Charging station planning method and system based on renewable energy sources

Abstract

The invention discloses a renewable energy source-based charging station planning method and system. The method comprises the steps of obtaining user charging demand data of a target area; obtaining a charging demand prediction result of the target area according to the user charging demand data and a preset electric vehicle charging demand prediction model; constructing a renewable energy utilization rate model of the target area according to the charging demand prediction result; and determining charging station planning information of the target area according to the renewable energy utilization rate model and a preset charging station comprehensive economic cost model. The method can reflect the charging behaviors of regional electric vehicle users in different scenes, achieves the precise prediction of the charging demands of the users, solves the problem of unstable power supply of the charging of the electric vehicles through a renewable energy utilization rate model, and balances the economy of a charging station and the renewable energy utilization rate.

Description

Technical Field

[0001] The present invention relates to the field of vehicle charging technology, and in particular to a charging station planning method and system based on renewable energy. Background Art

[0002] Electric vehicles (EVs), powered by electricity, have become a key development direction in the transportation sector. As the number of EVs surges year by year, existing technologies plan the capacity and location of charging stations by predicting user charging demand. However, these predictions fail to account for the variability in user charging behavior across different scenarios, making them difficult to accurately predict. Furthermore, the large-scale integration of intermittent and random renewable energy sources, such as photovoltaics and wind turbines, poses significant challenges to the regulation of the power system. For example, when renewable energy generation is abundant, there may be a power surplus; however, when generation is insufficient, it is difficult to meet the charging needs of EVs, resulting in unstable power supply for EV charging. Summary of the Invention

[0003] The present invention provides a charging station planning method and system based on renewable energy. Through user charging demand data and a preset electric vehicle charging demand prediction model, a charging demand prediction result is obtained to construct a renewable energy utilization model and determine the planning information of the charging station. It can reflect the charging behavior of regional electric vehicle users in different scenarios, realize accurate prediction of user charging demand, and solve the problem of unstable power supply faced by electric vehicle charging through the renewable energy utilization model.

[0004] To achieve the above objectives, an embodiment of the present invention provides a method for planning charging stations based on renewable energy, comprising: Obtain user charging demand data in the target area; Obtaining a charging demand prediction result for the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model; Constructing a renewable energy utilization rate model for the target area based on the charging demand prediction result; The charging station planning information of the target area is determined according to the renewable energy utilization rate model and a preset comprehensive economic cost model of the charging station.

[0005] As an improvement to the above solution, obtaining the charging demand prediction result of the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model includes: Inputting the user charging demand data into a preset electric vehicle charging demand prediction model to determine the correlation between the user charging demand data and the charging demand prediction result; Establishing a loss function of a preset electric vehicle charging demand prediction model based on the correlation relationship; The preset electric vehicle charging demand prediction model is predicted according to the loss function to obtain the charging demand prediction result of the target area.

[0006] As an improvement to the above solution, the step of constructing a renewable energy utilization rate model for the target area based on the charging demand prediction result includes: Clustering the charging demand prediction results to obtain a set of typical charging scenarios for the target area; A renewable energy utilization rate model for the target area is constructed based on the charging demand prediction results of each typical charging scenario in the typical charging scenario set, as well as the energy load data of the target area and the charging and discharging power of electric vehicles.

[0007] As an improvement to the above solution, determining the charging station planning information of the target area based on the renewable energy utilization rate model and a preset charging station comprehensive economic cost model includes: Constructing a charging station planning model for the target area based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations; A multi-objective evolutionary algorithm is used to iteratively solve the charging station planning model to obtain the charging station planning information of the target area.

[0008] As an improvement to the above solution, the charging station planning model for the target area is constructed based on the renewable energy utilization model and the preset comprehensive economic cost model of the charging station, including: Constructing an energy storage cost model, a user charging decision model, and a charging station investment cost model for the target area; Constructing a preset comprehensive economic cost model of charging stations in the target area based on the energy storage cost model, the user charging decision model, and the charging station investment cost model; A charging station planning model for the target area is constructed based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations.

[0009] As an improvement to the above solution, the user charging decision model is constructed through the electric vehicle charging cost model of the target area.

