CN118336163B

CN118336163B - An intelligent management method and related equipment for energy storage batteries

Info

Publication number: CN118336163B
Application number: CN202410764268.6A
Authority: CN
Inventors: 向超
Original assignee: Xiamen Beichenxing Energy Storage Development Co ltd
Current assignee: Xiamen Beichenxing Energy Storage Development Co ltd
Priority date: 2024-06-14
Filing date: 2024-06-14
Publication date: 2024-10-11
Anticipated expiration: 2044-06-14
Also published as: CN118336163A

Abstract

The present application belongs to the field of energy storage technology, and relates to an intelligent management method and related equipment applied to energy storage batteries, the method comprising: performing power prediction processing on historical discharge data according to a preset prediction algorithm to obtain predicted power information; calculating the health level of each battery cell according to the health level; sorting the battery cells according to the health level and the number of cycles to obtain a priority sequence; and charging and discharging the battery cells according to the priority sequence and the predicted power information. The present application prioritizes each battery cell according to the battery cell data of the energy storage system, and when charging and discharging are required, the battery cells with higher priority are used first, so that the parameters of the battery cells in the energy storage system can be consistent, so as to fully and efficiently exert the functions of the energy storage system. In addition, charging the battery cells according to the predicted power information can effectively avoid the risk of damaging the battery cell life and safety due to overcharging.

Description

Intelligent management method applied to energy storage battery and related equipment

Technical Field

The application relates to the technical field of human energy storage, in particular to an intelligent management method and related equipment applied to an energy storage battery.

Background

Peak clipping and valley filling means that an energy management system (ENERGY MANAGEMENT SYSTEM, EMS) releases electric energy by using an energy storage system in a peak period of a power grid so as to relieve the pressure of the power grid; the electric energy is stored during the off-peak period of the power grid, thereby storing the excess electric energy. Therefore, the electric energy is effectively managed, and a great amount of waste of the electric energy is avoided.

However, the applicant found that the conventional energy storage battery management method is generally simpler and coarser, and the charging and discharging are performed by setting fixed time at regular time, so that the service life of the whole energy storage system can be prolonged without considering the problem of the battery charging cycle life, and therefore, the problem of shortened service life caused by improper management mode of the conventional energy storage battery management method can be seen.

Disclosure of Invention

The embodiment of the application aims to provide an intelligent management method, an intelligent management device, computer equipment and a storage medium applied to an energy storage battery, so as to solve the problem that the service life is shortened due to an improper management mode in the traditional energy storage battery management method.

In order to solve the technical problems, the embodiment of the application provides an intelligent management method applied to an energy storage battery, the method is applied to an energy storage system, the energy storage system comprises a plurality of energy storage battery cells, and the method adopts the following technical scheme:

Receiving an energy storage management instruction carrying system identification information;

Reading a history database, and acquiring history discharge data of the energy storage system corresponding to the system identification information from the history database;

Carrying out electric quantity prediction processing according to a preset prediction algorithm and the historical discharge data to obtain current day predicted electric quantity information of the energy storage system;

Acquiring cell data of each cell in the plurality of energy storage cells, wherein the cell data comprises rated capacity, health degree and cycle times;

calculating the health grade of each battery cell according to the health degree;

Sequencing the battery cells according to the health grade and the cycle times to obtain a priority sequence;

acquiring electricity consumption valley value time corresponding to the energy storage system;

and if the current time meets the electricity consumption valley time, carrying out discharging operation on the battery cells in sequence according to the priority sequence and the predicted electric quantity information.

Further, the step of calculating the health grade of each cell according to the health degree specifically includes the following steps:

classifying the health degree of the battery cells according to a preset segmentation threshold and a battery cell classification algorithm to obtain the health grade, wherein the health grade is obtained by the battery cells Expressed as:；

Wherein, Representing the preset segmentation threshold value; Indicating the cell health of the nth cell.

Further, the step of obtaining the electricity consumption valley value time and the electricity consumption peak value time corresponding to the energy storage system specifically includes the following steps:

collecting historical electricity consumption data of a discharge object of the energy storage system, wherein the historical electricity consumption data comprises a period minimum electric quantity and first influence factor data related to the period minimum electric quantity;

Screening the first influence factor data according to the historical electricity consumption data and a preset correlation coefficient method to obtain a first key influence factor;

acquiring an electric quantity value and first electric time corresponding to the first key influence factor from the historical electric data to obtain a first model training set;

Inputting the first model training set into a first regression prediction model for model training to obtain a valley prediction model;

Collecting current influence factor data of the energy storage system in real time;

And inputting the current influence factor data into the valley prediction model to obtain the electricity consumption valley time.

Further, the first model training set is obtained through the following steps:

sequentially acquiring elements in the first key influence factors as target factors;

Acquiring an electric quantity change value and an electric quantity change time corresponding to the target factor from the historical electricity utilization data, and constructing triple data according to the electric quantity change value and the electric quantity change time, wherein the triple data comprises data before electric quantity change of the electric quantity change value, data after electric quantity change and the electric quantity change time;

Obtaining all triplet data corresponding to the target factors in the historical electricity utilization data to obtain triples, wherein each triplet data is an element in the triples;

and taking the ternary arrays of all elements in the first key influence factors as the first model training set.

Further, before the step of inputting the first model training set into the first regression prediction model to perform model training to obtain the valley prediction model, the method further comprises the following steps:

carrying out optimal solution search on penalty factors and kernel function parameters of a pre-constructed regression prediction model by adopting a particle swarm algorithm to obtain an optimal solution search result;

Setting the optimal solution search result as a model parameter into the pre-constructed regression prediction model to obtain an improved regression prediction model based on a particle swarm algorithm;

The valley prediction model is obtained through the following steps:

inputting the ternary arrays of all elements in the first key influence factors into the regression prediction model improved based on the particle algorithm;

And performing function fitting on the ternary arrays of all elements in the first key influence factors to obtain a fitting function for representing the comprehensive relation between the electric quantity change time and all the first key influence factors.

