Battery intelligent charging and discharging optimization method and system for new energy vehicle charging station

Abstract

The application relates to the technical field of new energy automobile charging management, in particular to a new energy automobile charging station battery intelligent charging and discharging optimization method and system, which comprises the following steps: a long short-term neural network (LSTM) model is used to construct a charging demand prediction model to predict charging demand in a future time period; a multi-type optimized charging and discharging strategy is constructed, including a peak clipping and valley filling strategy and a new energy consumption strategy; a battery charging efficiency evaluation model is constructed to monitor charging efficiency in real time and timely warn of abnormalities; based on the evaluated battery charging efficiency, a battery charging scheduling model of the charging station is constructed, and a globally optimal charging power distribution scheme is solved when multiple batteries are simultaneously charged; the application comprehensively considers charging demand prediction, charging and discharging strategy optimization, battery efficiency evaluation and charging scheduling and the like, and provides an effective solution for intelligent operation of a new energy automobile charging station.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle charging management technology, specifically to a method and system for optimizing intelligent charging and discharging of batteries in new energy vehicle charging stations. Background Technology

[0002] With the increasing popularity of new energy vehicles, the construction and operation of charging stations face numerous challenges. To improve the operational efficiency of charging stations and optimize resource allocation, it is necessary to accurately predict charging demand over a future period.

[0003] Charging stations face challenges such as fluctuating grid load and unstable renewable energy generation during operation. To balance grid load, charging stations need to rationally plan charging and discharging strategies, reducing charging during peak load periods and increasing charging during off-peak periods. Simultaneously, to promote the integration of renewable energy, charging stations need to prioritize renewable energy generation. However, existing charging and discharging strategies are mostly based on fixed rules, lacking flexibility and adaptability, and struggling to cope with dynamically changing grid conditions and renewable energy generation. During battery charging, charging efficiency is affected by parameters such as voltage, current, and temperature. When a charging station charges multiple batteries simultaneously, how to rationally allocate charging power is also a critical issue. Different batteries have different charging efficiencies and health states; simply distributing charging power evenly may lead to low overall charging efficiency and prolonged charging time. Therefore, it is necessary to dynamically adjust the charging power allocation based on the real-time status of the batteries and the charging station's load to achieve global optimization.

[0004] The operation of new energy vehicle charging stations faces multiple challenges, including charging demand forecasting, charging and discharging strategy optimization, battery charging efficiency assessment, and charging power scheduling. Traditional methods are insufficient to effectively address these challenges, necessitating the development of intelligent optimization methods to improve the operational efficiency and service quality of charging stations.

[0005] In view of this, the present invention proposes a method and system for optimizing intelligent charging and discharging of batteries in new energy vehicle charging stations. Summary of the Invention

[0006] To achieve the above objectives, this invention provides a method and system for intelligent charging and discharging optimization of batteries in new energy vehicle charging stations. The specific technical solution is as follows: The method for intelligent charging and discharging optimization of batteries in new energy vehicle charging stations includes:

[0007] A charging demand prediction model based on the Long Short-Term Neural Network (LSTM) model is constructed. By utilizing historical charging data and combining date and weather factors, a charging demand prediction model is established to predict the charging demand of new energy vehicles in the future.

[0008] Based on the charging demand of new energy vehicles in the future, we will construct multi-type optimized charging and discharging strategies for new energy vehicle charging stations, including peak shaving and valley filling strategies and new energy consumption strategies.

[0009] A battery charging efficiency evaluation model is constructed. The battery is charged using constant charging data over a period of time. Data on the battery's voltage, current, and temperature under constant charging data are collected to evaluate the battery charging efficiency and provide timely warnings when anomalies are detected.

[0010] Based on the evaluated battery charging efficiency, a battery charging scheduling model for the charging station is constructed, and the globally optimal charging power allocation scheme is solved when charging multiple batteries.

[0011] Preferably, historical charging data is acquired, including N charging records. The charging records include information on real-time charging power consumption, peak charging power consumption, and charging amount. The charging records are then integrated into a dataset.

[0012] Collect date type and weather data related to charging needs, and merge them with the charging record dataset to form a feature dataset;

[0013] A long short-term neural network (LSTM) model is constructed as a charging demand prediction model; the output layer of the LSTM model is defined, the output dimension is set to the length p of the future time period, and the mean squared error (MSE) is selected as the loss function.

[0014] The feature dataset X and the corresponding charging demand value Y are divided into a training set and a test set according to a predetermined ratio. The LSTM model is trained using the training set data, and the model parameters are updated through the backpropagation algorithm and the optimizer.

[0015] The trained LSTM model is evaluated using test set data, and the model's predictive performance metrics on the test set are calculated. Based on the model's predictive performance, the model's hyperparameters are adjusted, and the training and evaluation process is repeated until the predictive performance metrics meet the requirements.

