Charging station planning model determination method and device

Abstract

The invention discloses a charging station planning model determination method and device, and relates to the technical field of computers. The method comprises the following steps: determining driving characteristic indexes, travel probabilities and shortest driving paths of electric vehicles included in a to-be-analyzed electric vehicle set; constructing a charging load prediction model according to the driving characteristic index, the travel probability and the shortest driving path; constructing an upper-layer model according to the annual average resource consumption of the charging station and the annual average resource loss of the electric vehicle, and taking the charging load prediction model as a constraint condition of the upper-layer model; a lower layer model is determined, the lower layer model serves as a stability constraint condition of the upper layer model, and the lower layer model is a model combining operation resource consumption and carbon emission resource consumption of the seasonal power distribution network. The method fully considers the charging demand of the electric vehicle and seasonal wind and light uncertainty, optimizes the layout and planning of the charging station, and reduces the resource loss of the electric vehicle and the electric vehicle charging station.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for determining a charging station planning model. Background Art

[0002] With the popularization of electric vehicles, the construction and planning of electric vehicle charging station infrastructure has become one of the important issues in the energy field, and the planning model for charging stations has gradually attracted the attention of researchers.

[0003] At present, most of the planning models for electric vehicle charging stations are determined based on heuristic algorithms, such as ant colony algorithm, particle swarm algorithm, etc. The parameter settings of the heuristic algorithm have a great impact on the results, which can easily cause unreasonable planning of charging stations and affect the utilization rate of electric vehicle charging stations.

[0004] User groups, traffic flow, car usage habits and other factors in different regions will lead to differences in the temporal and spatial distribution of charging demand. The uncertainty brought by wind and solar power will affect the stability of the distribution network operation, and the access of charging stations will bring more severe challenges to the operation capacity of the distribution network. The uncertainty of seasonal wind and solar energy will directly affect the energy supply and operating resource consumption of charging stations. Therefore, considering the temporal and spatial distribution characteristics of charging demand and the uncertainty of seasonal wind and solar power provides ideas for the establishment of charging station planning models. Summary of the invention

[0005] The present invention provides a method, device, electronic device, storage medium and program product for determining a charging station planning model, so as to establish a charging station planning model and optimize the layout and planning of the charging station.

[0006] According to one aspect of the present invention, a method for determining a charging station planning model is provided, comprising:

[0007] Determine driving characteristic indicators, travel probabilities, and shortest driving paths of electric vehicles included in the electric vehicle set to be analyzed;

[0008] According to the driving characteristic index, the travel probability and the shortest driving path, a charging load prediction model is constructed, wherein the charging load prediction model is a model that reflects charging demand in combination with temporal and spatial distribution characteristics;

[0009] According to the average annual resource consumption of charging stations and the average annual resource loss of electric vehicles, an upper model is constructed, and the charging load prediction model is used as a constraint condition of the upper model;

[0010] Determine a lower model and use the lower model as a stability constraint condition of the upper model, wherein the lower model is a model combining seasonal distribution network operation resource consumption and carbon emission resource consumption;

[0011] An optimal solution of the upper model is determined, and the upper model after the optimal solution is determined is used as a charging station planning model.

[0012] According to another aspect of the present invention, there is provided a device for determining a charging station planning model, comprising:

[0013] A first determination module is used to determine the driving characteristic index, travel probability and shortest driving path of the electric vehicles included in the electric vehicle set to be analyzed;

[0014] A first construction module is used to construct a charging load prediction model according to the driving characteristic index, the travel probability and the shortest driving path, wherein the charging load prediction model is a model that reflects the charging demand in combination with the temporal and spatial distribution characteristics;

[0015] The second construction module is used to construct an upper model according to the annual average resource consumption of the charging station and the annual average resource loss of the electric vehicle, and use the charging load prediction model as a constraint condition of the upper model;

[0016] A second determination module is used to determine a lower-level model and use the lower-level model as a stability constraint condition of the upper-level model, wherein the lower-level model is a model combining seasonal distribution network operation resource consumption and carbon emission resource consumption;

[0017] The third determination module is used to determine the optimal solution of the upper model, and use the upper model after determining the optimal solution as the charging station planning model.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the charging station planning model determination method described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the charging station planning model determination method described in any embodiment of the present invention when executed.

[0023] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the method for determining a charging station planning model according to any embodiment of the present invention is implemented.

[0024] The technical solution of the embodiment of the present invention uses the annual average resource consumption of charging stations and the annual average resource loss of electric vehicles as the upper model, and uses the charging load prediction model that reflects the charging demand in combination with the temporal and spatial distribution characteristics, and the lower model that combines the seasonal distribution network operation resource consumption and carbon emission resource consumption as constraints. The optimal solution of the objective function is obtained through the constraints, thereby constructing a charging station planning model. The model takes into account the charging demand of electric vehicles and the uncertainty of seasonal wind and solar power, optimizes the layout and planning of charging stations, and reduces the resource loss of electric vehicles and electric vehicle charging stations.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1A is a flowchart of a method for determining a charging station planning model provided according to Embodiment 1 of the present invention;

[0028] Figure 1B is a flow chart of a real-time Dijkstra algorithm provided according to the first embodiment of the present invention;

[0029] Figure 2A is a flowchart of a charging load prediction model construction method provided according to Embodiment 2 of the present invention;

[0030] Figure 2B is a schematic diagram of a charging load prediction model construction process provided according to Embodiment 2 of the present invention;

[0031] Figure 3 is a structural schematic diagram of a device for determining a charging station planning model provided according to a third embodiment of the present invention;

[0032] Figure 4 It is a block diagram of an electronic device provided according to a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof 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.

[0035] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of relevant laws and regulations.