Further, if the current time meets the electricity consumption valley time, the step of sequentially performing discharging operation on the battery cell according to the priority sequence and the predicted electric quantity information specifically includes the following steps:

calling the cell with the highest priority in the priority sequence to discharge, and monitoring the real-time health degree data of the cell with the highest priority in real time;

Calculating the current available capacity of the battery cell with the highest priority according to the real-time health degree data;

When the current available capacity of the battery cell with the highest priority is consistent with the current available capacity of the battery cell with the next level, merging the battery cells with the next level for discharging;

And when the current available capacity of all the battery cells in the energy storage system is larger than the predicted electric quantity information and the difference value between the current available capacity of all the plurality of battery cells and the predicted electric quantity information meets the preset residual electric quantity, completing the discharging operation.

Further, after the step of obtaining the cell data of each cell in the plurality of energy storage cells, wherein the cell data includes rated capacity, health degree and cycle number, the method further includes the following steps:

if the plurality of energy storage battery cores are required to be charged, calculating the actual electric quantity value of each energy storage battery core according to the battery core data of the energy storage battery core;

sequencing the energy storage battery cells according to the actual electric quantity value and the sequence from the small electric quantity value to the large electric quantity value to obtain a sequence to be charged;

Determining an energy storage battery cell with the smallest actual electric quantity value in the sequence to be charged as a first battery cell to be charged and carrying out charging treatment;

If the electric quantity value of a first electric core to be charged in the charging process is equal to the actual electric quantity value of other energy storage electric cores in the next sequence in the sequence to be charged, combining the first electric core to be charged and the energy storage electric cores in the next sequence into a second electric core to be charged, and carrying out charging treatment on the second electric core to be charged;

and circulating the steps, and completing charging operation when the actual electric quantity value of each electric core in the energy storage electric core meets the maximum capacity.

In order to solve the technical problems, the embodiment of the application also provides an intelligent management device applied to an energy storage battery, the device is applied to an energy storage system, the energy storage system comprises a plurality of energy storage battery cells, and the device adopts the following technical scheme:

the instruction receiving module is used for receiving an energy storage management instruction carrying system identification information;

the historical data acquisition module is used for reading a historical database and acquiring historical discharge data of the energy storage system corresponding to the system identification information from the historical database;

The electric quantity prediction module is used for carrying out electric quantity prediction processing according to a preset prediction algorithm and the historical discharge data to obtain current day predicted electric quantity information of the energy storage system;

The battery cell data acquisition module is used for acquiring the battery cell data of each battery cell in the plurality of energy storage battery cells, wherein the battery cell data comprises rated capacity, health degree and cycle times;

the health level calculating module is used for calculating the health level of each battery cell according to the health degree;

the priority ordering module is used for ordering the battery cells according to the health grade and the cycle times to obtain a priority sequence;

The peak-valley time acquisition module is used for acquiring the electricity valley time of the system identification information;

and the discharging module is used for sequentially discharging the battery cells according to the priority sequence and the predicted electric quantity information if the current time meets the electricity consumption valley value time.

Further, the health level calculation module includes:

The health level calculation sub-module is used for carrying out classification operation on the battery cell health degree according to a preset segmentation threshold value and a battery cell classification algorithm to obtain the health level, wherein the health level is obtained by the battery cell health degree classification algorithm Expressed as:

；

In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:

The intelligent management system comprises a memory and a processor, wherein the memory stores computer readable instructions, and the processor executes the computer readable instructions to realize the steps of the intelligent management method applied to the energy storage battery.

In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:

the computer readable storage medium has stored thereon computer readable instructions which when executed by a processor implement the steps of the intelligent management method applied to an energy storage battery as described above.

The application provides an intelligent management method applied to an energy storage battery, which is applied to an energy storage system, wherein the energy storage system comprises a plurality of energy storage cells and comprises the following components: receiving an energy storage management instruction carrying system identification information; reading a history database, and acquiring history discharge data of the energy storage system corresponding to the system identification information from the history database; carrying out electric quantity prediction processing according to a preset prediction algorithm and the historical discharge data to obtain current day predicted electric quantity information of the energy storage system; acquiring cell data of each cell in the plurality of energy storage cells, wherein the cell data comprises rated capacity, health degree and cycle times; calculating the health grade of each battery cell according to the health degree; sequencing the battery cells according to the health grade and the cycle times to obtain a priority sequence; acquiring electricity consumption valley value time corresponding to the energy storage system; and if the current time meets the electricity consumption valley time, carrying out discharging operation on the battery cells in sequence according to the priority sequence and the predicted electric quantity information. Compared with the prior art, the method and the device have the advantages that the priority of each battery cell is ordered according to the battery cell data of the energy storage system, when the battery cells are required to be charged and discharged, the battery cells with higher priority are preferentially used, so that the parameters of the battery cells in the energy storage system tend to be consistent, the function of the energy storage system is fully and efficiently exerted, in addition, the battery cells are charged according to the predicted electric quantity information, and the risk of damaging the service life and the safety of the battery cells caused by overcharging can be effectively avoided.

Drawings

In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

Fig. 2 is a flowchart of an implementation of an intelligent management method applied to an energy storage battery according to an embodiment of the present application;

FIG. 3 is a flow chart of one embodiment of step S207 of FIG. 2;

FIG. 4 is a flowchart of one embodiment of obtaining a first model training set according to an embodiment of the present application;

FIG. 5 is a flowchart of a specific implementation of obtaining a valley prediction model according to an embodiment of the present application;

FIG. 6 is a flow chart of one embodiment of step S208 of FIG. 2;

FIG. 7 is a flow chart of an embodiment following step S204 in FIG. 2;

fig. 8 is a schematic structural diagram of an intelligent management device applied to an energy storage battery according to a second embodiment of the present application;

FIG. 9 is a schematic structural view of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.

