CN117955248A

CN117955248A - Energy storage power station battery state monitoring system, method, device and storage medium

Info

Publication number: CN117955248A
Application number: CN202410351205.8A
Authority: CN
Inventors: 查宏胜; 祁富俊
Original assignee: Suzhou Junhao Electric Power Co ltd
Current assignee: Suzhou Junhao Electric Power Co ltd
Priority date: 2024-03-26
Filing date: 2024-03-26
Publication date: 2024-04-30
Anticipated expiration: 2044-03-26
Also published as: CN117955248B

Abstract

Embodiments of the present disclosure provide a system, a method, an apparatus and a storage medium for monitoring a battery state of an energy storage power station, where the system includes: the system comprises a battery state monitoring module, a data storage device, a power generation and reception monitoring module, an alarm component, a power grid load monitoring module and a battery control module. The battery control module further includes a grid load estimation unit configured to: determining the estimated battery energy storage risk type and the confidence level thereof at least at one time point in the future based on the current working condition data, the historical working condition data, the generated power data, the power consumption data, the current and historical battery polarization characteristic data and the power grid load data; determining an overhaul instruction of at least one battery pack of the energy storage power station based on the estimated battery energy storage risk type and the confidence level thereof; and sending the overhaul instruction to a power station maintenance center. According to the method, the maintenance instruction is determined in advance by estimating the battery energy storage risk, so that maintenance is performed in time, and the operation safety of the energy storage power station is improved.

Description

Energy storage power station battery state monitoring system, method, device and storage medium

Technical Field

The present disclosure relates to the field of battery monitoring, and in particular, to a system, a method, an apparatus, and a storage medium for monitoring a battery state of an energy storage power station.

Background

An energy storage power station refers to a system of devices that perform the storage, conversion and release of recyclable electrical energy through a collection of multiple electrochemical cell storage media. The energy storage power station can be used as an independent system to be connected into a power grid, and plays roles of peak clipping, valley filling, standby power supply and the like for the power grid; the wind-solar energy storage system can also be formed together with new energy power generation, so that the generated energy and the used electricity are smoothed or a micro-grid is formed, and the energy utilization rate and the electric energy quality are improved.

At present, the analysis of the battery energy storage power station often depends on the operation of the power grid fluctuation and the energy storage power station, the abnormality can be monitored only when the fault or the battery decay occurs, the risk of the energy storage power station about the hidden danger related to the battery can not be estimated in advance, and unexpected emergencies such as fire disaster and the like easily occur.

Accordingly, it is desirable to provide an energy storage power station battery condition monitoring system, method, apparatus and storage medium to assess in advance the energy storage power station related risk.

Disclosure of Invention

One or more embodiments of the present specification provide an energy storage power station battery condition monitoring system. The system comprises: the battery state monitoring module is connected with the battery pack of the energy storage power station through a circuit and is configured to collect working condition data of the battery pack; the data storage device is configured to store the historical working condition data acquired by the battery state monitoring module; the power generation and reception monitoring module is configured to monitor power generation and reception data of the new energy power generation device and power consumption data of the power utilization device, which are connected with the energy storage power station circuit; an alarm part configured to issue alarm information when the operating condition data does not satisfy a preset operating condition; the power grid load monitoring module is configured to monitor power grid load data of a power grid accessed by the energy storage power station; the battery control module comprises a power grid load estimating unit; the grid load estimation unit is configured to: determining the estimated battery energy storage risk type and the confidence level thereof at least at one time point in the future based on the current working condition data, the historical working condition data, the generated power data, the power consumption data, the current and historical battery polarization characteristic data and the power grid load data; determining an overhaul instruction of at least one battery pack of the energy storage power station based on the estimated battery energy storage risk type and the confidence level thereof; and sending the overhaul instruction to a power station maintenance center.

In some embodiments, the battery control module further comprises a battery energy storage control unit; the battery energy storage control unit is configured to: predicting estimated power generation amount data and estimated power consumption amount data of at least one time point in the future based on the power generation amount data, the power consumption amount data and the power generation influence factors; determining a charging expected working condition and a discharging expected working condition of at least one time point in the future based on the estimated power generation amount data and the estimated power consumption amount data; determining electric quantity scheduling parameters among the new energy power generation device, the battery pack and the power grid based on the charging expected working condition, the discharging expected working condition and the current working condition data of the battery pack; the power dispatching parameters comprise battery power dispatching parameters and power grid power dispatching parameters of at least one time point in the future.

In some embodiments, the battery energy storage control unit is further configured to: based on the current and historical generated power data, power consumption data and power generation influence factors, predicting estimated generated power data of the new energy power generation device and estimated power consumption data of the power utilization device by using a generated power prediction model; the power generation and reception amount prediction model is a machine learning model.

In some embodiments, the battery energy storage control unit is configured to: based on current and historical working condition data, power generation amount data, power consumption data, current and historical battery polarization characteristic data and power grid load data, estimating and determining estimated battery energy storage risk type and confidence level of at least one future time point by using a risk estimation model; determining the battery pack with the confidence degree meeting the confidence degree condition as a target to be overhauled; and generating an overhaul instruction based on the target to be overhauled.

One or more embodiments of the present disclosure provide a method for monitoring a battery state of an energy storage power station. The method is applied to an energy storage power station battery state monitoring system, and is executed based on a battery control module of the energy storage power station battery state monitoring system, and comprises the following steps: determining the estimated battery energy storage risk type and the confidence level thereof at least at one time point in the future based on the current working condition data, the historical working condition data, the generated power data, the power consumption data, the current and historical battery polarization characteristic data and the power grid load data; determining an overhaul instruction of at least one battery pack of the energy storage power station based on the estimated battery energy storage risk type and the confidence level thereof; and sending the overhaul instruction to a power station maintenance center.

In some embodiments, the method further comprises: predicting estimated power generation amount data and estimated power consumption amount data of at least one time point in the future based on the power generation amount data, the power consumption amount data and the power generation influence factors; determining a charging expected working condition and a discharging expected working condition of at least one time point in the future based on the estimated power generation amount data and the estimated power consumption amount data; determining electric quantity scheduling parameters among the new energy power generation device, the battery pack and the power grid based on the charging expected working condition, the discharging expected working condition and the current working condition data of the battery pack; the power dispatching parameters comprise battery power dispatching parameters and power grid power dispatching parameters of at least one time point in the future.

In some embodiments, predicting estimated power generation amount data and estimated power consumption amount data for at least one point in time in the future based on the power generation amount data, the power consumption amount data, and the power generation influencing factors comprises: based on the current and historical generated power data, power consumption data and power generation influence factors, predicting estimated generated power data of the new energy power generation device and estimated power consumption data of the power utilization device by using a generated power prediction model; the power generation and reception amount prediction model is a machine learning model.

In some embodiments, determining the estimated battery energy storage risk type and its confidence level for the future at least one point in time based on the current and historical operating condition data, the generated power data, the used power data, and the grid load data comprises: based on current and historical working condition data, power generation amount data, power consumption data, current and historical battery polarization characteristic data and power grid load data, estimating and determining estimated battery energy storage risk type and confidence level of at least one future time point by using a risk estimation model; and determining an inspection instruction for at least one battery pack of the energy storage power station based on the estimated battery energy storage risk type and the confidence level thereof comprises: determining the battery pack with the confidence degree meeting the confidence degree condition as a target to be overhauled; and generating an overhaul instruction based on the target to be overhauled.

One or more embodiments of the present specification provide a processing apparatus comprising at least one processor and at least one memory; the at least one memory is configured to store computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement a method of energy storage plant battery condition monitoring.

One or more embodiments of the present description provide a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, perform a method of monitoring a state of a battery of an energy storage power station.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a block diagram of an energy storage power station battery condition monitoring system according to some embodiments of the present disclosure;

FIG. 2 is an exemplary flow chart of a method of monitoring the state of an energy storage power station battery according to some embodiments of the present description;

FIG. 3 is an exemplary flow chart for determining power scheduling parameters according to some embodiments of the present description;

FIG. 4 is a schematic diagram of determining estimated power generation amount data and estimated power usage amount data according to some embodiments of the present disclosure;

fig. 5 is a schematic diagram illustrating a determination of a predicted battery energy storage risk type according to some embodiments of the present disclosure.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

For how to monitor an energy storage power station, CN111584952B proposes a method and system for online evaluation of an electrochemical cell of an energy storage power station, which performs data analysis based on real-time data and historical data of the cell, and evaluates the running state of the cell from a short time scale and a long time scale. However, the method only monitors abnormality when faults or battery degradation occur, and cannot predict risks of hidden danger related to the battery of the energy storage power station in advance, so unexpected emergencies such as fire and the like are easy to occur.

Therefore, according to some embodiments of the specification, whether the energy storage risk of the battery exists in the future of the energy storage power station can be estimated based on the current working condition data, the historical working condition data, the power generation amount, the power consumption amount, the power grid load and other data of the battery pack, the corresponding overhaul instruction is determined in advance, and the staff is instructed to overhaul in time so as to avoid the occurrence of the energy storage risk, so that the operation safety of the energy storage power station is improved.

Fig. 1 is a block diagram of an energy storage power station battery condition monitoring system according to some embodiments of the present description. In some embodiments, as shown in fig. 1, the energy storage plant battery state monitoring system 100 may include a battery state monitoring module 110, a data storage device 120, a power generation and reception amount monitoring module 130, an alarm component 140, a grid load monitoring module 150, and a battery control module 160.

