Electric swap station energy optimization scheduling method, device, equipment and storage medium

Abstract

The embodiment of the invention discloses a battery swap station energy optimization scheduling method, device and equipment and a storage medium, and relates to the technical field of battery swap station battery scheduling. The method comprises the following steps: acquiring parameters of an autoregressive integral moving average model according to historical battery replacement times of a battery replacement station, and constructing a battery replacement demand prediction model according to the parameters of the autoregressive integral moving average model; according to a Monte Carlo method and the power conversion demand prediction model, determining a power conversion demand prediction input value corresponding to the preset scheduling moment; and solving according to the power conversion demand prediction input value, the target function and the constraint condition through the model prediction control model to obtain a target energy scheduling strategy. Therefore, the optimal scheduling of energy and the maximum saving of the charging cost can be realized, the overstock and waste of battery inventory are reduced, the turnover rate and the utilization rate of batteries are improved, and stable energy supply is provided.

Description

Technical Field

[0001] The present invention relates to the field of battery scheduling in a battery swapping station, and particularly to a method, device, equipment and storage medium for optimizing energy scheduling in a battery swapping station. Background Art

[0002] As an alternative solution for charging electric heavy trucks, battery swapping stations have gradually received more and more attention. The battery swapping mode can significantly improve the charging efficiency and battery endurance through rapid battery replacement. However, existing battery swapping stations still lack intelligence in resource scheduling and energy management, and fail to achieve optimal energy scheduling and maximum savings in charging costs. This not only causes waste of battery swapping resources but also may lead to unstable energy supply. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, device, equipment and storage medium for optimizing energy scheduling in a battery swapping station, which is used to comprehensively consider various factors affecting battery swapping to improve the operation efficiency of the battery swapping station and the operation efficiency of electric heavy trucks.

[0004] The present invention provides the following technical solutions:

[0005] In a first aspect, the present invention proposes a method for optimizing energy scheduling in a battery swapping station, including:

[0006] Obtaining autoregressive integrated moving average model parameters according to the historical battery swapping times of the battery swapping station, and constructing a battery swapping demand prediction model according to the autoregressive integrated moving average model parameters;

[0007] Determining the predicted input value of the battery swapping demand corresponding to the preset scheduling time according to the Monte Carlo method and the battery swapping demand prediction model;

[0008] Solving through a model predictive control model according to the predicted input value of the battery swapping demand, the objective function and the constraint conditions to obtain the target energy scheduling strategy.

[0009] In an embodiment, the method further includes:

[0010] Determining an electricity purchase cost expression for the battery swapping station according to the electricity purchase price, the charging efficiency and the charging power of the battery storage in the battery swapping station;

[0011] Determining an expression for the income from a single battery swap according to the capacity of a single battery and the unit price of electricity;

[0012] Determining an income expression for the battery swapping station according to the battery swapping demand of the battery swapping station and the expression for the income from a single battery swap;

[0013] Determining the objective function according to the electricity purchase cost expression for the battery swapping station and the income expression for the battery swapping station.

[0014] In one embodiment, the constraint conditions include battery state capacity constraint, battery operation and battery swapping constraint, and power percentage constraint. The method further includes:

[0015] For all times and all battery compartments of the battery swapping station, determining the battery state capacity constraint according to a preset full charge threshold, the battery compartment power, and a preset battery power range;

[0016] For all times and / or all battery compartments of the battery swapping station, determining the battery operation and battery swapping constraint according to the battery compartment state and the battery compartment service volume;

[0017] For all times and all battery compartments of the battery swapping station, determining the power percentage constraint according to a preset power percentage threshold.

[0018] In one embodiment, the battery state capacity constraint includes a non-linear SOC change constraint. The method further includes:

[0019] Based on an auxiliary variable, converting the non-linear SOC change constraint into a linear SOC change constraint according to a preset power threshold.

[0020] In one embodiment, the autoregressive integrated moving average model parameters include a target autoregressive order and a target moving average order. Obtaining the autoregressive integrated moving average model parameters according to the historical battery swapping times of the battery swapping station includes:

[0021] Obtaining stationary data according to the historical battery swapping times of the battery swapping station;

[0022] Obtaining an autocorrelation coefficient diagram and a partial autocorrelation coefficient diagram according to the stationary data;

[0023] Determining an autoregressive order range and a moving average order range according to the autocorrelation coefficient diagram and the partial autocorrelation coefficient diagram;

[0024] Based on minimizing the Akaike information criterion and the Bayesian information criterion, obtaining the target autoregressive order and the target moving average order according to the autoregressive order range and the moving average order range.

[0025] In one embodiment, solving, by the model predictive control model, according to the battery swapping demand prediction input values, the objective function, and the constraint conditions to obtain a target energy scheduling strategy includes:

[0026] Constructing an optimization problem including the objective function and the constraint conditions according to the battery swapping demand prediction input values;

[0027] Using a mixed integer linear programming solver to solve the optimization problem through the model predictive control model to obtain the target energy scheduling strategy.