It should be noted that, the intelligent management method applied to the energy storage battery provided by the embodiment of the application is generally executed by a server/terminal device, and correspondingly, the intelligent management device applied to the energy storage battery is generally arranged in the server/terminal device.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow chart of one embodiment of a smart management method applied to an energy storage battery in accordance with the present application is shown. The intelligent management method applied to the energy storage battery comprises the following steps: step S201, step S202, step S203, step S204, step S205, step S206, and step S207.

In step S201, an energy storage management instruction carrying system identification information is received.

In the embodiment of the application, the application mainly focuses on the safety, performance and service life management of the battery single layer, wherein the application can focus on a plurality of energy storage systems consisting of a plurality of batteries (electric cores).

In the embodiment of the application, the system identification information is mainly used for uniquely identifying a specific energy storage system needing to be subjected to directional intelligent management in the plurality of energy storage systems, wherein the system identification information can be set based on a digital serial number, for example: 001. 002, 003, etc.; the system identification information may also be set based on name abbreviations, such as: automobile energy storage system-QCCNXT, enterprise energy storage system-QYCNXT, etc.; the system identification information may also be set based on a numerical sequence number and a name abbreviation, for example: QCCNXT001, QYCNXT002, etc., it should be understood that the examples of system identification information herein are for ease of understanding only and are not intended to limit the present application.

In the embodiment of the present application, the energy storage management instruction is mainly used for instructing the server/terminal device executing the intelligent management method applied to the energy storage battery to start to perform automatic energy management on the current energy storage system corresponding to the system identification information, where the energy storage management instruction may be sent in a form of triggering a virtual key by a user, and may also perform data interaction in a form of an http protocol, where the energy storage management instruction carries the system identification information to be managed, and it should be understood that the example of the energy storage management instruction is only convenient to understand and is not used to limit the present application.

In step S202, a history database is read, and history discharge data of the energy storage system corresponding to the system identification information is acquired in the history database.

In the embodiment of the present application, the history database is mainly used for storing all record data of past history of the energy storage system, wherein the record data and system identification information of each energy storage system establish an association relationship, and as an example, record data of 7 days (which can be longer) of history discharge, for example, the installed capacity of the current energy storage system is 1MWh (1000 degrees of electricity), the rated power is as shown in the following table for the last 7 days:

first day

The next day

Third day

Fourth day

Fifth day

Sixth day

Seventh day

400 Degrees

600 Degrees

300 Degrees

500 Degree

400 Degrees

700 Degrees

400 Degrees

In step S203, the electric quantity prediction processing is performed according to the preset prediction algorithm and the historical discharge data, so as to obtain the current day predicted electric quantity information of the energy storage system.

In the embodiment of the present application, the preset prediction algorithm may be an electric quantity prediction method, which is mainly used for predicting the current electric quantity of the energy storage system used in the current day, and may be a moving average method, that is, predicting the future electric quantity demand based on the average value of the historical data, and may be an exponential smoothing method, that is, predicting the future electric quantity demand by weighting the historical data, specifically, an exponential smoothing method, a quadratic exponential smoothing method, a cubic exponential smoothing method, and the like, and may be a time series analysis method, that is, predicting the future electric quantity demand by analyzing the time series characteristics of the electric quantity data, specifically, an autoregressive moving average model (ARIMA), a seasonal autoregressive moving average model (SARIMA), an exponential smoothing state space model (ETS), and the like, which should be understood that the examples of the preset prediction algorithm are only convenient understanding and are not used for limiting the present application.

In step S204, cell data of each of the plurality of energy storage cells is obtained, where the cell data includes a rated capacity, a health degree, and a cycle number.

In the embodiment of the application, the energy storage system is composed of a plurality of electric cores, and the application needs to acquire electric core data of each electric core so as to analyze each electric core to acquire health information of each electric core, thereby sequencing priorities of each electric core for subsequent charge and discharge operation, wherein the electric core data comprises rated capacity, health degree (SOH), cycle number and other information.

In step S205, the health level of each cell is calculated according to the health degree.

In the embodiment of the present application, the health level is used to represent the loss degree of each battery cell in the current energy storage system, and in the embodiment of the present application, the health level may be a State of health (SOH); and then the health grade of each battery cell is determined according to the loss degree of the battery cell, that is, the health grade of the battery cell is strongly related to the health degree of the battery cell, wherein the battery cells are classified according to the health grade due to the extremely small difference of the health degrees of the battery cells, so that the battery cells with different health degrees are effectively distinguished, and the subsequent battery cell system management is convenient.

In step S206, the cells are ordered according to the health level and the cycle number, so as to obtain a priority sequence.

In the embodiment of the application, in order to enable parameters of the electric cores in the current energy storage system to be consistent so as to fully and efficiently perform the function of the energy storage system, the electric cores are required to be ordered, and specifically, after the health grade of each electric core is obtained, the electric cores with higher health grade and lower cycle times are set to be higher in priority by combining the cycle times (the cycle times are low and represent that the current battery is less in use, good in health and low in use rate), so that the electric cores with higher priority are preferentially used in the use process of the current energy storage system, the difference among the electric cores can still be ensured not to be too large along with the time, and the function of the energy storage system can be fully and efficiently performed.

In step S207, a power consumption valley time corresponding to the energy storage system is acquired.

In the embodiment of the application, the electricity consumption valley time refers to the electricity consumption low-peak period of the current energy storage system application scene, and otherwise, the electricity consumption high-peak period of the current energy storage system application scene is the electricity consumption peak period.

In step S208, if the current time satisfies the electricity consumption threshold time, the electric cells are sequentially discharged according to the priority sequence and the predicted electric quantity information.

In the embodiment of the application, when the electric discharge is required, the electric core to be discharged which meets the predicted electric quantity information is firstly required to be obtained from all the electric cores, and then the electric discharge operation is carried out according to the priority sequence of the electric core to be discharged.