[0016] Charging demand prediction is performed based on a trained charging demand prediction model. For a given future time period T = t1, t2, ..., t p Construct feature vectors for date type and weather factors. As input to the charging demand forecasting model; t p For the t-th time period in the future p At a certain point in time, For the tth p Feature vectors of date type and weather factors at each point in time;

[0017] Using a trained charging demand prediction model, the feature vector X for future time periods is...T To make predictions, we can obtain the predicted charging demand for future periods. in Indicates the t-th time period in the future p Forecast values ​​of charging demand at each point in time;

[0018] Charging demand forecast The output serves as the input for subsequent optimization of the charging and discharging strategy.

[0019] Preferably, multiple optimized charging and discharging strategies are used to construct new energy vehicle charging stations, including peak shaving and valley filling strategies and new energy consumption strategies;

[0020] The objective function of the peak shaving and valley filling strategy is defined as follows: The objective is to minimize the charging load at charging stations during peak hours and maximize the charging amount during off-peak hours. The objective function of the peak shaving and valley filling strategy is expressed as: Where t is the time within the future time period T, T peak T represents the set of peak periods. valley P represents the set of low-level periods. t This represents the charging power at a future time t;

[0021] The constraints of the peak shaving and valley filling strategy include the following: charging power constraint: 0 ≤ P t ≤P max , And charging amount constraints: ∑ t∈T P t Δt=E demand Among them, P max Let E represent the maximum charging power of the charging station, T represent the set of future time periods, Δt represent the time interval, and E represent the maximum charging power of the charging station. demand This represents the predicted total charging demand.

[0022] Preferably, the objective function of the renewable energy consumption strategy is defined, with the objective of maximizing the amount of renewable energy consumed by charging stations; the objective function of the renewable energy consumption strategy is expressed as: max∑ t∈T P t ·R t , where R t This represents the proportion of renewable energy generation to total electricity generation at future time t.

[0023] The constraints of the renewable energy consumption strategy include charging power constraints: 0 ≤ P t ≤P max , Charging amount constraint: ∑ t∈T P t Δt=E demand And the constraint on renewable energy generation: 0≤R t≤1,

[0024] Preferably, the objective functions of the peak shaving and valley filling strategy and the new energy consumption strategy are weighted and summed using a weighted summation method to construct a multi-objective optimization problem; the objective function after weighted summation is shown below:

[0025]

[0026] Wherein, λ1 and λ2 are the weight coefficients of peak shaving and valley filling strategies and new energy consumption strategies, respectively;

[0027] The constraints for solving the multi-objective optimization problem include the charging power constraint: 0 ≤ P t ≤P max , Charging amount constraint: ∑ t∈T P t Δt=E demand And the renewable energy generation constraint: 0≤R t ≤1,

[0028] Preferably, the battery is charged at a constant rate for a period of time, and the voltage, current and temperature parameters of the charging battery are collected at fixed time intervals Δt during the constant charging process.

[0029] A charging efficiency rating index S is defined to evaluate the charging efficiency of the battery. The value range of the charging efficiency rating index S is [0,1], where S=1 indicates that the battery is fully receiving constant charging output; S=0 indicates that the battery is not receiving any charging output.

[0030] Calculate the cumulative charging output Q during a constant charging process. out and battery cumulative received amount Q in : Among them I out,t Δt is the constant charging output current at time t; Δt is the time interval; K is the total number of sampling points; Among them I in,t It is the actual received current of the battery at time t;

[0031] Calculate the charging efficiency η, which is the cumulative amount of charge received by the battery Q. in With cumulative charging output Q out The ratio:

[0032]

[0033] Constructing the battery charging efficiency threshold η th When η≥η th When η < η, it indicates that the battery charging efficiency is qualified; when η < η thWhen this occurs, it indicates that the battery charging efficiency is unqualified, and a charging warning reminder is issued to the battery.

[0034] Preferably, the objective function of the battery charging scheduling model for the charging station is defined to maximize the weighted total charging efficiency score while satisfying the charging station load constraints. Where M is the total number of batteries in the charging station; w j S is the weighting coefficient of the j-th battery; j P is the charging efficiency rating index for the j-th battery; j It is the charging power allocated to the j-th battery;

[0035] The constraints of the battery charging scheduling model for charging stations include: charging station load constraints: Where P station (t) represents the maximum available charging power of the charging station at time t; battery charging power constraint: 0 ≤ P j ≤P j,max , Where P j,max It is the maximum charging power of the j-th battery; battery charging efficiency constraint: S j ≥S th , Where S th It is the threshold for the battery charging efficiency rating index;

[0036] Solving the battery charging scheduling model for the charging station transforms the optimization problem into a linear programming problem:

[0037]

[0038] The linear programming problem is solved using a linear programming algorithm to obtain the optimal solution P. best =[P′1,P′2...,P′ M ], where P′ M This represents the optimal charging power allocated to the Mth battery;

[0039] When the charging station is not fully loaded, that is No charging power is allocated to the rechargeable battery;

[0040] When the charging station is fully loaded, that is According to the optimal charging power allocation scheme P obtained from the solution best Distribute charging power to each battery. Let represent the optimal charging power allocated to the j-th battery, j∈[1,M].