[0010] To achieve the above objectives, an embodiment of the present invention provides a charging station planning system based on renewable energy, including: A charging demand data acquisition module is used to obtain user charging demand data in the target area; A charging demand result prediction module, configured to obtain a charging demand prediction result for the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model; An energy utilization model building module, configured to build a renewable energy utilization rate model for the target area based on the charging demand prediction result; The charging planning information determination module is used to determine the charging station planning information of the target area according to the renewable energy utilization rate model and a preset charging station comprehensive economic cost model.

[0011] As an improvement to the above solution, the charging demand result prediction module is used to: Inputting the user charging demand data into a preset electric vehicle charging demand prediction model to determine the correlation between the user charging demand data and the charging demand prediction result; Establishing a loss function of a preset electric vehicle charging demand prediction model based on the correlation relationship; The preset electric vehicle charging demand prediction model is predicted according to the loss function to obtain the charging demand prediction result of the target area.

[0012] As an improvement to the above solution, the energy utilization model construction module is used to: Clustering the charging demand prediction results to obtain a set of typical charging scenarios for the target area; A renewable energy utilization rate model for the target area is constructed based on the charging demand prediction results of each typical charging scenario in the typical charging scenario set, as well as the energy load data of the target area and the charging and discharging power of electric vehicles.

[0013] As an improvement to the above solution, the charging plan information determination module is configured to: Constructing a charging station planning model for the target area based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations; A multi-objective evolutionary algorithm is used to iteratively solve the charging station planning model to obtain the charging station planning information of the target area.

[0014] Compared with the prior art, the embodiment of the present invention discloses a method and system for planning charging stations based on renewable energy, which obtains user charging demand data in a target area; obtains charging demand forecast results for the target area based on the user charging demand data and a preset electric vehicle charging demand forecast model; constructs a renewable energy utilization model for the target area based on the charging demand forecast results; and determines charging station planning information for the target area based on the renewable energy utilization model and a preset charging station comprehensive economic cost model. The method and system can obtain charging demand forecast results based on user charging demand data and a preset electric vehicle charging demand forecast model to construct a renewable energy utilization model and determine charging station planning information, thereby reflecting the charging behavior of regional electric vehicle users in different scenarios, achieving accurate prediction of user charging demand, and solving the problem of unstable power supply faced by electric vehicle charging through the renewable energy utilization model, thereby balancing the economic efficiency of charging stations and renewable energy utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a method for planning a charging station based on renewable energy provided by an embodiment of the present invention; Figure 2 This is a structural diagram of a charging station planning system based on renewable energy provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0017] It should be noted that the terms "comprises" and "specifically" and any variations thereof in the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or are inherent to these processes, methods, products or apparatuses.

[0018] See also Figure 1 , Figure 1 : is a flow chart of a method for planning a charging station based on renewable energy provided by an embodiment of the present invention. The method for planning a charging station based on renewable energy includes: S1, obtaining user charging demand data in the target area; S2, obtaining a charging demand prediction result for the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model; S3, constructing a renewable energy utilization rate model for the target area based on the charging demand prediction result; S4: Determine the charging station planning information of the target area according to the renewable energy utilization rate model and a preset comprehensive economic cost model of the charging station.

[0019] Illustratively, the renewable energy-based charging station planning method according to the embodiment of the present invention is implemented by a charging station planning server, which is capable of exchanging information with target users. The charging station planning server obtains user charging demand data of the target area (such as meteorological data, date type, electric vehicle charging time, charging power, battery state of charge, charging pile power, etc.). It can be understood that the user charging demand data reflects the differences in charging behaviors of regional electric vehicle users in different scenarios; based on the user charging demand data and the preset electric vehicle charging demand prediction model, the charging demand prediction result of the target area is obtained; wherein, the preset electric vehicle charging demand prediction model is established by using a physical information neural network, and the electric vehicle charging demand prediction model is trained by using historical user charging demand data until the electric vehicle charging demand prediction model converges, thereby obtaining the preset electric vehicle charging demand prediction model, so the preset electric vehicle charging demand prediction model can be pre-trained; based on the charging demand prediction result, as well as the energy load data of the target area and the charging and discharging power of the electric vehicle, a renewable energy utilization model of the target area is constructed; based on the renewable energy utilization model and the preset charging station comprehensive economic cost model, the charging station planning information of the target area is determined using a multi-objective evolutionary algorithm. The embodiment of the present invention can obtain charging demand prediction results through user charging demand data and a preset electric vehicle charging demand prediction model to construct a renewable energy utilization model and determine the planning information of charging stations, so as to reflect the charging behavior of regional electric vehicle users in different scenarios, realize accurate prediction of user charging demand, and solve the problem of unstable power supply faced by electric vehicle charging through the renewable energy utilization model, so as to balance the economy of charging stations and renewable energy utilization.

