Charging and discharging method of energy storage system and energy storage system

Abstract

The invention provides a charging and discharging method of an energy storage system and the energy storage system, and the method comprises the steps: carrying out the prediction based on collected photovoltaic data, obtaining first photovoltaic power, and carrying out the prediction based on collected load data, and obtaining first load power; determining reserved power based on the first photovoltaic power and the first load power, wherein the reserved power is standby power set for ensuring stable operation of the energy storage system; and determining a charging and discharging strategy based on the reserved power and one or more preset targets. The method provided by the invention is beneficial to improving the charging and discharging efficiency, reducing the operation cost and improving the economic benefit.

Description

Technical Field

[0001] The present application relates to the field of energy storage, and in particular to a charging and discharging method of an energy storage system and an energy storage system. Background Art

[0002] In the photovoltaic and storage integration scenario, the charging and discharging scheduling strategy of the energy storage system is usually based on photovoltaic power generation and load demand. However, the uncertainty of photovoltaic power generation and load demand will lead to the inefficiency of the charging and discharging scheduling strategy. For example, the charging and discharging scheduling strategy lacks the ability to adapt to uncertain factors such as photovoltaic power generation and load demand. Especially in the scenario where photovoltaic power generation fluctuates greatly or load demand changes rapidly, the scheduling effect of the energy storage system is significantly reduced. Therefore, an efficient charging and discharging method of the energy storage system is urgently needed to solve the above problems. Summary of the invention

[0003] The embodiments of the present application provide a charging and discharging method, device and energy storage system for an energy storage system, which are helpful to improve the charging and discharging efficiency, reduce operating costs and improve economic benefits.

[0004] In a first aspect, an embodiment of the present application provides a charging and discharging method for an energy storage system, comprising: performing prediction based on collected photovoltaic data to obtain a first photovoltaic power, and performing prediction based on collected load data to obtain a first load power; determining a reserved power based on the first photovoltaic power and the first load power, wherein the reserved power is a backup power set to ensure stable operation of the energy storage system; determining a charging and discharging strategy based on the reserved power and one or more preset targets; wherein the one or more preset targets include at least a revenue target and / or an efficiency target, wherein the revenue target is used to maximize the revenue, and the efficiency target is used to maximize the energy storage operation efficiency; The profit target is represented by the following expression: ; T is a preset time span, and L discharge (t) is the discharge capacity of the energy storage system at time t, and L charge (t) is the charge amount of the energy storage system at time t, E(t) is the electricity price at time t, and C charge (t) is the charging operation cost of the energy storage system at time t, and C discharge (t) is the discharge operation cost of the energy storage system at time t, and C pv (t) is used to represent the negative benefits caused by the photovoltaic power prediction error at time t. load (t) is used to represent the negative benefits caused by the load power forecast error at time t; The C pv (t) is calculated by the following formula: ; The lambda pv (t) is the weight coefficient of photovoltaic at time t, and the λ pv (t) is determined by the photovoltaic power probability interval, the P pv-actual (t) is the real power of the photovoltaic at time t, and P pv-forecast (t) is the predicted power of photovoltaic at time t; The C load (t) is calculated by the following formula: ; The lambda load (t) is the weight coefficient of the load at time t, and the load (t) is determined by the load power probability interval, the P load-actual (t) is the real power of the load at time t, and P load-forecast (t) is the predicted power of the load at time t; The efficiency target is represented by the following expression: .

[0005] In one possible implementation, the photovoltaic power probability interval is obtained by calculating the first photovoltaic power through a preset Frank copula function, and the load power probability interval is obtained by calculating the first load power through the preset Frank copula function.

[0006] In one possible implementation, the determining of the charging and discharging strategy based on the reserved power and one or more preset targets includes: determining the charging and discharging strategy based on the reserved power, one or more preset targets and constraints; wherein the constraints include energy storage capacity balance constraints, site power balance constraints and remaining power constraints; The energy storage capacity balance constraint condition is represented by the following expression: ; The L reserve (t) is the reserved power at time t, and L rated (t) is the rated capacity of the energy storage system at time t; The site power balance constraint is represented by the following expression: ; The P grid (t) is the power of the power grid at time t, and P ess (t) is the energy storage power at time t, and P ess(t) used to characterize charging or discharging; The remaining power constraint condition is represented by the following expression: ; The Soc(t) is the remaining power of the energy storage system at time t, and the η charge is the charging efficiency, the η discharge is the discharge efficiency.

[0007] In one possible implementation, the prediction based on the collected photovoltaic data to obtain the first photovoltaic power, and the prediction based on the collected load data to obtain the first load power include: inputting the collected photovoltaic data into a preset prediction model for prediction to obtain the first photovoltaic power, and inputting the collected load data into the preset prediction model for prediction to obtain the first load power.

