A control method and system for energy storage converters based on intelligent integrated energy management

Abstract

The present invention relates to a method and system for controlling an energy storage converter based on intelligent integrated energy management, and belongs to the technical field of energy storage converter control. The method includes: obtaining basic power consumption data of a plant area, adding a timestamp to the basic power consumption data to obtain time series power consumption data, constructing a feature triple sequence according to the time series power consumption data, and calculating a predicted power consumption sequence through a time series prediction model according to the feature triple sequence; obtaining current data at the access point of the energy storage converter, and calculating a grid-connected and off-grid diagnosis result through a diagnosis model according to the current data at the access point of the energy storage converter and the predicted power consumption sequence; the intelligent terminal generates a grid-connected and off-grid transition signal according to the grid-connected and off-grid diagnosis result, and the energy storage converter performs grid-connected and off-grid operations according to the grid-connected and off-grid transition signal. The energy storage converter is able to quickly execute grid-connected and off-grid operation responses, effectively reduce energy consumption, and provide energy storage for the load in a timely manner.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage converter control, and specifically relates to an energy storage converter control method and system based on intelligent integrated energy management. Background Art

[0002] In today's society, with the continuous growth of energy consumption and the enhancement of environmental protection awareness, finding effective energy solutions to promote sustainable development has become a global focus. As an important link between renewable energy and traditional power grids, the optimization of energy storage converter performance and control strategy is of great significance for improving energy efficiency, reducing costs and coping with power grid fluctuations.

[0003] However, with the continuous expansion of system scale and the complexity of working environment, energy storage converters face severe challenges of high power density and functional stability. At present, energy storage converters have the following problems:

[0004] (1) Traditional unplanned islanding mainly relies on the energy storage inverter itself for detection. When a grid fault occurs, the energy storage inverter needs a certain amount of time to detect whether an islanding occurs. However, during the detection process, the energy storage inverter still works in the grid-connected mode and cannot quickly switch to the off-grid state, which will cause the components of the energy storage inverter to fail.

[0005] (2) Traditional planned islanding mainly relies on manual real-time monitoring of the power consumption of the plant to make decisions on on-grid and off-grid switching. This requires human support and is not predictive, which increases the response time of on-grid and off-grid switching. Summary of the invention

[0006] In order to solve the above problems existing in the prior art, the present invention provides a control method and system of an energy storage converter based on intelligent integrated energy management.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] Obtain basic electricity consumption data, add a timestamp to the basic electricity consumption data to obtain time series electricity consumption data, construct a feature triplet sequence based on the time series electricity consumption data, and calculate a predicted electricity consumption sequence based on the feature triplet sequence through a time series prediction model;

[0009] The characteristic triplet sequence is obtained by dividing the time series power consumption according to the time granularity to obtain the hourly power consumption, constructing the hourly characteristic triplet according to the hourly power consumption, and aggregating the hourly characteristic triplet to obtain the characteristic triplet sequence;

[0010] The triple expression of the feature at each time is:

[0011] ,

[0012] in, U i is the feature triplet at each time, m i For the date, d i For the moment, c i For electricity consumption;

[0013] Acquire current data of the energy storage converter access point, and calculate the on-grid and off-grid diagnosis result through the diagnosis model according to the current data of the energy storage converter access point and the predicted power consumption sequence;

[0014] The diagnostic model includes firstly making a judgment according to the current data of the energy storage converter access point, and outputting an off-grid diagnostic result if the current data of the energy storage converter access point is zero; if the current data of the energy storage converter access point is not zero, traversing the predicted power consumption sequence according to the current moment to obtain the predicted power consumption at the next moment, presetting a comparison threshold, and comparing the predicted power consumption at the next moment according to the comparison threshold and the predicted power consumption at the next moment, and outputting a grid-connected diagnostic result if the predicted power consumption at the next moment is greater than the threshold, and outputting an off-grid diagnostic result if the predicted power consumption at the next moment is less than the threshold;

[0015] The intelligent terminal generates an on-grid and off-grid transition signal according to the on-grid and off-grid diagnosis result, and the energy storage converter performs on-grid and off-grid operations according to the on-grid and off-grid transition signal.