[0041] A smart charging and discharging optimization system for batteries in new energy vehicle charging stations, which is used to implement the smart charging and discharging optimization method for batteries in new energy vehicle charging stations, includes: a charging demand prediction module, a multi-type optimization module, a charging efficiency evaluation module, and a charging scheduling module.

[0042] The charging demand prediction module is used to construct a charging demand prediction model based on the Long Short-Term Neural Network (LSTM) model. It uses historical charging data, combined with date and weather factors, to establish a charging demand prediction model and predict the charging demand of new energy vehicles in the future.

[0043] The multi-type optimization module constructs multi-type optimized charging and discharging strategies for new energy vehicle charging stations based on the charging demand of new energy vehicles in the future time period, and respectively constructs peak shaving and valley filling strategies and new energy consumption strategies.

[0044] The charging efficiency evaluation module is used to construct a battery charging efficiency evaluation model, charge the battery with constant charging data over a period of time, collect data on the battery's voltage, current, and temperature under constant charging data, evaluate the battery charging efficiency, and issue timely warnings when anomalies are detected.

[0045] The charging scheduling module constructs a battery charging scheduling model for the charging station based on the evaluated battery charging efficiency, and solves the globally optimal charging power allocation scheme when charging multiple batteries.

[0046] An electronic device includes a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations by calling the computer program stored in the memory.

[0047] A computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations.

[0048] The beneficial effects of this invention are as follows: This invention establishes an accurate charging demand prediction model by utilizing historical charging data and combining it with influencing factors such as date and weather; by predicting the charging demand of new energy vehicles in the future, it provides an important basis for the operation and resource allocation of charging stations.

[0049] Based on charging demand forecasting results, this invention constructs peak shaving and valley filling strategies and renewable energy consumption strategies, which can effectively address the problems of grid load fluctuations and the intermittency of renewable energy generation. The peak shaving and valley filling strategy balances the grid load and improves grid operating efficiency by increasing charging during periods of low grid load and reducing charging during periods of high load. The renewable energy consumption strategy promotes the efficient use of renewable energy generation, reduces fossil fuel consumption, and achieves the goals of environmental protection and energy conservation by prioritizing the use of renewable energy generation.

[0050] This invention evaluates the charging efficiency of a battery by collecting data such as voltage, current, and temperature during constant charging. It can also detect abnormalities in the battery charging process in a timely manner, such as decreased charging efficiency or abnormal temperature, thereby providing early warning and ensuring charging safety.

[0051] Based on battery charging efficiency evaluation results, this invention constructs a battery charging scheduling model for charging stations. When multiple batteries are charging simultaneously, it can solve for the globally optimal charging power allocation scheme. By rationally allocating charging power, it can maximize the overall charging efficiency of the charging station and provide users with better charging services. Attached Figure Description

[0052] Figure 1 Flowchart of the intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations provided by the present invention;

[0053] Figure 2 The diagram shows the structure of the intelligent charging and discharging optimization system for new energy vehicle charging stations provided by this invention. Detailed Implementation

[0054] To better understand the invention, various aspects of the invention will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of the invention and are not intended to limit the scope of the invention in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0055] In the accompanying drawings, the size, dimensions, and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustrative purposes only and are not strictly to scale. As used herein, the terms “approximately,” “about,” and similar terms are used to indicate approximation rather than degree, and are intended to illustrate inherent deviations in measured or calculated values ​​that will be recognized by one of ordinary skill in the art. Furthermore, the order in which the steps are described in this invention does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.

[0056] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of the invention, the word "may" is used to mean "one or more embodiments of the invention." And the term "exemplary" is intended to refer to examples or illustrations.

[0057] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formalized sense.

[0058] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0059] Example 1

[0060] Reference Figure 1 This is the first embodiment of the present invention, which provides a method for optimizing the intelligent charging and discharging of batteries in new energy vehicle charging stations.

[0061] S1: Construct a charging demand prediction model based on the Long Short-Term Neural Network (LSTM) model. Utilize historical charging data, combined with date and weather factors, to establish a charging demand prediction model and predict the charging demand of new energy vehicles in the future.