[0020] For example, meteorological data (such as temperature, precipitation, and sunshine duration), date types (weekdays, weekends, and holidays), electric vehicle charging time, battery state of charge, and charging station power are collected from the target area as input vectors for a pre-set electric vehicle charging demand prediction model. The correlation between these input variables and the charging demand prediction results is analyzed, and a physical information neural network is used to establish the loss function of the pre-set electric vehicle charging demand prediction model for model training and prediction. For example, analysis revealed that during holidays, electric vehicle charging demand in areas near tourist attractions increases significantly due to the increase in tourists. By learning this pattern, the model can more accurately predict charging demand in different scenarios. Based on the charging demand prediction results, a Gaussian mixture model (GMM) is used for clustering. The target area is divided into functional areas, such as commercial, residential, and industrial areas. By combining different time periods, a set of typical charging scenarios for each functional area and time period throughout the year is obtained. For example, in commercial areas, charging demand during weekdays is mainly concentrated in the lunchtime and after-get off work hours. Clustering can clearly identify these typical charging scenarios. Based on the charging demand forecast results for each typical charging scenario in the set of typical charging scenarios, as well as the target area's energy load data (grid load curve, renewable energy output (such as distributed photovoltaic and small wind power generation), and energy storage), and the charging and discharging power of electric vehicles, a renewable energy utilization model for the target area is constructed. For example, during a period of time when renewable energy generation in the target area is high, grid load is low, and charging demand is high, the utilization of renewable energy during charging can be improved by adjusting the charging and discharging strategies of energy storage and electric vehicles, thereby achieving a rational allocation of energy. A pre-defined comprehensive economic cost model for charging stations is established by combining energy storage costs, electric vehicle charging costs, costs influenced by user charging decisions, and the electricity purchase costs of charging piles. This model comprehensively assesses the operating costs of charging stations, providing a basis for formulating reasonable charging strategies and optimizing operational management. Based on the renewable energy utilization model and the pre-defined comprehensive economic cost model for charging stations, a planning objective function for the charging station planning model for the target area is constructed, such as one with the goals of maximizing renewable energy utilization and minimizing comprehensive economic costs. When planning charging stations in target areas, adjusting the weights of the planning objective function can balance the relationship between renewable energy utilization and economic costs, ultimately finding the optimal planning solution. Because the charging station planning model is a mixed-integer nonlinear programming problem, the concept of Pareto optimality can be utilized. Through multiple iterations of a multi-objective evolutionary algorithm, various constraints can be considered to ultimately determine planning information for charging stations in different areas (such as the optimal location and number of stations).

[0021] Specifically, step S2 includes: S21, inputting the user charging demand data into a preset electric vehicle charging demand prediction model to determine a correlation between the user charging demand data and a charging demand prediction result; S22, establishing a loss function of a preset electric vehicle charging demand prediction model based on the correlation relationship; S23 , predicting a preset electric vehicle charging demand prediction model according to the loss function to obtain a charging demand prediction result of the target area.

[0022] For example, meteorological data is collected, covering factors such as temperature, humidity, and weather conditions, as these factors can influence user travel and charging needs. For example, users may be more inclined to charge earlier or later during extreme weather conditions. Day types are clearly defined, distinguishing between weekdays, weekends, and holidays, as user travel patterns and charging behaviors vary significantly across different day types. Electric vehicle charging times are recorded to analyze charging frequency during different time periods. Battery state of charge is monitored to understand the vehicle's remaining charge level. Charging station power levels are monitored, as their size influences charging time and efficiency. The collected data is cleaned to remove duplicate and erroneous data, and then normalized to bring data of varying dimensions to a consistent scale, improving data quality and model training effectiveness. The preprocessed data is used as input vectors and fed into a pre-defined electric vehicle charging demand prediction model. The model is constructed based on a physical information neural network, which establishes a loss function by determining the correlation between input variables and predicted charging demand. During training, network parameters are continuously adjusted and the loss function optimized, enabling the model to learn complex patterns and features in the data, such as identifying the correlation between holidays and high charging demand in specific areas. During training, methods such as cross-validation can be used to divide the model into training and validation sets to prevent overfitting, enhance its generalization capabilities, and ensure good predictive performance on diverse data. After training is complete and the model meets performance standards, relevant data for real-time or future forecasts for the target area is input. The model then calculates and infers based on the learned patterns and characteristics, outputting a forecast of charging demand for the target area. These results may include charging demand for different time periods and functional areas, presented in numerical form. This provides a key basis for charging station planning, power allocation, and other aspects, helping to optimize resource allocation and alleviate charging challenges.