[0036] Embodiment 1

[0037] Figure 1A This is a flowchart of a charging station planning model determination method provided according to the first embodiment of the present invention. This embodiment can be applied to reduce the resource loss of electric vehicles and electric vehicle charging stations. The method can be executed by a charging station planning model determination device. The charging station planning model determination device can be implemented in the form of hardware and / or software. The charging station planning model determination device can be configured in an electronic device. As shown in Figure 1, the method includes:

[0038] S110, determining driving characteristic indicators, travel probabilities, and shortest driving paths of electric vehicles included in the set of electric vehicles to be analyzed.

[0039] In this embodiment, an electric vehicle can be understood as a vehicle that uses electric energy as power and drives its wheels through an electric motor. There are various ways to charge electric vehicles, such as charging piles, solar charging, etc. The set of electric vehicles to be analyzed can be understood as a set of a part of electric vehicles obtained from the set of electric vehicles, for use in the embodiments of this application. Driving characteristic indicators can be understood as indicators used to describe and measure various behaviors and performances of vehicles during driving, including the vehicle charge state, vehicle departure time, driving speed, destination stay time, and return time of electric vehicles. The travel probability can be understood as an indicator used to describe the travel characteristics of users. There are many factors that affect the travel probability, mainly including travel purpose, time arrangement, destination selection, etc. The shortest driving path can be understood as the shortest path from the starting point to the end point of the traffic flow. Advanced models or technologies can be used to analyze and calculate the road network to find the shortest path.

[0040] Specifically, a set of electric vehicles to be analyzed is obtained through multivariate parameter stratified sampling, and driving characteristic indicators such as vehicle charge state, vehicle departure time, and dwell time of the electric vehicles in the set of electric vehicles to be analyzed are first obtained based on different probability distributions. Multivariate parameter stratified sampling is based on stratified sampling, considering multiple variables to stratify the whole, and then independently sampling in each layer to ensure that representative samples can be obtained in different layers to improve sample accuracy. The travel probability of electric vehicles is obtained through the improved OD matrix, and the shortest driving path of electric vehicles is obtained through the Dijkstra's Algorithm. The improved OD matrix is ​​to improve the estimation and prediction accuracy of the start-to-end matrix of traffic flow in time and space changes by adopting advanced models and technologies, thereby optimizing traffic management and planning. The Dijkstra algorithm can calculate the shortest path from one vertex to the remaining vertices, which solves the shortest path problem in the weighted graph.

[0041] For example, the travel probability of each electric vehicle is obtained by improving the dynamic OD matrix and introducing the holiday electric vehicle travel increment factor. The shortest path between ODs is searched by using the real-time Dijkstra algorithm for path guidance, such as Figure 1B 1 is a flowchart of a real-time Dijkstra algorithm provided according to the first embodiment of the present invention, so as to obtain the shortest driving path of an electric vehicle. In the figure, Vi and Vj are two different nodes, and set O and set D are two arrays, which respectively record the nodes for which the shortest path has been obtained and the nodes for which the shortest path has not been obtained. The driving characteristic indicators of electric vehicles include vehicle charge state, departure time, and stay time. The vehicle charge state obeys the normal distribution.

[0042] N SOC (0.6,0.1 2 )

[0043] For example, the departure time follows a Burr XII distribution, where t s is the departure time, c1 and c2 are shape parameters, and α is the scale parameter.

[0044]

[0045] For example, the residence time in industrial and commercial areas follows a generalized extreme value distribution, and the residence time in residential areas follows a Weibull distribution. r is the residence time in the industrial zone, t z is the stay time in the commercial area, t h is the residence time in residential areas, ρ is the proportionality coefficient, and ι is the shape parameter.

[0046]

[0047] S120: construct a charging load prediction model based on the driving characteristic index, the travel probability and the shortest driving path, wherein the charging load prediction model is a model that reflects charging demand in combination with spatiotemporal distribution characteristics.

[0048] In this embodiment, the charging load prediction model can be understood as a model for predicting the charging demand of electric vehicles in a specific area. The charging load prediction model is constructed through driving characteristic indicators, travel probability, shortest driving path, holiday information, etc. of electric vehicles. The spatiotemporal distribution characteristics can be understood as the distribution and change law of something in the two dimensions of time and space. In traffic flow, the time distribution characteristics are characteristics affected by time factors, including morning and evening peaks, holidays, etc., and the spatial distribution characteristics are characteristics affected by geographical location factors, including different cities, different functional areas, main and secondary roads, etc. The charging demand can be understood as the demand of electric vehicles for charging equipment and power supply, reflecting the travel needs of electric vehicle users.

[0049] Specifically, according to the driving characteristic indicators of different types of vehicles that have been obtained, the change values ​​of the driving characteristic indicators during the driving process of electric vehicles are recorded, and the charging load prediction model is constructed in combination with the travel probability and the shortest driving path. Since the spatiotemporal distribution characteristics are taken into account when obtaining the driving characteristic indicators and calculating the travel probability and the shortest driving path, the charging load prediction model is a model that reflects the charging demand in combination with the spatiotemporal distribution characteristics.

[0050] For example, due to the different travel characteristics of electric vehicles, the vehicle types are divided into private cars and non-private cars. According to the driving characteristic indicators of different vehicle types that have been obtained, the change values ​​of the electric vehicle driving characteristic indicators are recorded respectively during the driving process of the electric vehicle, and the charging load prediction model is constructed in combination with the travel probability and the shortest driving path.

[0051] S130: construct an upper model according to the annual average resource consumption of charging stations and the annual average resource loss of electric vehicles, and use the charging load prediction model as a constraint condition of the upper model.