[0028] In one embodiment, determining the predicted input value of the battery swapping demand corresponding to the preset scheduling time according to the Monte Carlo method and the battery swapping demand prediction model includes:

[0029] Determine N preset scheduling times;

[0030] Based on a preset prediction step, obtain the first predicted value of the battery swapping demand at the first preset scheduling time through the battery swapping demand prediction model;

[0031] Based on the Monte Carlo method, obtain the second predicted values of the battery swapping demand corresponding to the 2nd to Nth preset scheduling times according to the historical battery swapping data of the battery swapping station;

[0032] Use the first predicted value of the battery swapping demand and the second predicted values of the battery swapping demand as the predicted input values of the battery swapping demand.

[0033] In a second aspect, the present invention provides a device for optimizing the energy scheduling of a battery swapping station, including:

[0034] A construction module, configured to obtain the autoregressive integrated moving average model parameters according to the historical battery swapping times of the battery swapping station, and construct a battery swapping demand prediction model according to the autoregressive integrated moving average model parameters;

[0035] A determination module, configured to determine the predicted input value of the battery swapping demand corresponding to the preset scheduling time according to the Monte Carlo method and the battery swapping demand prediction model;

[0036] A solution module, configured to solve through a model predictive control model according to the predicted input value of the battery swapping demand, the objective function, and the constraint conditions to obtain an objective energy scheduling strategy.

[0037] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, it implements the method for optimizing the energy scheduling of a battery swapping station as described in the first aspect.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the method for optimizing the energy scheduling of a battery swapping station as described in the first aspect.

[0039] The energy optimization scheduling method, device, equipment and storage medium disclosed by the present invention obtain the autoregressive integrated moving average (ARIMA) model parameters according to the historical battery swapping times of the battery swapping station, and construct a battery swapping demand prediction model according to the ARIMA model parameters; determine the predicted input values of the battery swapping demand corresponding to the preset scheduling time according to the Monte Carlo method and the battery swapping demand prediction model; solve through a model predictive control model according to the predicted input values of the battery swapping demand, the objective function and the constraint conditions to obtain the target energy scheduling strategy. In this way, by using the historical battery swapping times data to determine the parameters of the ARIMA model, the time series characteristics of the battery swapping demand can be captured; the autoregressive integrated moving average model is used to accurately predict the future battery swapping demand, providing a reliable basis for subsequent scheduling decisions; the Monte Carlo method corrects the prediction results of the battery swapping demand prediction model by simulating various possible battery swapping demand scenarios, effectively compensating for the prediction errors, and ensuring the accuracy and stability of the optimized scheduling; the model predictive control model can solve based on the current predicted input values of the battery swapping demand, the objective function and the constraint conditions, and generate a series of optimal or sub-optimal target energy scheduling strategies through continuous rolling optimization, ensuring that while meeting the battery swapping demand, the battery swapping station can achieve the optimal energy scheduling and the maximum savings in charging costs, reduce the backlog and waste of battery inventory, improve the turnover rate and utilization rate of the batteries, and provide a stable energy supply; at the same time, by reasonably arranging the charging time and charging amount, the idle rate of the charging equipment can be reduced, and the utilization efficiency of the equipment can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] To more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the protection scope of the present invention. In each drawing, similar components are numbered similarly.

[0041] Figure 1 FIG. shows a flowchart of the energy optimization scheduling method for a battery swapping station proposed in this embodiment;

[0042] Figure 2 FIG. shows another flowchart of the energy optimization scheduling method for a battery swapping station proposed in this embodiment;

[0043] Figure 3 FIG. shows a schematic diagram of the predicted result of the battery swapping demand proposed in this embodiment;

[0044] Figure 4 FIG. shows still another flowchart of the energy optimization scheduling method for a battery swapping station proposed in this embodiment;

[0045] Figure 5 FIG. shows yet another flowchart of the energy optimization scheduling method for a battery swapping station proposed in this embodiment;

[0046] Figure 6 A schematic diagram showing the charging amount curves at each moment after the optimized scheduling proposed in this embodiment;

[0047] Figure 7 A schematic diagram showing the charging amount curves at each moment before the optimized scheduling proposed in this embodiment;

[0048] Figure 8 A schematic diagram showing the charging amount statistics during the peak-valley and normal periods proposed in this embodiment;

[0049] Figure 9 A schematic structural diagram of the energy optimized scheduling device for the battery swapping station proposed in this embodiment.

[0050] Explanation of the attached drawing reference numerals:

[0051] 900 - Energy optimized scheduling device for the battery swapping station; 901 - Construction module; 902 - Determination module; 903 - Solving module. Detailed implementation manners

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0053] Generally, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0054] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present invention are only intended to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0055] In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0056] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present invention pertain. The terms (such as those defined in a commonly used dictionary) will be interpreted as having the same meaning as their contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in various embodiments of the present invention.