[0008] In one possible implementation manner, the preset prediction model is a FEDformer model.

[0009] In one possible implementation, the step of inputting the collected photovoltaic data into a preset prediction model for prediction to obtain a first photovoltaic power, and the step of inputting the collected load data into the preset prediction model for prediction to obtain a first load power includes: inputting the collected photovoltaic data into the preset prediction model to obtain a second photovoltaic power, and inputting the collected load data into the preset prediction model to obtain a second load power; performing time correction on the second photovoltaic power, and performing the time correction on the second load power; determining the photovoltaic power prediction value after the time correction as the first photovoltaic power, and determining the load power prediction value after the time correction as the first load power; wherein the time correction is used to adjust the sensitivity of the prediction value to time; The time correction of the second photovoltaic power is achieved by the following calculation formula: ; The P pv-corrected (t) is the photovoltaic power prediction value after the time correction, and the P pv (t) is the second photovoltaic power at time t, the β pv is the photovoltaic correction factor, the W pv (t) is the time weight factor of PV at time t; The time correction of the second load power is achieved by the following calculation formula: ; The P load-corrected (t) is the load power forecast value after the time correction, and P load(t) is the second load power at time t, the β load is the load correction factor, the W load (t) is the time weight factor of the load at time t.

[0010] In one possible implementation, before determining the time-corrected photovoltaic power prediction value as the first photovoltaic power and determining the time-corrected load power prediction value as the first load power, the method further includes: performing correlation correction based on the time-corrected photovoltaic power prediction value and the first parameter correlation to obtain the first photovoltaic power; and performing correlation correction based on the time-corrected load power prediction value and the second parameter correlation to obtain the first load power; wherein the first parameter correlation and the second parameter correlation are used to adjust the sensitivity of the prediction value to the correlation between parameters.

[0011] In one possible implementation, the first parameter correlation is represented by a first correlation matrix, the first correlation matrix includes correlation coefficients between parameters in the photovoltaic data, and the second parameter correlation is represented by a second correlation matrix, the second correlation matrix includes correlation coefficients between parameters in the load data; The first correlation matrix is ​​represented by the following expression: ; The R pv is the first correlation matrix, the C pv (r i,pv , r j,pv ) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The correlation coefficient between The second correlation matrix is ​​represented by the following expression: ; The R laod is the second correlation matrix, the C load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The correlation coefficient between .

[0012] In one possible implementation, the correlation coefficient in the first correlation matrix is ​​calculated using the following calculation formula: ; The cov pv (r i,pv , r j,pv) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The covariance between the Var pv (r i,pv ) is the ith photovoltaic parameter r i,pv The variance, the Var pv (r j,pv ) is the jth photovoltaic parameter r j,pv The variance of The correlation coefficient in the second correlation matrix is ​​calculated by the following calculation formula: ; The cov load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The covariance between the Var load (r i,load ) is the i-th load parameter r i,load The variance, the Var load (r j,load ) is the jth load parameter r j,load The variance of .

[0013] In a second aspect, an embodiment of the present application provides a charging and discharging device for an energy storage system, comprising one or more functional modules, wherein the one or more functional modules are used to execute the charging and discharging method as described in the first aspect.

[0014] In a third aspect, an embodiment of the present application provides an energy storage system, comprising: a processor and a memory, wherein the memory is used to store a computer program; the processor is used to run the computer program to implement the charging and discharging method as described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a readable storage medium, in which a program is stored, and when the program is run on an energy storage system, the energy storage system implements the charging and discharging method as described in the first aspect.

[0016] In a fifth aspect, an embodiment of the present application provides a program, which, when executed on a processor of an energy storage system, enables the energy storage system to execute the charging and discharging method as described in the first aspect.

[0017] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a charging and discharging method for an energy storage system provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a charging and discharging device of an energy storage system provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of the energy storage system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In the embodiments of the present application, unless otherwise specified, the character " / " indicates that the objects before and after the association are in an or relationship. For example, A / B can represent A or B. "And / or" describes the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone.

[0020] It should be pointed out that the words "first", "second", etc. involved in the embodiments of the present application are only used to distinguish the description purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated, nor can they be understood as indicating or implying order.

[0021] In the embodiments of the present application, "at least one" means one or more, and "more" means two or more. In addition, "at least one of the following" or similar expressions refers to any combination of these items, which may include any combination of single items or plural items. For example, at least one of A, B, or C can represent: A, B, C, A and B, A and C, B and C, or A, B and C. Among them, each of A, B, and C can be an element itself, or a set containing one or more elements.