[0023] It is worth noting that the loss function measures the difference between the model's predicted value and the true value, while also incorporating physical constraint information so that the model not only fits the data but also conforms to physical laws. By summing these physical constraint terms and combining them with the data fitting terms to form a loss function, the model can take into account both data fitting and physical law compliance during training. The loss function is expressed as: , (1) Where, Represents the data fitting term, which is used to measure the model prediction Charging demand forecast value With the True observations The difference between The sum of the squares of the differences between the predicted and true values for each training sample reflects how well the model fits the known data. The squaring operation is used to amplify the error, making the model pay more attention to data points with large prediction deviations, and to encourage the model to adjust parameters to reduce the difference during training. represents the physical constraint term, which is used to incorporate physical laws into the model; is the dimension of the input vector; For the The total number of dimensional input vectors; represents the correlation coefficient; It is a function, usually an activation function, used to transform or filter the physical constraints. ; Indicates at point The dependent variable For independent variables The partial derivative of For the The manually input part of the training sample corresponds to data points related to physical constraints.

[0024] The physical information neural network in the embodiment of the present invention combines physical experience with data-driven methods to explore the complex nonlinear relationship between input features and charging demand. From the two levels of physical principles and data-driven methods, it can more realistically reflect the charging behavior of electric vehicle users under different traffic conditions, climatic conditions, and holiday scenarios, improve the accuracy of charging demand prediction, and achieve accurate prediction of user charging demand, thereby providing reliable data support for subsequent charging station planning.

[0025] Specifically, step S3 includes: S31, clustering the charging demand prediction results to obtain a set of typical charging scenarios for the target area; S32: Constructing a renewable energy utilization rate model for the target area based on the charging demand prediction result of each typical charging scenario in the typical charging scenario set, as well as the energy load data of the target area and the charging and discharging power of electric vehicles.

[0026] For example, a pre-set electric vehicle charging demand forecasting model is used to obtain charging demand forecast data for different time periods and functional areas. This data reflects the charging power demand of electric vehicle users within the target area. Energy load data for the target area (e.g., grid load curve, renewable energy output, and energy storage) is collected. The grid load data for the target area at different time periods is collected to form a grid load curve. This curve illustrates the changes in grid load at each moment and is crucial for assessing the role of renewable energy in meeting grid demand. The power output data of various renewable energy sources (e.g., photovoltaics and wind turbines) within the target area at different times is compiled. Due to the intermittent and random nature of renewable energy, its output fluctuates over time and with factors such as weather. The charging and discharging power of energy storage devices during each time period is determined, as well as the power changes during the charging and discharging process of electric vehicles. The charging and discharging behavior of energy storage and electric vehicles can regulate the balance of power supply and demand. The collected data is cleaned, organized, and standardized to ensure accuracy and consistency. For example, outliers are removed, missing values are filled, and data from different sources are standardized to the same time scale and units. A renewable energy utilization model for the target area is constructed based on these data. It is understandable that since factors such as charging demand and renewable energy output will change over time, the model needs to be updated and adjusted regularly. The model should be continuously optimized based on new data and actual operating conditions to ensure that the model can accurately reflect the renewable energy utilization status in the target area and provide continuous and effective support for charging station planning.