[0057] Embodiment 1

[0058] With the increasing global emphasis on environmental protection and sustainable transportation, electric heavy-duty trucks (electric heavy trucks) as a solution to replace traditional fuel trucks have become an important part of promoting green transportation policies. Due to their advantages such as zero emissions and high energy efficiency, electric heavy trucks are gradually being applied in fields such as logistics, transportation, and mining. However, electric heavy trucks face problems such as long charging times, insufficient charging facilities, and limited battery range during operation. Especially in the context of long-distance transportation and high-load operation, the rapid consumption of battery power and the uncontrollability of charging time will greatly affect transportation efficiency.

[0059] When existing battery swapping stations conduct resource scheduling and energy management, they often fail to fully consider various factors such as the battery's state of charge, the real-time demand of heavy trucks, and electricity price fluctuations, resulting in low energy scheduling efficiency of the battery swapping station.

[0060] The embodiments of the present disclosure provide a method for optimizing energy scheduling of a battery swapping station, which is used to comprehensively consider various factors affecting battery swapping to improve the operation efficiency of the battery swapping station and the operation effectiveness of electric heavy trucks.

[0061] Please refer to Figure 1 , a method for optimizing energy scheduling of a battery swapping station includes steps S101 to S103, and the following is a detailed description of each step.

[0062] Step S101, obtain autoregressive integrated moving average model parameters according to the historical battery swapping times of the battery swapping station, and construct a battery swapping demand prediction model according to the autoregressive integrated moving average model parameters.

[0063] In this embodiment, obtain the battery swapping times data of the battery swapping station in the past period of time, use the historical battery swapping times data of the battery swapping station to determine the autoregressive integrated moving average model parameters, and further construct an ARIMA battery swapping demand prediction model according to the autoregressive integrated moving average model parameters.

[0064] Among them, since the ARIMA model is based on stationary time series for modeling. If the data does not meet the stationarity requirements, it may be necessary to process it through methods such as differencing and logarithmic transformation. In addition, in order to determine the autoregressive integrated moving average model parameters, some statistical methods are usually required, such as information criteria (such as AIC, BIC) or graphical methods (such as the autocorrelation function ACF and partial autocorrelation function PACF plots).

[0065] Please refer to Figure 2 , in a specific embodiment, the autoregressive integrated moving average model parameters include the target autoregressive order and the target moving average order, and step S101 includes steps S1011 to S1014. The following will explain each step in detail.

[0066] Step S1011, obtain stationary data according to the historical battery swapping times of the battery swapping station.

[0067] In this embodiment, perform a stationarity test on the historical battery swapping times N swap of the battery swapping station. If the historical battery swapping times N swap data is not stationary, then perform differencing stationary processing on the data to obtain stationary data, ensuring the normal establishment of the battery swapping demand prediction model. Among them, common stationarity detection methods include time series plots, autocorrelation functions, and unit root tests.

[0068] Step S1012, obtain the autocorrelation coefficient plot and the partial autocorrelation coefficient plot according to the stationary data.

[0069] In this embodiment, obtain the autocorrelation coefficient plot and the partial autocorrelation coefficient plot according to the stationary data. The autocorrelation coefficient (ACF) measures the correlation between the current value and past values in a time series, and the partial autocorrelation coefficient (PACF) is the correlation between the current value and past values after excluding the influence of intermediate variables.

[0070] Step S1013, determine the autoregressive order range and the moving average order range according to the autocorrelation coefficient plot and the partial autocorrelation coefficient plot.

[0071] In this embodiment, initially set the autoregressive order range and the moving average order range in the ARIMA model through the autocorrelation coefficient (ACF) plot and the partial autocorrelation coefficient (PACF) plot.

[0072] Step S1014, based on minimizing the Akaike information criterion and the Bayesian information criterion, obtain the target autoregressive order and the target moving average order according to the autoregressive order range and the moving average order range.

[0073] In this embodiment, a grid search method is adopted. Taking the minimization of the Akaike information criterion and the Bayesian information criterion as the standard, the optimal autoregressive order p and moving average order q are determined according to the autoregressive order range and the moving average order range.

[0074] It should be noted that the expression of the battery swapping demand prediction model is: In the formula, N swap,i is the predicted value of the battery swapping demand at time t; N swap,t-i is the observed data at time t - i, that is, the lag term of the time series; ∈ t-i is the error term at time t - i, that is, the gap between the predicted value and the actual observed value; θ i is the moving average coefficient, which is used to control the influence degree of past errors on the current moment value.

[0075] Step S102: Determine the predicted input value of the battery swapping demand corresponding to the preset scheduling moment according to the Monte Carlo method and the battery swapping demand prediction model.

[0076] In this embodiment, the predicted value of the battery swapping demand at the preset scheduling moment is predicted according to the battery swapping demand prediction model. At the same time, the Monte Carlo method is used to correct the predicted value of the battery swapping demand output by the battery swapping demand prediction model, comprehensively considering the randomness and uncertainty of the battery swapping demand, so as to provide a more comprehensive prediction result.