[0022] In the embodiments of the present application, "exemplary", "in some embodiments", "in another embodiment", etc. are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present concepts in a concrete way.

[0023] In the embodiments of the present application, "of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings to be expressed are consistent. In the embodiments of the present application, communication and transmission can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings to be expressed are consistent. For example, transmission can include sending and / or receiving, which can be a noun or a verb.

[0024] The equal to involved in the embodiments of the present application can be used in conjunction with greater than, and is applicable to the technical solution adopted when greater than, and can also be used in conjunction with less than, and is applicable to the technical solution adopted when less than. It should be noted that when equal to is used in conjunction with greater than, it cannot be used in conjunction with less than; when equal to is used in conjunction with less than, it cannot be used in conjunction with greater than.

[0025] In the photovoltaic and storage integration scenario, the charging and discharging scheduling strategy of the energy storage system is usually based on photovoltaic power generation and load demand. However, the uncertainty of photovoltaic power generation and load demand will lead to the inefficiency of the charging and discharging scheduling strategy. For example, the charging and discharging scheduling strategy lacks the ability to adapt to uncertain factors such as photovoltaic power generation and load demand. Especially in the scenario where photovoltaic power generation fluctuates greatly or load demand changes rapidly, the scheduling effect of the energy storage system is significantly reduced. Therefore, an efficient charging and discharging method of the energy storage system is urgently needed to solve the above problems.

[0026] Based on the above problems, the present application provides a charging and discharging method, which helps to improve the charging and discharging efficiency, reduce operating costs and improve economic benefits.

[0027] Figure 1 A schematic flow chart of an embodiment of the charging and discharging method provided in the present application includes the following steps: Step 101, collecting photovoltaic data and load data.

[0028] Specifically, the photovoltaic data may be photovoltaic power generation data. For the convenience of explanation, photovoltaic power generation is referred to as photovoltaic herein.

[0029] The load data may be load demand data. For the convenience of explanation, this article will refer to the demand as load.

[0030] In some optional embodiments, the photovoltaic data may include but is not limited to timestamp, meter accumulated electric energy, solar radiation, ambient temperature, photovoltaic module temperature, wind speed, atmospheric pressure, weather category code, and active power data.

[0031] In some optional embodiments, the load data may include but is not limited to timestamp, ambient temperature, weather category code, power consumption, meter accumulated power, peak and valley data, and number of personnel.

[0032] In some optional embodiments, energy storage system status data may also be collected. The energy storage system status data may be collected through a meter, a local energy management system (Energy Management System, EMS), an energy storage control unit (System Site Control Unit, SCU) or a battery management unit (Battery Management Unit, BMU), or the energy storage system status data may be collected through other methods, which is not specifically limited in the embodiments of the present application.

[0033] The energy storage system status data may include, but is not limited to, the energy storage remaining capacity (State of Charge, SOC) status, power conversion system (Power Convert System, PCS) power, current, voltage and other data.

[0034] It is understandable that the above energy storage system status data can be uploaded to the energy storage big data cloud platform at a preset period (for example, 30 seconds) via the Message Queuing Telemetry Transport (MQTT) protocol or other protocols to provide support for charging and discharging scheduling decisions and real-time control of the energy storage system.

[0035] Step 102: predicting based on the collected photovoltaic data to obtain a first photovoltaic power, and predicting based on the collected load data to obtain a first load power.

[0036] In some optional embodiments, the above prediction can be performed by a preset prediction model.

[0037] For example, the collected photovoltaic data can be input into a preset prediction model for prediction to obtain a first photovoltaic power. Also, the collected load data can be input into a preset prediction model for prediction to obtain a first load power.

[0038] Among them, the preset prediction model can use the improved FEDformer model for model training, or the preset prediction model can use other models for model training, and the embodiments of the present application do not make special limitations on this.

[0039] The preset prediction model can be trained with a photovoltaic dataset and a load dataset as input.

[0040] Among them, the above-mentioned photovoltaic data set and load data set can be data sets composed of data collected at a preset time granularity (1 minute) within a historical time period (for example, 1 year). The photovoltaic data set and load data set contain the characteristics of photovoltaics and loads. Combined with the time series characteristics of photovoltaics and loads, the prediction accuracy and efficiency can be significantly improved through training.

[0041] It is understandable that the above historical event segments and time granularity may also be other values, and the embodiments of the present application do not specifically limit this.

[0042] In some optional embodiments, the photovoltaic data may be predicted by a preset prediction model to obtain a second photovoltaic power, the second photovoltaic power may be time-corrected to obtain a photovoltaic power prediction value after time correction, and the photovoltaic power prediction value after time correction may be determined as the first photovoltaic power. Also, the load data may be predicted by a preset prediction model to obtain a second load power, the second load power may be time-corrected to obtain a load power prediction value after time correction, and the load power prediction value after time correction may be determined as the first load power.