[0027] For example, the Gaussian mixture model (GMM) is used to cluster the charging demand forecast results to obtain a set of typical charging scenarios for each functional area and time period within the target area within a year. Based on the charging demand forecast results for each typical charging scenario in this set, combined with the grid load curve, renewable energy output, energy storage, and the charging and discharging power of electric vehicles, the expression for the renewable energy utilization model is obtained as follows: , (2) Where, is the utilization rate of renewable energy; The total time period for charging the vehicle can be set to 24 hours; represent Load demand during the time period; For The total number of electric vehicles charged during the time period; Representative Electric vehicles in The charging and discharging power of the time period, For energy storage The charging and discharging power of the time period, For renewable energy Output during a time period.

[0028] Specifically, step S4 includes: S41, constructing a charging station planning model for the target area based on the renewable energy utilization model and a preset charging station comprehensive economic cost model; S42: Iteratively solving the charging station planning model using a multi-objective evolutionary algorithm to obtain charging station planning information for the target area.

[0029] For example, when determining charging station planning information for a target area, a renewable energy utilization model and a comprehensive economic cost model for charging stations are two key elements. The former focuses on the efficiency of renewable energy utilization during the charging process, while the latter prioritizes the economic inputs and outputs of charging stations. Based on the renewable energy utilization model and the pre-set comprehensive economic cost model for charging stations, an objective function for the charging station planning model for the target area is constructed. This objective function aims to balance renewable energy utilization and economic costs, improving renewable energy utilization while reducing the comprehensive economic costs of charging stations. Constraints (such as power constraints, cost constraints, and demand constraints) are set for the charging station planning model. Power constraints consider grid capacity and equipment performance to ensure that the total charging power of the charging station, renewable energy generation power, and energy storage charging and discharging power are within safety and equipment limits. For example, the total charging power of the charging station cannot exceed the grid's power supply capacity during a certain period, and the energy storage charging and discharging power must be within its rated power. Cost constraints, based on the investment budget, limit the total energy storage cost, charging station construction cost, and operation and maintenance costs to within an acceptable range. For example, the sum of the energy storage investment cost and the charging station construction cost cannot exceed a pre-set funding limit. Ensure that the planned charging stations can meet the charging needs of electric vehicles within the target area. Demand constraints, based on historical and predicted data on electric vehicle ownership and charging demand distribution, ensure a reasonable number and layout of charging piles, reducing user waiting times. Because the charging station planning model is a mixed-integer nonlinear programming problem, a multi-objective evolutionary algorithm (such as NSGA-II) is employed to iteratively solve the problem based on the concept of Pareto optimality. During the solution process, the algorithm continuously adjusts decision variables such as the charging station location (represented by geographic coordinates or regional divisions) and the number of charging piles to find a solution that optimizes the objective function while satisfying the constraints. After multiple iterations, a series of Pareto optimal solutions are obtained. These solutions represent different charging station planning scenarios, including different combinations of location and number of charging piles. Decision makers can then select the most appropriate planning scenario based on their actual situation, thereby determining the charging station planning information (such as the charging station location and number of charging piles) for the target area.

[0030] Among them, the objective function The expression is: , (3) Where, Represents the comprehensive economic cost of the charging station.

[0031] More specifically, step S41 includes: S411, constructing an energy storage cost model, a user charging decision model, and a charging station investment cost model for the target area; S412: Constructing a preset comprehensive economic cost model for charging stations in the target area based on the energy storage cost model, the user charging decision model, and the charging station investment cost model; S413: Constructing a charging station planning model for the target area according to the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations.

[0032] More specifically, the user charging decision model is constructed through the electric vehicle charging cost model of the target area.

[0033] For example, the energy storage cost model is mainly composed of energy storage investment cost and energy storage operation and maintenance cost; the energy storage investment cost is determined by the purchased energy storage capacity; the energy storage operation and maintenance cost is determined by the energy storage charging and discharging efficiency loss. The expression of the energy storage cost model is: , (4) Where, is the energy storage cost; The periodic time period can be set to 365 days; Indicates the The energy storage cost during the charging and discharging time of each energy storage; is the charging and discharging time of energy storage; is the energy storage investment cost coefficient; is the energy storage operation and maintenance cost coefficient; is the capacity of energy storage; The number of charge and discharge cycles of energy storage.