In some embodiments, an energy storage power station may include a battery pack, an energy storage converter (Power Conversion System, PCS), and an energy management system (ENERGY MANAGEMENT SYSTEM, EMS). The battery pack may include at least one energy storage battery, and generates electric energy through discharging and stores energy through charging. The energy management system EMS may convert the dc power generated by the battery pack into ac power through the inversion process of the energy storage converter PCS or the bi-directional inverter, and transmit the ac power to a power grid (e.g., an electric power facility or an end user, etc.). When the energy storage is less, the energy management system EMS can also extract electric power from the power grid to charge the battery so as to ensure the normal storage of electric energy.

In some embodiments, the energy storage power station may further comprise a new energy power generation device. The new energy power generation device is an electronic device that generates power using new energy such as solar energy and wind energy. In some embodiments, the new energy power generation device may include at least one of a wind power generation device, a solar power generation device, and a hydro power generation device.

In some embodiments, the new energy power generation device may be connected to the battery pack and the energy storage converter PCS through a circuit.

It should be noted that, because the new energy power generation device generates electricity and the load electricity is unstable, the energy storage power station relies on the electric quantity stored by the battery pack to balance the system energy of the energy storage power station. For example, when the load power of the energy storage power station is greater than the generated power of the new energy power generation device, the power grid, the new energy power generation device, and the battery pack may simultaneously supply power to the load.

In some embodiments, the energy storage power station may further comprise a power station maintenance center. The power station maintenance center can receive the overhaul instructions, and the corresponding equipment is overhauled by the distribution staff based on the overhaul instructions so as to avoid accidents caused by electromagnetism. For more details on the service instruction, reference is made to fig. 2 and the associated description below.

The battery state monitoring module 110 is a circuit module that monitors the battery pack. In some embodiments, the battery status monitoring module 110 may be in electrical connection with a battery pack of the energy storage power station, and the battery status monitoring module may be configured to collect operating condition data of the battery pack. In some embodiments, the battery status monitoring module may collect the working condition data of each battery in the battery pack through a temperature sensor, a voltmeter, and other detection devices, and then aggregate the working condition data into the battery pack, and send the working condition data to the data storage device 120. For more details on the operating mode data, reference may be made to FIG. 2 and its associated description below.

The data storage 120 refers to an electronic device that stores power station related data. In some embodiments, the data storage 120 may be used to store historical operating condition data collected by the battery condition monitoring module. The historical working condition data can reflect the past working state of the battery pack, and provides reference data for predicting the energy storage risk of the battery. For more details on historical operating condition data, reference may be made to FIG. 2 and its associated description below.

The power generation and reception amount monitoring module 130 is a circuit module for monitoring power generation and reception amount data of the energy storage power station. In some embodiments, the power generation and generation monitoring module 130 is configured to monitor power generation data of the new energy power generation device and power usage data of the power usage device in circuit connection with the energy storage power station. For example, the power generation and reception monitoring module 130 may monitor the power generated by the new energy power generation device and transmitted to the power grid and the power received from the outside (such as the power grid) through monitoring components such as a power meter, and the like, and monitor the power consumption data of the power consumption device. In some embodiments, the powered device may include a load apparatus that accesses the power grid. For more details on the power generation amount data and the power consumption amount data, reference is made to fig. 2 and the description thereof below.

The alarm unit 140 is a unit that gives an alarm message to give a reminder. In some embodiments, alert component 140 may be configured to issue alert information when the operating condition data does not meet a preset operating condition. In some embodiments, the alert component 140 may include one or more devices such as an indicator light, a horn, a display screen, and the like.

In some embodiments, the preset operating conditions may be set according to human experience or historical operating condition data corresponding to when the battery energy storage risk occurs. For example, if the preset operating condition is that the current of the battery pack does not exceed 1A, when the real-time current of the battery pack exceeds 1A, the battery control module 160 may drive the alarm component 140 to alarm in time.

The grid load monitoring module 150 is a circuit module that monitors grid load data of the grid. In some embodiments, the grid load monitoring module 150 may be configured to monitor grid load data of a grid accessed by the energy storage power station. In some embodiments, the grid load monitoring module 150 may collect grid load data for the grid through monitoring components such as a power meter, and the like. For more details on grid load data, reference may be made to fig. 2 and the associated description below.

The battery control module 160 is a circuit module that predicts, adjusts, and controls the state of the battery pack. In some embodiments, the battery control module 160 may determine power scheduling parameters based on current operating condition data of the battery to adjust power between the new energy power generation device, the battery pack, and the power grid to reduce grid fluctuations. For more details on the power scheduling parameters, reference is made to fig. 3 and the related description below.

In some embodiments, the battery control module 160 may include a grid load estimation unit 161.

The grid load estimating unit 161 is an electronic unit that predicts grid load data. In some embodiments, the grid load estimation unit 161 may be configured to: determining the estimated battery energy storage risk type and the confidence level thereof at least at one time point in the future based on the current working condition data, the historical working condition data, the generated power data, the power consumption data, the current and historical battery polarization characteristic data and the power grid load data; determining an overhaul instruction of at least one battery pack of the energy storage power station based on the estimated battery energy storage risk type and the confidence level thereof; and sending the overhaul instruction to a power station maintenance center. For more details on estimating battery energy storage risk type and its confidence level, and service instructions, see fig. 2 and its associated description below.

In some embodiments, the grid load estimation unit 161 may be further configured to: based on current and historical working condition data, power generation amount data, power consumption data, current and historical battery polarization characteristic data and power grid load data, estimating and determining estimated battery energy storage risk type and confidence level of at least one future time point by using a risk estimation model; determining the battery pack with the confidence degree meeting the confidence degree condition as a target to be overhauled; and generating an overhaul instruction based on the target to be overhauled. For more on the risk prediction model, confidence conditions, and the object to be serviced, reference is made to fig. 5 and the related description below.

In some embodiments, the battery control module 160 may include a battery energy storage control unit 162.

The battery energy storage control unit 162 refers to an electronic unit that adjusts the energy storage of the battery pack. In some embodiments, the battery energy storage control unit 162 may be configured to: predicting estimated power generation amount data and estimated power consumption amount data of at least one time point in the future based on the power generation amount data, the power consumption amount data and the power generation influence factors; determining a charging expected working condition and a discharging expected working condition of at least one time point in the future based on the estimated power generation amount data and the estimated power consumption amount data; determining electric quantity scheduling parameters among the new energy power generation device, the battery pack and the power grid based on the charging expected working condition, the discharging expected working condition and the current working condition data of the battery pack; the power dispatching parameters comprise battery power dispatching parameters and power grid power dispatching parameters of at least one time point in the future. For more factors affecting power generation, estimated power generation amount data, estimated power consumption amount data, expected charging conditions, and expected discharging conditions, reference is made to fig. 3 and the description thereof below.

In some embodiments, the battery energy storage control unit 162 may be further configured to: based on the current and historical generated power data, power consumption data and power generation influence factors, predicting estimated generated power data of the new energy power generation device and estimated power consumption data of the power utilization device by using a generated power prediction model; the power generation and reception amount prediction model is a machine learning model. For more details of the power generation amount prediction model, reference may be made to fig. 4 and its associated description below.

In some embodiments, the battery control module 160 may also include a power generation device monitoring module.

The power generation device monitoring module is an electronic unit for monitoring the power generation and reception amount of the new energy power generation device. In some embodiments, the power generation device monitoring module may be configured to: monitoring operation monitoring images and operation monitoring data of the new energy power generation device; the power generation and reception amount prediction model further includes a power generation and reception feature determination layer configured to determine a power generation and reception feature of the new energy power generation device based on the operation monitoring image, the historical overhaul data. For more details on the operational monitoring image, operational monitoring data, and the subject feature determination layer, reference is made to FIG. 4 and its associated description below.

It should be noted that the above description of the energy storage power station battery state monitoring system and the modules thereof is for convenience of description only, and is not intended to limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the battery state monitoring module, the data storage device, the power generation and reception amount monitoring module, the alarm component, the grid load monitoring module and the battery control module disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.

Fig. 2 is a main flow diagram of an energy storage power station battery condition monitoring system according to some embodiments of the present description. As shown in fig. 2, the process 200 includes the following steps. In some embodiments, the process 200 may be performed by the battery control module 160 described above.

Step 210, determining the estimated battery energy storage risk type and the confidence level thereof at least at one time point in the future based on the current working condition data, the historical working condition data, the generated power data, the power consumption data, the current and historical battery polarization characteristic data and the power grid load data.

The operating condition data refers to data related to the operation of the battery pack. In some embodiments, the current working condition data may reflect a working state of the battery pack at a current time point, and the historical working condition data may reflect a working state of the battery pack at least one time point in the history, so as to provide a reference for subsequently regulating and controlling the electric quantity of the battery pack.

In some embodiments, the operating condition data may include voltage current, remaining capacity, temperature rise, state of charge, battery remaining energy state, current density, etc. of the battery pack.

The voltage and the current can reflect whether the battery pack is in a normal working state, and if the voltage and the current exceed the rated current or the rated voltage of the battery pack, the battery pack can be judged to be in an abnormal working state.

The residual capacity refers to the residual charge amount of the battery pack which can be released in the future, and the unit of the residual charge amount can be ampere-hour A and milliampere-hour mAh. The remaining capacity may be used to direct the future point in time to control the charge and discharge state of the battery pack at the future point in time. For example, the larger the remaining capacity, the more charge the battery pack can release in the future, and thus the need to charge it is eliminated.