[0077] In a specific embodiment, step S102 includes: determining N preset scheduling moments; based on the preset prediction step length, obtaining the first predicted value of the battery swapping demand at the first preset scheduling moment through the battery swapping demand prediction model; based on the Monte Carlo method, obtaining the second predicted values of the battery swapping demand corresponding to the 2nd to Nth preset scheduling moments according to the historical battery swapping data of the battery swapping station; using the first predicted value of the battery swapping demand and the second predicted values of the battery swapping demand as the predicted input values of the battery swapping demand.

[0078] In this embodiment, N specific time points for predicting the battery swapping demand in the future are clarified, that is, N preset scheduling moments. The selection of the preset scheduling moment is usually based on actual needs, such as the battery swapping habits of users, the scheduling requirements of the power grid, or the operation strategy of the battery swapping station, etc. The preset scheduling moment can be a fixed time point (such as a certain moment every day), or a time point dynamically generated based on a certain rule.

[0079] Furthermore, the prediction step length of the battery swapping demand prediction model is set to 1, that is, the battery swapping demand at the next moment (t + 1) is predicted each time, and the result is used as the first predicted value of the battery swapping demand at time t + 1, so as to reduce the error accumulation that may occur in long-time step prediction.

[0080] Further, for the predicted values of the second battery swapping demands at the subsequent N - 1 preset scheduling times (the 2nd to the Nth preset scheduling times), the Monte Carlo method is used to simulate based on the historical battery swapping data of the battery swapping station in the past two weeks.

[0081] Further, the predicted value of the first battery swapping demand and the predicted values of the second battery swapping demands are combined as the input numerical values for the predicted battery swapping demands of the subsequent Model Predictive Control (MPC) model. The input numerical values for the predicted battery swapping demands reflect the possible future battery swapping demand situations of the battery swapping station.

[0082] Please refer to Figure 3 , the proportion of cases where the prediction error is greater than 2 times is only 2.7%. This means that the battery swapping demand prediction method proposed in this embodiment has high accuracy. In most cases, the prediction error of the battery swapping demand is small, thus effectively avoiding the situation where vehicles cannot perform battery swapping when arriving at the battery swapping station.

[0083] It should be noted that when using the model predictive control method for rolling optimization, it is necessary to consider the battery swapping demands at the subsequent N preset scheduling times, so as to make a unified plan for the system. Therefore, accurately predicting the battery swapping demands at the subsequent N preset scheduling times is crucial.

[0084] However, when the ARIMA model performs multi-step prediction, as the prediction step length increases, its prediction accuracy usually gradually decreases. In order to improve the reliability and accuracy of the prediction, it is necessary to use the historical battery swapping information to correct the prediction results of the ARIMA model, thereby effectively compensating for the prediction error and ensuring the accuracy and stability of the optimized scheduling.

[0085] Step S103, solve through the model predictive control model according to the input numerical values for the predicted battery swapping demands, the objective function, and the constraint conditions to obtain the target energy scheduling strategy.

[0086] In this embodiment, through the solution and optimization of the MPC model, a target energy scheduling strategy that simultaneously meets the requirements of the input numerical values for the predicted battery swapping demands, as well as the optimized objective function and constraint conditions, is obtained. Among them, according to the operation objectives and constraint conditions of the battery swapping station, the objective function is defined to measure the pros and cons of the energy scheduling strategy; and the constraint conditions will ensure that the obtained energy scheduling strategy is feasible in actual operation.

[0087] It should be noted that by using the model predictive control model to solve based on the current input numerical values for the predicted battery swapping demands, the objective function, and the constraint conditions, and through continuous rolling optimization, the target energy scheduling strategies corresponding to each moment are generated, ensuring that while the battery swapping station meets the battery swapping demands, it can achieve the optimal energy scheduling and maximize the savings of the charging cost, reduce the backlog and waste of battery inventory, improve the turnover rate and utilization rate of the batteries, and provide a stable energy supply.

[0088] In a specific embodiment, step S103 includes: constructing an optimization problem including the objective function and the constraint conditions according to the input value of the battery swapping demand prediction; using a mixed-integer linear programming solver to solve the optimization problem through the model predictive control model to obtain the target energy scheduling strategy.

[0089] In this embodiment, the input value of the battery swapping demand prediction, the objective function, and the constraint conditions are integrated into an optimization problem. The optimization problem is usually expressed in the form of mathematical programming, such as linear programming.

[0090] Further, a mixed-integer linear programming solver is used to solve the optimization problem by using the MPC model to obtain a series of optimal control variables, and these variables will constitute the target energy scheduling strategy.

[0091] Please refer to Figure 4 , in a specific embodiment, the method further includes steps S401 to S404, and the following will elaborate on each step.

[0092] Step S401, determining an expression for the electricity purchase cost of the battery swapping station according to the electricity purchase price, the charging efficiency, and the charging power of the battery storage in the battery swapping station.