[0062] Acquire historical charging data, including N charging records. Each charging record includes information such as real-time charging power consumption, peak charging power consumption, and charging capacity. Integrate the charging records into a dataset D = {d1, d2, d...} i ,...,d N}, where d i Let N represent the i-th charging record, and N be the total number of charging records.

[0063] Collect date type and weather data related to charging needs, and merge them with the charging record dataset to form a feature dataset X = {x1, x2, x...} i ,...,x N}, where x iLet N represent the feature vector corresponding to the i-th charging record. The feature vector has a dimension of N.

[0064] The feature dataset is normalized to scale the value range of each feature to the interval [0, 1]. The formula is as follows: Where x ij Let x′ represent the j-th feature value of the i-th charging record. ij This represents the normalized eigenvalues.

[0065] Construct a Long Short-Term Neural Network (LSTM) model as a charging demand prediction model; define the input layer of the LSTM model, taking the feature dataset X as input, with the input length being the dimension N of the feature vector; define the hidden layers of the LSTM model, setting an appropriate number of hidden units h and the number of layers l, for example, 2 layers of LSTM, with 100 hidden units in each layer.

[0066] The main calculation formula for LSTM is as follows: Forget gate: f t =σ(W f ·[h t-1 ,x t ]+b f Input gate: i t =σ(W i ·[h t-1 ,x t ]+b i Output gate: o t =σ(W o ·[h t-1 ,x t ]+b o Candidate memory cell status: Memory cell status: Hidden state: h t =o t *tanh(C t ).

[0067] Among them, f t σ represents the output of the forget gate time step, with a value range of [0,1], controlling whether the memory cell state information from the previous time step is forgotten; σ represents the Sigmoid activation function, used to compress the input to the range [0,1]; W f and b f Let h represent the weight matrix and bias term of the forget gate, respectively. t-1 Let x represent the hidden state at the previous time step t-1. t i represents the input vector at the current time step t; t The input gate output represents time step t; W i and b i These represent the weight matrix and bias term of the input gate, respectively;t The output gate represents the output at time step t; W o and b o These represent the weight matrix and bias term of the output gate, respectively; The candidate memory cell state represents the state at time step t, encoding new information at the current time step; tanh represents the hyperbolic tangent activation function, compressing the input to the range [1, 1]; W C and b C C represents the weight matrix and bias term of the candidate memory cells, respectively; t h represents the state of memory cells at time step t; t This represents the hidden state at time step t.

[0068] Define the output layer of the LSTM model and set the output dimension to the length p of the future time period. For example, if the charging demand is predicted for the next 24 hours, the output dimension will be 24. Define the loss function of the LSTM model and choose the mean squared error (MSE) as the loss function.

[0069] The feature dataset X and the corresponding charging demand value Y are divided into a training set X according to a predetermined ratio. train ,Y train and test set X test ,Y test For example, 80% of the data is used as the training set and 20% as the test set; using the training set data X train ,Y train The LSTM model is trained by updating its parameters through backpropagation and an optimizer (such as Adam), iterating until the model converges or reaches a preset number of iterations; the test set data X is then used. test ,Y test The trained LSTM model is evaluated by calculating its prediction performance metrics on the test set, including mean absolute error (MAE) and root mean square error (RMSE). Based on the model's prediction performance, the hyperparameters are adjusted, and the training and evaluation process is repeated until the prediction performance metrics meet the requirements.

[0070] Charging demand prediction is performed based on a trained charging demand prediction model. For a given future time period T = t1, t2, ..., t p Construct feature vectors for date type and weather factors. As input to the charging demand forecasting model; t p For the t-th time period in the future p At a certain point in time, For the tth p Feature vectors of date type and weather factors at each point in time.

[0071] Using a trained charging demand prediction model, the feature vector X for future time periods is... T To make predictions, we can obtain the predicted charging demand for future periods. in Indicates the t-th time period in the future p Forecasted charging demand at specific points in time.

[0072] Charging demand forecast The output serves as the input for subsequent optimization of the charging and discharging strategy.

[0073] Step S1 constructs an LSTM-based charging demand prediction model, combining historical charging data, date, and weather factors to accurately predict the charging demand of new energy vehicles in the future. The prediction results provide reliable input data for subsequent optimization of charging and discharging strategies.

[0074] S2: Based on the charging demand of new energy vehicles in the future time period, construct multi-type optimized charging and discharging strategies for new energy vehicle charging stations, and construct peak shaving and valley filling strategies and new energy consumption strategies respectively to solve the problems of supply and demand imbalance and energy waste.

[0075] The objective function of the peak shaving and valley filling strategy is defined as follows: The objective is to minimize the charging load at charging stations during peak hours and maximize the charging amount during off-peak hours. The objective function of the peak shaving and valley filling strategy is expressed as: Where t is the time within the future time period T, T peak T represents the set of peak periods. valley P represents the set of low-level periods. t This represents the charging power at a future time t.