The temperature rise refers to a temperature difference value that the temperature of the battery pack is higher than the ambient temperature, and the temperature rise can reflect the heat-generating and heat-dissipating conditions of the battery pack in operation. For example, the larger the temperature rise, the larger the heat dissipation condition of the battery pack in operation, and the larger the heat dissipation, the more likely the battery energy storage risk will occur.

The state of charge refers to the ratio of the remaining capacity of the battery to the capacity of the fully charged state, which is commonly expressed as a percentage. For example, a state of charge of 0% may indicate that the battery pack is in a fully discharged state.

The remaining energy of the battery pack refers to the amount of work that can be done in the future, and may be in watt-hours Wh, kilowatt-hours kWh, etc. The battery remaining energy state refers to a ratio of remaining energy of the battery pack to rated energy, and may also be expressed in terms of a percentage. For example, a battery remaining energy state of 0% may indicate that the battery pack is not energized and is in a state of failing to perform work.

The current density refers to the amount of current that passes through the cell per unit surface area. In some embodiments, the current density may reflect the energy conversion rate of the battery, so that the operating state of the battery pack may be determined. Energy conversion refers to the conversion of energy into chemical energy per unit time. For example, the higher the current density, the higher the energy conversion rate of the battery, and the higher the energy conversion rate of the battery, the more likely the battery generates excessive heat, expands or ages in advance, and the like, and a certain energy storage risk exists.

In some embodiments, the battery control module may collect current operating condition data of the battery pack through the battery state monitoring module, and may also read historical operating condition data of the battery pack through the data storage device. For more details on the battery status monitoring module and the data storage device, reference is made to fig. 1 and its associated description above.

The generated energy is the electric energy generated by the new energy power generation device in a certain area and is transmitted to the power grid in the area. The power receiving amount refers to the amount of power received by the new energy power generation device from the outside in a certain area. Because the new energy power generation device may also need electric energy to supply power when not generating power, for example, the control system of the new energy power generation device needs additional electric energy to supply power so as to drive the generator of the new energy power generation device to generate power.

Correspondingly, in some embodiments, the power generation amount data of the new energy power generation device may affect the load of the battery pack of the energy storage system. For example, the generated energy of the new energy power generation device fluctuates, so that the battery pack is frequently charged and discharged, the power grid is easy to fluctuate, the charging and discharging of the battery pack in the energy storage power station are easy to be unexpected, and the battery energy storage risk exists.

The electricity consumption data refers to the amount of electricity consumed by an electricity consumption device (e.g., a load) for a certain period of time. Because the power usage device is not stationary, the power usage data of the power usage device may also affect the load of the battery pack of the energy storage system. For example, the electricity consumption of the electricity consumption device fluctuates, which causes frequent charge-discharge switching of the battery pack and easy fluctuation of the power grid, and thus the energy storage risk of the battery in the energy storage power station can be caused.

In some embodiments, the battery control module may collect the power generation and reception data of the new energy power generation device and the power consumption data of the power consumption device through the power generation and reception detection module. For more details of the power generation and reception amount detection module, the new energy power generation device, and the power utilization device, reference is made to fig. 1 and the description thereof.

The battery polarization characteristic data is characteristic data of a potential shift phenomenon occurring in the battery. The polarization voltage is related to the voltage, current, temperature, current change rate of the battery, and exhibits a characteristic of decay with time. The characteristic state of the battery can be characterized by drawing a 5-dimensional coordinate system according to the voltage, current, temperature, current change rate and time of the battery. The current and historical battery polarization characteristic data can draw the characteristic state of the battery, and the characteristic state is subjected to similarity evaluation with the normal characteristic state and the abnormal characteristic state, so that the working state and the risk condition of the battery can be obtained.

In some embodiments, the battery control module may collect current and historical operating condition data of the battery pack through the battery state monitoring module, and determine battery polarization characteristic data based on current density and voltage in the operating condition data. For more details of the power generation and detection module, reference is made to fig. 1 and the description thereof.

Grid load data refers to the extraction of electrical power from the grid. In some embodiments, the grid load data may also affect the load of the battery pack of the energy storage system. For example, the larger the fluctuation of the power grid load data, the more likely the power grid is to have fluctuation, and the more likely the battery is to be charged and discharged, the battery energy storage risk is caused.

In some embodiments, the battery control module may collect grid load data of the grid through the grid load monitoring module described above. For more details of the grid load monitoring module, reference is made to fig. 1 and its associated description above.

The estimated battery energy storage risk type refers to the type of energy storage risk frequently caused by battery charging and discharging. When the power grid frequently fluctuates, the load of the battery pack needs to be frequently changed, the charging and discharging states are frequently switched, and unexpected emergencies, such as fires, and the like, of the battery pack are easy to occur. In some embodiments, the estimated battery energy storage risk type may include one or more of leakage, false electricity, breakage, fire, and the like.

The confidence degree of the estimated battery energy storage risk type refers to the confidence degree of the emergency of the battery pack at least at one time point in the future, for example, the confidence degree of the first battery pack in existence of leakage risk is 0.9. The higher the confidence level at a future point in time, the more likely the battery pack is to be in emergency at that future point in time.

In some embodiments, the battery control module may determine the estimated battery energy storage risk type and the confidence level thereof at least at one future point in time in various manners such as vector library matching, modeling, and the like based on the current operating condition data and the historical operating condition data, the power generation amount data, the power consumption amount data, the current and historical battery polarization characteristic data, and the power grid load data.

For example, the battery control module may construct a battery feature vector based on the current operating condition data and the historical operating condition data, the generated power data, the power consumption data, the current and historical battery polarization characteristic data and the grid load data, retrieve the battery feature vector in the risk vector database, retrieve a reference battery feature vector similar to the battery feature vector, and determine a reference estimated battery energy storage risk type and a reference confidence level corresponding to the reference battery feature vector as the estimated battery energy storage risk type and the confidence level.

The risk vector database stores a plurality of reference battery feature vectors, a plurality of corresponding reference estimated battery energy storage risk types and reference confidence degrees thereof. The reference battery feature vector may be constructed based on historical energy storage power plant data. The reference estimated battery energy storage risk type can be constructed based on the battery energy storage risk actually appearing in the history, and the reference confidence level can be constructed based on the ratio of the number of times of the battery energy storage risk actually appearing in the history to the number of times of the battery energy storage risk type estimated in the history, and can be determined by manual labeling. For more details on determining the type of pre-estimated battery energy storage risk and its confidence level, see fig. 5 and its associated description below.

Step 220, determining an overhaul instruction for at least one battery pack of the energy storage power station based on the estimated battery energy storage risk type and the confidence level thereof.

The overhaul instruction is an instruction for reminding a worker to overhaul equipment with risks. In some embodiments, the overhaul instructions may instruct the staff to overhaul the corresponding battery pack to avoid an emergency of the battery pack. In some embodiments, the overhaul instructions may include an address of an overhaul target, a risk reason, etc. Further details of the service instruction are provided in fig. 1 and related description.

In some embodiments, the battery control module may determine the service order of at least one battery pack of the energy storage power station in a variety of ways. The battery control module may determine that the battery energy storage risk type is greater than a preset confidence threshold, so as to determine that the battery energy storage risk exists, and accordingly determine a corresponding maintenance instruction based on information such as a battery pack corresponding to the battery energy storage risk type and a time point. The preset confidence threshold value can be determined according to the ratio of the number of times of the battery energy storage risk actually appearing in the history to the number of times of the battery energy storage risk type estimated in the history, or can be determined by means of manual labeling and the like. For more details on determining service instructions, reference is made to fig. 5 and its associated description below.

And 230, sending the overhaul instruction to a power station maintenance center.

In some embodiments, the battery control module may send the service instruction to the plant maintenance center in a variety of ways, such as by voice, text, etc. The power station maintenance center can estimate future time points corresponding to the battery energy storage risk types from near to far according to the overhaul instructions, and allocate staff to overhaul; the staff may also be allocated based on other allocation bases. For more details on the plant maintenance center, reference is made to fig. 1 and the description related thereto.

In the embodiment of the specification, whether the energy storage risk of the battery exists in the future of the energy storage power station can be estimated based on the current working condition data, the historical working condition data, the power generation amount, the power consumption amount, the current and historical battery polarization characteristic data, the power grid load and other data of the battery pack, a corresponding overhaul instruction is determined in advance, and workers are instructed to overhaul in time, so that the occurrence of the energy storage risk is avoided, and the operation safety of the energy storage power station is improved.

Fig. 3 is an exemplary flow chart for determining power scheduling parameters according to some embodiments of the present description. In some embodiments, as shown in FIG. 3, the process 300 includes the following steps. In some embodiments, the process 300 may be performed by the battery control module 160 described above.

Step 310, predicting estimated power generation amount data and estimated power consumption amount data of at least one time point in the future based on the power generation amount data, the power consumption amount data and the power generation influencing factors.

The power generation influencing factors refer to environmental influencing factors to which the new energy power generation device is subjected. In some embodiments, the power generation influencing factors may be related to the type of new energy power generation device. For example, the new energy power generation device is a solar power generation device, and the power generation influencing factors may include weather data, season data, geographical features, etc. at the present and future points in time. The weather data may include, among other things, light level, temperature, fog concentration, etc.