In the embodiment of the application, the discharging operation can be to call the cell with the highest priority in the priority sequence for discharging and monitor the real-time health data of the cell with the highest priority in real time; calculating the available capacity of the battery cell with the highest priority according to the real-time health degree data; when the available capacity of the battery cell with the highest priority is consistent with the health degree of the battery cell of the next health grade, combining the battery cells of the next health grade for discharging; and when the available capacity of all the battery cores in the energy storage system meets the preset residual electric quantity, completing the discharging operation.

In the embodiment of the application, the actual electric quantity of each battery cell is sequenced, and the electric quantity value is monitored in real time, so that the charging sequence and the safety of the charging process are ensured. Meanwhile, according to the maximum capacity of the battery cell, overcharge is avoided, so that the service life and safety of the battery cell are protected.

In an embodiment of the present application, an intelligent management method applied to an energy storage battery is provided, including: receiving an energy storage management instruction carrying system identification information; reading a history database, and acquiring history discharge data of an energy storage system corresponding to the system identification information from the history database; carrying out electric quantity prediction processing according to a preset prediction algorithm and historical discharge data to obtain current day predicted electric quantity information of the energy storage system; acquiring cell data of each cell in a plurality of energy storage cells, wherein the cell data comprises rated capacity, health degree and cycle times; calculating the health grade of each cell according to the health degree; sequencing the battery cells according to the health grade and the cycle times to obtain a priority sequence; acquiring electricity consumption valley value time corresponding to an energy storage system; and if the current time meets the electricity consumption valley time, sequentially performing discharging operation on the battery cells according to the priority sequence and the predicted electric quantity information. Compared with the prior art, the method and the device have the advantages that the priority of each battery cell is ordered according to the battery cell data of the energy storage system, when the battery cells are required to be charged and discharged, the battery cells with higher priority are preferentially used, so that the parameters of the battery cells in the energy storage system tend to be consistent, the function of the energy storage system is fully and efficiently exerted, in addition, the battery cells are charged according to the predicted electric quantity information, and the risk of damaging the service life and the safety of the battery cells caused by overcharging can be effectively avoided.

In some alternative implementations of the present embodiment, the step 205 includes the following steps:

Classifying the health degree of the battery cells according to a preset segmentation threshold value and a battery cell classifying algorithm to obtain health grades, wherein the health grades Expressed as:；

In the embodiment of the application, after the health degree of each cell is obtained, health degree information of all the cells is sequentially input into the cell classification algorithm to perform health grade calculation, so that the health grade of all the cells is obtained.

With continued reference to fig. 3, a flowchart of one embodiment of step S207 of fig. 2 is shown, only the portions relevant to the present application being shown for ease of illustration.

In some optional implementations of the present embodiment, step S207 specifically includes: step S301, step S302, step S303, step S304, step S305, and step S306.

In step S301, historical electricity consumption data of a discharging object of the energy storage system is collected, wherein the historical electricity consumption data includes a period minimum electric quantity and first influence factor data related to the period minimum electric quantity.

In the embodiment of the application, the influence factor data comprise economic dimension data and meteorological dimension data; economic dimension data such as purchasing manager Index (PurchasingManagers' Index, PMI) and industrial producer factory price Index (ProducerPriceIndex, PPI); the purchasing manager index PMI is formed by weighting a new order index, a production index, a practitioner index, a supplier distribution index and a main raw material inventory index through surveys in corresponding orders of the purchasing manager, and is one of the advance indexes for monitoring macro economic trends. Because the manufacturing industry has the characteristics of large scale and high energy consumption in the electricity consumption, the fluctuation of the production condition can influence the electricity consumption trend of the whole society to a large extent, so that the PMI can predict the fluctuation of the electricity consumption growth condition of the whole society to a certain extent. The factory price index PPI of an industrial producer is used for measuring price fluctuation trend in the production field, the side face of the factory price index PPI can reflect production requirements and enterprise operation conditions, and the intensity of industrial production activities is directly related to industrial electricity consumption increase conditions, so that the electricity consumption increase level of the whole society is determined. Weather dimensional data, such as weather factors including air temperature, precipitation, relative humidity, etc.; these elements are very closely related to the amount of electricity used in life.

In step S302, a screening operation is performed on the first influencing factor data according to the historical electricity consumption data and a preset correlation coefficient method, so as to obtain a first key influencing factor.

In the embodiment of the present application, the preset correlation coefficient method may beWherein, the method comprises the steps of, wherein,Indicating that the current energy storage system is at the firstThe power change value before and after the minimum power of the secondary period or the maximum power of the period,Representing the corresponding average value of the electric quantity change of the current energy storage system in the historical electricity utilization data,Represent the firstA time interval of change before and after the minimum charge of the secondary period or the maximum charge of the period,Representing the corresponding average change time interval of the current energy storage system in the historical electricity usage data,The closer the value is to 1 or-1, the greater the influence representing the key influence factor.

In the embodiment of the application, the first key influence factors are screened out through the correlation coefficient method and the acquisition of each parameter value, so that the data size of training data is effectively reduced, and the training speed of the model is improved to a certain extent.

In step S303, an electric quantity value corresponding to the first key influencing factor and the first electric time are obtained from the historical electric consumption data, so as to obtain a first model training set.

In step S304, the first model training set is input to the first regression prediction model to perform model training, so as to obtain a valley prediction model.

In the embodiment of the application, the regression prediction model is a pre-constructed regression prediction model, and specifically, is a prediction model based on a Support Vector Regression (SVR) algorithm.

In step S305, current influencing factor data of the energy storage system is collected in real time.

In step S306, the current influencing factor data is input to the valley prediction model, and the electricity consumption valley time is obtained.

In the embodiment of the application, the current influence factor data of the energy storage system is acquired in real time, and the current influence factor data is analyzed according to the trained regression prediction model, so that the electricity consumption valley time and the electricity consumption peak time which accord with the current application environment are obtained, the utilization rate of energy sources can be effectively improved, and the energy source waste is avoided.

