Electric vehicle charging station planning method and device
Through the combination of integrated learning algorithms and multiple intelligent algorithms, an electric vehicle charging station planning model is built, which solves the problems of nonlinearity and multi-objective complexity in charging station planning, and achieves more stable planning results.
Patent Information
- Application Number
- CN202111517953.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-13
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2041-12-13
AI Technical Summary
In the planning of electric vehicle charging stations, the prior art is prone to poor convergence due to the complexity of nonlinear, multi-objectives and large power grids, resulting in unstable planning accuracy.
The charging station planning model is constructed using integrated learning algorithm, combining the upper optimizer with multiple sub-optimizers, including simulated annealing algorithm, bacterial foraging algorithm, gray wolf optimization algorithm and particle swarm algorithm, and calculate the day through Monte Carlo stochastic simulation and probability statistics Charging timing load data, optimize charging station planning scheme to maximize profits.
It improves the adaptability and accuracy of charging station planning, avoids local convergence state, and ensures the stability and effectiveness of the planning scheme.
Smart Images

Figure CN114169624B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of charging station planning, and in particular to a method and device for planning an electric vehicle charging station. Background Art
[0002] With the increasing severity of air pollution and the shortage of traditional fossil energy, clean and efficient electric vehicles are of great significance to solving environmental and energy problems. Electric vehicles have good development prospects due to their advantages such as low noise, energy saving, high efficiency and zero emissions.
[0003] Charging stations are an important support system in the electric vehicle industry chain and an important supporting facility for electric vehicles. The access location and capacity of charging stations are extremely important. Improper selection will lead to urban traffic congestion, inconvenience for users, and even excessive line losses in the distribution network, and serious reduction in voltage quality at the end of the line and even the entire system.
[0004] At present, the existing research on the objective function of electric vehicle charging station planning mainly focuses on maximizing the economic benefits and minimizing carbon emissions of electric vehicle charging stations. The solutions to this problem mainly include pure mathematical optimization methods such as traditional nonlinear programming and swarm intelligence algorithms. However, this method is prone to poor convergence and falls into a local convergence state in the face of the nonlinearity and multi-objective of charging stations and the complexity of large power grids, affecting the accuracy of electric vehicle charging station planning. Summary of the invention
[0005] The present application provides an electric vehicle charging station planning method and device, which are used to solve the technical problem that the prior art is prone to poor convergence and falls into a local convergence state, resulting in unstable accuracy of electric vehicle charging station planning due to the nonlinearity and multi-objective of charging stations and the complexity of large power grids.
[0006] The first aspect of the present application provides a method for planning an electric vehicle charging station, comprising:
[0007] Obtaining the distribution network topology data, total load data and daily charging time series load data of the target area, wherein the daily charging time series load data is obtained based on the electric vehicle travel data and electric vehicle charging data statistics of the target area in different time periods;
[0008] Obtaining a charging station planning model constructed based on a preset charging station planning revenue maximization objective function, charging station planning constraints, and charging station planning solution training samples, wherein the charging station planning model is an integrated learning model, including: an upper optimizer and a plurality of sub-optimizers including different intelligent algorithms, and both the upper optimizer and the sub-optimizers include the charging station planning revenue maximization objective function and the charging station planning constraints;
[0009] According to the distribution network topology data, the total load data and the daily charging time sequence load information, combined with the charging station planning scheme information, the charging station planning model is used to solve and determine the target charging station planning scheme with the maximum planning benefit, wherein the charging station planning scheme information specifically includes: charging station candidate location information and charging station capacity information.
[0010] Preferably, the process of acquiring the daily charging time series load data specifically includes:
[0011] According to the electric vehicle travel data and electric vehicle charging data in the target area in different time periods, simulation calculations are performed through the Monte Carlo random simulation algorithm and probability statistics calculation method to obtain the daily charging time series load curve.