[0043] The time correction may be used to adjust the sensitivity of the predicted value (for example, the predicted value may be the second photovoltaic power or the second load power) to time.

[0044] Exemplarily, the above-mentioned method of performing time correction on the second photovoltaic power can be implemented by the following calculation formula: ; Among them, P pv-corrected (t) is the photovoltaic power after the second photovoltaic power is corrected for time. In this embodiment, P pv-corrected (t) can be used as the first photovoltaic power at time t, P pv (t) is the second photovoltaic power at time t, β pv is the photovoltaic correction factor, W pv (t) is the time weight factor of photovoltaic.

[0045] Through time correction, the sensitivity of the predicted value of PV power to the time weight can be dynamically adjusted to improve the dynamic adaptability and robustness of the prediction results.

[0046] The above-mentioned method of performing time correction on the second load power can be realized by the following calculation formula: ; Among them, P load-corrected (t) is the load power after time correction of the second load power. In this embodiment, P load-corrected (t) can be used as the first load power at time t, P load (t) is the second load power at time t, β load is the load correction factor, W load (t) is the time weight factor of the load.

[0047] Through time correction, the sensitivity of the predicted value of load power to the time weight can be dynamically adjusted to improve the dynamic adaptability and robustness of the prediction results.

[0048] In some optional embodiments, after obtaining the time-corrected photovoltaic power, correlation correction can be performed based on the time-corrected photovoltaic power and the first parameter correlation to obtain the first photovoltaic power, and the first parameter correlation can be represented by a first correlation matrix. And, after obtaining the time-corrected load power, correlation correction can be performed based on the time-corrected load power and the second parameter correlation to obtain the first load power, and the second parameter correlation can be represented by a second correlation matrix.

[0049] Exemplarily, the first correlation matrix can be represented by the following expression: ; Among them, R pv is the first correlation matrix, C pv (r i,pv , r j,pv ) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The correlation coefficient between .

[0050] The correlation coefficient in the first correlation matrix can be calculated by the following formula: ; Among them, cov pv (r i,pv , r j,pv ) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The covariance between pv (r i,pv ) is the ith photovoltaic parameter r i,pv The variance of pv (r j,pv ) is the jth photovoltaic parameter r j,pv The variance of The second correlation matrix can be represented by the following expression: ; Among them, R laod is the second correlation matrix, C load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The correlation coefficient between .

[0051] The correlation coefficient in the second correlation matrix can be calculated by the following formula: ; Among them, cov load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The covariance between load (r i,load ) is the i-th load parameter r i,load The variance of load (r j,load ) is the jth load parameter r j,load The variance of .

[0052] Quantifying the correlation between different parameters by the ratio of covariance to variance can improve the accuracy of the predicted values.

[0053] In an embodiment of the present application, the correlation coefficients between different parameters are stored in a correlation matrix (e.g., a first correlation matrix and a second correlation matrix). The most relevant input features can be identified through the correlation matrix, such as the relationship between temperature and light intensity, thereby improving the accuracy of the predicted values.

[0054] Step 103: determining a reserved power based on the first photovoltaic power and the first load power, where the reserved power is a backup power set to ensure stable operation of the energy storage system.

[0055] Specifically, the reserved power may be determined by the difference between the first photovoltaic power and the first load power.

[0056] Step 104: Determine a charge and discharge strategy based on the reserved power and one or more preset targets.

[0057] Specifically, the charging and discharging strategy can be optimized with multiple objectives through one or more preset objectives.

[0058] Among them, one or more preset goals may include but are not limited to a profit target and / or an efficiency target, the profit target is used to maximize the profit, and the efficiency target is used to maximize the energy storage operation efficiency.

[0059] It is understandable that, through one or more of the above preset goals, combined with real-time constraints, an optimal energy storage charging and discharging strategy can be generated.