In some embodiments, the power generation influencing factors may influence the generated power of the new energy power generation device at a future point in time. For example, when the new energy power generation device is a wind power generation device, the larger the wind power data at the future time point, the larger the generated power at the future time point of the new energy power generation device.

In some embodiments, the battery control module may obtain the power generation influencing factor through a manual input manner, or may obtain the power generation influencing factor through other manners such as a third party network platform (e.g., a weather forecast network, etc.).

In some embodiments, the historical power generation amount data and power consumption data may also affect the estimated power generation amount data and the estimated power consumption amount data for at least one future point in time. For example, the larger the historical power generation amount data is, the larger the predicted power generation amount data at the predicted future point in time is. For more details on the acquisition of power generation and usage data, reference is made to fig. 2 and its associated description above.

The estimated power generation amount data and the estimated power consumption amount data refer to the predicted power generation amount data of the new energy power generation device at the future time point and the power consumption amount data of the electric equipment at the future time point.

It should be noted that, when the power of the new energy power generation device decreases, the power generation and reception monitoring module may monitor the decrease of the power of the new energy power generation device (e.g., the estimated power generation and reception data) and send a signal to the battery pack to request the battery pack to release electric energy to the load, thereby providing additional auxiliary power supply and maintaining the stability of the power grid.

In some embodiments, the battery control module may determine estimated power generation amount data and estimated power consumption amount data of the power at a future point in time through vector library matching and model recognition based on the historical power generation amount data, the historical power consumption amount data and the power generation influence factors. For example, the battery control module may construct a power generation and reception feature vector based on the historical power generation and reception data, the historical power consumption data, and the power generation influencing factors, use a pre-estimated power generation and reception feature vector database based on the power generation and reception feature vector, find a corresponding reference power generation and reception feature vector based on the vector distance, and determine the reference pre-estimated power generation and reception data and the reference pre-estimated power consumption data corresponding to the reference power generation and reception feature vector as the pre-estimated power generation and reception data and the pre-estimated power consumption data of the power at a future time point.

The estimated power vector database stores a plurality of reference power generation and reception feature vectors, a plurality of corresponding reference estimated power generation and reception data and reference estimated power consumption data, the reference power generation and reception feature vectors can be constructed according to historical power generation and reception data, historical power consumption data and historical power generation influence factors of a first historical time point, and the corresponding reference estimated power generation and reception data and reference estimated power consumption data can be constructed according to power generation and power consumption data of a second historical time point. Wherein the second historical point in time is later than the first historical point in time. For more details on the estimated power generation amount data and the estimated power consumption amount data, refer to fig. 4 and the description thereof below.

Step 320, determining a charging expected working condition and a discharging expected working condition of at least one time point in the future based on the estimated power generation amount data and the estimated power consumption amount data.

The expected charging condition refers to a working condition in which a battery pack or a power grid is not needed to assist in supplying power to an electric device. That is, the new energy power generation device generates enough power without auxiliary power supply by the battery pack or the power grid, and can also supply power to the power grid or the battery pack. In some embodiments, the charging desired conditions may include a desired charging power of the battery pack.

The expected discharging working condition refers to the working condition that the battery pack or the power grid is required to assist in supplying power to the power utilization device. That is, the new energy power generation device is insufficient in power generation, and a battery pack or a power grid is required for auxiliary power supply. In some embodiments, the discharge expected operating condition may include an expected discharge power of the battery pack. For more details on the amount of power generated, the amount of power used, and the amount of power received, reference is made to fig. 2 and the description thereof.

In some embodiments, the battery control module may determine, as the charging expected operating condition, an operating state in which the estimated power generation amount of the new energy power generation device is greater than or equal to a sum of the estimated power consumption amount of the power utilization device and the estimated power reception amount of the new energy power generation device. In other words, in some embodiments, the battery control module may determine that the estimated power generation amount of the new energy power generation device is smaller than the working state of the sum of the estimated power consumption amount of the power utilization device and the estimated power receiving amount of the new energy power generation device as the expected discharging working condition. Accordingly, in some embodiments, the battery control module may determine the expected charge power or the discharge power thereof based on the estimated power generation amount data and the estimated power consumption amount data. For example, when the charging expected working condition is determined, the battery control module may use a difference between the estimated power generation amount of the new energy power generation device and the sum of the estimated power consumption amount of the power utilization device and the estimated power receiving amount of the new energy power generation device as the expected charging power.

That is, the battery control module may assist in timely power supply when the power generated by the new energy power generation device decreases (e.g., determined as a discharging expected condition), and leave a battery pack and a power grid free to receive power generated by the new energy power generation device when the power generated by the new energy power generation device increases (e.g., determined as a charging expected condition), so as to avoid increasing the risk of battery energy storage.

And 330, determining electric quantity scheduling parameters among the new energy power generation device, the battery pack and the power grid based on the charging expected working condition, the discharging expected working condition and the current working condition data of the battery pack.

The power dispatching parameter refers to a parameter of transferring electric energy among the new energy power generation device, the battery and the power grid. For example, the power schedule parameter may include the amount of power provided by the new energy power generation device to the battery pack and the grid for charging when in the charging expectancy condition.

In some embodiments, the power scheduling parameters may include a battery power scheduling parameter and a grid power scheduling parameter for at least one point in time in the future. The battery power dispatching parameter refers to the power provided by the battery pack or the energy provided by the battery pack, and the power grid power dispatching parameter refers to the power provided by the power grid or the power provided by the power grid. For more details on the current operating condition data, reference is made to FIG. 1 and its associated description.

In some embodiments, the battery control module may determine the power scheduling parameters between the new energy power generation device, the battery pack, and the power grid using a variety of modes, such as an economy mode, a safety mode, and the like. In some embodiments, the battery control module may select a corresponding mode to calculate the power schedule parameter based on a confidence level of the estimated battery energy storage risk type.

The economy mode refers to a calculation mode giving priority to grid stability. For example, when the confidence of the estimated battery energy storage risk type of the battery pack is less than a preset health threshold, the battery control module may select the economy mode to calculate the power schedule parameter. The preset health threshold may be determined according to human experience or a health confidence of the historical battery pack. In the economy mode, the battery pack has a higher health level, and the battery pack can maintain a higher electric quantity or be full of electricity for a long time.

In the expected charging condition in the economy mode, the battery control module can control the new energy power generation device to charge the battery pack until the battery is full or until the power supply stage is finished. Correspondingly, the battery power dispatching parameter may be a difference value between the battery power after the charging is finished and the current remaining energy of the battery, and the power grid power dispatching parameter may be a difference value between the surplus power of the new energy power generation device and the battery power dispatching parameter. The surplus electric quantity is the surplus electric quantity which can be provided for the power grid or the battery pack besides the new energy power generation device which supplies power for the power utilization device.

In the expected discharging working condition of the economic mode, the battery control module can adopt the battery pack to supply power for the power utilization device, and if the power utilization device still needs other electric quantity, the battery control module can utilize the power grid to supply power for the power utilization device. Correspondingly, the battery power dispatching parameter may be a difference value between the power to be supplemented of the power utilization device and the power generation capacity of the new energy power generation device, and the power grid power dispatching parameter may be a difference value between the power to be supplemented of the power utilization device and the battery power dispatching parameter. The electric quantity to be supplemented of the electric device is the electric quantity which is needed to be supplemented by the electric device except for the power supply of the new energy power generation device.

The safety mode refers to a calculation mode in which the risk of storing energy of the battery pack is prioritized. For example, when the confidence of the estimated battery energy storage risk type of the battery pack is greater than a preset health threshold, the battery control module may select a safety mode to calculate the power schedule parameter. In the safety mode, the health degree of the battery pack is low, the battery pack keeps high electric quantity for a long time or is full of electricity for a long time, risks such as damage and explosion exist, and the battery pack can be only charged to a preset energy storage threshold value.

In some embodiments, the preset energy storage threshold may be related to a confidence in the estimated battery energy storage risk type. For example, the higher the confidence of the estimated battery energy storage risk type, the greater the probability of the battery pack risk in the future, the lower the preset energy storage threshold needs to be set, so as to avoid damage, explosion and the like of the battery pack. The preset energy storage threshold value can be determined through various modes such as a query table and a network based on the confidence level. For example, the battery control module may query, based on the confidence level, a preset energy storage threshold corresponding to a reference confidence level similar to the confidence level in an energy storage threshold corresponding table, where the energy storage threshold corresponding table may store a plurality of preset energy storage thresholds corresponding to the reference confidence level, and the energy storage threshold corresponding table may be based on various manners such as manual experience or historical data.

And in the expected charging working condition of the safety mode, the battery control module can control the new energy power generation device to charge the battery pack to a preset energy storage threshold value or until the power supply stage is finished. Correspondingly, the battery power scheduling parameter may be a difference value between a preset energy storage threshold and the current remaining energy of the battery pack, and the power scheduling parameter may be a difference value between the surplus power of the new energy power generation device and the battery power scheduling parameter. The battery control module is in the charging expected operating mode of the safe mode, which is similar to the specific implementation of the discharging expected operating mode of the healthy mode. For more details on the new energy generation device, the battery pack and the power grid, reference is made to fig. 1 and the related description.

In the embodiment of the specification, the charging expected working condition and the discharging expected working condition of the future time point are determined by predicting the power generation amount data and the power consumption data at the future time point, and the electric energy dispatching parameters among the corresponding new energy power generation device, the corresponding battery and the corresponding electric power dispatching parameters among the electric network can be determined and adopted to dispatch the electric energy so as to ensure the stability of the electric network and avoid the occurrence of energy storage risks, thereby improving the operation safety of the energy storage power station.