[0034] The user charging decision model is constructed based on the electric vehicle charging cost model in the target area, and a mixed logit model is used to describe the bounded rational behavior of users in charging decisions. The expression of the user charging decision model is: , (5) Where, For the User charging decisions in typical charging scenarios; A collection of typical charging scenarios; is a natural constant; Represents the user's rationality; the cost of charging electric vehicles; Represents the total number of charging stations to be selected by the user; For the The cost of charging electric vehicles at each charging station; Represents the first The time when a typical charging scenario occurs; For The total number of electric vehicles that require charging during a time period.

[0035] The charging cost model of electric vehicles is mainly composed of charging prices , additional driving costs , Charging queue costs and environmental added value The expression of the electric vehicle charging cost model is determined as follows: , (6) Where, is the rated power of the charging pile; is the total charging time; Time-of-use electricity price for electric vehicles; The charging time period of the electric vehicle at the charging station; represents the initial travel time; is the driving time after detour; Represents the average time cost of users; Represents the user's queue time; Score points of interest (POIs) near the initial charging station; for The weight of the class interest point; Near a charging station the number of class interest points; 、 、 and Charging price , additional driving costs , Charging queue costs and environmental added value cost coefficient.

[0036] The charging station investment cost model mainly includes the construction cost and operation and maintenance cost of the charging station. The expression of the charging station investment cost model is: , (7) Where, Investing in charging stations; It is a 0-1 variable, representing whether Build charging stations; Represents the number of additional charging stations; and They represent the land area required to build a charging station and the land area required to add charging piles respectively; Represents the land rental cost per unit area; and Represent the operation and maintenance costs of charging stations and charging piles respectively; Represents the unit price of the charging pile; Represents the supporting construction cost of the power grid corresponding to unit capacity.

[0037] Based on the above energy storage cost model, user charging decision model and charging station investment cost model, the comprehensive economic cost model of the charging station is expressed as follows: , (8) Where, The cost of purchasing electricity for the charging pile.

[0038] The embodiment of the present invention discloses a method for planning charging stations based on renewable energy, which obtains user charging demand data for a target area; obtains a charging demand forecast result for the target area based on the user charging demand data and a preset electric vehicle charging demand forecast model; constructs a renewable energy utilization model for the target area based on the charging demand forecast result; and determines charging station planning information for the target area based on the renewable energy utilization model and a preset charging station comprehensive economic cost model. The method can obtain the charging demand forecast result based on the user charging demand data and the preset electric vehicle charging demand forecast model to construct a renewable energy utilization model and determine charging station planning information, thereby reflecting the charging behavior of electric vehicle users in the region under different scenarios, achieving accurate prediction of user charging demand, and solving the problem of unstable power supply faced by electric vehicle charging through the renewable energy utilization model, thereby balancing the economic efficiency of the charging station and the renewable energy utilization rate.

[0039] See also Figure 2 , Figure 2 1 is a schematic diagram of a charging station planning system 10 based on renewable energy provided by an embodiment of the present invention. The charging station planning system 10 based on renewable energy includes: A charging demand data acquisition module 11 is used to acquire charging demand data of users in a target area; A charging demand result prediction module 12 is configured to obtain a charging demand prediction result of the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model; An energy utilization model building module 13 is configured to build a renewable energy utilization rate model for the target area based on the charging demand prediction result; The charging planning information determination module 14 is configured to determine the charging station planning information of the target area according to the renewable energy utilization rate model and a preset charging station comprehensive economic cost model.

[0040] Specifically, the charging demand result prediction module 12 is used to: Inputting the user charging demand data into a preset electric vehicle charging demand prediction model to determine the correlation between the user charging demand data and the charging demand prediction result; Establishing a loss function of a preset electric vehicle charging demand prediction model based on the correlation relationship; The preset electric vehicle charging demand prediction model is predicted according to the loss function to obtain the charging demand prediction result of the target area.

[0041] Specifically, the energy utilization model building module 13 is used to: Clustering the charging demand prediction results to obtain a set of typical charging scenarios for the target area; A renewable energy utilization rate model for the target area is constructed based on the charging demand prediction results of each typical charging scenario in the typical charging scenario set, as well as the energy load data of the target area and the charging and discharging power of electric vehicles.

[0042] Specifically, the charging plan information determination module 14 is used to: Constructing a charging station planning model for the target area based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations; A multi-objective evolutionary algorithm is used to iteratively solve the charging station planning model to obtain the charging station planning information of the target area.