[0076] The constraints of the peak shaving and valley filling strategy include the following: charging power constraint: 0 ≤ P t ≤P max , And charging amount constraints: ∑ t∈T P t Δt=E demand Among them, P max Let E represent the maximum charging power of the charging station, T represent the set of future time periods, Δt represent the time interval, and E represent the maximum charging power of the charging station. demand This represents the predicted total charging demand.

[0077] A linear programming algorithm is used to solve for the optimal charging power allocation under the peak shaving and valley filling strategy. The objective function and constraints are transformed into a standard linear programming form, and the simplex method is used to solve it, thus obtaining the optimal charging power allocation for each time period. To achieve the goal of peak shaving and valley filling.

[0078] The objective function of the renewable energy consumption strategy is defined as maximizing the amount of renewable energy (such as solar and wind power) consumed by charging stations and reducing curtailment of solar and wind power. The objective function of the renewable energy consumption strategy can be expressed as: max∑ t∈T P t ·R t , where R t This represents the proportion of renewable energy generation to total power generation during time period t.

[0079] The constraints of the renewable energy consumption strategy include charging power constraints: 0 ≤ P t ≤P max , Charging amount constraint: Σ t∈T P t Δt=E demand And the constraint on renewable energy generation: 0≤R t ≤1,

[0080] A nonlinear programming algorithm is used to solve for the optimal charging power allocation in the renewable energy consumption strategy. The objective function and constraints are transformed into a standard nonlinear programming form and solved using a sequential quadratic programming algorithm. The optimal charging power allocation for each time period is then obtained. To achieve the goal of absorbing new energy sources.

[0081] The objective functions of the peak shaving and valley filling strategy and the new energy consumption strategy are weighted and summed using a weighted summation method to construct a multi-objective optimization problem; the objective function after weighted summation is shown below:

[0082]

[0083] Wherein, λ1 and λ2 are the weighting coefficients of the peak shaving and valley filling strategy and the renewable energy consumption strategy, respectively; the weighting coefficients λ1 and λ2 of the peak shaving and valley filling strategy and the renewable energy consumption strategy can be dynamically adjusted according to the actual operation to adapt to changes in charging demand and renewable energy power generation.

[0084] The constraints for solving the multi-objective optimization problem include the charging power constraint: 0 ≤ P t ≤P max , Charging amount constraint: Σ t∈T P t Δt=E demand And the renewable energy generation constraint: 0≤R t ≤1,

[0085] The solution algorithm employs a nonlinear programming approach to solve the multi-objective optimization problem, obtaining the optimal charging power allocation that balances peak shaving and valley filling with renewable energy consumption. Algorithms such as sequential quadratic programming or interior-point methods are used to obtain the optimal charging power allocation for each time period.

[0086] Based on the optimal charging power allocation obtained from the solution Develop corresponding charging strategies and preferential policies to guide electric vehicle users to charge their vehicles during appropriate time periods.

[0087] Step S2, based on predicted charging demand, constructs peak-shaving and valley-filling strategies and renewable energy consumption strategies, and solves for the optimal charging power allocation scheme using linear and nonlinear programming algorithms. The peak-shaving and valley-filling strategy effectively reduces charging load during peak hours and improves charging capacity utilization during off-peak hours. The renewable energy consumption strategy maximizes the absorption of renewable energy by charging stations, reducing the curtailment of solar and wind power.

[0088] S3: Construct a battery charging efficiency evaluation model. Charge the battery with constant charging data over a period of time, collect data on the battery's voltage, current, and temperature under constant charging data, evaluate the battery charging efficiency, and issue timely warnings when anomalies are detected.

[0089] Define a charging efficiency rating index S to evaluate the charging efficiency of the battery; the value range of the charging efficiency rating index S is [0,1], where S=1 indicates that the battery is fully receiving constant charging output; S=0 indicates that the battery is not receiving any charging output.

[0090] Calculate the cumulative charging output Q during a constant charging process. out and battery cumulative received amount Q in : Among them I out,t Δt is the constant charging output current at time t; Δt is the time interval; K is the total number of sampling points; Among them I in,t It is the actual received current of the battery at time t.

[0091] Calculate the charging efficiency η, which is the cumulative amount of charge received by the battery Q. in With cumulative charging output Q out The ratio:

[0092]

[0093] Constructing the battery charging efficiency threshold η th When η≥η th When η < η, it indicates that the battery charging efficiency is qualified; when η < η th When this occurs, it indicates that the battery charging efficiency is unqualified, and a charging warning reminder is issued to the battery.