[0012] Preferably, the charging station planning revenue maximization objective function is specifically:
[0013] max:C=C1+C2-C3-C4-C5
[0014]
[0015]
[0016]
[0017]
[0018]
[0019] Where C1 is the annual electricity sales revenue of the electric vehicle charging station; C2 is the equivalent revenue of CO2 emission reduction; C3 is the construction investment cost of the electric vehicle charging station; C4 is the annual operation and maintenance cost of the electric vehicle charging station; C5 is the network loss cost, d is the number of days; m is the number of nodes of the electric vehicle charging station; P j,t is the charging load of the jth charging station at time t; C6 is the charging electricity price of the electric vehicle; C7 is the on-grid electricity price; W is the power consumption of the electric vehicle for 100 kilometers; R1 is the carbon dioxide emissions of the electric vehicle for 100 kilometers; R2 is the carbon dioxide emissions of the fuel vehicle for 100 kilometers; γ is the trading price of carbon emissions converted into economy, C g is the fixed investment cost of a single electric vehicle charging station; h is the discount rate; s is the useful life of the electric vehicle charging station; P j,ev is the rated capacity of the jth node charging station; C ev is the investment and construction cost of the electric vehicle charging station per unit capacity, Cy,ev is the operation and maintenance cost of the electric vehicle charging station per unit capacity, p is the electricity price; L is the number of branches; Il is the magnitude of the current in the lth branch at time t; R l is the resistance corresponding to the lth branch.
[0020] Preferably, the charging station planning constraints specifically include: node power balance constraints, charging station installation capacity constraints, branch power constraints, node voltage power constraints and charging station capacity demand constraints.
[0021] Preferably, the algorithms included in each of the sub-optimizers are: simulated annealing algorithm, bacterial foraging algorithm, grey wolf optimization algorithm and particle swarm algorithm.
[0022] A second aspect of the present application provides an electric vehicle charging station planning device, comprising:
[0023] A data acquisition unit, used to acquire the distribution network topology data, total load data and daily charging time series load data of the target area, wherein the daily charging time series load data is obtained based on the electric vehicle travel data and electric vehicle charging data statistics of the target area in different time periods;
[0024] A charging station planning model acquisition unit, used to acquire a charging station planning model constructed based on a preset charging station planning benefit maximization objective function, charging station planning constraints, and charging station planning solution training samples, wherein the charging station planning model is an integrated learning model, including: an upper optimizer and a plurality of sub-optimizers including different intelligent algorithms, and the upper optimizer and the sub-optimizer both include the charging station planning benefit maximization objective function and the charging station planning constraints;
[0025] The target scheme determination unit is used to determine the target charging station planning scheme with the maximum planning benefit by solving the charging station planning model based on the distribution network grid topology data, the total load data and the daily charging time sequence load information in combination with the charging station planning scheme information, wherein the charging station planning scheme information specifically includes: charging station candidate location information and charging station capacity information.
[0026] Preferably, the process of acquiring the daily charging time series load data specifically includes:
[0027] According to the electric vehicle travel data and electric vehicle charging data in the target area in different time periods, simulation calculations are performed through the Monte Carlo random simulation algorithm and probability statistics calculation method to obtain the daily charging time series load curve.
[0028] Preferably, the charging station planning revenue maximization objective function is specifically:
[0029] max:C=C1+C2-C3-C4-C5
[0030]
[0031]
[0032]
[0033]
[0034]
[0035] Where C1 is the annual electricity sales revenue of the electric vehicle charging station; C2 is the equivalent revenue of CO2 emission reduction; C3 is the construction investment cost of the electric vehicle charging station; C4 is the annual operation and maintenance cost of the electric vehicle charging station; C5 is the network loss cost, d is the number of days; m is the number of nodes of the electric vehicle charging station; P j,t is the charging load of the jth charging station at time t; C6 is the charging electricity price of the electric vehicle; C7 is the on-grid electricity price; W is the power consumption of the electric vehicle for 100 kilometers; R1 is the carbon dioxide emissions of the electric vehicle for 100 kilometers; R2 is the carbon dioxide emissions of the fuel vehicle for 100 kilometers; γ is the trading price of carbon emissions converted into economy, C g is the fixed investment cost of a single electric vehicle charging station; h is the discount rate; s is the useful life of the electric vehicle charging station; P j,ev is the rated capacity of the jth node charging station; C ev is the investment and construction cost of the electric vehicle charging station per unit capacity, Cy,ev is the operation and maintenance cost of the electric vehicle charging station per unit capacity, p is the electricity price; L is the number of branches; I l is the magnitude of the current in the lth branch at time t; R l is the resistance corresponding to the lth branch.