In some embodiments, the power scheduling parameter may also be related to grid electricity prices. The battery control module can also determine the surplus electric quantity and the electric quantity to be supplemented of the new energy power generation device at least at one time point in the future based on the charging expected working condition, the discharging expected working condition, the estimated power generation quantity data and the estimated power consumption quantity data; generating at least one candidate power scheduling parameter based on the surplus power and the power to be supplemented; and determining a target electric quantity scheduling parameter based on the candidate electric quantity scheduling parameter, the electric grid price and a preset energy storage threshold value.

Grid electricity prices refer to the price at which the grid provides electrical energy to consumer devices. In some embodiments, grid electricity prices may affect the policy of the battery control module to determine the power scheduling parameters. For example, in the case where the power generation amount of the new-energy power generation device and the power supply amount of the battery pack can satisfy the power consumption device, the battery control module may not purchase electric energy from the power grid. The battery control module can provide electric energy to the power grid as much as possible when the power grid electricity price is high; and when the electricity price of the power grid is low, the power grid is controlled to charge the battery pack. In some embodiments, the battery control module may obtain the grid electricity price via a network, manual input, or the like.

In some embodiments, the battery control module may calculate the surplus power and the power to be replenished at least at one future point in time based on the charging expected condition, the discharging expected condition, the estimated power generation amount data, and the estimated power consumption amount data. For example, the surplus power may be a difference between the estimated power generation amount data and the estimated power consumption amount data when the charging is in the expected condition. When the electric quantity to be supplemented is in the expected discharging working condition, the electric quantity to be supplemented can be the difference value between the estimated power consumption data and the estimated power generation data. For more details on the amount of power to be replenished and the amount of excess power, see step 330 and the description thereof.

In some embodiments, the battery control module may randomly generate at least one candidate power schedule parameter based on the surplus power and the power to be replenished. The battery control module can randomly generate battery pack charging quantity and battery pack power supply quantity so as to determine corresponding power grid charging quantity and power grid power supply quantity.

In some embodiments, the battery control module may require that the battery charge amount be less than or equal to the difference between the preset energy storage threshold and the current battery charge amount during each of the charging desired conditions. And in each discharging expected working condition, the difference value between the current battery pack electric quantity and the battery pack power supply quantity is larger than or equal to a preset energy storage threshold value. That is, the randomly generated battery charge amount, battery power supply amount, and the like cannot be used for the battery power consumption, and the preset energy storage threshold may be used for coping with an emergency.

For example, assume that the battery pack is in a discharge expected condition at least twice, and the amount of electricity to be replenished required for the first discharge expected condition and the second discharge expected condition, respectively, is (100, 110). The first expected discharging working condition may be 3 to 4 hours in the future, the second expected discharging working condition may be 7 hours in the future, 100 is the electric quantity to be supplemented required by the first expected discharging working condition, and 110 is the electric quantity to be supplemented required by the second expected discharging working condition. The initial current electric quantity of the battery pack is 50; the surplus electric quantity of the new energy power generation device corresponding to 2 charging expected working conditions (such as a first charging expected working condition and a second charging expected working condition) in the future is (30, 40) in the 1 st to 2 th hours, and the surplus electric quantity in the future is (50, 20) in the 5 th to 6 th hours. The first charging expected working condition may be 1 to 2 hours in the future, the second charging expected working condition may be 5 to 6 hours in the future, 30 in (30, 40) is the margin electric quantity representing 1 hour in the future, and 40 in (30, 40) is the margin electric quantity representing 2 hours in the future. Randomly generating battery pack charge amounts (25, 35) corresponding to the 2 expected charging working conditions and in the future 1 to 2 hours, and battery pack charge amounts (40, 20) in the future 5 to 6 hours; the randomly generated battery pack power supply quantity corresponding to the 2 expected discharging working conditions is 90,70. The preset energy storage threshold of the battery pack may be 20.

And the electric network charge amount of the electric network corresponding to the 2 charging expected working conditions for the 1 st to 2 nd hours in the future is (30-25=5, 40-35=5), the electric network charge amount of the electric network corresponding to the 5 th to 6 th hours in the future is (50-40=10, 20-20=0), and the electric network power supply amounts of the 2 discharging expected working conditions are (100-90=10, 110-70=40).

In some embodiments, the preset energy storage threshold may be related to historical overhaul data, historical pre-estimated battery energy storage risk types and their confidence, historical power generation amount data.

In some embodiments, the historical overhaul data, the historical pre-estimated battery energy storage risk type and its confidence, and the historical power generation amount data may affect the setting of the preset energy storage threshold. For example, the more times of the historical overhaul data, the more the last overhaul time point in the historical overhaul data is far from the current time point, or the higher the type of the historical estimated battery energy storage risk, or the more unstable the historical generated electricity quantity data, the lower the health degree of the battery is, the lower the preset energy storage threshold value can be set so as to prevent the battery from malfunctioning.

In some embodiments, the battery control module may determine the preset energy storage threshold using a vector database based on historical overhaul data, historical risk types and their confidence, historical power generation amount data.

For example, the battery control module may construct a threshold feature vector based on the historical overhaul data, the historical risk type and its confidence level, and the historical power generation amount data, retrieve the threshold feature vector from the energy storage threshold vector library, retrieve a reference threshold feature vector similar to the threshold feature vector, and determine a reference preset energy storage threshold corresponding to the reference threshold feature vector as the preset energy storage threshold.

The energy storage threshold value vector library stores a plurality of reference threshold value feature vectors and a plurality of corresponding reference preset energy storage threshold values. The reference threshold feature vector is constructed based on historical overhaul data, historical risk types, and confidence levels and historical power generation and reception data. The reference preset energy storage threshold value can be constructed based on a historical prediction energy storage threshold value, and can be determined by manual annotation.

In the embodiment of the specification, the influence of the historical overhaul data, the historical estimated battery energy storage risk type, the confidence coefficient thereof and the historical generated power data is considered, so that the set preset energy storage threshold is closer to the optimal energy storage threshold of the battery, the stability of a power grid is ensured, the occurrence of energy storage risk is avoided, and the operation safety of an energy storage power station is improved.

In some embodiments, the battery control module may also determine the target power scheduling parameter based on the candidate power scheduling parameter, the grid power price, and a preset energy storage threshold. For example, the battery control module may calculate, based on the grid electricity price and a preset energy storage threshold, a corresponding grid gain and grid fluctuation using each candidate electricity scheduling parameter, and select, as the target electricity scheduling parameter, the candidate electricity scheduling parameter having a larger grid gain and a smaller grid fluctuation, so as to balance the grid gain and the grid fluctuation.

In the embodiment of the specification, by considering the influence of the power grid electricity price on the charging expected working condition and the discharging expected working condition, the optimal candidate electric quantity scheduling parameter is selected from the plurality of candidate electric quantity scheduling parameters to serve as the target electric quantity scheduling parameter, so that the power grid income and the power grid fluctuation are balanced, the power grid stability is ensured, the occurrence of energy storage risks is avoided, the operation safety of an energy storage power station is improved, and meanwhile, the income of power transmission to the power grid is improved.

In some embodiments, the battery control module may further determine a power cost and an energy storage risk index of the candidate power scheduling parameter based on the grid power price and a preset energy storage threshold; carrying out weighted summation on the electricity cost and the energy storage risk index, and determining the adaptability of the candidate electric quantity scheduling parameters; the first coefficient of the electricity cost and the second coefficient of the energy storage risk index are related to the current mode of the system; based on the fitness, a target power scheduling parameter is determined.

The electricity cost refers to the balance data of future transactions with the power grid. In some embodiments, the electricity costs may be the difference between the revenue of providing electrical energy to the grid in the future (i.e., the sales revenue) and the expenditure of providing electrical energy to the grid (i.e., the buying expenditure). In some embodiments, the cost of electricity may be positive or negative. For example, when the electricity costs are negative, it may be stated that the battery energy storage control unit requires the grid to provide electrical energy in the future overall stage, requiring expenditure.

In some embodiments, the battery control module may calculate, based on the grid electricity prices and the preset energy storage threshold, at least one point in time in the future for each candidate electricity scheduling parameter, provide revenue for the electricity grid and pay for the electricity grid to provide electricity, thereby determining electricity costs for the at least one point in time in the future corresponding to the candidate electricity scheduling parameter. Further examples of obtaining grid electricity prices and preset energy storage thresholds may be found in the above description.

The energy storage risk index refers to the degree of risk of energy storage of the battery pack. In some embodiments, the energy storage risk index may be related to a length of time that the charge of the battery is greater than a preset energy storage threshold. For example, the longer the duration, the more likely the battery is to present an energy storage risk, the higher the energy storage risk index.

In some embodiments, the battery control module may query the corresponding energy storage risk index by querying a table or the like based on each candidate power scheduling parameter, the grid power price, and the preset energy storage threshold. For example, the battery control module may query a preset risk correspondence table for an energy storage risk index corresponding to the candidate power scheduling parameter based on the candidate power scheduling parameter, the grid power price, and a preset energy storage threshold. The preset risk correspondence table can be constructed according to manual experience or based on historical power scheduling parameters and historical energy storage risk indexes.