[0052] In this embodiment, the average annual resource consumption of a charging station can be understood as the resource consumption of a charging station in one year, including the annual construction resource consumption and the annual operation and maintenance resource consumption. The annual construction resource consumption includes the basic investment consumption of the charging station, the resource consumption of fast charging piles and slow charging piles, and the annual operation and maintenance resource consumption includes the maintenance staff salary consumption and equipment loss resource consumption. The average annual resource loss of electric vehicles can be understood as the resource consumption generated by electric vehicles during one year's driving, including the time loss of charging route and the loss of empty driving on the charging route. Constraints can be understood as limiting factors imposed on a specific problem. Constraints can screen out feasible solutions that meet the actual situation and can be expressed in the form of inequalities or equations.

[0053] Specifically, various resource losses will occur during the construction and operation of charging stations. Electric vehicles will also incur resource losses due to empty driving distance, time consumption, etc. during driving. This embodiment constructs an upper-level model based on the average annual resource consumption of charging stations and the average annual resource loss of electric vehicles. The upper-level model includes an upper-level objective function and an upper-level constraint condition. The charging load prediction model constructed in S120 is constrained to the upper-level model and can also be used as a constraint condition of the upper-level model. The upper-level objective function and the upper-level constraint condition can be understood as the optimization target and decision variable in the two-level optimization problem.

[0054] Exemplarily, the upper objective function of the upper model is constructed according to the sum of the annual average resource consumption f1 of the charging station and the annual average resource loss f2 of the electric vehicle.

[0055] minf upper =f1+f2

[0056] For example, the annual average resource consumption of the charging station f1 includes the annual construction resource consumption C build , Annual operation and maintenance resource consumption C maint .

[0057] f1=C build +C maint

[0058] For example, the annual construction resource consumption includes the basic investment consumption C of the charging station. iv , resource consumption of fast charging piles and slow charging piles C pc .

[0059] C build =C iv +C pc

[0060]

[0061] C pc,i =C fast N fast,i,o +C slow N slow,i,o

[0062] In the formula, C iv,i is the basic investment consumption of the i-th charging station, C pc,i is the resource consumption of the fast charging pile and slow charging pile of the i-th charging station; N is the number of charging stations, y is the service life of the charging station, r0 is the discount rate; N fast,i,o is the number of fast charging piles in the i-th charging station belonging to functional area ο, N slow,i,o is the number of slow charging piles in the i-th charging station belonging to functional area ο, C fast is the resource consumption of a single fast charging pile, C slow It is the resource consumption of a single slow charging pile.

[0063] For example, the annual operation and maintenance resource consumption C maint Including the consumption of maintenance staff salaries and equipment loss resources.

[0064]

[0065] C cp,i =365·T day (P fast N fast,i,o +P slow N s l ow,i,o )

[0066] Where P fast is the fast charging pile power, P slow is the slow charging pile power, T day is the average daily usage time of the charging pile; C cp,i is the annual operating capacity of the i-th charging station, represents the salary rate of maintenance staff, and υ represents the equipment loss rate.

[0067] For example, the annual average resource loss of electric vehicles f2 includes the charging time loss C lost 、Charging route idling loss C empty :

[0068] f2=C lost +C empty

[0069]

[0070] Where θ is the unit consumption of driving, N c,i is the number of electric vehicles that need to be charged in the i-th charging station, △T i,n The time required for an electric vehicle that needs to be charged to travel from its current location to the charging station; i,n is the distance from the nth electric vehicle to the i-th charging station, △E i,n is the power consumption per kilometer of the nth electric vehicle, C i,chp Unit charging consumption of the i-th charging station.

[0071] Exemplarily, the upper-level constraints of the upper-level model include the number of charging stations, the charging demand, the distance between charging stations, and the number of regional charging piles:

[0072] N min ≤N≤N max

[0073] (P fast N fast,i,o +P slow N slow,i,o )T D ≥P rd,i

[0074]

[0075]

[0076] Where N min is the minimum number of sites to be built, N max T is the maximum number of sites to be built; D There are 24 periods in a day, P rd,i is the total charging demand in the i-th charging station; S is the set of charging demand points within the service range of each alternative charging station, u represents the set containing charging station i, δ i,u is a 0 / 1 variable; t is the ratio coefficient of fast charging piles and slow charging piles, and Y is the set of ranges in different areas.

[0077] S140, determining a lower-level model, and using the lower-level model as a stability constraint condition for the upper-level model, wherein the lower-level model is a model that combines seasonal distribution network operation resource consumption and carbon emission resource consumption.

[0078] In this embodiment, seasonal distribution network operation resource consumption can be understood as the resource consumption caused by the operation of the distribution network due to changes in electricity demand, equipment operating environment and other factors in different seasons, including gas turbine resource consumption, diesel unit resource consumption, photovoltaic power generation resource consumption, wind power generation resource consumption, wind abandonment resource consumption, light abandonment resource consumption, demand response consumption, electricity purchase consumption, and electricity sales consumption. Carbon emission resource consumption can be understood as the resource consumption caused by greenhouse gas emissions such as carbon dioxide generated by energy use.

[0079] Specifically, the lower-level model is constructed according to the seasonal distribution network operation resource consumption and carbon emission resource consumption. The lower-level model includes the lower-level objective function and the lower-level constraint conditions, among which the seasonal distribution network operation resource consumption needs to consider the seasonal wind and solar uncertainty. The lower-level model is converted into the constraint conditions of the upper-level model by constructing a function, thereby converting the two-level model into a single-level model. The lower-level objective function and the lower-level constraint conditions can be understood as the local optimization objectives and local decision variables in the two-level optimization problem, which are constrained by the upper-level objective function and the upper-level constraint conditions.