In some optional implementations of the embodiments of the present application, the historical electricity consumption data may further include periodic maximum electricity consumption and second influence factor data related to the periodic maximum electricity consumption, and specifically, the present application may further calculate electricity consumption peak time according to the periodic maximum electricity consumption and the second influence factor data related to the periodic maximum electricity consumption, so as to perform a charging operation in the electricity consumption peak time period.

In some optional implementations of the embodiments of the present application, if the current time meets the electricity peak time, the charging operation may be performed on the battery cell according to the priority sequence.

In an embodiment of the present application, the charging operation may be:

(1) And obtaining rated capacity, available capacity and health degree of each battery cell, such as rated capacity 314Ah of a certain battery cell and 40% of residual electric quantity. The health degree is 95%;

(2) The actual electric quantity is calculated, and the formula is as follows: (rated capacity x remaining capacity) xhealth = actual capacity, calculated using the above example data to obtain an actual capacity of (314 Ah x 40%) x95% = 119.32Ah;

(3) Sorting the actual electric quantity, and charging the battery cells with low charge quantity in the charging process;

(4) Monitoring the electric quantity value of the battery cell in real time;

(5) When the electric quantity is overlapped, charging the uncharged battery cells into a charging queue (for example, the electric quantity of a certain batch of battery cells is 90Ah, the next batch of battery cells is 110Ah, the 90Ah is charged firstly, and when the 90Ah reaches 110Ah, the charging of the 110Ah is started originally);

(6) And calculating the current maximum capacity according to the rated capacity and the health degree, and automatically powering off when the electric quantity of the battery cell is equal to the maximum capacity.

With continued reference to fig. 4, a flowchart of a specific implementation of step S303 in fig. 3 for obtaining the first model training set according to the first embodiment of the present application is shown, and for convenience of explanation, only a portion relevant to the present application is shown.

In some optional implementations of this embodiment, the first model training set may specifically include: step S401, step S402, step S403, and step S404 are obtained.

In step S401, elements in the first key influence factor are sequentially acquired as target factors.

In step S402, an electric quantity change value and an electric quantity change time corresponding to the target factor are obtained from the historical electricity consumption data, and triple data is constructed according to the electric quantity change value and the electric quantity change time, wherein the triple data includes data before electric quantity change, data after electric quantity change and the electric quantity change time of the electric quantity change value.

In step S403, all triples of data corresponding to the historical electricity consumption data of the target factor are obtained, and triples are obtained, where each triples of data is an element in the triples.

In step S404, a triplet of all elements in the first key influencing factor is used as the first model training set.

In this embodiment of the present application, assuming that the number of all key influencing factors is 10, 10 triples are obtained, and each triplet corresponds to a different key influencing factor. The ternary group construction and the ternary group construction have the advantages that the subsequent data analysis is convenient, and meanwhile, the change value and the change time interval of the electric quantity before and after the period minimum electric quantity or the period maximum electric quantity is changed can be obtained.

In the embodiment of the present application, step S401 to step S404 only describe the manner of obtaining the first model training set, and for the second model training set, the same manner is adopted for constructing, which may specifically be: sequentially acquiring elements in the second heavy point influence factors as target factors; acquiring an electric quantity change value and an electric quantity change time corresponding to a target factor from historical electricity utilization data, and constructing triple data according to the electric quantity change value and the electric quantity change time, wherein the triple data comprises data before electric quantity change of the electric quantity change value, data after electric quantity change and the electric quantity change time; obtaining all triplet data corresponding to the historical electricity utilization data of the target factors to obtain triples, wherein each triplet data is an element in the triples; and taking the ternary arrays of all elements in the second heavy point influence factors as a second model training set.

With continued reference to fig. 5, a flowchart of a specific implementation of obtaining a valley prediction model according to step S304 in fig. 3 is shown, and for convenience of explanation, only a portion relevant to the present application is shown.

In some optional implementations of the present embodiment, before step S304, further includes: in step S501 and step S502, the valley prediction model may specifically include, in step S304: step S503 and step S504 are obtained.

In step S501, an optimal solution search is performed on penalty factors and kernel function parameters of the pre-constructed regression prediction model by using a particle swarm algorithm, so as to obtain an optimal solution search result.

In the embodiment of the application, the main idea of optimizing the SVR algorithm by the particle swarm algorithm is to utilize the searching capability of the particle swarm, and find out the penalty factor and the kernel function parameter of the support vector regression algorithm by optimizing, and the two parameters directly determine the prediction precision and the training time of the model. The purpose of searching the optimal solution is to improve the prediction accuracy of the model and reduce the training time.

In step S502, the optimal solution search result is set as a model parameter into a pre-constructed regression prediction model, and a regression prediction model improved based on a particle swarm algorithm is obtained.

In step S503, the triples of all elements in the first key influencing factor are input into the regression prediction model improved based on the particle algorithm.

In step S504, a function fitting is performed on the ternary arrays of all the elements in the first key influencing factors, so as to obtain a fitting function for characterizing the comprehensive relationship between the electric quantity change time and all the first key influencing factors.

In the embodiment of the application, the support vector regression algorithm is combined with the ternary arrays corresponding to all key influence factors to perform function fitting, so that a fitting function for representing the comprehensive relation between the change time interval and all key influence factors is obtained, and when the prediction is performed later, the corresponding change time interval can be calculated according to the fitting function only by obtaining the data of all key influence factors.

With continued reference to fig. 6, a flowchart of one embodiment of step S208 of fig. 2 is shown, only the portions relevant to the present application being shown for ease of illustration.

In some optional implementations of the present embodiment, step S208 specifically includes: step S601, step S602, step S603, and step S604.

In step S601, the cell with the highest priority is called in the priority sequence to discharge, and real-time health data of the cell with the highest priority is monitored in real time.

In step S602, the current available capacity of the cell with the highest priority is calculated according to the real-time health data.

In the embodiment of the present application, the available capacity refers to the available capacity data of the current battery cell of the current energy storage system, and if the rated capacity of each battery cell of the current energy storage system is 314Ah and the health degree is 90%, the actual available capacity of the battery cell is 314×0.9= 282.6Ah by way of example.