The fitness is an indicator describing the individual performance of the candidate power schedule parameters. In some embodiments, the fitness may be used as a reference basis for eliminating candidate power scheduling parameters. For example, the smaller the fitness, the smaller the electricity cost and the time length that the battery power is larger than the optimal energy storage threshold, the smaller the probability of accident of the battery pack, and the more suitable the power scheduling parameter is as the target power scheduling parameter.

In some embodiments, the battery control module may weight sum the electricity cost and the energy storage risk index to determine the fitness of the candidate power schedule parameters. Illustratively, the fitness of the candidate power schedule parameter may be a sum of a product of the power cost and the first coefficient, and a product of the energy storage risk index and the second coefficient.

In some embodiments, the first coefficient and the second coefficient may be related to a current mode of the system. The current mode of the system may include an economy mode, a security mode, and the like. For example, when the current mode of the system is the economy mode, the battery control module may increase the first coefficient to increase the impact of electricity costs on fitness. When the current mode of the system is the safety mode, the battery control module can increase the second coefficient to increase the influence of the energy storage risk index on the fitness.

In some embodiments, the battery control module may determine the target power schedule parameter using a preset algorithm. An exemplary preset algorithm flow is provided below to detail a specific implementation of determining the target power scheduling parameter. In some embodiments, the preset algorithm may be executed by the battery control module. The preset algorithm flow may include:

And step 1, coding the randomly generated candidate electric quantity scheduling parameters.

In some embodiments, the battery control module may number the charging expected operating condition and the discharging expected operating condition, and perform coding operations such as binary coding, real coding, and the like based on the numbers. For example, the battery control module may encode a candidate power schedule parameter to obtain codes (S1, S2, L3, L4, S5, S6, L7). Wherein S represents a charging expected working condition; l represents a discharge expected working condition; the values represent future points in time, and the codes (S1, S2, L3, L4, S5, S6, L7) may represent sub-power scheduling parameters for each 7 hours in the future.

In some embodiments, each polynomial encoded may also include a battery charge and a grid supply for the corresponding point in time. For example, let s1= (N1, M1). Where N1 represents the charge of the battery at the first hour and M1 represents the charge of the grid at the first hour. For another example, let l3= (N3, M3). Where N3 represents the battery supply (corresponding to the 3 rd hour) and M3 represents the grid supply (corresponding to the 3 rd hour). The specific implementation of randomly generated candidate power schedule parameters, as well as the battery pack charge and grid supply may be found in the above description.

And 2, setting an initial solution space.

In some embodiments, the battery control module may generate X initial scheduling parameters, i.e., X initial solutions, based on the encoding in step 1.

And step 3, setting a fitness function, and determining the fitness of each candidate electric quantity scheduling parameter.

In some embodiments, the battery control module may set the fitness to a first coefficient of electricity cost + a second coefficient of energy storage risk index. The electricity cost can be future electricity selling income-electricity buying expenditure. The electricity selling income may be equal to a product of the amount of electricity sold to the power grid and the electricity price at the corresponding point in time, and the electricity buying expense may be equal to a product of the amount of electricity purchased from the power grid and the electricity price at the corresponding point in time.

In some implementations, the battery control module may use a time period based on which the battery charge is greater than a preset energy storage threshold as the energy storage risk index. For more details on fitness, electricity costs and energy storage risk index, see the relevant description above.

And 4, selecting preferentially according to the selection function.

In some embodiments, the battery control module may determine the selection function based on an operator such as roulette. Wherein, the selection probability of the candidate power schedule parameter can be inversely related to the fitness. For example, the smaller the fitness, the greater the probability of the candidate power schedule parameter being selected. Illustratively, the probability of selection of the candidate power schedule parameter may be 1- [ fitness/total fitness value of a certain candidate power schedule parameter ]. The total fitness value may be a sum of fitness of all candidate power scheduling parameters.

And 5, intersecting.

The crossover means that two individuals are used as parents to exchange and combine, and offspring with excellent characteristics are obtained. In some embodiments, the battery control module may select two candidate power schedule parameters from the plurality of candidate power schedule parameters to intersect, resulting in a new candidate power schedule parameter as a child. Where crossover probability refers to the probability that two individuals cross. For example, the crossover probability may be set to (0.4-0.99). In some embodiments, the types of intersections may further include: single point crossing, multi-point crossing, uniform crossing, etc.

The single-point cross refers to the type that the candidate power scheduling parameters exchange a plurality of data at one cross point. The multi-point crossing refers to the type of data of the cross point carton that the candidate power schedule parameter exchanges across the plurality of cross points. The uniform crossing refers to scanning each data (such as the battery pack charge amount) in the candidate power scheduling parameters in turn, and judging whether the data crosses the data of another candidate power scheduling parameter or not based on the crossing probability.

And 6, performing mutation.

Variation refers to changing the data of the offspring. In some embodiments, the battery control module may mutate the candidate power schedule parameters as children according to the mutation probability, and change the data of the candidate power schedule parameters. Wherein the probability of variation may be 0.5. In some embodiments, the variety of variations may further include: basic position variation, uniform variation, non-uniform variation, and the like.

The basic bit mutation refers to that the candidate power scheduling parameters are mutated on the basis of mutation probability in data at one or more randomly designated positions. The uniform variation refers to replacing each data in the candidate power scheduling parameters according to the variation probability by using random numbers uniformly distributed within a preset range. The non-uniform variation refers to that random disturbance is performed on the data of the candidate power scheduling parameters, and the result after the disturbance is used as the data after the variation.

And 7, selecting the child generation.

In some embodiments, the battery control module may select a candidate power schedule parameter that meets a preset power condition. The preset electric quantity condition may include: in each charging expected working condition of the candidate electric quantity scheduling parameter, the charging quantity of the battery pack is smaller than or equal to the difference value between the preset energy storage threshold value and the current electric quantity of the battery pack; and in each discharging expected working condition, the difference value between the current battery pack electric quantity and the battery pack power supply quantity is larger than or equal to a preset energy storage threshold value. That is, the randomly generated battery charge amount, battery power supply amount, and the like cannot be used for the battery power consumption, and the preset energy storage threshold may be used for coping with an emergency. Further examples of preset charge conditions may be found in the related description above.

And 8, eliminating the candidate electric quantity scheduling parameters.

In some embodiments, the battery control module may replace the candidate power scheduling parameters with a larger fitness (the smaller the fitness is, the better the fitness is) in the original population with the newly generated candidate power scheduling parameters (e.g., the candidate power scheduling parameters generated in step 5 and step 6). For example, the battery control module may sort the candidate power scheduling parameters (such as the candidate power scheduling parameters generated in the step 1 and the step 2) in the original population from large to small according to the fitness, and eliminate a preset number of candidate power scheduling parameters with the front fitness (i.e. the higher fitness). The preset number can be set according to various modes such as manual experience, network inquiry and the like.

In some embodiments, the battery control module may repeat the above steps 3 to 8, and repeat the evolution until the iteration stop condition is satisfied.

The iteration stop condition may include: the maximum number of evolutions has been completed, the fitness reaches a preset desired value, the fitness value remains the same for the preset number of iterations, or the fitness difference between the two iterations is below a preset difference threshold. The number of evolutions, the preset expected value, the preset iteration number and the preset difference threshold can be set according to various modes such as manual experience, network inquiry and the like.

In some embodiments, after the iteration stops, the battery control module may select the candidate power scheduling parameter with the smallest fitness as the target power scheduling parameter, so as to balance the grid gain and the grid fluctuation.

In the embodiment of the specification, the power consumption cost and the energy storage risk index of the candidate electric quantity scheduling parameters are calculated, and the respective coefficients are also related to the current mode of the system, so that the fitness obtained by weighting and summing can reflect the performance of the candidate electric quantity scheduling parameters more accurately, the optimal target electric quantity scheduling parameters can be selected, the stability of a power grid is ensured, the occurrence of energy storage risk is avoided, and the operation safety of an energy storage power station is improved.

FIG. 4 is a schematic diagram illustrating determining estimated power generation amount data and estimated power consumption amount data according to some embodiments of the present disclosure. In some embodiments, as shown in fig. 4, the battery control module may predict estimated power generation amount data 450 of the new energy power generation device and estimated power consumption amount data 460 of the power generation device using a power generation amount prediction model 440 based on current and historical power generation amount data 410, power consumption amount data 420, and power generation influencing factors 430; the power generation and reception amount prediction model 440 is a machine learning model.

In some embodiments, the power generation and reception amount prediction model 440 may be a machine learning model, such as a Recurrent Neural Network (RNN), or the like.

In some embodiments, the inputs to the power generation and power generation prediction model 440 may include current and historical power generation and power generation data 410, current and historical power usage data 420, and power generation influencing factors 430. For more details on the current and historical power generation amount data 410, the current and historical power usage amounts, reference may be made to fig. 2-3 and their associated description above. For more details on the power generation influencing factor 430, see FIG. 3 and its associated description above.

In some embodiments, the output of the power generation and reception amount prediction model 440 may include: estimated power generation amount data 450 and estimated power consumption amount data 460 for at least one point in time in the future. For more details on the estimated power generation amount data 450 and the estimated power consumption amount data 460, refer to fig. 3 and the description thereof.

In some embodiments, the power generation and reception quantity prediction model 440 may be obtained based on a large amount of training data training. The training data may include training samples and labels. For example, the training samples may include current and historical power generation amount data of the samples, current and historical power consumption amount data of the samples, and sample power generation amount influencing factors, and the labels of the training samples may be actual power generation amount and power consumption data of the samples at future time points.