[0036] Preferably, the charging station planning constraints specifically include: node power balance constraints, charging station installation capacity constraints, branch power constraints, node voltage power constraints and charging station capacity demand constraints.
[0037] Preferably, the algorithms included in each of the sub-optimizers are: simulated annealing algorithm, bacterial foraging algorithm, grey wolf optimization algorithm and particle swarm algorithm.
[0038] It can be seen from the above technical solutions that this application has the following advantages:
[0039] The present application utilizes an integrated learning algorithm to construct a charging station planning model, integrates multiple intelligent algorithms through sub-optimizers in the integrated learning architecture, and applies them to the planning of electric vehicle charging stations respectively, and combines the characteristics of different intelligent algorithms in each sub-optimizer through an upper-level optimizer. It has stronger adaptability in the face of the nonlinearity and multi-objectives of charging stations and the complexity of large power grids, and solves the technical problem that the prior art is prone to poor convergence and falls into a local convergence state in the face of the nonlinearity and multi-objectives of charging stations and the complexity of large power grids, resulting in unstable accuracy of electric vehicle charging station planning. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0041] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for planning an electric vehicle charging station provided in the present application.
[0042] Figure 2 Schematic diagram of the IEEE 33-node distribution network system grid model.
[0043] Figure 3 A schematic structural diagram of an embodiment of an electric vehicle charging station planning device provided in the present application. DETAILED DESCRIPTION
[0044] The embodiments of the present application provide an electric vehicle charging station planning method and device, which are used to solve the technical problem that the prior art is prone to poor convergence and falls into a local convergence state, resulting in unstable accuracy of electric vehicle charging station planning due to the nonlinearity and multi-objective of charging stations and the complexity of large power grids.
[0045] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described below are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0046] See also Figure 1 The first embodiment of the present application provides a method for planning an electric vehicle charging station. Figure 2The IEEE 33-node distribution network system shown in the figure is taken as the research object. Figure 2 The nodes 2, 7, 15, 21, and 31 shown are nodes to be planned for an electric vehicle charging station. The method includes:
[0047] Step 101: Obtain distribution network topology data, total load data, and daily charging time series load data of a target area.
[0048] Among them, the daily charging time series load data is obtained based on the electric vehicle travel data and electric vehicle charging data statistics in the target area in different time periods.
[0049] More specifically, the daily charging time series load data mentioned in this embodiment may include:
[0050] According to the electric vehicle travel data and electric vehicle charging data in the target area in different time periods, simulation operations are performed through the Monte Carlo random simulation algorithm and probability statistics calculation method to obtain the daily charging time series load curve.
[0051] Generally speaking, users will choose the end of each trip in a day as the starting time for charging. Based on the data from the 2009 U.S. Department of Transportation's NHTS survey of U.S. household vehicles, the end time of the last trip of the car satisfies the normal distribution, and its probability density function is:
[0052]
[0053] Where t is the starting charging time; μ is the expected end time; σ is the standard deviation of the end time; these two parameters vary with the driving characteristics of different types of vehicles.
[0054] The travel distance of electric vehicle users in each section follows a log-normal distribution, and its probability density function is:
[0055]
[0056] Where, s is the daily mileage, in km; μ D is the expectation of lns; σ D is the standard deviation of lns. These two parameters vary with the driving characteristics of different types of vehicles.
[0057] The charging time is composed of the initial state of charge and the daily mileage, and the formula is as follows:
[0058]
[0059] Where, Tc is the charging time; β is the percentage of battery capacity when fully charged; SOC0 is the percentage of battery initial capacity; η is the charging efficiency; PC is the charging power of the electric vehicle; E b is the rated capacity of the battery. The charging load curve can be accumulated by randomly extracting the initial state of charge and initial charging time of the electric vehicle through the Monte Carlo method.