[0093] In this embodiment, the electricity purchase cost of the battery swapping station depends on the electricity purchase price, the charging efficiency, and the charging power of the battery storage in the battery swapping station. Then the expression for the electricity purchase cost F 1 is In the formula, t is the time index, J is the index of the battery storage position, P j,t is the charging power of the jth battery storage in the battery swapping station at time t, EP t is the electricity purchase price at time t, and η is the charging efficiency.

[0094] Step S402, determining an expression for the single-time battery swapping income according to the single-cell battery capacity and the electricity unit price.

[0095] In this embodiment, the single-time battery swapping income depends on the single-cell battery capacity and the electricity unit price. Since only fully charged batteries can be swapped, and the battery power is assumed to be 20% after swapping, the income of each battery swapping is fixed. Then the expression for the single-time battery swapping income R is R = (1 - 0.2) × Cap × SP. In the formula, Cap is the single-cell battery capacity selected for the project, and SP is the selling price per degree of electricity, that is, the electricity unit price.

[0096] Step S403, determining an expression for the battery swapping income of the battery swapping station according to the battery swapping demand of the battery swapping station and the single-time battery swapping income expression.

[0097] In this embodiment, the battery swapping income of the battery swapping station depends on the battery swapping demand of the battery swapping station and the single-time battery swapping income. Then the expression for the battery swapping income F 2 is

[0098] Step S404: Determine the objective function according to the electricity purchase cost expression and the battery swapping cost expression of the battery swapping station.

[0099] In this embodiment, the objective function aims to minimize profit or minimize loss, so the objective function is minF = F 1 -F 2 .

[0100] Please refer to Figure 5 , in a specific embodiment, the constraint conditions include battery state capacity constraint, battery operation battery swapping constraint, and power percentage constraint. The method further includes steps S501 to S503, and the following is a detailed description of each step.

[0101] Step S501: For all times and all battery compartments of the battery swapping station, determine the battery state capacity constraint according to the preset full charge threshold, the battery compartment power, and the preset battery power range.

[0102] In this embodiment, the preset full charge threshold is the maximum value that the battery compartment power should reach to avoid overcharging, thereby protecting the battery and extending its service life; the battery compartment power is the actual power of the current battery compartment; the preset battery power range is the minimum and maximum values that the battery compartment power should maintain to ensure sufficient power can be provided when needed, while avoiding performance degradation or damage caused by too low power. The battery state capacity constraint applies to all times and all battery compartments of the battery swapping station.

[0103] Exemplarily, the battery state capacity constraint includes full charge constraint, SOC change constraint, and SOC constraint. Among them, the full charge constraint is used to judge whether the battery in the compartment is fully charged, and the full charge constraint is expressed as In the formula, T full is the full charge threshold, and W j,t is a 0-1 variable used to represent whether the j-th battery compartment of the battery swapping station is fully charged at time t. When the j-th battery compartment of the battery swapping station is fully charged at time t, W j,t is 1, and vice versa, W j,t is 0.

[0104] The SOC change constraint is used to ensure that the power of the battery in the compartment changes reasonably during charging and battery swapping. The SOC change constraint is expressed as In the formula, SOC j,t represents the battery power in the j-th battery compartment of the battery swapping station at time t; V j,t is a 0-1 variable used to represent whether the j-th battery compartment of the battery swapping station has undergone battery swapping at time t. When the battery in the j-th battery compartment of the battery swapping station is swapped out at time t, V j,t is 0, and vice versa, Vj,t is 1. P j,t-1 represents the battery charge percentage of the battery in the j-th battery compartment of the battery swapping station at time t - 1.

[0105] The SOC constraint is used to limit the battery charge within a reasonable preset battery charge range, and the SOC constraint is expressed as In the formula, 0 to 100 is the preset battery charge range.

[0106] Step S502, for all times and / or all battery compartments of the battery swapping station, determine the battery operation and swapping constraint according to the battery compartment status and the battery compartment service volume.

[0107] In this embodiment, the battery compartment status includes states such as whether the battery compartment is idle, whether it is charging, whether it is swapping batteries, etc. The battery compartment service volume is the number of battery swapping services provided by the battery compartment within a period of time. The battery operation and swapping constraint applies to all times and / or all battery compartments of the battery swapping station.

[0108] Exemplarily, the battery operation and swapping constraint includes a compartment swapping constraint and a swapping demand constraint. Among them, the compartment swapping constraint is used to ensure that unoccupied compartments are not allowed to perform battery swapping operations, and the compartment swapping constraint is expressed as In the formula, W j,t-1 is also a 0 - 1 variable, representing whether the j-th battery compartment of the battery swapping station is in the "available for battery swapping" state at time t - 1.

[0109] The swapping demand constraint is used to ensure that each battery swapping station can meet its swapping demand at each time, and the swapping demand constraint is expressed as In the formula, D t represents the swapping demand of the battery swapping station at time t. represents the number of fully charged batteries in all battery compartments at time t.

[0110] Step S503, for all times and all battery compartments of the battery swapping station, determine the charge percentage constraint according to the preset charge percentage threshold.