[0094] Step S3 constructs a battery charging efficiency evaluation model, collects voltage, current, and temperature data of the battery under constant charging conditions, and evaluates the battery's charging efficiency. The charging efficiency score quantifies the battery's ability to receive constant charging output, providing an important reference for the battery's health status. When the charging efficiency falls below a threshold, the model issues a timely warning, effectively preventing abnormal battery charging.

[0095] S4: Based on the evaluated battery charging efficiency, construct a battery charging scheduling model for the charging station, and solve the globally optimal charging power allocation scheme when charging multiple batteries.

[0096] Define the objective function of the battery charging scheduling model for the charging station: maximize the weighted total charging efficiency score while satisfying the charging station load constraints. Where M is the total number of batteries in the charging station; w j S is the weighting coefficient of the j-th battery; j P is the charging efficiency rating index for the j-th battery; j It is the charging power allocated to the j-th battery;

[0097] The constraints of the battery charging scheduling model for charging stations include: charging station load constraints: Where P station (t) represents the maximum available charging power of the charging station at time t; battery charging power constraint: 0 ≤ P j ≤P j,max , Where P j,max It is the maximum charging power of the j-th battery; battery charging efficiency constraint: S j ≥S th , Where S th It is the threshold for the battery charging efficiency rating index;

[0098] Solving the battery charging scheduling model for charging stations: Transforming the optimization problem into a linear programming problem:

[0099]

[0100] The linear programming problem is solved using a linear programming algorithm to obtain the optimal solution P. best =[P′1,P′2...,P′ M ], where P' M This represents the optimal charging power allocated to the Mth battery;

[0101] When the charging station is not fully loaded, that is No charging power is allocated to the rechargeable battery;

[0102] When the charging station is fully loaded, that is According to the optimal charging power allocation scheme P obtained from the solution best Distribute charging power among the batteries, where Let represent the optimal charging power allocated to the j-th battery, where j∈[1,M].

[0103] Step S4 constructs a battery charging scheduling model for the charging station based on the evaluated battery charging efficiency. Using a linear programming algorithm, a globally optimal charging power allocation scheme is obtained while satisfying the charging station's load constraints.

[0104] Example 2

[0105] Reference Figure 2 The second embodiment of the present invention provides an intelligent charging and discharging optimization system for batteries in new energy vehicle charging stations.

[0106] The system includes: a charging demand prediction module, a multi-type optimization module, a charging efficiency evaluation module, and a charging scheduling module.

[0107] The charging demand prediction module is used to construct a charging demand prediction model based on a long short-term neural network (LSTM) model. It utilizes historical charging data, combined with date and weather factors, to establish a charging demand prediction model and predict the charging demand of new energy vehicles in the future.

[0108] The multi-type optimization module constructs multi-type optimized charging and discharging strategies for new energy vehicle charging stations based on the charging demand of new energy vehicles in the future time period, and respectively constructs peak shaving and valley filling strategies and new energy consumption strategies.

[0109] The charging efficiency evaluation module is used to construct a battery charging efficiency evaluation model. It charges the battery with constant charging data over a period of time, collects data on the battery's voltage, current, and temperature under constant charging data, evaluates the battery charging efficiency, and issues timely warnings when anomalies are detected.

[0110] The charging scheduling module constructs a battery charging scheduling model for the charging station based on the evaluated battery charging efficiency, and solves the globally optimal charging power allocation scheme when charging multiple batteries.

[0111] Example 3

[0112] The present invention also provides an electronic device. This electronic device may include one or more processors and one or more memories. The memories store computer-readable code, which, when executed by the one or more processors, can perform the intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations as described above.

[0113] The methods or systems according to embodiments of the present invention can also be implemented using the architecture of the electronic devices of the present invention.

[0114] Electronic devices may include buses, one or more CPUs, read-only memory (ROM), random access memory (RAM), communication ports connected to a network, input / output components, hard disks, etc.

[0115] Storage devices in electronic devices, such as ROM or hard disks, can store the intelligent charging and discharging optimization method for new energy vehicle charging station batteries provided by this invention.

[0116] The intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations includes: constructing a charging demand prediction model based on a long short-term neural network (LSTM) model, utilizing historical charging data and incorporating date and weather factors to predict the charging demand of new energy vehicles in the future; based on the future charging demand, constructing multiple optimized charging and discharging strategies for new energy vehicle charging stations, including peak shaving and valley filling strategies and new energy consumption strategies; constructing a battery charging efficiency evaluation model, charging the battery with constant charging data over a period of time, collecting data on battery voltage, current, and temperature under constant charging data, evaluating battery charging efficiency, and issuing timely warnings for anomalies; and based on the evaluated battery charging efficiency, constructing a battery charging scheduling model for the charging station, solving for the globally optimal charging power allocation scheme when charging multiple batteries.