[0060] Step 102: Obtain a charging station planning model constructed based on a preset charging station planning benefit maximization objective function, charging station planning constraints, and charging station planning solution training samples.
[0061] Among them, the charging station planning model is an integrated learning model, including: an upper-level optimizer and multiple sub-optimizers containing different intelligent algorithms, and both the upper-level optimizer and the sub-optimizer contain the charging station planning profit maximization objective function and the charging station planning constraints.
[0062] It should be noted that the charging station planning model mentioned in this embodiment is constructed based on a pre-built ensemble learning optimizer and is combined with initialization of various ensemble learning parameters and candidate locations and capacity sample data of charging stations.
[0063] The integrated learning model of this embodiment includes 4 sub-optimizers, and the intelligent algorithms contained in these sub-optimizers are simulated annealing algorithm, bacterial foraging algorithm, gray wolf optimization algorithm, particle swarm algorithm, and multi-searcher optimization algorithm in the upper optimizer. The population size in the multi-searcher optimization algorithm is preferably 200, and the maximum number of iterations is 500.
[0064] Update the parameters of the integrated learning algorithm, and use the forward-backward method to calculate the power flow based on the grid structure, load and charging load information.
[0065] The present invention establishes an optimal planning model for electric vehicle charging stations with the greatest benefits. Its objective function is:
[0066] max:C=C1+C2-C3-C4-C5 (4)
[0067] Among them, C1 is the annual electricity sales revenue of the electric vehicle charging station; C2 is the equivalent benefit of CO2 emission reduction; C3 is the construction investment cost of the electric vehicle charging station; C4 is the annual operation and maintenance cost of the electric vehicle charging station; C5 is the network loss cost.
[0068] The annual electricity sales revenue of an electric vehicle charging station can be expressed as:
[0069]
[0070] Where, d is the number of days; m is the number of nodes of the electric vehicle charging station; P j,t is the charging load of the jth charging station at time t; C6 is the charging electricity price of electric vehicles; C7 is the grid-connected electricity price.
[0071] The carbon emission reduction benefits of electric vehicles can be expressed as:
[0072]
[0073] Among them, W is the power consumption of an electric car traveling 100 kilometers; R1 is the carbon dioxide emissions of an electric car traveling 100 kilometers; R2 is the carbon dioxide emissions of a fuel car traveling 100 kilometers; γ is the transaction price of carbon emissions converted into economy.
[0074] The average annual investment and construction cost of electric vehicle charging stations can be expressed as:
[0075]
[0076] Among them, C g is the fixed investment cost of a single electric vehicle charging station; h is the discount rate; s is the useful life of the electric vehicle charging station; P j,ev is the rated capacity of the jth node charging station; C ev It is the investment and construction cost of electric vehicle charging station per unit capacity.
[0077] The annual operation and maintenance cost of an electric vehicle charging station can be expressed as:
[0078]
[0079] Among them, Cy,ev is the operation and maintenance cost per unit capacity of the electric vehicle charging station.
[0080] The network loss cost of electric vehicles can be expressed as:
[0081]
[0082] Among them, p is the electricity price; L is the number of branches; I l is the magnitude of the current in the lth branch at time t; R l is the resistance corresponding to the lth branch.
[0083] A series of constraints need to be met during the planning of electric vehicle charging stations.
[0084] The node power balance constraint can be expressed as:
[0085]
[0086] Among them, P i , Q i are the active power and reactive power of node i respectively; V i 、V j are the voltages of nodes i and j respectively; G ij and Bij are the conductance and susceptance of the line between node i and node j respectively; θ ij is the voltage phase angle difference between node i and node j.
[0087] The installation capacity constraint of electric vehicle charging stations can be expressed as:
[0088] P i,min ≤P i ≤P i,max (11)
[0089] Among them, P i is the rated installed capacity of the i-th charging station; P i,max , P i,min The upper and lower limits of the installed capacity of the i-th charging station.
[0090] The branch power constraint can be expressed as:
[0091] S ij ≤S ij max (12)
[0092] Among them, S ij is the rated power of branch ij; S ij max is the maximum transmission power of branch ij.