[0111] In this embodiment, the preset charge percentage threshold is the maximum battery charge percentage that should be observed when the battery compartment is charging. Determine the charge percentage constraint according to the preset charge percentage threshold, and the charge percentage constraint applies to all times and all battery compartments of the battery swapping station.

[0112] Exemplarily, the charge percentage constraint is used to ensure that the current charge percentage does not exceed the maximum charge percentage, and the charge percentage constraint is expressed as 100 is the preset charge percentage threshold, and P j,t represents the battery charge percentage of the battery in the j-th battery compartment of the battery swapping station at time t.

[0113] In a specific embodiment, the battery state capacity constraint includes a non-linear SOC change constraint, and the method further includes: based on an auxiliary variable, converting the non-linear SOC change constraint into a linear SOC change constraint according to a preset power threshold.

[0114] In this embodiment, according to the SOC change constraint SOC j,t = P j,t-1 + 20×(1 - V j,t ) + SOC j,t ×V j,t It can be seen that the existence of SOC j,t ×V j,t makes the optimization problem a mixed-integer non-linear programming problem. However, the mixed-integer non-linear programming problem is usually very complex, with a long solution time and high computational resource consumption, resulting in difficult solution. Therefore, it is necessary to introduce an auxiliary variable to convert the non-linear SOC change constraint into a linear SOC change constraint to improve the solvability and solution efficiency of the model.

[0115] Exemplarily, set In the formula, A j,t is the introduced auxiliary variable, and it is restricted within a reasonable value range. At this time, the linear SOC change constraint is expressed as is the preset power threshold (maximum value).

[0116] Exemplarily, taking the operation of a certain battery swapping station for one year as an example, the results show that without optimized scheduling, the electricity purchase cost is 3.3723 million yuan, and after scheduling, it only costs 3.266 million yuan, with the charging cost reduced by 3.2%. The charging amount curves at each moment after optimized scheduling are as Figure 6 shown, and the charging amount curves at each moment before optimized scheduling are as Figure 7 shown. It can be seen that the optimized scheduling model will transfer the charging amount at some peak-time electricity price moments to other normal-time or valley-time electricity prices, effectively reducing the charging cost during high electricity price periods. Please refer to Figure 8 , the histogram (1) represents before scheduling, and the histogram (2) represents after scheduling. After the optimized scheduling of this battery swapping station, the charging amount at peak-time electricity price is significantly reduced, while the charging amounts at normal time and valley time increase, reducing the charging cost.

[0117] The energy optimization scheduling method for the battery swapping station proposed in this embodiment obtains the autoregressive integrated moving average (ARIMA) model parameters based on the historical battery swapping times of the battery swapping station, and constructs a battery swapping demand prediction model according to the ARIMA model parameters; determines the predicted input values of the battery swapping demand corresponding to the preset scheduling moment according to the Monte Carlo method and the battery swapping demand prediction model; and solves through the model predictive control model according to the predicted input values of the battery swapping demand, the objective function, and the constraint conditions to obtain the target energy scheduling strategy. In this way, by using the historical battery swapping times data to determine the parameters of the ARIMA model, the time series characteristics of the battery swapping demand can be captured; the autoregressive integrated moving average model is used to accurately predict the future battery swapping demand, providing a reliable basis for subsequent scheduling decisions; the Monte Carlo method corrects the prediction results of the battery swapping demand prediction model by simulating multiple possible battery swapping demand scenarios, effectively compensating for the prediction errors and ensuring the accuracy and stability of the optimized scheduling; the model predictive control model can solve based on the current predicted input values of the battery swapping demand, the objective function, and the constraint conditions, and generate a series of optimal or sub-optimal target energy scheduling strategies through continuous rolling optimization, ensuring that while the battery swapping station meets the battery swapping demand, it can achieve the optimal scheduling of energy and the maximum savings in charging costs, reduce the backlog and waste of battery inventory, improve the turnover rate and utilization rate of the batteries, and provide a stable energy supply; at the same time, by reasonably arranging the charging time and charging amount, the idle rate of the charging equipment can be reduced, and the utilization efficiency of the equipment can be improved.

[0118] Embodiment 2

[0119] In addition, an energy optimization scheduling device 900 for a battery swapping station is provided in an embodiment of the present disclosure. Please refer to Figure 9 , and the device includes:

[0120] A construction module 901, configured to obtain autoregressive integrated moving average (ARIMA) model parameters according to the historical battery swapping times of the battery swapping station, and construct a battery swapping demand prediction model according to the ARIMA model parameters;

[0121] A determination module 902, configured to determine the predicted input values of the battery swapping demand corresponding to the preset scheduling moment according to the Monte Carlo method and the battery swapping demand prediction model;

[0122] A solution module 903, configured to solve through a model predictive control model according to the predicted input values of the battery swapping demand, the objective function, and the constraint conditions to obtain a target energy scheduling strategy.