[0080] For example, the lower objective function of the lower model is constructed based on the seasonal distribution network operation resource consumption and carbon emission resource consumption. The lower objective function and the lower constraint conditions are converted into the stability constraint conditions of the upper model through the Lagrangian function. The lower objective function mainly includes the gas turbine resource consumption C gas , diesel unit resource consumption C diesel , Photovoltaic power generation resource consumption C pv , wind power generation resource consumption C wind , wind curtailment resource consumption C pvcut , Abandoned light resource consumption C windcut 、Demand response consumption C DR , Power consumption C buy 、Electricity consumption C sell and carbon emissions and resource consumption

[0081]

[0082] For example, the gas turbine resource consumption C gas , where M is the set of distribution network nodes, π s is the probability of scenario s occurring, is the unit resource consumption of gas turbine output, is the gas turbine output, T is the total dispatching time, T sm is the time period of a typical day in summer, T wt The time period for a typical day in winter.

[0083]

[0084] For example, the diesel engine resource consumption C diesel , where is the unit resource consumption of the diesel generator set output, Power for diesel units.

[0085]

[0086] For example, for the uncertainty of wind power and photovoltaic power, a multi-scenario method is used to process it. Assuming that the power of wind power and photovoltaic power obeys the normal distribution, a large number of power scenarios that obey the probability distribution constraints are first generated using multivariate parameter stratified sampling, and then the synchronous back-generation elimination algorithm is considered to reduce the scenarios, and the original scenarios are reduced based on the "bulldozer distance". Photovoltaic power generation resource consumption Cpv, wind power generation resource consumption C wind , where is the resource consumption per unit of wind power output, Contribute to wind power; is the resource consumption per unit of photovoltaic output, Power for photovoltaics.

[0087]

[0088] For example, the wind curtailment resource consumption C pvcut , Abandoned light resource consumption C windcut , where is the unit resource consumption of wind power abandonment, is the abandoned wind volume; is the resource consumption per abandoned light unit, is the amount of abandoned light; To forecast the output of wind power, For photovoltaic prediction, is the wind power forecast deviation rate, Predict the deviation rate for photovoltaics.

[0089]

[0090] For example, the demand response consumption C DR , where To reduce the load unit consumption, To reduce the load; is the unit consumption of transferable load, is the transferable load, It is a 0 / 1 variable.

[0091]

[0092] For example, the electricity consumption Cbuy , electricity consumption C sell , where is the unit consumption of electricity purchased, For the purchase of electricity; is the consumption of electricity sales units, For electricity sales.

[0093]

[0094] For example, the carbon emission resource consumption C co2 , where is the carbon emission base price, For gas turbine carbon emissions, Carbon quotas for gas turbines, Carbon emissions from diesel engines, Carbon quota for diesel units, To reduce carbon emissions from electricity purchases, To purchase carbon quotas for electricity; is the carbon emission coefficient of the gas turbine, is the gas turbine carbon quota factor; is the carbon emission coefficient of the diesel unit, is the carbon quota coefficient of the diesel unit; is the carbon emission coefficient of electricity purchase, is the carbon quota coefficient for electricity purchases.

[0095]

[0096]

[0097] Exemplarily, the lower-level constraints include gas turbine output constraints, gas turbine ramping constraints, diesel unit output constraints, diesel unit ramping constraints, wind power, photovoltaic output constraints, power purchase and sales constraints, demand response constraints, distribution network flow constraints, and power balance constraints.

[0098] Exemplarily, the gas turbine output constraint is: It is the upper limit of gas turbine output.

[0099]

[0100] Exemplarily, the gas turbine ramp constraint is: They are the upper and lower limits of gas turbine climbing respectively.

[0101]

[0102] For example, the diesel engine output constraint is: It is the upper limit of diesel generator set output.

[0103]

[0104] Exemplarily, the diesel engine climbing constraint is: They are the upper and lower limits of the diesel engine climbing grade respectively.

[0105]

[0106] Exemplary: wind power and photovoltaic output constraints.

[0107]

[0108] For example, the power purchase and sale constraints are: They are the upper limits of electricity purchase and electricity sales respectively.

[0109]

[0110] An exemplary,demand response constraint is,where, To reduce the load factor, is the transferable load factor.

[0111]

[0112] For example, the power flow constraint of the distribution network is: is the injected power, is the load power, is the total branch active power injected into node x, is the total branch active power flowing out of node x, and The meaning is similar. are the active power and reactive power flowing into line xz, They represent the minimum and maximum voltages at node x, r xz is the resistance value of line xz, x xz is the reactance value of line xz, S l is the line capacity.

[0113]

[0114] An exemplary,power balance constraint is,where, Charging loads for electric vehicles.

[0115]

[0116] S150: Determine the optimal solution of the upper model, and use the upper model after the optimal solution is determined as a charging station planning model.

[0117] In this embodiment, the optimal solution can be understood as a solution that enables the objective function to reach the optimal value among all possible solutions to a specific problem.

[0118] Specifically, the upper-level constraints, the lower-level constraints and the stability constraints converted from the lower-level model are used as constraints, and the upper-level objective function is used as the objective function. The optimal solution of the objective function is solved through the above three types of constraints, and the upper-level model after determining the optimal solution is used as the charging station planning model.

[0119] Exemplarily, the upper layer objective function is used as the objective function.

[0120] minf upper =f1+f2

[0121] Exemplarily, the upper-level constraints, the lower-level constraints and the stability constraints converted from the lower-level model are used as constraints to solve the optimal solution of the objective function, thereby obtaining a charging station planning model after the conversion of the two-level planning model of the electric vehicle charging station considering the temporal and spatial distribution characteristics.