In step S603, when the current available capacity of the cell with the highest priority is consistent with the current available capacity of the cell with the next level, the cells with the next level are combined for discharging.

In the embodiment of the application, the classification of the current used battery cells can be obtained; calculating the classification of the next type of electric core, and if the current electric core is classified as n, the classification of the next type of electric core is classified as n+1; calculating the health degree range of the next type of electric core according to the classification of the next type of electric core, and assuming that the preset segmentation threshold is 5, the health degree range of the next type of electric core is (n+1) 5; checking whether the available capacity of the current battery core is within the health range of the next battery core; if yes, automatically switching to the next type of battery cell (the next type of battery cell is newly added); the available capacity of the next type of cell serves as the available capacity of the currently used cell.

In step S604, when the current available capacities of all the battery cells in the energy storage system are greater than the predicted electric quantity information and the difference between the current available capacities of all the plurality of battery cells and the predicted electric quantity information meets the preset residual electric quantity, the discharging operation is completed.

In the embodiment of the application, the balance of the cell health of the energy storage system can be ensured through the discharging operation, which is the dynamic configuration of the discharging process.

With continued reference to fig. 7, a flowchart of one embodiment after step S204 in fig. 2 is shown, only the portions relevant to the present application being shown for ease of illustration.

In some optional implementations of the present embodiment, after step S204, further includes: step S701, step S702, step S703, step S704, and step S705.

In step S701, if a plurality of energy storage cells need to be charged, an actual electrical value of each energy storage cell is calculated according to the cell data of the energy storage cells.

In the embodiment of the present application, the actual electric quantity value refers to the current stored electric quantity of the battery cell, and as an example, for example, data of a certain battery cell is: rated capacity 314Ah, remaining capacity 40%. Health 95%, then the actual power value of the cell is (314 Ah x 40%) ×95% = 119.32Ah.

In step S702, the energy storage cells are ordered according to the actual electric quantity value and the order of the electric quantity values from small to large, so as to obtain a sequence to be charged.

In step S703, the energy storage cell with the smallest actual electric quantity value in the sequence to be charged is determined as the first cell to be charged and is subjected to charging processing.

In step S704, if the electric quantity value of the first to-be-charged battery cell in the charging process is equal to the actual electric quantity values of the other to-be-charged battery cells in the next sequence in the to-be-charged sequence, the first to-be-charged battery cell and the next to-be-charged battery cell are combined into the second to-be-charged battery cell, and the second to-be-charged battery cell is charged.

In step S705, the above steps are looped, and the charging operation is completed when the actual electric quantity value of each cell in the energy storage cells satisfies the maximum capacity.

In the embodiment of the application, the battery cells are charged in batches according to the priority sequence, and meanwhile, when the obtained electric quantity value of the battery cells is equal to the actual electric quantity value of the energy storage battery cells in the next sequence, the energy is combined and charged, so that the charging sequence and the safety of the charging process are effectively ensured, in addition, the charging completion operation is controlled according to the maximum capacity of the battery cells, the condition of overcharging is avoided, and the service life of the battery cells is effectively prolonged.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions. The intelligent management system can be applied to the intelligent management X field of the energy storage battery, so that the construction of a smart city is promoted.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

Examples

With further reference to fig. 7 and 8, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an intelligent management device applied to an energy storage battery, where an embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various electronic devices.

As shown in fig. 7 and 8, the intelligent management device 200 applied to an energy storage battery of the present embodiment includes: an instruction receiving module 210, a historical data obtaining module 220, a power predicting module 230, a core data obtaining module 240, a health level calculating module 250, a priority ordering module 260, a peak-to-valley time obtaining module 270, and a discharging module 280, wherein:

The instruction receiving module 201 is configured to receive an energy storage management instruction carrying system identification information;

a historical data acquisition module 202, configured to read a historical database, and acquire historical discharge data of the energy storage system corresponding to the system identification information in the historical database;

the electricity quantity prediction module 203 is configured to perform electricity quantity prediction processing according to a preset prediction algorithm and historical discharge data, so as to obtain current day predicted electricity quantity information of the energy storage system;

The cell data acquisition module 204 is configured to acquire cell data of each of the plurality of energy storage cells, where the cell data includes a rated capacity, a health degree, and a cycle number;

the health level calculating module 205 is configured to calculate a health level of each cell according to the health level;

the priority ranking module 206 is configured to perform ranking operation on the battery cells according to the health level and the cycle number, so as to obtain a priority sequence;

A peak-to-valley time obtaining module 207, configured to obtain a power consumption valley time of the system identification information;

and the discharging module 208 is configured to sequentially perform discharging operations on the battery cells according to the priority sequence and the predicted electric quantity information if the current time meets the electricity consumption threshold time.

In this embodiment, an intelligent management device 200 applied to an energy storage battery is provided, including: the instruction receiving module 201 is configured to receive an energy storage management instruction carrying system identification information; a historical data acquisition module 202, configured to read a historical database, and acquire historical discharge data of the energy storage system corresponding to the system identification information in the historical database; the electricity quantity prediction module 203 is configured to perform electricity quantity prediction processing according to a preset prediction algorithm and historical discharge data, so as to obtain current day predicted electricity quantity information of the energy storage system; the cell data acquisition module 204 is configured to acquire cell data of each of the plurality of energy storage cells, where the cell data includes a rated capacity, a health degree, and a cycle number; the health level calculating module 205 is configured to calculate a health level of each cell according to the health level; the priority ranking module 206 is configured to perform ranking operation on the battery cells according to the health level and the cycle number, so as to obtain a priority sequence; a peak-to-valley time obtaining module 207, configured to obtain a power consumption valley time of the system identification information; and the discharging module 208 is configured to sequentially perform discharging operations on the battery cells according to the priority sequence and the predicted electric quantity information if the current time meets the electricity consumption threshold time. Compared with the prior art, the method and the device have the advantages that the priority of each battery cell is ordered according to the battery cell data of the energy storage system, when the battery cells are required to be charged and discharged, the battery cells with higher priority are preferentially used, so that the parameters of the battery cells in the energy storage system tend to be consistent, the function of the energy storage system is fully and efficiently exerted, in addition, the battery cells are charged according to the predicted electric quantity information, and the risk of damaging the service life and the safety of the battery cells caused by overcharging can be effectively avoided.