[0123] Optionally, the device further includes a processing module, which is configured to determine an electricity purchase cost expression for the battery swapping station according to the electricity purchase price, the charging efficiency, and the charging power of the battery storage in the battery swapping station; determine a single battery swapping income expression according to the single battery capacity and the unit electricity price; determine a battery swapping income expression for the battery swapping station according to the battery swapping demand of the battery swapping station and the single battery swapping income expression; and determine the objective function according to the electricity purchase cost expression and the battery swapping income expression of the battery swapping station.

[0124] Optionally, the constraint conditions include a battery state capacity constraint, a battery operation battery swapping constraint, and a power percentage constraint. The processing module is configured to determine the battery state capacity constraint for all times and all battery storages of the battery swapping station according to a preset full charge threshold, the battery storage power, and a preset battery power range; determine the battery operation battery swapping constraint for all times and / or all battery storages of the battery swapping station according to the battery storage state and the battery storage service volume; and determine the power percentage constraint for all times and all battery storages of the battery swapping station according to a preset power percentage threshold.

[0125] Optionally, the battery state capacity constraint includes a non-linear SOC change constraint. The processing module is configured to convert the non-linear SOC change constraint into a linear SOC change constraint based on auxiliary variables according to a preset power threshold.

[0126] Optionally, the autoregressive integrated moving average model parameters include a target autoregressive order and a target moving average order. The construction module 901 is configured to obtain stationary data according to the historical battery swapping times of the battery swapping station; obtain an autocorrelation coefficient diagram and a partial autocorrelation coefficient diagram according to the stationary data; determine an autoregressive order range and a moving average order range according to the autocorrelation coefficient diagram and the partial autocorrelation coefficient diagram; and obtain the target autoregressive order and the target moving average order based on minimizing the Akaike information criterion and the Bayesian information criterion according to the autoregressive order range and the moving average order range.

[0127] Optionally, the solving module 903 is configured to construct an optimization problem including the objective function and the constraint conditions according to the battery swapping demand prediction input value; and use a mixed integer linear programming solver to solve the optimization problem through the model predictive control model to obtain the target energy scheduling strategy.

[0128] Optionally, the determining module 902 is configured to determine N preset scheduling times; obtain a first battery swapping demand prediction value for the first preset scheduling time through the battery swapping demand prediction model based on a preset prediction step; obtain second battery swapping demand prediction values corresponding to the 2nd to Nth preset scheduling times according to the historical battery swapping data of the battery swapping station based on the Monte Carlo method; and use the first battery swapping demand prediction value and the second battery swapping demand prediction values as the battery swapping demand prediction input values.

[0129] The device provided by the embodiments of the present disclosure can execute the steps of the energy optimization scheduling method for the battery swapping station provided in Embodiment 1. To avoid repetition, it will not be elaborated here.

[0130] The energy optimization scheduling device for the battery swapping station proposed in this embodiment obtains the autoregressive integrated moving average (ARIMA) model parameters according to the historical battery swapping times of the battery swapping station, and constructs a battery swapping demand prediction model according to the ARIMA model parameters; determines the predicted input values of the battery swapping demand corresponding to the preset scheduling moment according to the Monte Carlo method and the battery swapping demand prediction model; and solves through a model predictive control model according to the predicted input values of the battery swapping demand, the objective function, and the constraint conditions to obtain the target energy scheduling strategy. In this way, by using the historical battery swapping times data to determine the parameters of the ARIMA model, the time series characteristics of the battery swapping demand can be captured; the autoregressive integrated moving average model is used to accurately predict the future battery swapping demand, providing a reliable basis for subsequent scheduling decisions; the Monte Carlo method corrects the prediction results of the battery swapping demand prediction model by simulating various possible battery swapping demand scenarios, effectively compensating for the prediction errors, and ensuring the accuracy and stability of the optimization scheduling; the model predictive control model can solve based on the current predicted input values of the battery swapping demand, the objective function, and the constraint conditions, and generate a series of optimal or sub-optimal target energy scheduling strategies through continuous rolling optimization, ensuring that while meeting the battery swapping demand, the battery swapping station can achieve the optimal energy scheduling and the maximum savings in charging costs, reduce the backlog and waste of battery inventory, improve the turnover rate and utilization rate of the batteries, and provide a stable energy supply; at the same time, by reasonably arranging the charging time and charging amount, the idle rate of the charging equipment can be reduced, and the utilization efficiency of the equipment can be improved.

[0131] Embodiment 3

[0132] In addition, the embodiments of the present disclosure provide a computer device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the energy optimization scheduling method for the battery swapping station described in Embodiment 1 is implemented.

[0133] The device provided by the embodiments of the present disclosure can execute the steps of the energy optimization scheduling method for the battery swapping station provided in Embodiment 1. To avoid repetition, it will not be elaborated here.

[0134] Embodiment 4

[0135] The embodiments of the present disclosure propose a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the energy optimization scheduling method for the battery swapping station described in Embodiment 1 of this disclosure is implemented.

[0136] In this embodiment, the computer-readable storage medium can be a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk, an optical disk, or the like.

