0072] In the selective migration process, migration attempts are only made between grids that are adjacent to the current charging pile or meet specific conditions (such as the difference in traffic volume is less than a certain threshold, the difference in parking volume is less than a certain threshold, etc.), without changing the layout of grids in other areas. For example, for a charging pile in a certain grid, only the four grids adjacent to it are considered for migration, and the fitness of the layout after migration is calculated to see whether it is improved. If it is improved, the migration result is retained. The first optimized layout set is obtained by performing two-step optimization operations on all charging piles in the initial layout.

[0073] Randomly select some layout schemes from the initialization layout and the first optimized layout set as the initial schemes for the second iteration optimization. Use the optimization method similar to that in step S322 to perform the second iteration optimization on these selected schemes. After each iteration, determine whether to stop the iteration according to the set convergence condition. When the convergence condition is met, select the layout with the highest fitness (i.e., the layout with the largest fitness function value) from all the layout schemes that have undergone the second iteration optimization as the second charging pile layout.

[0074] Through multiple rounds of iterations and a two-step optimization strategy, the positions of charging piles are gradually adjusted to find the optimal layout solution. This process ensures the reasonable layout of charging piles, meets the spacing constraints, and achieves the convergence of optimization goals, ensuring that the final layout can effectively improve the coverage and efficiency of charging piles.

[0075] In summary, the partition layout method of the automobile charging pile group provided in the embodiment of the present application has the following technical effects:

[0076] For the layout area of ​​charging piles, the regional grids are divided according to the preset range and grid standards of the regional division set for different road section types. By introducing the road section type as a division constraint and combining the regional grid method to refine the overall layout area, it is helpful to accurately identify the charging demand characteristics of different areas and provide a basis for subsequent decision-making. The two key decision variables of vehicle flow and parking volume are set. By calling periodic historical data records, the corresponding planning unit is supervised and trained based on the decision logic of different decision variables. The first and second planning units are integrated to generate a 0-1 planning model. The planning is also determined by identifying the output of the planning unit, mapping the planning to determine the charging point pair and determining the planned charging point according to the spacing and preset interval processing, and planning layout decisions are made. The first charging pile layout containing the locations where charging piles must be set and cannot be set is preliminarily determined, laying a framework foundation for the overall layout. Taking the first charging pile layout as a benchmark, the non-determined settings are identified, and optimization iterations are performed to further improve the rationality of the layout to adapt to the complex and changeable actual situation. Finally, the second charging pile layout is determined to achieve global optimization in local adjustments. The first charging pile layout and the second charging pile layout are integrated to determine the distribution layout result of the charging pile group, which not only retains the stability of the layout but also takes into account the differences between regions, thereby forming a scientific and reasonable charging pile distribution plan.

[0077] In general, the embodiment of the present application establishes a preliminary layout framework through regional grid division and multi-dimensional decision variables, combines the optimization iteration of flexible regions to determine the local optimization layout, and finally integrates the two layout results to determine the final distribution layout result. This solution comprehensively considers multiple factors such as road section type, traffic flow, parking volume, etc., takes into account the accuracy, flexibility and globality of the layout, realizes the scientific and reasonable layout of the charging pile group, effectively reduces the uneven distribution and waste of charging piles, thereby improving the convenience of electric vehicle charging and the utilization efficiency of charging pile resources.

[0078] Embodiment 2, as Figure 3 As shown, the embodiment of the present application provides a zoning layout device for a vehicle charging pile group, the device comprising:

[0079] The regional grid division module 10 is used to divide the regional grids based on a preset range for the charging pile layout area, wherein the road section type is used as the division constraint.

[0080] The first planning and layout module 20 is used to set decision variables, make planning and layout decisions for the regional grid by training a 0-1 planning model, and determine the first charging pile layout, wherein the decision variables include a first decision variable based on vehicle flow and a second decision variable based on parking volume.

[0081] The second planning and layout module 30 is used to identify non-determined settings based on the first charging pile layout, and perform optimization iteration to determine the second charging pile layout, wherein the non-determined settings are adjustable layouts to be optimized.

[0082] The distribution layout module 40 is used to integrate the first charging pile layout and the second charging pile layout to determine the distribution layout result of the charging pile group.

[0083] Furthermore, the first planning and layout module 20 in the embodiment of the present application is also used to perform the following steps:

[0084] Set the decision variables: ; .

[0085] in, is the first decision variable, Refers to Charging points to The traffic flow at each charging demand point, Refers to the high flow threshold, Refers to the low flow threshold; is the second decision variable, Refers to Charging points to The parking volume of charging demand points, is the high parking volume threshold, is a low parking volume threshold; Refers to the charging pile settings. It means that no charging pile is set up. and This is an undefined setting.

[0086] Furthermore, the first planning and layout module 20 in the embodiment of the present application is also used to perform the following steps:

[0087] In combination with the regional grid, periodic historical data records are called, wherein the historical data records include vehicle flow records and parking records; a first decision logic based on the first decision variable is used to supervise the training of a first planning unit based on the vehicle flow records; a second decision logic based on the second decision variable is used to supervise the training of a second planning unit based on the parking records; and the first planning unit and the second planning unit are integrated to generate the 0-1 planning model.

[0088] Furthermore, the first planning and layout module 20 in the embodiment of the present application is also used to perform the following steps:

[0089] The first plan and the second plan are determined by identifying the outputs of the first planning unit and the second planning unit; the first plan and the second plan are mapped to determine multiple pairs of charging points, wherein the mapped charging point pair of the first plan and the second plan is a pair of charging points; the multiple pairs of charging points are traversed, and if the spacing of the mapped charging point pair is less than a preset interval, the center position of the spacing is the planned charging point; if the spacing of the mapped charging point pair is greater than the preset interval, the mapped charging point pair is used as the planned charging point, wherein the preset interval is the interval constraint condition for the charging pile layout.