[0122] The technical solution of the embodiment of the present invention uses the annual average resource consumption of charging stations and the annual average resource loss of electric vehicles as the upper model, and uses the charging load prediction model that reflects the charging demand in combination with the temporal and spatial distribution characteristics, and the lower model that combines the seasonal distribution network operation resource consumption and carbon emission resource consumption as constraints. The optimal solution of the objective function is obtained through the constraints, thereby constructing a charging station planning model. The model takes into account the charging demand of electric vehicles and the uncertainty of seasonal wind and solar power, optimizes the layout and planning of charging stations, and reduces the resource loss of electric vehicles and electric vehicle charging stations.

[0123] Based on the above embodiment, a variant embodiment of the above embodiment is proposed. It should be noted that in order to make the description concise, only the differences from the above embodiment are described in the variant embodiment.

[0124] Furthermore, the travel probability of the electric vehicles included in the set of electric vehicles to be analyzed is determined, including: performing calculations based on the number of road nodes in the road network, the first number of electric vehicles in the road network, and the second number of electric vehicles to determine the travel probability of the electric vehicles included in the set of electric vehicles to be analyzed; wherein the number of road nodes includes the destination corresponding to the set of electric vehicles to be analyzed, the first number of electric vehicles includes the number of electric vehicles starting from the first node to the second node in the road network, and the second number of electric vehicles includes the number of all electric vehicles starting from the first node in the road network.

[0125] Specifically, first obtain the destination number of all electric vehicles in the set of electric vehicles to be analyzed in the road network, determine the destination number as the number of road nodes, randomly select a node as the first node, and then select a node different from the first node as the second node. The number of all electric vehicles moving from the first node to the second node is taken as the first number of electric vehicles, and the number of all electric vehicles starting from the first node is taken as the second number of electric vehicles.

[0126] For example, first, the number of destinations m of all electric vehicles in the set of electric vehicles to be analyzed in the road network is obtained as the number of road nodes, a node is randomly selected as the first node i, and a node different from the first node i is selected as the second node j. The number of all electric vehicles moving from the first node to the second node is taken as the first electric vehicle number The number of all electric vehicles starting from the first node is taken as the second number of electric vehicles

[0127] Optionally, the method performs calculations based on the number of road nodes in the road network and the first number of electric vehicles and the second number of electric vehicles in the road network to determine the travel probability of electric vehicles included in the electric vehicle set to be analyzed, including: for each electric vehicle in the electric vehicle set to be analyzed, determining the ratio of the first number of electric vehicles to the second number of electric vehicles, the first number of electric vehicles and the second number of electric vehicles being the numbers determined after associating the holiday electric vehicle travel increment factor; and determining the ratio as the travel probability of the electric vehicle.

[0128] Specifically, since holidays are an important factor affecting travel probability, this embodiment introduces a holiday electric vehicle travel increment factor, redetermines the first number of electric vehicles and the second number of electric vehicles, and uses the ratio of the two as the travel probability of electric vehicles.

[0129] For example, the holiday electric vehicle travel increment factor ψ is introduced, and the first electric vehicle number is The second number of electric vehicles is According to the improved OD matrix The ratio of the two is taken as the travel probability of electric vehicles

[0130]

[0131] Furthermore, the lower-level model includes a lower-level objective function and a lower-level constraint condition, and the method of using the lower-level model as the stationarity constraint condition of the upper-level model includes: based on the relaxation variable factor and the Lagrange multiplier, respectively integrating the inequalities and equations in the lower-level constraint conditions to obtain an integrated result; constructing a Lagrangian function according to the integrated result and the lower-level objective function; and using the result that the derivative of the Lagrangian function is equal to zero as the stationarity constraint condition of the upper-level model.

[0132] In this embodiment, the slack variable factor can be understood as the variable introduced by integrating the inequality constraint into the equality constraint in the optimization problem. The Lagrange multiplier can be understood as the problem of converting the constrained problem into the unconstrained problem in the optimization problem in order to solve the introduced variable. The constraints are integrated into the objective function through the Lagrange multiplier and the slack variable factor, and the Lagrangian function is constructed, so that the constrained optimization problem that is originally difficult to solve directly can be solved by finding the extreme value of the Lagrangian function.

[0133] Specifically, by introducing the slack variable factor, the inequality in the lower constraint condition is converted into an equation and integrated into the Lagrangian function, and the Lagrangian multiplier is introduced to integrate the equation in the lower constraint condition into the Lagrangian function. Combined with the lower objective function, the three are integrated to obtain the Lagrangian function, and a Lagrangian function including the lower objective function and the lower constraint condition is obtained. Then, according to the principle of solving the optimization problem by the Lagrangian multiplier method, the Lagrangian function is differentiated and its derivative is equal to zero to obtain a new constraint condition, which is used as the stationarity constraint condition of the upper model.

[0134] Exemplarily, the lower model is transformed into the constraint condition of the upper objective function through the relaxation variable factor μ and the Lagrangian multiplier λ. To simplify the complexity of the formula, the Lagrangian function L is constructed by taking the gas turbine as an example, and the other elements are similar.

[0135]

[0136] Exemplarily, the Lagrangian function L is differentiated and the derivative is set equal to 0, thereby obtaining the Lagrangian stationarity constraint:

[0137]

[0138] Exemplarily, in the formula, This type of dual variable is nonlinear and needs to be linearized through the big-M method. The big-M method introduces an infinitely large real number and constructs an auxiliary problem, thereby linearizing the nonlinear problem and making it easier to solve.

[0139]

[0140] In the formula, is a 0 / 1 variable, and M is an infinite real number.

[0141] Further, the determining of the optimal solution of the upper model and using the upper model after the optimal solution is determined as the charging station planning model includes: taking the following formula as the objective function, taking the stability constraint condition, the lower constraint condition of the lower model and the upper constraint condition of the upper model as constraint conditions, determining the optimal solution of the upper model,

[0142] minf upper =f1+f2

[0143] In the above formula, f1 is the average annual resource consumption of the charging station, and f2 is the average annual resource loss of the electric vehicle; the upper model after determining the optimal solution is used as the charging station planning model.