[0060] For example, the profit target can be represented by the following expression: ; Among them, T is the preset time span, L discharge(t) is the discharge amount of the energy storage system at time t, L charge (t) is the charge amount of the energy storage system at time t, E(t) is the electricity price at time t, C charge (t) is the charging operation cost of the energy storage system at time t, C discharge (t) is the discharge operation cost of the energy storage system at time t, C pv (t) is used to represent the negative benefits caused by the photovoltaic power prediction error at time t, C load (t) is used to represent the negative benefits caused by the load power forecast error at time t; C pv (t) can be calculated by the following formula: ; Among them, λ pv (t) is the weight coefficient of photovoltaic at time t, λ pv (t) is determined by the photovoltaic power probability interval, P pv-actual (t) is the real power of the photovoltaic at time t, P pv-forecast (t) is the predicted power of photovoltaic at time t; It is understandable that the photovoltaic power probability interval can be obtained by calculating the Frank-Copula correlation function. For example, the photovoltaic prediction value at time t can be input into the Frank-Copula correlation function to obtain the photovoltaic power probability interval. Alternatively, the photovoltaic power probability interval can be obtained by calculating other functions, which is not specifically limited in the present embodiment. C load (t) can be calculated by the following formula: ; Among them, λ load (t) is the weight coefficient of the load at time t, λ load (t) is determined by the load power probability interval, P load-actual (t) is the real power of the load at time t, and P load-forecast (t) is the predicted power of the load at time t.

[0061] It is understandable that the load power probability interval can be obtained by calculating the Frank-Copula correlation function. For example, the load forecast value at time t can be input into the Frank-Copula correlation function to obtain the load power probability interval. Alternatively, the load power probability interval can be obtained by calculating other functions, which is not specifically limited in the embodiments of the present application.

[0062] It should be noted that charging and discharging can satisfy the constraint conditions shown in the following formula, which can be energy storage capacity balance constraint conditions: ; Among them, L reserve (t) is the reserved power at time t, L rated (t) is the rated capacity of the energy storage system at time t.

[0063] The efficiency target can be expressed as follows: .

[0064] It can be understood that in order to achieve the above efficiency target, the constraint conditions shown in the following formula can be satisfied, and the constraint conditions can include site power balance constraint conditions and remaining power constraint conditions.

[0065] Exemplarily, the site power balance constraint condition can be represented by the following expression: ; Among them, P grid (t) is the power of the power grid at time t, P ess (t) is the energy storage power at time t, P ess (t) is used to characterize the charging power or discharging power at time t.

[0066] It should be noted that the maximum value of PV power is limited by the inverter, the maximum value of grid power and energy storage power is limited by PCS, and the maximum value of load power is based on the demand of the site transformer.

[0067] The remaining power constraint is represented by the following expression: ; Among them, Soc(t) is the remaining power of the energy storage system at time t, η charge is the charging efficiency, η discharge is the discharge efficiency.

[0068] It is understandable that the remaining power can be determined by the energy storage system status data.

[0069] Figure 2 A schematic diagram of the structure of the charging and discharging device of the energy storage system provided in the embodiment of the present application is shown in FIG. Figure 2 As shown, the charging and discharging device 20 of the energy storage system may include: a prediction module 21 and a determination module 22; wherein, A prediction module 21, configured to perform prediction based on the collected photovoltaic data to obtain a first photovoltaic power, and to perform prediction based on the collected load data to obtain a first load power; A determination module 22 determines a reserved power based on the first photovoltaic power and the first load power, wherein the reserved power is a backup power set to ensure stable operation of the energy storage system; and determines a charge and discharge strategy based on the reserved power and one or more preset targets; The one or more preset targets include at least a revenue target and / or an efficiency target, wherein the revenue target is used to maximize the revenue, and the efficiency target is used to maximize the energy storage operation efficiency; The profit target is represented by the following expression: ; T is a preset time span, and L discharge (t) is the discharge capacity of the energy storage system at time t, and L charge (t) is the charge amount of the energy storage system at time t, E(t) is the electricity price at time t, and C charge (t) is the charging operation cost of the energy storage system at time t, and C discharge (t) is the discharge operation cost of the energy storage system at time t, and C pv (t) is used to represent the negative benefits caused by the photovoltaic power prediction error at time t. load (t) is used to represent the negative benefits caused by the load power forecast error at time t; The C pv (t) is calculated by the following formula: ; The lambda pv (t) is the weight coefficient of photovoltaic at time t, and the λ pv (t) is determined by the photovoltaic power probability interval, the P pv-actual (t) is the real power of the photovoltaic at time t, and P pv-forecast (t) is the predicted power of photovoltaic at time t; The C load (t) is calculated by the following formula: ; The lambda load (t) is the weight coefficient of the load at time t, and the load (t) is determined by the load power probability interval, the P load-actual (t) is the real power of the load at time t, and P load-forecast (t) is the predicted power of the load at time t; The efficiency target is represented by the following expression: .

[0070] In one possible implementation, the photovoltaic power probability interval is obtained by calculating the first photovoltaic power through a preset Frank copula function, and the load power probability interval is obtained by calculating the first load power through the preset Frank copula function.