[0117] Furthermore, the electronic device may also include a user interface. Of course, the architecture of this invention is merely exemplary; in implementing different devices, one or more components of the electronic device disclosed in this invention may be omitted according to actual needs.

[0118] Example 4

[0119] The present invention also discloses a computer-readable storage medium.

[0120] Computer-readable instructions are stored on a computer-readable storage medium.

[0121] When computer-readable instructions are executed by a processor, the intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations disclosed in this application can be performed.

[0122] Storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. Furthermore, according to embodiments of the present invention, the processes described in the above-mentioned flowcharts can be implemented as computer software programs.

[0123] For example, this invention provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be executed by a processor to perform instructions corresponding to the method steps provided by this invention. For example: constructing a charging demand prediction model based on a Long Short-Term Neural Network (LSTM) model, utilizing historical charging data, and combining date and weather factors to establish the charging demand prediction model to predict the charging demand of new energy vehicles in the future; based on the future charging demand of new energy vehicles, constructing multi-type optimized charging and discharging strategies for new energy vehicle charging stations, including peak shaving and valley filling strategies and new energy consumption strategies; constructing a battery charging efficiency evaluation model, charging the battery with constant charging data over a period of time, collecting data on the battery's voltage, current, and temperature under constant charging data, evaluating battery charging efficiency, and issuing timely warnings for any anomalies; based on the evaluated battery charging efficiency, constructing a battery charging scheduling model for charging stations, and solving for the globally optimal charging power allocation scheme when charging multiple batteries.

[0124] When the computer program is executed by the central processing unit (CPU), it performs the functions defined in the method of the present invention. The method, apparatus, and device of the present invention may be implemented in many ways. For example, the method, apparatus, and device of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0125] The above-described order of steps for the method is for illustrative purposes only, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated.

[0126] Furthermore, in some embodiments, the invention may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the method according to the invention. Therefore, the invention also covers recording media storing programs for performing the method according to the invention.

[0127] In addition, the parts of the technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art have not been described in detail, so as to avoid excessive elaboration.

[0128] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing intelligent charging and discharging of batteries in new energy vehicle charging stations, characterized in that, include: A charging demand prediction model based on the Long Short-Term Neural Network (LSTM) model is constructed. By utilizing historical charging data and combining date and weather factors, a charging demand prediction model is established to predict the charging demand of new energy vehicles in the future. Based on the charging demand of new energy vehicles in the future, we will construct multi-type optimized charging and discharging strategies for new energy vehicle charging stations, including peak shaving and valley filling strategies and new energy consumption strategies. Construct multiple optimized charging and discharging strategies for new energy vehicle charging stations, including peak shaving and valley filling strategies and new energy consumption strategies; The objective function of the peak shaving and valley filling strategy is defined as follows: The objective is to minimize the charging load at charging stations during peak hours and maximize the charging amount during off-peak hours. The objective function of the peak shaving and valley filling strategy is expressed as: ;in, It is a future time period Within the time, Represents a set of peak periods. This represents a set of low-period periods. Indicates future time The charging power; The constraints of peak shaving and valley filling strategies include charging power constraints: And charging capacity constraints: ;in, This indicates the maximum charging power of the charging station. Represents a set of future time periods. Indicates time interval, This represents the predicted total charging demand. The objective functions of the peak shaving and valley filling strategy and the new energy consumption strategy are weighted and summed using the weighted summation method to construct a multi-objective optimization problem. The objective function after weighted summation is shown below: ； in, and These are the weighting coefficients for peak shaving and valley filling strategies and new energy consumption strategies, respectively. The constraints for solving multi-objective optimization problems include charging power constraints: Charging capacity constraints: And constraints on renewable energy generation: ; A battery charging efficiency evaluation model is constructed. The battery is charged using constant charging data over a period of time. Data on the battery's voltage, current, and temperature under constant charging data are collected to evaluate the battery charging efficiency and provide timely warnings when anomalies are detected. Based on the evaluated battery charging efficiency, a battery charging scheduling model for the charging station is constructed, and the globally optimal charging power allocation scheme is solved when charging multiple batteries.