The training sample can be actual power generation and reception amount data, power consumption data and power generation amount influencing factors in a first historical time period in the historical power data of the energy storage power station, and the label of the training sample can be actual power generation and reception amount and power consumption data in a second historical time period in the historical power data of the energy storage power station. The second historical period is a future point in time of the first historical period.

In the embodiment of the present disclosure, when predicting the estimated power generation amount data 450 and the estimated power consumption amount data 460 of at least one future time point, the information such as the power generation amount influencing factors is considered, so that the predicted power generation amount and power consumption data more conform to the actual situation, and the accuracy of the prediction is improved. And meanwhile, the machine learning model is used for prediction, so that the prediction efficiency can be accelerated, and the timeliness of electric energy management can be improved.

In some embodiments, the power generation and reception quantity prediction model 440 further includes a power generation and reception characteristic determination layer. The battery control module can utilize the initiation feature determination layer to determine the initiation features of the new energy power generation device based on the operation monitoring image and the historical overhaul data.

In some embodiments, the subject feature determination layer may be a machine learning model, such as a Convolutional Neural Network (CNN), or the like. In some embodiments, the power generation and reception amount prediction model 440 may further include a prediction layer, which may be a machine learning model, such as a Recurrent Neural Network (RNN), or the like.

In some embodiments, the input to the subject feature determination layer may include a sequence of operational monitoring images, historical overhaul data, a sequence of operational monitoring data.

The operation monitoring image sequence is an operation monitoring image of the new energy power generation device shot at a continuous time point, and can reflect appearance data and dynamic conditions of the new energy power generation device, such as the rotating speed of fan blades of the separated generator, whether the new energy power generation device is in a working state or not, and the like.

The operation monitoring data sequence refers to the operation condition of the internal components of the new energy power generation device at continuous time points. For example, for a solar power plant, the operational monitoring data sequence may include a temperature data sequence, a photoelectric conversion efficiency sequence, etc.; for wind power plants, the operational monitoring data sequences may include vibration data sequences, temperature data, etc.; for a hydro-power generation device, the operational monitoring data sequence may include a vibration data sequence, a temperature data sequence, a pressure data sequence, a flow data sequence, and the like.

In some embodiments, the battery control module may collect the sequence of operational monitoring images and the sequence of operational monitoring data through the power plant monitoring module described above, see FIG. 1 and its associated description for further details. For more details on historical service data, see FIG. 3 and its associated description above.

In some embodiments, the output of the launch feature determination layer may include launch features of the new energy power generation device.

The generated characteristics refer to hardware characteristics of the new energy power generation device, which can influence the power generation efficiency of the power generation device. In some embodiments, different types of new energy power generation devices may result in different launch characteristics. For example, where the new energy power generation device is a solar panel, the exposed features may include damage or contamination of the surface of the solar panel, loss that may be present inside the solar panel, and the like. When the new energy power generation device is a wind power generation device, the receiving characteristics can comprise the integrity of the fan blades, the health condition of the rotor driven by the fan blades and the like.

In some embodiments, the inputs to the prediction layer may include current and historical power generation amount data 410, current and historical power usage amount data 420, power generation characteristics, and power generation influencing factors 430. For more details on the current and historical power generation amount data 410, the current and historical power usage amounts, reference may be made to fig. 2-3 and their associated description above. For more details on the power generation influencing factor 430, see FIG. 3 and its associated description above.

In some embodiments, the output of the prediction layer may include: estimated power generation amount data 450 and estimated power consumption amount data 460 for at least one point in time in the future. For more details on the estimated power generation amount data 450 and the estimated power consumption amount data 460, refer to fig. 3 and the description thereof.

In some embodiments, the subject feature determination layer may be trained based on a large amount of training data. The training data may include training samples and labels. For example, the training samples may include sample run monitoring images, sample overhaul data, and sample run monitoring data, with the labels being actual launch features to which the samples correspond. For example, the labels of the training samples may include: integrity 90%, dirt level 50, component parameters, etc. The component parameters may include problems existing in the internal components of the new energy power generation device, such as short circuit, open circuit, breakage, etc.

The training samples can be actual operation monitoring images, historical overhaul data and actual operation monitoring data in historical electric energy data of the energy storage power station, labels of the training samples can be annotated in a manual detection mode, and historical hardware features of the new energy device can be queried to determine.

In some embodiments, the prediction layer is obtained by training based on a large amount of training data. The training data may include training samples and labels. For example, the training samples may include current and historical power generation amount data, current and historical power consumption amount data, current and historical power generation amount data, current and current power generation characteristics, and current power generation amount influencing factors, and the labels of the training samples may be actual power generation amount and power consumption data at future time points corresponding to the samples. The training sample can be actual power generation and reception amount data, power consumption amount data, power generation characteristics and power generation amount influence factors in a first historical time period in the historical power data of the energy storage power station, and the label of the training sample can be actual power generation and power consumption amount data in a second historical time period in the historical power data of the energy storage power station. The second historical period is a future point in time of the first historical period.

In the embodiment of the present disclosure, when predicting the predicted power generation amount data 450 and the predicted power consumption amount data 460 of at least one future time point, the information such as the operation monitoring image sequence, the historical overhaul data, the operation monitoring data sequence and the like is considered, so that the power generation characteristics, the power generation amount data 410 and the power consumption data obtained by prediction are more in accordance with the actual situation, and the accuracy of prediction is improved. And meanwhile, the prediction is performed by utilizing the initiation and reception characteristic determining layer and the prediction form, so that the prediction efficiency can be accelerated, and the timeliness of electric energy management can be improved.

Fig. 5 is a schematic diagram illustrating a determination of a predicted battery energy storage risk type according to some embodiments of the present disclosure. In some embodiments, as shown in FIG. 5, the battery control module may evaluate the estimated battery energy storage risk type 550 and its confidence 560, which determine at least one point in the future, using a risk prediction model 540 based on current and historical operating condition data 510, power generation and reception data 410, power usage data 420, current and historical battery polarization characteristic data 520, and grid load data 530; and generating an overhaul instruction based on the target to be overhauled.

In some embodiments, the risk prediction model 540 may be a machine learning model, such as a Recurrent Neural Network (RNN), or the like.

In some embodiments, the inputs to risk prediction model 540 may include current and historical operating condition data 510, current and predicted power generation amount data 410, current and predicted power usage amount data 420, current and historical battery polarization characteristic data 520, and grid load data 530. For more details on operating condition data 510, power generation amount data 410, power usage amount data 420, current and historical battery polarization characteristic data 520, and grid load data 530, reference is made to fig. 2-4 and their associated descriptions above.

In some embodiments, the output of the risk prediction model 540 may include the predicted battery energy storage risk type 550 and its confidence 560 for at least one point in time in the future. For example, the output of the risk prediction model 540 may be: the confidence 560 that the first battery pack is at risk of leakage is 0.9. For more details on estimating battery energy storage risk type 550 and its confidence 560, see FIG. 2 and its associated description above.

In some embodiments, risk prediction model 540 may be derived by model training based on training samples, including samples and labels. The samples comprise historical and current sample working condition data, current and estimated sample power generation quantity data, current and estimated sample power consumption quantity data, current and historical sample battery polarization characteristic data and sample power grid load data, and training samples are constructed through actually collected data; the label to which the sample corresponds is determined by the actual risk type to which the sample corresponds. The types of the training samples are determined based on labels corresponding to the samples, and the difference value of the number of the training samples of each type in all the training samples does not exceed a preset difference value threshold.

In some embodiments, the sample may be historical data of the actually collected energy storage power station, for example, the sample working condition data may be historical working condition data of a sample battery pack, the sample power generation and reception amount data may be historical power generation and reception amount data of a sample new energy power generation device, the sample power consumption amount data may be historical power consumption amount data of a sample power consumption device, the sample battery polarization characteristic data may be historical battery polarization characteristic data of the sample battery pack, and the sample power grid load data may be historical power grid load data of a sample power grid.

In some embodiments, the tag may be the type of risk actually present for the battery pack to which the sample corresponds. When the tag of the risk type in which the sample battery exists may be set to 1, the tag of the risk type in which the electric sample battery does not exist may be set to 0. For example, the risk to which the sample battery actually corresponds is leakage, then its corresponding label is [ leakage, 1), (virtual electricity, 0), (broken, 0) ].

In some embodiments, the training sample types are based on labels corresponding to the samples, and the number difference of the training samples of each type in all the training samples is set to not exceed a preset difference threshold. That is, the number of training samples of each type may be relatively even. For example, there are 5 training samples of the leakage type, the virtual electricity type, the breakage type, the fire type and the risk-free type, and then the proportion of the 5 training samples can be adjusted according to the requirement, but the difference of the number of the 5 training samples does not exceed the preset difference threshold. In some embodiments, the preset difference threshold may be determined based on human experience or big data in a variety of ways.

For example, assuming that the duty ratio of the training samples with the leakage type label is 96% and the duty ratio of the other training samples is 1%, the model after training is easy to judge the risk of leakage only accurately, but judging the risk of leakage or no risk of other types is poor, so that the universality of the model is low, the duty ratio of the other training samples can be increased, the number difference between the training samples of different types is reduced, and the universality of the model is improved.