[0071] In one possible implementation, the determination module 22 is further configured to determine a charging and discharging strategy based on the reserved power, one or more preset targets and constraints; The constraints include energy storage capacity balance constraints, site power balance constraints and remaining power constraints; The energy storage capacity balance constraint condition is represented by the following expression: ; The L reserve (t) is the reserved power at time t, and L rated (t) is the rated capacity of the energy storage system at time t; The site power balance constraint is represented by the following expression: ; The P grid (t) is the power of the power grid at time t, and P ess (t) is the energy storage power at time t, and P ess (t) used to characterize charging or discharging; The remaining power constraint condition is represented by the following expression: ; The Soc(t) is the remaining power of the energy storage system at time t, and the η charge is the charging efficiency, the η discharge is the discharge efficiency.

[0072] In one possible implementation, the prediction module 21 is further used to input the collected photovoltaic data into a preset prediction model for prediction to obtain a first photovoltaic power, and to input the collected load data into the preset prediction model for prediction to obtain a first load power.

[0073] In one possible implementation manner, the preset prediction model is a FEDformer model.

[0074] In one possible implementation, the prediction module 21 is further used to input the collected photovoltaic data into the preset prediction model to obtain the second photovoltaic power, and input the collected load data into the preset prediction model to obtain the second load power; Performing time correction on the second photovoltaic power, and performing the time correction on the second load power; Determine the time-corrected photovoltaic power prediction value as the first photovoltaic power, and determine the time-corrected load power prediction value as the first load power; Wherein, the time correction is used to adjust the sensitivity of the predicted value to time; The time correction of the second photovoltaic power is achieved by the following calculation formula: ; The P pv-corrected (t) is the photovoltaic power prediction value after the time correction, and the P pv (t) is the second photovoltaic power at time t, the β pv is the photovoltaic correction factor, the W pv (t) is the time weight factor of PV at time t; The time correction of the second load power is achieved by the following calculation formula: ; The P load-corrected (t) is the load power forecast value after the time correction, and P load (t) is the second load power at time t, the β load is the load correction factor, the W load (t) is the time weight factor of the load at time t.

[0075] In one possible implementation, the prediction module 21 is further used to perform correlation correction based on the time-corrected photovoltaic power prediction value and the first parameter correlation to obtain the first photovoltaic power; and perform correlation correction based on the time-corrected load power prediction value and the second parameter correlation to obtain the first load power; The first parameter correlation and the second parameter correlation are used to adjust the sensitivity of the predicted value to the correlation between parameters.

[0076] In one possible implementation, the first parameter correlation is represented by a first correlation matrix, the first correlation matrix includes correlation coefficients between parameters in the photovoltaic data, and the second parameter correlation is represented by a second correlation matrix, the second correlation matrix includes correlation coefficients between parameters in the load data; The first correlation matrix is ​​represented by the following expression: ; The R pv is the first correlation matrix, the Cpv (r i,pv , r j,pv ) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The correlation coefficient between The second correlation matrix is ​​represented by the following expression: ; The R laod is the second correlation matrix, the C load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The correlation coefficient between .

[0077] In one possible implementation, the correlation coefficient in the first correlation matrix is ​​calculated using the following calculation formula: ; The cov pv (r i,pv , r j,pv ) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The covariance between the Var pv (r i,pv ) is the ith photovoltaic parameter r i,pv The variance, the Var pv (r j,pv ) is the jth photovoltaic parameter r j,pv The variance of The correlation coefficient in the second correlation matrix is ​​calculated by the following calculation formula: ; The cov load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The covariance between the Var load (r i,load ) is the i-th load parameter r i,load The variance, the Var load (r j,load ) is the jth load parameter r j,load The variance of .

[0078] Figure 2The charging and discharging device 20 of the energy storage system provided in the illustrated embodiment can be used to implement the technical solution of the method embodiment shown in the present application. Its implementation principle and technical effects can be further referred to the relevant description in the method embodiment.

[0079] It should be understood that the division of the various modules of the charging and discharging device 20 of the above energy storage system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the detection module can be a separately established processing element, or it can be integrated in a chip of the terminal device. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. In the implementation process, each step of the above method or each of the above modules can be completed by an integrated logic circuit of hardware in the processor element or instructions in software form.

[0080] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more microprocessors (DSP), or one or more field programmable gate arrays (FPGA). For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0081] Figure 3 The schematic diagram of the structure of an energy storage system 300 provided in an embodiment of the present application is as follows. The energy storage system 300 may include: at least one processor; and at least one memory connected to the processor in communication. The memory stores program instructions executable by the processor. The processor in the energy storage system 300 calls the program instructions to execute the actions performed in the storage access method provided in the embodiment of the present application.