[0144] Specifically, the upper constraint conditions, lower constraint conditions and the stability constraint conditions obtained by the Lagrange multiplier method are used as constraint conditions, the upper objective function is used as the objective function, the optimal solution of the objective function is determined by the constraint conditions, and the upper model after determining the optimal solution is used as the charging station planning model.

[0145] Embodiment 2

[0146] Figure 2A : is a flowchart of a method for constructing a charging load prediction model according to Embodiment 2 of the present invention. This embodiment is developed for the charging load prediction model in the above embodiment. The method includes:

[0147] S210. For each electric vehicle, determine the vehicle type of the vehicle according to the driving characteristic index of the vehicle, where the vehicle type indicates whether the vehicle is a private car.

[0148] Specifically, a set of electric vehicles to be analyzed is obtained through multivariate parameter stratified sampling. Depending on the type of electric vehicles, their driving characteristic indicators are different. In this embodiment, the vehicle types are divided into private cars and non-private cars, and whether a vehicle is a private car is determined based on the different driving characteristic indicators of the two.

[0149] Exemplarily, each vehicle in the set of electric vehicles to be analyzed is divided into private cars and non-private cars through different driving characteristic indicators. The driving characteristic indicators of private cars include vehicle charge state, departure time, driving speed and destination stay time. The destinations include commercial areas, residential areas and industrial areas, thereby establishing a private car travel chain, which specifically includes three travel chains: residential area-industrial area-residential area, residential area-commercial area-residential area, and residential area-industrial area-commercial area-residential area. The driving characteristic indicators of non-private cars include vehicle charge state, departure time, driving speed and return time. The driving speed obeys the log-normal distribution, where v is the driving speed.

[0150]

[0151] For example, the return time follows a Burr XII distribution, where t b is the return moment, c3 and c4 are shape parameters, and β is the scale parameter.

[0152]

[0153] S220: Select a target characteristic index corresponding to the vehicle type from the driving characteristic indexes.

[0154] In this embodiment, the target characteristic index may be understood as a driving characteristic index selected from the driving characteristic indexes for model construction.

[0155] Specifically, depending on the type of electric vehicle, the travel characteristics of different electric vehicles are different, resulting in differences in the target characteristic indicators selected from the driving characteristic indicators.

[0156] Exemplarily, the vehicle types are divided into private cars and non-private cars. Private cars select vehicle charge state and destination stay time as target feature indicators, and non-private cars select vehicle charge state and departure time as target feature indicators.

[0157] S230: Determine a change value of the target characteristic index after the vehicle travels according to the travel probability and the shortest driving path.

[0158] Specifically, after the electric vehicles in the electric vehicle set to be analyzed travel according to the travel probability and the shortest driving path, the target characteristic index will change. The change value of the target characteristic index during the driving of the electric vehicle is recorded according to different vehicle types for use in model training.

[0159] For example, after the electric vehicle travels according to the travel probability and the shortest driving path, the change value of the target characteristic index is recorded according to different vehicle types. For private cars, the change value of the vehicle's state of charge and the destination stay time are recorded, and for non-private cars, the change value of the vehicle's state of charge and the interval between two departure times are recorded.

[0160] S240: construct the charging load prediction model according to the change value corresponding to each of the vehicles.

[0161] Specifically, according to the changing values ​​of target characteristic indicators of different vehicle types, a charging load prediction model considering the temporal and spatial distribution characteristics is constructed.

[0162] Exemplarily, a charging load prediction model is constructed according to the change values ​​of the target characteristic indicators of private cars and non-private cars. Figure 2B It is a schematic diagram of a charging load prediction model building process provided according to the second embodiment of the present invention, SOC represents the vehicle charge state, and the travel chain type is the three private car travel chains established in S210.

[0163] Optionally, the selecting a target characteristic index corresponding to the vehicle type from the driving characteristic indexes includes:

[0164] If the vehicle type indicates that the vehicle is a private car, the vehicle state of charge and the destination stay time are selected from the driving characteristic indicators, and the vehicle state of charge and the destination stay time are used as target characteristic indicators; otherwise, the vehicle state of charge and the vehicle departure time are selected from the driving characteristic indicators, and the vehicle state of charge and the vehicle departure time are used as target characteristic indicators.

[0165] Specifically, electric vehicles are divided into private cars and non-private cars, and the types of electric vehicles in the set of electric vehicles to be analyzed are determined. Since private cars have relatively fixed routes, long charging times and relatively fixed charging locations, while non-private cars have more trips, irregular routes, short charging times and irregular charging locations, two conditions need to be considered when selecting target characteristic indicators. If the electric vehicle is a private car, the vehicle charge state and destination stay time are selected as target characteristic indicators from the driving characteristic index value. If it is a non-private car, the vehicle charge state and vehicle departure time are selected as target characteristic indicators from the driving characteristic index value.

[0166] The embodiment of the present invention provides a method for constructing a charging load prediction model, which determines the vehicle type and selects the target characteristic index according to the driving characteristic index, records the change value of the target characteristic index during the driving process of the electric vehicle, and constructs a charging load prediction model in combination with the travel probability and the shortest driving path. The model takes into account the temporal and spatial distribution characteristics and reflects the charging demand, and can be used as a constraint condition in the construction process of the charging station planning model.