[0043] A charging station planning system 10 based on renewable energy provided in an embodiment of the present invention can implement all processes of the charging station planning method based on renewable energy of the above-mentioned embodiment. The functions of each module in the system and the technical effects achieved are respectively the same as the functions and technical effects achieved by the charging station planning method based on renewable energy of the above-mentioned embodiment, and will not be repeated here.

[0044] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A charging station planning method based on renewable energy, characterized in that: include: Obtain user charging demand data in the target area; Obtaining a charging demand prediction result for the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model; Constructing a renewable energy utilization rate model for the target area based on the charging demand prediction result; The charging station planning information of the target area is determined according to the renewable energy utilization rate model and a preset comprehensive economic cost model of the charging station.

2. The method for planning a charging station based on renewable energy according to claim 1, wherein: Obtaining a charging demand prediction result for the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model includes: Inputting the user charging demand data into a preset electric vehicle charging demand prediction model to determine the correlation between the user charging demand data and the charging demand prediction result; Establishing a loss function of a preset electric vehicle charging demand prediction model based on the correlation relationship; The preset electric vehicle charging demand prediction model is predicted according to the loss function to obtain the charging demand prediction result of the target area.

3. The method for planning a charging station based on renewable energy according to claim 1, wherein: The step of constructing the renewable energy utilization rate model for the target area according to the charging demand prediction result includes: Clustering the charging demand prediction results to obtain a set of typical charging scenarios for the target area; A renewable energy utilization rate model for the target area is constructed based on the charging demand prediction results of each typical charging scenario in the typical charging scenario set, as well as the energy load data of the target area and the charging and discharging power of electric vehicles.

4. The method for planning a charging station based on renewable energy according to claim 1, wherein: The determining of the charging station planning information of the target area according to the renewable energy utilization rate model and the preset charging station comprehensive economic cost model includes: Constructing a charging station planning model for the target area based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations; A multi-objective evolutionary algorithm is used to iteratively solve the charging station planning model to obtain the charging station planning information of the target area.

5. The method for planning a charging station based on renewable energy according to claim 4, wherein: The step of constructing a charging station planning model for the target area based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations includes: Constructing an energy storage cost model, a user charging decision model, and a charging station investment cost model for the target area; Constructing a preset comprehensive economic cost model of charging stations in the target area based on the energy storage cost model, the user charging decision model, and the charging station investment cost model; A charging station planning model for the target area is constructed based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations.

6. The method for planning a charging station based on renewable energy according to claim 5, wherein: The user charging decision model is constructed by using the electric vehicle charging cost model of the target area.

7. A charging station planning system based on renewable energy, characterized in that: include: A charging demand data acquisition module is used to obtain user charging demand data in the target area; A charging demand result prediction module, configured to obtain a charging demand prediction result for the target area based on the user charging demand data and a preset electric vehicle charging demand prediction model; An energy utilization model building module, configured to build a renewable energy utilization rate model for the target area based on the charging demand prediction result; The charging planning information determination module is used to determine the charging station planning information of the target area according to the renewable energy utilization rate model and a preset charging station comprehensive economic cost model.

8. The renewable energy-based charging station planning system according to claim 7, characterized in that: The charging demand result prediction module is used to: Inputting the user charging demand data into a preset electric vehicle charging demand prediction model to determine the correlation between the user charging demand data and the charging demand prediction result; Establishing a loss function of a preset electric vehicle charging demand prediction model based on the correlation relationship; The preset electric vehicle charging demand prediction model is predicted according to the loss function to obtain the charging demand prediction result of the target area.

9. The renewable energy-based charging station planning system according to claim 7, characterized in that: The energy utilization model construction module is used to: Clustering the charging demand prediction results to obtain a set of typical charging scenarios for the target area; A renewable energy utilization rate model for the target area is constructed based on the charging demand prediction results of each typical charging scenario in the typical charging scenario set, as well as the energy load data of the target area and the charging and discharging power of electric vehicles.

10. The renewable energy-based charging station planning system according to claim 7, characterized in that: The charging plan information determination module is used to: Constructing a charging station planning model for the target area based on the renewable energy utilization rate model and a preset comprehensive economic cost model for charging stations; A multi-objective evolutionary algorithm is used to iteratively solve the charging station planning model to obtain the charging station planning information of the target area.

Images