[0082] like Figure 3 As shown, the energy storage system 300 is in the form of a general-purpose computing device. The components of the energy storage system 300 may include, but are not limited to: one or more processors 310, a memory 320, a communication bus 340 connecting different system components (including the memory 320 and the processor 310), and a communication interface 330.

[0083] The communication bus 340 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnection (PCI) bus.

[0084] The energy storage system 300 typically includes a variety of computer system readable media, which can be any available media that can be accessed by a terminal device, including volatile and non-volatile media, removable and non-removable media.

[0085] The memory 320 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The terminal device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Figure 3 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (such as a compact disc read only memory (hereinafter referred to as: CD-ROM), a digital versatile disc read only memory (hereinafter referred to as: DVD-ROM) or other optical media) can be provided. In these cases, each drive can be connected to the communication bus 340 through one or more data medium interfaces. The memory 320 may include at least one program product, which has a set (for example, at least one) of program modules, which are configured to perform the functions of each embodiment of the present application.

[0086] A program / utility having a set (at least one) of program modules may be stored in memory 320, such program modules including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules generally perform the functions and / or methods of the embodiments described herein.

[0087] The energy storage system 300 may also communicate with one or more external devices (e.g., keyboards, pointing devices, displays, etc.), one or more devices that enable a user to interact with the terminal device, and / or any device that enables the terminal device to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via the communication interface 330. In addition, the energy storage system 300 may also communicate with the network adapter ( Figure 3 The network adapter may communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via the communication bus 340. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the energy storage system 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays of Independent Drives; hereinafter referred to as: RAID) systems, tape drives, and data backup storage systems.

[0088] The processor 310 executes various functional applications and data processing by running the programs stored in the memory 320, such as implementing the method provided in the embodiment of the present application.

[0089] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present application is only a schematic illustration and does not constitute a structural limitation on the energy storage system 300. In other embodiments of the present application, the energy storage system 300 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0090] In the above embodiments, the processor involved may include, for example, a CPU, a DSP, a microcontroller or a digital signal processor, and may also include a GPU, an embedded neural network processor (Neural-network Process Units; hereinafter referred to as: NPU) and an image signal processor (Image Signal Processing; hereinafter referred to as: ISP). The processor may also include necessary hardware accelerators or logic processing hardware circuits, such as ASIC, or one or more integrated circuits for controlling the execution of the program of the technical solution of the present application. In addition, the processor may have the function of operating one or more software programs, and the software programs may be stored in a storage medium.

[0091] An embodiment of the present application also provides a readable storage medium, in which a program is stored. When the program is run on a system, the system executes the method provided by the embodiment shown in the present application.

[0092] An embodiment of the present application also provides a program product, which includes a program. When the program product is run on a system, the system executes the method provided by the embodiment shown in the present application.

[0093] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0094] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0095] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0096] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0097] The above is only a specific implementation of the present application. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A charging and discharging method for an energy storage system, characterized in that: The method comprises: Predicting based on the collected photovoltaic data to obtain a first photovoltaic power, and predicting based on the collected load data to obtain a first load power; Determine a reserved power based on the first photovoltaic power and the first load power, wherein the reserved power is a backup power set to ensure stable operation of the energy storage system; Determining a charging and discharging strategy based on the reserved power and one or more preset targets; The one or more preset targets include at least a revenue target and / or an efficiency target, wherein the revenue target is used to maximize the revenue, and the efficiency target is used to maximize the energy storage operation efficiency; The profit target is represented by the following expression: ； Where T is the preset time span, L discharge (t) is the discharge capacity of the energy storage system at time t, L charge (t) is the charge amount of the energy storage system at time t, E(t) is the electricity price at time t, C charge (t) is the charging operation cost of the energy storage system at time t, C discharge (t) is the discharge operation cost of the energy storage system at time t, C pv (t) is used to represent the negative benefits caused by the photovoltaic power prediction error at time t, C load (t) is used to represent the negative benefits caused by the load power forecast error at time t; The C pv (t) is calculated by the following formula: ； In the formula, λ pv (t) is the weight coefficient of photovoltaic at time t, and the λ pv (t) is determined by the photovoltaic power probability interval, P pv-actual (t) is the real power of the photovoltaic at time t, P pv-forecast (t) is the predicted power of photovoltaic at time t; The C load (t) is calculated by the following formula: ； In the formula, λ load (t) is the weight coefficient of the load at time t, and the load (t) is determined by the load power probability interval, P load-actual (t) is the real power of the load at time t, P load-forecast (t) is the predicted power of the load at time t; The efficiency target is represented by the following expression: 。 2. The method according to claim 1, characterized in that The photovoltaic power probability interval is obtained by calculating the first photovoltaic power using a preset Frankcopula function, and the load power probability interval is obtained by calculating the first load power using the preset Frankcopula function.