[0167] Embodiment 3

[0168] Figure 3 This is a schematic diagram of the structure of a device for determining a charging station planning model provided by Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0169] A first determination module 310 is used to determine the driving characteristic index, travel probability and shortest driving path of the electric vehicles included in the electric vehicle set to be analyzed;

[0170] A first construction module 320 is used to construct a charging load prediction model according to the driving characteristic index, the travel probability and the shortest driving path, wherein the charging load prediction model is a model that reflects charging demand in combination with spatiotemporal distribution characteristics;

[0171] A second construction module 330 is used to construct an upper model according to the average annual resource consumption of the charging station and the average annual resource loss of the electric vehicle, and use the charging load prediction model as a constraint condition of the upper model;

[0172] A second determination module 340 is used to determine a lower-level model and use the lower-level model as a stability constraint condition of the upper-level model, wherein the lower-level model is a model combining seasonal distribution network operation resource consumption and carbon emission resource consumption;

[0173] The third determination module 350 is used to determine the optimal solution of the upper model, and use the upper model after determining the optimal solution as the charging station planning model.

[0174] The technical solution of the embodiment of the present invention completes the construction of the charging station planning model through the mutual cooperation and collaboration between the modules. The annual average resource consumption of the charging station and the annual average resource loss of the electric vehicle are used as the upper model, the charging load prediction model that reflects the charging demand combined with the temporal and spatial distribution characteristics, and the lower model that combines the seasonal distribution network operation resource consumption and carbon emission resource consumption are used as constraints. The optimal solution of the objective function is obtained through the constraints, thereby constructing the charging station planning model. The model takes into account the charging demand of electric vehicles and the seasonal uncertainty of wind and light, optimizes the layout and planning of charging stations, and reduces the resource loss of electric vehicles and electric vehicle charging stations.

[0175] In one embodiment, the charging station planning model determination device further includes a probability determination module, including:

[0176] A probability determination unit, configured to determine the travel probability of the electric vehicles included in the set of electric vehicles to be analyzed by performing calculations based on the number of road nodes in the road network, the number of first electric vehicles and the number of second electric vehicles in the road network;

[0177] Among them, the number of road nodes includes the destination corresponding to the set of electric vehicles to be analyzed, the first number of electric vehicles includes the number of electric vehicles starting from the first node in the road network to the second node, and the second number of electric vehicles includes the number of all electric vehicles starting from the first node in the road network.

[0178] In one embodiment, the probability determination unit is specifically configured to:

[0179] For each electric vehicle in the set of electric vehicles to be analyzed, determining a ratio of a first number of electric vehicles to a second number of electric vehicles, wherein the first number of electric vehicles and the second number of electric vehicles are respectively numbers determined after associating holiday electric vehicle travel increment factors;

[0180] The ratio is determined as the travel probability of the electric vehicle.

[0181] In one embodiment, the lower layer model includes a lower layer objective function and a lower layer constraint condition, and the second determination module 340 is specifically used to:

[0182] Based on the slack variable factor and the Lagrange multiplier, the inequalities and the equalities in the lower constraint conditions are respectively integrated to obtain an integrated result;

[0183] Constructing a Lagrangian function according to the integration result and the lower layer objective function;

[0184] The result of the derivative of the Lagrangian function being equal to zero is used as a stationarity constraint condition of the upper model.

[0185] In one embodiment, the third determination module 350 is specifically configured to:

[0186] The following formula is the objective function, and the optimal solution of the upper model is determined by taking the stability constraint condition, the lower constraint condition of the lower model and the upper constraint condition of the upper model as constraint conditions,

[0187] minf upper =f1+f2

[0188] In the above formula, f1 is the average annual resource consumption of the charging station, and f2 is the average annual resource loss of the electric vehicle;

[0189] The upper model after determining the optimal solution is used as the charging station planning model.

[0190] In one embodiment, the first building block 320 includes:

[0191] a type determination unit, configured to determine, for each electric vehicle, a vehicle type of the vehicle according to a driving characteristic index of the vehicle, wherein the vehicle type indicates whether the vehicle is a private car;

[0192] A selection unit, configured to select a target characteristic index corresponding to the vehicle type from the driving characteristic index;

[0193] A change value determination unit, used to determine a change value of the target characteristic index after the vehicle travels according to the travel probability and the shortest driving path;

[0194] A construction unit is used to construct the charging load prediction model according to the change value corresponding to each of the vehicles.

[0195] In one embodiment, the selection unit is specifically configured to:

[0196] If the vehicle type indicates that the vehicle is a private car, the vehicle state of charge and the destination stay time are selected from the driving characteristic indicators, and the vehicle state of charge and the destination stay time are used as target characteristic indicators; otherwise, the vehicle state of charge and the vehicle departure time are selected from the driving characteristic indicators, and the vehicle state of charge and the vehicle departure time are used as target characteristic indicators.

[0197] Embodiment 4

[0198] According to an embodiment of the present invention, the present invention also provides an electronic device, a computer-readable storage medium and a computer program product.

[0199] Figure 4 It is a block diagram of an electronic device provided according to Embodiment 4 of the present invention, and the electronic device can implement the charging station planning model determination method described in the embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0200] like Figure 4As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0201] A number of components in the electronic device are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0202] The processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as a charging station planning model determination method.

[0203] In some embodiments, the charging station planning model determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the charging station planning model determination method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to execute the charging station planning model determination method in any other appropriate manner (e.g., by means of firmware).

[0204] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0205] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0206] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0207] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0208] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0209] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0210] In some embodiments, the computer program product includes a computer program, and when the computer program is executed by a processor, the method for determining a charging station planning model provided in an embodiment of the present invention is implemented.