[0093] The node voltage power can be expressed as:
[0094] U i min ≤U i ≤U i max (13)
[0095] Among them, U i max , U i min are the upper and lower limits of the voltage allowed for node i.
[0096] The capacity demand constraint of electric vehicle charging stations can be expressed as:
[0097]
[0098] Among them, P demand The charging capacity required for electric vehicles.
[0099] Step 103: Based on the distribution network topology data, total load data, and daily charging sequence load information, combined with the charging station planning scheme information, a charging station planning model is used to solve and determine the target charging station planning scheme with the maximum planning benefit, wherein the charging station planning scheme information specifically includes: charging station candidate location information and charging station capacity information.
[0100] The ensemble learning optimizer is used to calculate the values of each target model in the charging station planning model. First, the four lower-level sub-optimizers in the ensemble learning algorithm parameters, namely the simulated annealing algorithm, the bacterial foraging algorithm, the gray wolf optimization algorithm, and the particle swarm algorithm, are optimized. Each algorithm is optimized for 10 generations, and the optimized optimal solution is passed to the upper-level optimizer, namely the multi-searcher optimization algorithm. The optimal solution of the lower layer is used as the parent of the upper optimizer, and 1,000 individuals are randomly generated. The upper optimizer continues to optimize and evolve for 20 generations, and the optimal individual of the upper optimization algorithm can be obtained. At the same time, the optimal individual obtained by the upper optimizer is passed to the lower optimizer, and the optimization direction of the lower optimizer is guided.
[0101] Determine whether the convergence conditions are met. If so, obtain the fitness value and optimal solution of the optimal individual and output the target charging station planning scheme with the best benefit; if not, continue iterative optimization until the convergence conditions are met.
[0102] The present application utilizes an integrated learning algorithm to construct a charging station planning model, integrates multiple intelligent algorithms through sub-optimizers in the integrated learning architecture, and applies them to the planning of electric vehicle charging stations respectively, and combines the characteristics of different intelligent algorithms in each sub-optimizer through an upper-level optimizer. It has stronger adaptability in the face of the nonlinearity and multi-objectives of charging stations and the complexity of large power grids, and solves the technical problem that the prior art is prone to poor convergence and falls into a local convergence state in the face of the nonlinearity and multi-objectives of charging stations and the complexity of large power grids, resulting in unstable accuracy of electric vehicle charging station planning.
[0103] The above content is a detailed description of an embodiment of an electric vehicle charging station planning method provided by the present application. The following is a detailed description of an embodiment of an electric vehicle charging station planning device provided by the present application.
[0104] See also Figure 3 The second embodiment of the present application provides an electric vehicle charging station planning device, comprising:
[0105] The data acquisition unit 201 is used to acquire the distribution network topology data, total load data and daily charging time series load data of the target area, wherein the daily charging time series load data is obtained based on the electric vehicle travel data and electric vehicle charging data statistics of the target area in different time periods.
[0106] The charging station planning model acquisition unit 202 is used to obtain a charging station planning model constructed based on a preset charging station planning benefit maximization objective function, charging station planning constraints, and charging station planning scheme training samples, wherein the charging station planning model is an integrated learning model, including: an upper-level optimizer and multiple sub-optimizers containing different intelligent algorithms, and both the upper-level optimizer and the sub-optimizer contain the charging station planning benefit maximization objective function and the charging station planning constraints.
[0107] The target scheme determination unit 203 is used to determine the target charging station planning scheme with the maximum planning benefit based on the distribution network topology data, total load data and daily charging time sequence load information, combined with the charging station planning scheme information, and solved through the charging station planning model, wherein the charging station planning scheme information specifically includes: charging station candidate location information and charging station capacity information.
[0108] Furthermore, the process of acquiring daily charging time series load data specifically includes:
[0109] According to the electric vehicle travel data and electric vehicle charging data in the target area in different time periods, simulation operations are performed through the Monte Carlo random simulation algorithm and probability statistics calculation method to obtain the daily charging time series load curve.