2. The intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations according to claim 1, characterized in that, Obtain historical charging data, including A charging record, which includes information on real-time charging power consumption, peak charging power consumption, and charging amount, is integrated into a dataset. Collect date type and weather data related to charging needs, and merge them with the charging record dataset to form a feature dataset; Construct a Long Short-Term Memory (LSTM) neural network model as a charging demand prediction model; define the output layer of the LSTM model, and set the output dimension to the length of the future time period. We choose mean squared error (MSE) as the loss function. feature dataset and the corresponding charging demand value The data is divided into training and testing sets according to a predetermined ratio. The LSTM model is trained using the training set data, and the model parameters are updated through the backpropagation algorithm and optimizer. The trained LSTM model is evaluated using test set data, and the model's predictive performance metrics on the test set are calculated. Based on the model's predictive performance, the model's hyperparameters are adjusted, and the training and evaluation process is repeated until the predictive performance metrics meet the requirements. Charging demand is predicted based on a trained charging demand prediction model for a given future time period. Construct feature vectors for date type and weather factors. As input to the charging demand forecasting model; For the first time period in the future At a certain point in time, For the first Feature vectors of date type and weather factors at each point in time; Using a trained charging demand prediction model, the feature vectors for future time periods are analyzed. To make predictions, we can obtain the predicted charging demand for future periods. ,in Indicates the first term in the future time period Forecast values ​​of charging demand at each point in time; Charging demand forecast The output serves as the input for subsequent optimization of the charging and discharging strategy.

3. The intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations according to claim 2, characterized in that, Define the objective function of the renewable energy consumption strategy, which aims to maximize the amount of renewable energy absorbed by charging stations; the objective function of the renewable energy consumption strategy is expressed as: ,in, Indicates future time The proportion of renewable energy generation in total electricity generation; The constraints of the renewable energy consumption strategy include charging power constraints: Charging constraints: And constraints on renewable energy generation: .

4. The intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations according to claim 3, characterized in that, The battery is charged at a constant rate for a period of time, with fixed time intervals during the constant charging process. Collect parameters such as voltage, current, and temperature of the rechargeable battery; Define charging efficiency rating indicators Used to evaluate battery charging efficiency; charging efficiency rating index The range of values ​​is ,in This indicates that the battery is fully receiving constant charge output; This indicates that the battery is not receiving any charging output. Calculate the cumulative charging output during a constant charging process and cumulative battery reception : ;in yes Constant charging output current at all times; It is a time interval; This is the total number of sampling points; ;in yes The actual current received by the battery at any given moment; Calculate charging efficiency That is, the cumulative amount of battery received. With cumulative charging output The ratio: ； Constructing battery charging efficiency thresholds ,when When the battery charging efficiency is within acceptable limits, it indicates that the battery charging efficiency is qualified; when... When this occurs, it indicates that the battery charging efficiency is unqualified, and a charging warning reminder is issued to the battery.

5. The intelligent charging and discharging optimization method for batteries in new energy vehicle charging stations according to claim 4, characterized in that, Define the objective function of the battery charging scheduling model for the charging station: maximize the weighted total charging efficiency score while satisfying the charging station load constraints. ;in This represents the total number of batteries in the charging station. It is the first The weighting coefficient of each battery; It is the first The charging efficiency rating index for each battery. Is assigned to the first The charging power of each battery; The constraints of the battery charging scheduling model for charging stations include: charging station load constraints: ;in It is a charging station at any time Maximum available charging power; Battery charging power constraints: ;in It is the first Maximum charging power of each battery; Battery charging efficiency constraints: ;in It is the threshold for the battery charging efficiency rating index; Solving the battery charging scheduling model for the charging station transforms the optimization problem into a linear programming problem: ； ； The optimal solution to the linear programming problem is obtained by using a linear programming algorithm. ,in Indicates assignment to the first The optimal charging power for each battery; When the charging station is not fully loaded, that is No charging power is allocated to the rechargeable battery. Indicates assignment to the first The optimal charging power for each battery ; When the charging station is fully loaded, that is According to the optimal charging power allocation scheme obtained from the solution Distribute the charging power to each battery.

6. A smart charging and discharging optimization system for batteries in new energy vehicle charging stations, used to implement the smart charging and discharging optimization method for batteries in new energy vehicle charging stations as described in any one of claims 1 to 5, characterized in that, include: The module includes a charging demand prediction module, a multi-type optimization module, a charging efficiency evaluation module, and a charging scheduling module. The charging demand prediction module is used to construct a charging demand prediction model based on the Long Short-Term Neural Network (LSTM) model. It uses historical charging data, combined with date and weather factors, to establish a charging demand prediction model and predict the charging demand of new energy vehicles in the future. The multi-type optimization module constructs multi-type optimized charging and discharging strategies for new energy vehicle charging stations based on the charging demand of new energy vehicles in the future time period, and respectively constructs peak shaving and valley filling strategies and new energy consumption strategies. The charging efficiency evaluation module is used to construct a battery charging efficiency evaluation model, charge the battery with constant charging data over a period of time, collect data on the battery's voltage, current, and temperature under constant charging data, evaluate the battery charging efficiency, and issue timely warnings when anomalies are detected. The charging scheduling module constructs a battery charging scheduling model for the charging station based on the evaluated battery charging efficiency, and solves the globally optimal charging power allocation scheme when charging multiple batteries.

Images