[0090] Furthermore, the regional grid division module 10 of the embodiment of the present application is also used to perform the following steps:

[0091] For the road section type, a preset range of area division is set and a grid standard is determined, wherein the grid standard corresponds to the road section type one by one; for the charging pile layout area, the road section type is identified and matched with the grid standard, and the regional grid is divided and determined.

[0092] Furthermore, the second planning and layout module 30 in the embodiment of the present application is also used to perform the following steps:

[0093] Based on the first charging pile layout, an optimization space is constructed, wherein the optimization space takes the regional grid as the range; in combination with the interval constraint condition, iterative optimization is performed in the optimization space until the convergence condition is met, and the second charging pile layout is determined.

[0094] Furthermore, the second planning and layout module 30 in the embodiment of the present application is also used to perform the following steps:

[0095] Based on the optimization space and the interval constraint condition, determine the initialization layout; traverse the initialization layout, perform two-step optimization, and determine the first optimized layout set, wherein the two-step optimization includes global migration and selective migration; based on the initialization layout and the first optimized layout set, randomly select a layout plan and perform secondary iterative optimization until the convergence condition is met, and select the highest fitness layout as the second charging pile layout.

[0096] Through the above-mentioned detailed description of the zoning layout method of the automobile charging pile group in this specification, those skilled in the art can clearly understand the zoning layout device of the automobile charging pile group in this embodiment. For the device disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant parts can be referred to the description of the method part.

[0097] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A zoning layout method for a vehicle charging pile group, characterized in that: The method comprises: For the charging pile layout area, the regional grid is divided based on the preset range, where the road section type is used as the division constraint; Setting decision variables, making planning and layout decisions for the regional grid by training a 0-1 planning model, and determining a first charging pile layout, wherein the decision variables include a first decision variable based on vehicle flow and a second decision variable based on parking volume; Taking the first charging pile layout as a reference, identifying an undetermined setting, and performing optimization iteration to determine a second charging pile layout, wherein the undetermined setting is an adjustable layout to be optimized; Combining the first charging pile layout and the second charging pile layout to determine a distribution layout result of a charging pile group; The setting of decision variables includes Set the decision variables: ; ; in, is the first decision variable, Refers to Charging points to The traffic flow at each charging demand point, Refers to the high flow threshold, Refers to the low flow threshold; is the second decision variable, Refers to Charging points to The parking volume of charging demand points, is the high parking volume threshold, is a low parking volume threshold; Refers to the charging pile settings. It means that no charging pile is set up. and For non-deterministic settings; The training of the 0-1 planning model comprises: In combination with the regional grid, calling periodic historical data records, wherein the historical data records include vehicle flow records and parking records; Based on the first decision logic of the first decision variable, supervise and train a first planning unit based on the vehicle flow record; Based on the second decision logic of the second decision variable, supervising and training a second planning unit based on the parking record; Integrating the first planning unit and the second planning unit to generate the 0-1 planning model; Integrating the first planning unit and the second planning unit to generate the 0-1 planning model includes: Determine a first plan and a second plan by identifying outputs of the first planning unit and the second planning unit; Mapping the first plan and the second plan to determine a plurality of pairs of charging points, wherein a pair of charging points mapped from the first plan and the second plan is a pair of charging points; Traversing the plurality of pairs of charging points, if the distance between the mapped charging point pairs is less than a preset interval, taking the center position of the distance as the planned charging point, and if the distance between the mapped charging point pairs is greater than a preset interval, taking the mapped charging point pairs as the planned charging point, wherein the preset interval is an interval constraint condition for the layout of charging piles; Based on the first charging pile layout, construct an optimization space, wherein the optimization space is based on the regional grid; In combination with the interval constraint condition, iterative optimization is performed in the optimization space until a convergence condition is met, and the second charging pile layout is determined; Performing iterative optimization in the optimization space includes: Determining an initialization layout based on the optimization space and the spacing constraint condition; Traversing the initialization layout, performing two-step optimization, and determining a first optimized layout set, wherein the two-step optimization includes global migration and selective migration; Based on the initialization layout and the first optimized layout set, a layout scheme is randomly selected and a secondary iterative optimization is performed until a convergence condition is met, and the layout with the highest fitness is selected as the second charging pile layout.

2. The method for zoning and arranging a group of automobile charging piles according to claim 1, characterized in that: The dividing of the regional grids based on the preset range includes: For the road section type, a preset range of area division is set, and a grid standard is determined, wherein the grid standard corresponds to the road section type one by one; For the charging pile layout area, the road section type is identified and matched with the grid standard, and the regional grid is divided and determined.

3. A zoning layout device for a group of car charging piles, characterized in that: The device is used to execute the partition layout method of the automobile charging pile group according to any one of claims 1-2, comprising: A regional grid division module, the regional grid division module is used to divide the regional grid based on a preset range for the charging pile layout area, wherein the road section type is used as a division constraint; A first planning and layout module, the first planning and layout module is used to set decision variables, and to make planning and layout decisions for the regional grid by training a 0-1 planning model to determine the first charging pile layout, wherein the decision variables include a first decision variable based on vehicle flow and a second decision variable based on parking volume; A second planning and layout module, the second planning and layout module is used to identify non-determined settings based on the first charging pile layout, and perform optimization iteration to determine a second charging pile layout, wherein the non-determined settings are adjustable layouts to be optimized; A distribution layout module is used to integrate the first charging pile layout and the second charging pile layout to determine the distribution layout result of the charging pile group.

Images