In the implementation of the present specification, by setting that the number difference value of each type of training sample does not exceed the preset difference value threshold, the number difference between different types of training samples can be reduced, and the model after training can accurately judge various risks or no risks, so that the universality of the risk prediction model 540 is improved.

In some embodiments, the confidence condition may include that the confidence 560 meets a preset confidence threshold. Correspondingly, the battery control module may determine a battery pack for which the confidence 560 of the estimated battery energy storage risk type 550 reaches a confidence threshold as a target to be serviced.

In some embodiments, the battery control module may determine the initial preset confidence threshold by way of a look-up table or the like based on the pre-estimated battery energy storage risk type 550. For example, the battery control module may query a corresponding initial preset confidence threshold in a confidence 560 correspondence table based on the estimated battery energy storage risk type 550. The confidence 560 correspondence table may be established based on human experience or historical battery energy storage risk data, etc.

In some embodiments, the battery control module may also adjust the initial preset confidence threshold based on the actual inspection results. The inspection result is fed back by a worker after the object to be inspected is inspected. For example, when the actual inspection result matches the estimated battery energy storage risk type 550, the battery control module may appropriately reduce the initial preset confidence threshold corresponding to the estimated battery energy storage risk type 550.

In some embodiments, the battery control module may further perform prediction of a preset number of times, and perform statistical analysis on the prediction result to determine a battery pack to be overhauled, where the preset number of times is related to historical overhauling data of the battery pack.

The preset number of times refers to a preset number of times of continuous operation of the risk prediction model 540. For example, assuming that the preset number of times can be predicted once at 1 minute intervals, the data collected at 9:59 is input for the first time, and the data collected at 10:00 is input for the second time.

In some embodiments, the preset number of times may be related to historical overhaul data of the battery pack and the estimated degree of stability of the power generation amount. The estimated stability of the generated power can reflect the fluctuation of the power generation and the power consumption of the new energy power generation device in a future time period. In some embodiments, the stability of the estimated power generation amount may be expressed as a variance of a plurality of estimated power generation amounts, for example, the greater the variance is, the lower the stability of the estimated power generation amount is, and the greater the fluctuation of power generation and power consumption of the new energy power generation device in a future time period is.

The historical overhaul frequency is lower, the latest overhaul is farther from the current time point, the estimated stability of the generated power is lower, and the battery pack is poorer in health state, so that the greater preset times can be set, the target to be overhauled can be timely determined, and sudden accidents of the battery can be avoided.

The estimated result refers to an output result obtained after the risk estimation model 540 is operated according to a preset number of times. For example, the prediction may include a predicted battery energy storage risk type 550 and its confidence 560 for a plurality of time points in the future.

In some embodiments, the battery control module may determine whether the battery pack is a target to be serviced based on the number of times the confidence 560 satisfies the confidence condition. For example, in the predicted result of the preset number of times, the number of times the confidence 560 is greater than the preset confidence threshold exceeds the preset number of times; the battery control module may determine the battery pack as a battery pack requiring service treatment. The preset times can be determined according to manual experience or historical overhaul data.

In some embodiments, the battery control module may determine whether the battery pack is a target to be overhauled according to a comparison result of an average value of the plurality of confidences 560 and a preset confidence threshold value. For example, in the predicted results of the preset number of times, the confidence average value of the plurality of predicted battery energy storage risk types 550 is greater than the preset confidence threshold, and then the battery pack is determined as the battery pack that needs maintenance processing. For more details on the confidence conditions and the preset confidence threshold, reference is made to the above description of the correlation.

In the embodiment of the present disclosure, through the running risk prediction model 540 of the preset times, a plurality of predicted battery energy storage risk types 550 and confidence degrees 560 thereof can be obtained, so that accuracy of model prediction can be improved, stability of a power grid can be ensured, occurrence of energy storage risks can be avoided, and running safety of an energy storage power station can be improved.

There is also provided in one or more embodiments of the present specification an energy storage power station battery condition monitoring device comprising at least one processor and at least one memory; at least one memory for storing computer instructions; at least one processor is configured to execute at least some of the computer instructions to implement the energy storage power station battery condition monitoring method as described in any of the embodiments above.

The processor can refer to an operation and control core of the battery state monitoring device of the energy storage power station, and is a final execution unit for information processing and program running. Such as a central processing unit, a graphics processor, a field programmable gate array, etc. In some embodiments, the processor may perform the energy storage power station battery condition monitoring methods illustrated in fig. 2-5 above, and for further details of the methods, reference may be made to the related description above.

There is further provided in one or more embodiments of the present specification a computer readable storage medium storing computer instructions that, when read by a computer, the computer performs the method of monitoring the condition of a battery of an energy storage power station as described in any of the embodiments above.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure does not imply that the subject matter of the present description requires more features than are set forth in the claims. Indeed, less than all of the features of a single embodiment disclosed above.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. An energy storage power station battery condition monitoring system, comprising:

the battery state monitoring module is connected with the battery pack of the energy storage power station through a circuit and is configured to collect working condition data of the battery pack;

the data storage device is configured to store the historical working condition data acquired by the battery state monitoring module;

The power generation and reception monitoring module is configured to monitor power generation and reception data of the new energy power generation device and power consumption data of the power utilization device, which are connected with the energy storage power station circuit;

An alarm part configured to issue alarm information when the operating condition data does not satisfy a preset operating condition;

the power grid load monitoring module is configured to monitor power grid load data of a power grid accessed by the energy storage power station;

the battery control module comprises a power grid load estimation unit;

The grid load estimation unit is configured to:

Determining a predicted battery energy storage risk type and a confidence coefficient thereof at least at one time point in the future based on the current working condition data and the historical working condition data, the power generation and reception amount data, the power consumption amount data, the current and historical battery polarization characteristic data and the power grid load data;

Determining an overhaul instruction for at least one battery pack of the energy storage power station based on the estimated battery energy storage risk type and the confidence level thereof;

And sending the overhaul instruction to a power station maintenance center.

2. The energy storage power station battery state monitoring system of claim 1, wherein the battery control module further comprises a battery energy storage control unit;

the battery energy storage control unit is configured to:

Predicting estimated power generation amount data and estimated power consumption amount data of at least one time point in the future based on the power generation amount data, the power consumption amount data and power generation influence factors;

Determining a charging expected working condition and a discharging expected working condition of at least one time point in the future based on the estimated power generation amount data and the estimated power consumption amount data;

Determining electric quantity scheduling parameters among the new energy power generation device, the battery pack and the power grid based on the charging expected working condition, the discharging expected working condition and the current working condition data of the battery pack;

The power dispatching parameters comprise battery power dispatching parameters and power grid power dispatching parameters of at least one time point in the future.

3. The energy storage power station battery state monitoring system of claim 2, wherein the battery energy storage control unit is further configured to:

Based on the current and historical generated power data, the power consumption data and the power generation influence factors, predicting estimated power generation quantity data of the new energy power generation device and estimated power consumption data of the power utilization device by using a power generation and reception quantity prediction model; the power generation and reception quantity prediction model is a machine learning model.

4. The energy storage power station battery state monitoring system of claim 1, wherein the grid load estimation unit is configured to:

based on the current and historical working condition data, the power generation and reception amount data, the power consumption amount data, the current and historical battery polarization characteristic data and the power grid load data, estimating and determining an estimated battery energy storage risk type and a confidence coefficient of the estimated battery energy storage risk type at least at one time point in the future by using a risk estimation model;

Determining the battery pack with the confidence degree meeting the confidence degree condition as a target to be overhauled;

And generating the overhaul instruction based on the target to be overhauled.

5. An energy storage power station battery state monitoring method, which is characterized by being applied to an energy storage power station battery state monitoring system, and being executed based on a battery control module of the energy storage power station battery state monitoring system, the method comprises the following steps:

determining the estimated battery energy storage risk type and the confidence level thereof at least at one time point in the future based on the current working condition data, the historical working condition data, the generated power data, the power consumption data, the current and historical battery polarization characteristic data and the power grid load data;

And sending the overhaul instruction to a power station maintenance center.

6. The energy storage power station battery condition monitoring method of claim 5, further comprising:

determining electric quantity scheduling parameters among the new energy power generation device, the battery pack and the power grid based on the expected charging working condition, the expected discharging working condition and the current working condition data of the battery pack;

7. The method of claim 6, wherein predicting estimated power generation amount data and estimated power consumption amount data for at least one future point in time based on the power generation amount data, the power consumption amount data, and power generation influencing factors comprises:

8. The method of claim 6, wherein determining the estimated battery energy storage risk type and the confidence level thereof for the future at least one time point based on the current operating condition data and the historical operating condition data, the generated power data, the power consumption data and the grid load data comprises:

Based on the current and historical working condition data, the power generation and reception amount data, the power consumption amount data, the current and historical battery polarization characteristic data and the power grid load data, estimating and determining an estimated battery energy storage risk type and a confidence coefficient of the estimated battery energy storage risk type at least at one time point in the future by using a risk estimation model; and

The determining, based on the estimated battery energy storage risk type and the confidence level thereof, an overhaul instruction for at least one battery pack of the energy storage power station includes:

And generating the overhaul instruction based on the target to be overhauled.

9. A processing device, the device comprising at least one processor and at least one memory;

the at least one memory is configured to store computer instructions;

The at least one processor is configured to execute at least some of the computer instructions to implement the method of any one of claims 5-8.

10. A computer readable storage medium storing computer instructions which, when read by a computer in the storage medium, perform the method of any one of claims 5-8.