In some optional implementations of this embodiment, the health level calculation module 250 includes:

The health level calculation sub-module is used for classifying the health degree of the battery cells according to a preset segmentation threshold value and a battery cell classification algorithm to obtain health levels, wherein the health levels are obtained by the classification operation of the battery cells Expressed as:

；

In some optional implementations of this embodiment, the peak-to-valley time obtaining module 270 includes: the system comprises an electricity utilization data acquisition sub-module, a screening sub-module, a training set acquisition sub-module, a model training sub-module, a current factor acquisition sub-module and a time prediction sub-module, wherein:

The power utilization data acquisition sub-module is used for acquiring historical power utilization data of a discharging object of the energy storage system, wherein the historical power utilization data comprises a period minimum electric quantity and first influence factor data related to the period minimum electric quantity;

The screening sub-module is used for carrying out screening operation on the first influence factor data according to the historical electricity utilization data and a preset correlation coefficient method to obtain a first key influence factor;

The training set acquisition sub-module is used for acquiring an electric quantity value corresponding to a first key influence factor and first electric time from historical electricity utilization data to obtain a first model training set;

the model training sub-module is used for inputting the first model training set into the first regression prediction model to carry out model training so as to obtain a valley prediction model;

The current factor acquisition sub-module is used for acquiring current influence factor data of the energy storage system in real time;

and the time prediction sub-module is used for inputting the current influence factor data into the valley value prediction model to obtain electricity consumption valley value time.

In some optional implementations of this embodiment, the training set obtaining submodule includes: the training device comprises a target factor determining unit, a triplet constructing unit, a triplet acquiring unit and a first training set acquiring unit, wherein:

the target factor determining unit is used for sequentially acquiring elements in the first key influence factors as target factors;

The three-dimensional structure construction unit is used for acquiring an electric quantity change value and an electric quantity change time corresponding to the target factors from the historical electricity utilization data and constructing three-dimensional structure data according to the electric quantity change value and the electric quantity change time, wherein the three-dimensional structure data comprises data before electric quantity change of the electric quantity change value, data after electric quantity change and the electric quantity change time;

The ternary array acquisition unit is used for acquiring all ternary array data corresponding to the historical electricity utilization data of the target factors to obtain ternary arrays, wherein each ternary array data is an element in the ternary array;

And the first training set acquisition unit is used for taking the ternary arrays of all elements in the first key influence factors as a first model training set.

In some optional implementations of this embodiment, the peak-to-valley time obtaining module 270 includes: an optimal solution searching sub-module and a model obtaining sub-module, wherein the model training sub-module comprises: an array input unit and a function fitting unit, wherein:

The optimal solution searching sub-module is used for carrying out optimal solution searching on penalty factors and kernel function parameters of the pre-constructed regression prediction model by adopting a particle swarm algorithm to obtain an optimal solution searching result;

the model acquisition sub-module is used for setting the optimal solution search result as a model parameter into a pre-constructed regression prediction model to obtain a regression prediction model based on the particle swarm algorithm improvement;

The array input unit is used for inputting the ternary arrays of all elements in the first key influence factors into the regression prediction model improved based on the particle algorithm;

And the function fitting unit is used for performing function fitting on the ternary arrays of all elements in the first key influence factors to obtain a fitting function for representing the comprehensive relation between the electric quantity change time and all the first key influence factors.

In some optional implementations of this embodiment, the discharging module 280 includes: the device comprises an electronic discharging module, an available capacity calculating sub-module, a discharging merging sub-module and a finished electronic discharging module, wherein:

the discharging module is used for calling the battery cell with the highest priority in the priority sequence to discharge and monitoring the real-time health data of the battery cell with the highest priority in real time;

The available capacity calculation operator module is used for calculating the current available capacity of the battery cell with the highest priority according to the real-time health degree data;

The discharging merging sub-module is used for merging the battery cells of the next level to discharge when the current available capacity of the battery cell with the highest priority is consistent with the current available capacity of the battery cells of the next level;

And the completion discharging module is used for completing discharging operation when the current available capacity of all the battery cores in the energy storage system is larger than the predicted electric quantity information and the difference value between the current available capacity of all the plurality of battery cores and the predicted electric quantity information meets the preset residual electric quantity.

In some optional implementations of this embodiment, the apparatus 200 further includes: the device comprises a battery cell calling module, an electricity value calculating module, an electricity value sorting module, a charging merging module and a charging ending module, wherein:

The battery cell calling module is used for calling the battery cell with the highest priority in the priority sequence as the energy storage battery cell if the plurality of energy storage battery cells need to be charged;

The electric quantity value calculation module is used for calculating the actual electric quantity value of each energy storage electric core according to the electric core data of the energy storage electric core;

The electric quantity value sequencing module is used for sequencing the energy storage battery cores according to the actual electric quantity value and the order of the electric quantity values from small to large to obtain a sequence to be charged;

the charging module is used for determining an energy storage battery cell with the smallest actual electric quantity value in the sequence to be charged as a first battery cell to be charged and carrying out charging treatment;

the charging merging module is used for merging the first to-be-charged battery cell and the next to-be-charged battery cell into a second to-be-charged battery cell and carrying out charging treatment on the second to-be-charged battery cell if the electric quantity value of the first to-be-charged battery cell in charging is equal to the actual electric quantity value of other to-be-charged battery cells in the next to-be-charged sequence;

And the charging ending module is used for cycling the steps, and completing the charging operation when the actual electric quantity value of each electric core in the energy storage electric core meets the maximum capacity.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 8 and fig. 9, fig. 8 and fig. 9 are basic structural block diagrams of a computer device according to the present embodiment.