3. The method according to claim 1, characterized in that: Determining the charging and discharging strategy based on the reserved power and one or more preset targets includes: Determining a charging and discharging strategy based on the reserved power, one or more preset targets and constraints; The constraints include energy storage capacity balance constraints, site power balance constraints and remaining power constraints; The energy storage capacity balance constraint condition is represented by the following expression: ； Where, L reserve (t) is the reserved power at time t, L rated (t) is the rated capacity of the energy storage system at time t; The site power balance constraint is represented by the following expression: ； Where P grid (t) is the power of the power grid at time t, P ess (t) is the energy storage power at time t, and P ess (t) used to characterize charging or discharging; The remaining power constraint condition is represented by the following expression: ； Where Soc(t) is the remaining power of the energy storage system at time t, η charge is the charging efficiency, η discharge is the discharge efficiency.

4. The method according to claim 1, characterized in that: The method of performing prediction based on the collected photovoltaic data to obtain the first photovoltaic power and performing prediction based on the collected load data to obtain the first load power includes: The collected photovoltaic data is input into a preset prediction model for prediction to obtain a first photovoltaic power, and the collected load data is input into the preset prediction model for prediction to obtain a first load power.

5. The method according to claim 4, characterized in that The preset prediction model is the FEDformer model.

6. The method according to claim 4, characterized in that The step of inputting the collected photovoltaic data into a preset prediction model for prediction to obtain a first photovoltaic power, and the step of inputting the collected load data into the preset prediction model for prediction to obtain a first load power comprises: Inputting the collected photovoltaic data into the preset prediction model to obtain a second photovoltaic power, and inputting the collected load data into the preset prediction model to obtain a second load power; Performing time correction on the second photovoltaic power, and performing the time correction on the second load power; Determine the time-corrected photovoltaic power prediction value as the first photovoltaic power, and determine the time-corrected load power prediction value as the first load power; Wherein, the time correction is used to adjust the sensitivity of the predicted value to time; The time correction of the second photovoltaic power is achieved by the following calculation formula: ； Where P pv-corrected (t) is the photovoltaic power prediction value after correction at the time, P pv (t) is the second photovoltaic power at time t, β pv is the photovoltaic correction factor, W pv (t) is the time weight factor of PV at time t; The time correction of the second load power is achieved by the following calculation formula: ； Where P load-corrected (t) is the load power forecast value after the correction of the time, P load (t) is the second load power at time t, β load is the load correction factor, W load (t) is the time weight factor of the load at time t.

7. The method according to claim 6, characterized in that Before determining the time-corrected photovoltaic power prediction value as the first photovoltaic power and determining the time-corrected load power prediction value as the first load power, the method further includes: Performing correlation correction based on the time-corrected photovoltaic power prediction value and the first parameter correlation to obtain the first photovoltaic power; and performing correlation correction based on the time-corrected load power prediction value and the second parameter correlation to obtain the first load power; The first parameter correlation and the second parameter correlation are used to adjust the sensitivity of the predicted value to the correlation between parameters.

8. The method according to claim 7, characterized in that The first parameter correlation is represented by a first correlation matrix, the first correlation matrix includes correlation coefficients between parameters in the photovoltaic data, and the second parameter correlation is represented by a second correlation matrix, the second correlation matrix includes correlation coefficients between parameters in the load data; The first correlation matrix is ​​represented by the following expression: ； In the formula, R pv is the first correlation matrix, C pv (r i,pv , r j,pv ) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The correlation coefficient between The second correlation matrix is ​​represented by the following expression: ； In the formula, R laod is the second correlation matrix, C load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The correlation coefficient between .

9. The method according to claim 8, characterized in that The correlation coefficient in the first correlation matrix is ​​calculated by the following calculation formula: ； In the formula, cov pv (r i,pv , r j,pv ) is the ith photovoltaic parameter r i,pv and the jth photovoltaic parameter r j,pv The covariance between pv (r i,pv ) is the ith photovoltaic parameter r i,pv The variance of pv (r j,pv ) is the jth photovoltaic parameter r j,pv The variance of The correlation coefficient in the second correlation matrix is ​​calculated by the following calculation formula: ； In the formula, cov load (r i,load , r j,load ) is the i-th load parameter r i,load and the jth load parameter r j,load The covariance between load (r i,load ) is the i-th load parameter r i,load The variance of load (r j,load ) is the jth load parameter r j,load The variance of .

10. An energy storage system, characterized in that: include: A processor and a memory, wherein the memory is used to store a program; and the processor is used to run the program to implement the charging and discharging method of the energy storage system as described in any one of claims 1 to 9.

Images