[0110] Furthermore, the objective function of maximizing the revenue of charging station planning is specifically:
[0111] max:C=C1+C2-C3-C4-C5
[0112]
[0113]
[0114]
[0115]
[0116]
[0117] Where C1 is the annual electricity sales revenue of the electric vehicle charging station; C2 is the equivalent revenue of CO2 emission reduction; C3 is the construction investment cost of the electric vehicle charging station; C4 is the annual operation and maintenance cost of the electric vehicle charging station; C5 is the network loss cost, d is the number of days; m is the number of nodes of the electric vehicle charging station; P j,tis the charging load of the jth charging station at time t; C6 is the charging electricity price of the electric vehicle; C7 is the on-grid electricity price; W is the power consumption of the electric vehicle for 100 kilometers; R1 is the carbon dioxide emissions of the electric vehicle for 100 kilometers; R2 is the carbon dioxide emissions of the fuel vehicle for 100 kilometers; γ is the trading price of carbon emissions converted into economy, C g is the fixed investment cost of a single electric vehicle charging station; h is the discount rate; s is the useful life of the electric vehicle charging station; P j,ev is the rated capacity of the jth node charging station; C ev is the investment and construction cost of the electric vehicle charging station per unit capacity, Cy,ev is the operation and maintenance cost of the electric vehicle charging station per unit capacity, p is the electricity price; L is the number of branches; I l is the magnitude of the current in the lth branch at time t; R l is the resistance corresponding to the lth branch.
[0118] Furthermore, the charging station planning constraints specifically include: node power balance constraints, charging station installation capacity constraints, branch power constraints, node voltage power constraints, and charging station capacity demand constraints.
[0119] Furthermore, the algorithms included in each sub-optimizer are: simulated annealing algorithm, bacterial foraging algorithm, grey wolf optimization algorithm and particle swarm optimization algorithm.
[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0121] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0122] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0126] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for planning an electric vehicle charging station, characterized in that: include: Obtaining the distribution network topology data, total load data and daily charging time series load data of the target area, wherein the daily charging time series load data is obtained based on the electric vehicle travel data and electric vehicle charging data statistics of the target area in different time periods; Obtaining a charging station planning model constructed based on a preset charging station planning revenue maximization objective function, charging station planning constraints, and charging station planning solution training samples, wherein the charging station planning model is an integrated learning model, including: an upper optimizer and a plurality of sub-optimizers including different intelligent algorithms, and both the upper optimizer and the sub-optimizers include the charging station planning revenue maximization objective function and the charging station planning constraints; According to the distribution network topology data, the total load data and the daily charging time sequence load information, combined with the charging station planning scheme information, the charging station planning model is used to solve and determine the target charging station planning scheme with the maximum planning benefit, wherein the charging station planning scheme information specifically includes: charging station candidate location information and charging station capacity information; The charging station planning benefit maximization objective function is specifically: ; Where C1 is the annual electricity sales revenue of the electric vehicle charging station; C2 is the equivalent revenue of CO2 emission reduction; C3 is the construction investment cost of the electric vehicle charging station; C4 is the annual operation and maintenance cost of the electric vehicle charging station; C5 is the network loss cost, d is the number of days; m is the number of nodes of the electric vehicle charging station; P j,t is the charging load of the jth charging station at time t; C6 is the charging electricity price of the electric vehicle; C7 is the on-grid electricity price; W is the power consumption of the electric vehicle for 100 kilometers; R1 is the carbon dioxide emissions of the electric vehicle for 100 kilometers; R2 is the carbon dioxide emissions of the fuel vehicle for 100 kilometers; To convert carbon emissions into economic trading prices, is the fixed investment cost of a single electric vehicle charging station; h is the discount rate; s is the useful life of the electric vehicle charging station; is the rated capacity of the j-th node charging station; is the investment and construction cost of the electric vehicle charging station per unit capacity, Cy,ev is the operation and maintenance cost of the electric vehicle charging station per unit capacity, p is the electricity price; L is the number of branches; is the magnitude of the current in the lth branch at time t; is the resistance corresponding to the lth branch.