[0211] The technical solution of the embodiment of the present invention is to determine the method, device, electronic device, storage medium and program product through the charging station planning model, with the annual average resource consumption of the charging station and the annual average resource loss of the electric vehicle as the upper model, and the charging load prediction model that reflects the charging demand in combination with the spatiotemporal distribution characteristics, and the lower model that combines the seasonal distribution network operation resource consumption and carbon emission resource consumption as the constraint conditions, and obtain the optimal solution of the objective function through the constraint conditions, so as to construct the charging station planning model. The model takes into account the charging demand of electric vehicles and the seasonal wind and light uncertainty, optimizes the layout and planning of charging stations, and reduces the resource loss of electric vehicles and electric vehicle charging stations.

[0212] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0213] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a charging station planning model, characterized in that: include: Determine driving characteristic indicators, travel probabilities, and shortest driving paths of electric vehicles included in the electric vehicle set to be analyzed; According to the driving characteristic index, the travel probability and the shortest driving path, a charging load prediction model is constructed, wherein the charging load prediction model is a model that reflects charging demand in combination with temporal and spatial distribution characteristics; According to the average annual resource consumption of charging stations and the average annual resource loss of electric vehicles, an upper model is constructed, and the charging load prediction model is used as a constraint condition of the upper model; Determine a lower model and use the lower model as a stability constraint condition of the upper model, wherein the lower model is a model combining seasonal distribution network operation resource consumption and carbon emission resource consumption; An optimal solution of the upper model is determined, and the upper model after the optimal solution is determined is used as a charging station planning model.

2. The method according to claim 1, characterized in that Determining the travel probability of the electric vehicles included in the set of electric vehicles to be analyzed further includes: Performing calculations based on the number of road nodes in the road network, the number of first electric vehicles and the number of second electric vehicles in the road network to determine the travel probability of electric vehicles included in the set of electric vehicles to be analyzed; Among them, the number of road nodes includes the destination corresponding to the set of electric vehicles to be analyzed, the first number of electric vehicles includes the number of electric vehicles starting from the first node in the road network to the second node, and the second number of electric vehicles includes the number of all electric vehicles starting from the first node in the road network.

3. The method according to claim 2, characterized in that The performing calculation according to the number of road nodes in the road network, the number of first electric vehicles and the number of second electric vehicles in the road network to determine the travel probability of electric vehicles included in the set of electric vehicles to be analyzed further includes: For each electric vehicle in the set of electric vehicles to be analyzed, determining a ratio of a first number of electric vehicles to a second number of electric vehicles, wherein the first number of electric vehicles and the second number of electric vehicles are respectively numbers determined after associating holiday electric vehicle travel increment factors; The ratio is determined as the travel probability of the electric vehicle.

4. The method according to claim 1, characterized in that: The lower layer model includes a lower layer objective function and a lower layer constraint condition, and the lower layer model is used as a stationarity constraint condition of the upper layer model, including: Based on the slack variable factor and the Lagrange multiplier, the inequalities and the equalities in the lower constraint conditions are respectively integrated to obtain an integrated result; Constructing a Lagrangian function according to the integration result and the lower layer objective function; The result of the derivative of the Lagrangian function being equal to zero is used as a stationarity constraint condition of the upper model.

5. The method according to claim 1, characterized in that The step of determining the optimal solution of the upper model and using the upper model after determining the optimal solution as the charging station planning model includes: The following formula is the objective function, and the optimal solution of the upper model is determined by taking the stability constraint condition, the lower constraint condition of the lower model and the upper constraint condition of the upper model as constraint conditions, <h2 style=";text-align:left;direction:ltr">minf<h2 style=";text-align:left;direction:ltr"> upper <h2 style=";text-align:left;direction:ltr"> (f1+f2) In the above formula, f1 is the average annual resource consumption of the charging station, and f2 is the average annual resource loss of the electric vehicle; The upper model after determining the optimal solution is used as the charging station planning model.

6. The method according to claim 1, characterized in that The constructing of a charging load prediction model according to the driving characteristic index, the travel probability and the shortest driving path includes: For each electric vehicle, determining a vehicle type of the vehicle according to the driving characteristic index of the vehicle, the vehicle type indicating whether the vehicle is a private car; Selecting a target characteristic index corresponding to the vehicle type from the driving characteristic indexes; Determine a change value of the target characteristic index after the vehicle travels according to the travel probability and the shortest driving path; The charging load prediction model is constructed according to the change value corresponding to each of the vehicles.

7. The method according to claim 6, characterized in that The step of selecting the target characteristic index corresponding to the vehicle type from the driving characteristic indexes includes: If the vehicle type indicates that the vehicle is a private car, the vehicle state of charge and the destination stay time are selected from the driving characteristic indicators, and the vehicle state of charge and the destination stay time are used as target characteristic indicators; otherwise, the vehicle state of charge and the vehicle departure time are selected from the driving characteristic indicators, and the vehicle state of charge and the vehicle departure time are used as target characteristic indicators.

8. A device for determining a charging station planning model, characterized in that: include: A first determination module is used to determine the driving characteristic index, travel probability and shortest driving path of the electric vehicles included in the electric vehicle set to be analyzed; A first construction module is used to construct a charging load prediction model according to the driving characteristic index, the travel probability and the shortest driving path, wherein the charging load prediction model is a model that reflects the charging demand in combination with the temporal and spatial distribution characteristics; The second construction module is used to construct an upper model according to the annual average resource consumption of the charging station and the annual average resource loss of the electric vehicle, and use the charging load prediction model as a constraint condition of the upper model; A second determination module is used to determine a lower-level model and use the lower-level model as a stability constraint condition of the upper-level model, wherein the lower-level model is a model combining seasonal distribution network operation resource consumption and carbon emission resource consumption; The third determination module is used to determine the optimal solution of the upper model, and use the upper model after determining the optimal solution as the charging station planning model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method according to any one of claims 1 to 7 when executed.

11. A computer program product, characterized in that The computer program product comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images