The computer device 300 includes a memory 310, a processor 320, and a network interface 330 communicatively coupled to each other via a system bus. It should be noted that only computer device 300 having components 310-330 is shown in the figures, but it should be understood that not all of the illustrated components need be implemented, and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 310 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 may be an internal storage unit of the computer device 300, such as a hard disk or a memory of the computer device 300. In other embodiments, the memory 310 may also be an external storage device of the computer device 300, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 300. Of course, the memory 310 may also include both internal storage units and external storage devices of the computer device 300. In this embodiment, the memory 310 is generally used to store an operating system and various application software installed on the computer device 300, such as computer readable instructions applied to an intelligent management method of an energy storage battery. In addition, the memory 310 may also be used to temporarily store various types of data that have been output or are to be output.

The processor 320 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In this embodiment, the processor 320 is configured to execute computer readable instructions stored in the memory 310 or process data, for example, execute computer readable instructions of the intelligent management method applied to the energy storage battery.

The network interface 330 may include a wireless network interface or a wired network interface, the network interface 330 typically being used to establish communication connections between the computer device 300 and other electronic devices.

According to the computer equipment provided by the application, the priority of each battery core is ordered according to the battery core data of the energy storage system, when the battery cores are required to be charged and discharged, the battery cores with higher priority are preferentially used, so that the parameters of the battery cores in the energy storage system tend to be consistent, the function of the energy storage system is fully and efficiently exerted, in addition, the battery cores are charged according to the predicted electric quantity information, and the risk of damaging the service life and the safety of the battery cores caused by overcharging can be effectively avoided.

The present application also provides another embodiment, namely, a computer readable storage medium, where computer readable instructions are stored, where the computer readable instructions can be executed by at least one processor, so that the at least one processor performs the steps of the intelligent management method applied to an energy storage battery as described above.

According to the computer readable storage medium provided by the application, the priority of each battery core is ordered according to the battery core data of the energy storage system, when the battery cores are required to be charged and discharged, the battery cores with higher priority are preferentially used, so that the parameters of the battery cores in the energy storage system tend to be consistent, the function of the energy storage system is fully and efficiently exerted, in addition, the battery cores are charged according to the predicted electric quantity information, and the risk of damaging the service life and the safety of the battery cores caused by overcharging can be effectively avoided.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.

It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.

Claims

1. The intelligent management method applied to the energy storage battery is characterized by being applied to an energy storage system, wherein the energy storage system comprises a plurality of energy storage cells and comprises the following steps of:

If the current time meets the electricity consumption valley time, sequentially performing discharging operation on the battery cells according to the priority sequence and the predicted electric quantity information;

the step of calculating the health grade of each cell according to the health degree specifically comprises the following steps:

Wherein, Representing the preset segmentation threshold value; the cell health of the nth cell is represented;

And if the current time meets the electricity consumption valley time, sequentially performing discharging operation on the battery cell according to the priority sequence and the predicted electric quantity information, wherein the method specifically comprises the following steps of:

and when the current available capacity of all the battery cells in the energy storage system is larger than the predicted electric quantity information and the difference value between the current available capacity of all the plurality of energy storage battery cells and the predicted electric quantity information meets the preset residual electric quantity, completing the discharging operation.

2. The intelligent management method for an energy storage battery according to claim 1, wherein the step of obtaining the electricity consumption valley time corresponding to the energy storage system comprises the following steps:

3. The intelligent management method applied to an energy storage battery according to claim 2, wherein the first model training set is obtained by:

4. The intelligent management method for an energy storage battery according to claim 3, further comprising, before the step of inputting the first model training set to a first regression prediction model for model training, the steps of:

The valley prediction model is obtained through the following steps:

inputting the ternary arrays of all elements in the first key influence factors into the regression prediction model improved based on the particle swarm algorithm;

5. The intelligent management method applied to an energy storage battery according to claim 1, wherein after the step of acquiring the cell data of each cell in the plurality of energy storage cells, wherein the cell data includes a rated capacity, a health degree, and a cycle number, the method further includes the steps of:

If the electric quantity value of a first electric core to be charged in the charging process is equal to the actual electric quantity value of other energy storage electric cores in the next sequence in the sequence to be charged, merging the first electric core to be charged and the energy storage electric cores in the next sequence into a second electric core to be charged, and carrying out charging treatment on the second electric core to be charged;

6. The utility model provides an intelligent management device for energy storage battery, its characterized in that, the device is applied to energy storage system, energy storage system includes a plurality of energy storage electric core, includes:

The discharging module is used for sequentially discharging the battery cells according to the priority sequence and the predicted electric quantity information if the current time meets the electricity consumption valley time;

The health level calculation module includes: a health level calculation sub-module, wherein:

The health level calculation sub-module is configured to perform a classification operation on the health level of the battery cell according to a preset segmentation threshold and a battery cell classification algorithm to obtain the health level, where the health level is Expressed as:

；

the discharge module includes: the device comprises an electronic discharging module, an available capacity calculating sub-module, a discharging merging sub-module and a finished electronic discharging module, wherein:

The discharging module is used for calling the battery cell with the highest priority in the priority sequence to discharge and monitoring the real-time health degree data of the battery cell with the highest priority in real time;

The discharging merging submodule is used for merging the battery cells of the next level to discharge when the current available capacity of the battery cell with the highest priority is consistent with the current available capacity of the battery cell of the next level;

And the completion discharging electronic module is used for completing the discharging operation when the current available capacity of all the battery cores in the energy storage system is larger than the predicted electric quantity information and the difference value between the current available capacity of all the plurality of energy storage battery cores and the predicted electric quantity information meets the preset residual electric quantity.

7. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the intelligent management method of any of claims 1 to 5 applied to an energy storage battery.

8. A computer readable storage medium, characterized in that it has stored thereon computer readable instructions which, when executed by a processor, implement the steps of the intelligent management method applied to an energy storage battery according to any of claims 1 to 5.