2. The electric vehicle charging station planning method according to claim 1, characterized in that: The process of acquiring the daily charging time series load data specifically includes: According to the electric vehicle travel data and electric vehicle charging data in the target area in different time periods, simulation calculations are performed through the Monte Carlo random simulation algorithm and probability statistics calculation method to obtain the daily charging time series load curve.
3. The electric vehicle charging station planning method according to claim 1, characterized in that: The charging station planning constraints specifically include: node power balance constraints, charging station installation capacity constraints, branch power constraints, node voltage power constraints, and charging station capacity demand constraints.
4. The electric vehicle charging station planning method according to claim 1, characterized in that: The algorithms included in each of the sub-optimizers are: simulated annealing algorithm, bacterial foraging algorithm, grey wolf optimization algorithm and particle swarm algorithm.
5. An electric vehicle charging station planning device, characterized in that: include: A data acquisition unit, used to acquire the distribution network topology data, total load data and daily charging time series load data of the target area, wherein the daily charging time series load data is obtained based on the electric vehicle travel data and electric vehicle charging data statistics of the target area in different time periods; A charging station planning model acquisition unit, used to acquire a charging station planning model constructed based on a preset charging station planning benefit maximization objective function, charging station planning constraints, and charging station planning solution training samples, wherein the charging station planning model is an integrated learning model, including: an upper optimizer and a plurality of sub-optimizers including different intelligent algorithms, and the upper optimizer and the sub-optimizer both include the charging station planning benefit maximization objective function and the charging station planning constraints; a target solution determination unit, configured to determine a target charging station planning solution with the maximum planning benefit by solving the charging station planning model according to the distribution network topology data, the total load data and the daily charging time sequence load information, in combination with the charging station planning solution information, wherein the charging station planning solution information specifically includes: charging station candidate location information and charging station capacity information; The charging station planning benefit maximization objective function is specifically: ; Where C1 is the annual electricity sales revenue of the electric vehicle charging station; C2 is the equivalent revenue of CO2 emission reduction; C3 is the construction investment cost of the electric vehicle charging station; C4 is the annual operation and maintenance cost of the electric vehicle charging station; C5 is the network loss cost, d is the number of days; m is the number of nodes of the electric vehicle charging station; P j,t is the charging load of the jth charging station at time t; C6 is the charging electricity price of the electric vehicle; C7 is the on-grid electricity price; W is the power consumption of the electric vehicle for 100 kilometers; R1 is the carbon dioxide emissions of the electric vehicle for 100 kilometers; R2 is the carbon dioxide emissions of the fuel vehicle for 100 kilometers; To convert carbon emissions into economic trading prices, is the fixed investment cost of a single electric vehicle charging station; h is the discount rate; s is the useful life of the electric vehicle charging station; is the rated capacity of the j-th node charging station; is the investment and construction cost of the electric vehicle charging station per unit capacity, Cy,ev is the operation and maintenance cost of the electric vehicle charging station per unit capacity, p is the electricity price; L is the number of branches; is the magnitude of the current in the lth branch at time t; is the resistance corresponding to the lth branch.
6. The electric vehicle charging station planning device according to claim 5, characterized in that: The process of acquiring the daily charging time series load data specifically includes: According to the electric vehicle travel data and electric vehicle charging data in the target area in different time periods, simulation calculations are performed through the Monte Carlo random simulation algorithm and probability statistics calculation method to obtain the daily charging time series load curve.
7. The electric vehicle charging station planning device according to claim 5, characterized in that: The charging station planning constraints specifically include: node power balance constraints, charging station installation capacity constraints, branch power constraints, node voltage power constraints, and charging station capacity demand constraints.
8. The electric vehicle charging station planning device according to claim 5, characterized in that: The algorithms included in each of the sub-optimizers are: simulated annealing algorithm, bacterial foraging algorithm, grey wolf optimization algorithm and particle swarm algorithm.
Citation Information
Patent Citations
Electric-vehicle recharging station planning method
CN108805321A
A charging pile fault prediction method based on an expandable lifting tree
CN109190670A
Number configuration method and device of charging piles and distribution system of charging piles
CN112200471A
Charging pile address determination method and device
CN112381313A
Power prediction system, power prediction device, power prediction method, program, and storage medium
WO2020027202A1