[0137] The computer-readable storage medium provided in this embodiment can implement the energy optimization scheduling method of the swapping station provided in Embodiment 1. To avoid repetition, it will not be elaborated here.

[0138] In all the examples shown and described here, any specific value should be construed as merely exemplary, not as a limitation. Therefore, other examples of the exemplary embodiments can have different values.

[0139] It should be noted that like reference numerals and letters denote like items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0140] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, and these all belong to the protection scope of the present invention.

Claims

1. A method for optimizing energy scheduling of a battery swap station, characterized in that: include: Obtaining autoregressive integral moving average model parameters according to the historical number of battery swaps at the battery swap station, and constructing a battery swap demand prediction model according to the autoregressive integral moving average model parameters; Determine the battery swap demand prediction input value corresponding to the preset scheduling time according to the Monte Carlo method and the battery swap demand prediction model; The model predictive control model is used to solve the target energy scheduling strategy according to the predicted input value, objective function and constraint conditions of the battery replacement demand.

2. The energy optimization scheduling method for battery swap stations according to claim 1 is characterized in that: The method further comprises: Determine the electricity purchase cost expression of the battery swap station based on the electricity purchase price, charging efficiency and charging power of the battery compartment of the battery swap station; Determine the income expression of a single battery replacement based on the single battery capacity and the unit price of electricity; Determine the battery swap revenue expression of the battery swap station according to the battery swap demand of the battery swap station and the single battery swap revenue expression; The objective function is determined based on the expression of the electricity purchasing cost of the battery swap station and the expression of the electricity swap income of the battery swap station.

3. The energy optimization scheduling method for battery swap stations according to claim 1 is characterized in that: The constraint conditions include battery state capacity constraint, battery operation replacement constraint and power percentage constraint, and the method further includes: For all battery compartments at all times and in all battery swap stations, the battery state capacity constraint is determined according to a preset full charge threshold, the battery compartment power level, and a preset battery power range; For all battery compartments at all times and / or in the battery swap station, the battery operation swap constraint is determined according to the battery compartment status and the battery compartment service volume; For all battery compartments at all times and in the battery swap station, the power percentage constraint is determined according to a preset power percentage threshold.

4. The method for optimizing the energy scheduling of a battery swap station according to claim 3, characterized in that: The battery state capacity constraint includes a nonlinear SOC change constraint, and the method further includes: Based on the auxiliary variable, the nonlinear SOC change constraint is converted into a linear SOC change constraint according to a preset power threshold.

5. The method for optimizing the energy scheduling of a battery swap station according to any one of claims 1 to 4, characterized in that: The autoregressive integral moving average model parameters include a target autoregressive order and a target moving average order. The autoregressive integral moving average model parameters are obtained according to the historical number of battery swaps at the battery swap station, including: Acquire stable data according to the historical number of battery swaps at the battery swap station; Obtain an autocorrelation coefficient graph and a partial autocorrelation coefficient graph according to the stationary data; Determining an autoregressive order range and a moving average order range according to the autocorrelation coefficient graph and the partial autocorrelation coefficient graph; Based on minimizing the Akaike information criterion and the Bayesian information criterion, the target autoregressive order and the target moving average order are obtained according to the autoregressive order range and the moving average order range.

6. The method for optimizing the energy scheduling of a battery swap station according to any one of claims 1 to 4, characterized in that: The model predictive control model is solved according to the predicted input value, objective function and constraint conditions of the battery swap demand to obtain a target energy scheduling strategy, including: Constructing an optimization problem including the objective function and the constraint conditions according to the battery swap demand prediction input value; A mixed integer linear programming solver is used to solve the optimization problem through the model predictive control model to obtain the target energy scheduling strategy.

7. The method for optimizing the energy scheduling of a battery swap station according to any one of claims 1 to 4, characterized in that: The step of determining the battery swap demand prediction input value corresponding to the preset scheduling time according to the Monte Carlo method and the battery swap demand prediction model includes: Determine N preset scheduling times; Based on a preset prediction step, obtaining a first battery swap demand prediction value at a first preset scheduling moment through the battery swap demand prediction model; Based on the Monte Carlo method, the second battery swap demand prediction value corresponding to the second to N preset scheduling moments is obtained according to the historical battery swap data of the battery swap station; The first battery swap demand prediction value and the second battery swap demand prediction value are used as the battery swap demand prediction input values.

8. An energy optimization and dispatching device for a battery swap station, characterized in that: include: A construction module is used to obtain autoregressive integral moving average model parameters according to the historical number of battery swaps at the battery swap station, and to construct a battery swap demand prediction model according to the autoregressive integral moving average model parameters; A determination module, used to determine the battery swap demand prediction input value corresponding to the preset scheduling time according to the Monte Carlo method and the battery swap demand prediction model; The solution module is used to solve the target energy scheduling strategy according to the predicted input value, objective function and constraint conditions of the battery replacement demand through the model predictive control model.

9. A computer device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the energy optimization scheduling method for the battery swap station as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the energy optimization scheduling method for a battery swap station as described in any one of claims 1 to 7.

Images