[0016] Specifically, the feature triplet sequence is to divide the time series power consumption according to the time granularity to obtain the hourly power consumption, construct the hourly feature triplet according to the hourly power consumption, and collect the hourly feature triplet to obtain the feature triplet sequence.

[0017] Specifically, the time series prediction model includes a coding model and a decoding model. The coding model is used to encode the feature triple sequence to obtain a feature code, and the decoding model is used to calculate the predicted power consumption sequence based on the feature code.

[0018] Specifically, the coding model includes a fully connected layer, a position coding layer, an encoder, and a normalization layer. The specific calculation steps are:

[0019] S401: performing high-dimensional space mapping through the fully connected layer according to the feature triple sequence to obtain an extended feature sequence;

[0020] S402: Obtaining a coding vector through sinusoidal position coding according to the extended feature sequence;

[0021] S403: the encoder performs encoding according to the encoding vector by using a Layer Norm method to obtain an initial encoding;

[0022] S404: The normalization layer performs normalization according to the initial code to obtain the feature code.

[0023] Specifically, the decoding model includes a memory unit and a fully connected layer, and the specific calculation steps are as follows:

[0024] S501: Obtain context coding by calculating through the memory unit according to the feature coding;

[0025] S502: Calculating predicted power consumption through the fully connected layer according to the context coding, obtaining a judgment parameter value, and performing an addition operation on the judgment parameter value to obtain a new judgment parameter value;

[0026] S503: judging according to the new judgment parameter value, if the new judgment parameter value is equal to twenty-four, executing S504; if the new judgment parameter value is less than twenty-four, adding the predicted power consumption to the predicted power consumption sequence, presetting a sliding window, intercepting the predicted power consumption sequence according to the sliding window to obtain a new power consumption sequence, and repeating the steps S401-S404 and the steps S501-S503 according to the new power consumption sequence;

[0027] S504: Aggregate each of the predicted power consumption to obtain the predicted power consumption sequence.

[0028] Specifically, the diagnostic model includes first making a judgment based on the current data of the energy storage inverter access point. If the current data of the energy storage inverter access point is zero, outputting an off-grid diagnostic result; if the current data of the energy storage inverter access point is not zero, traversing the predicted power consumption sequence at the current moment to obtain the predicted power consumption at the next moment, presetting a comparison threshold, and comparing the comparison threshold with the predicted power consumption at the next moment. If the predicted power consumption at the next moment is greater than the threshold, outputting a grid-connected diagnostic result; if the predicted power consumption at the next moment is less than the threshold, outputting an off-grid diagnostic result.

[0029] Specifically, the on-grid and off-grid operation includes on-grid to off-grid operation and off-grid to on-grid operation. The on-grid to off-grid operation is to switch the power outer loop to the voltage outer loop, and the off-grid to on-grid operation is to switch the voltage outer loop to the power outer loop.

[0030] A storage converter control system based on intelligent integrated energy management, comprising: a data acquisition module, a data processing module, and a grid-connected and off-grid module;

[0031] The data acquisition module is used to acquire basic power consumption data, add a timestamp to the basic power consumption data to obtain time series power consumption data, construct a feature triple sequence based on the time series power consumption data, and calculate a predicted power consumption sequence based on the feature triple sequence through a time series prediction model;

[0032] The characteristic triplet sequence is obtained by dividing the time series power consumption according to the time granularity to obtain the hourly power consumption, constructing the hourly characteristic triplet according to the hourly power consumption, and aggregating the hourly characteristic triplet to obtain the characteristic triplet sequence;

[0033] The triple expression of the feature at each time is:

[0034] ,

[0035] Among them, Ui is the characteristic triplet of each hour, mi is the date, di is the time, and ci is the power consumption;

[0036] The data processing module is used to obtain the current data of the energy storage converter access point, and calculate the on-grid and off-grid diagnosis result through the diagnosis model according to the current data of the energy storage converter access point and the predicted power consumption sequence;

[0037] The diagnostic model includes firstly making a judgment according to the current data of the energy storage converter access point, and outputting an off-grid diagnostic result if the current data of the energy storage converter access point is zero; if the current data of the energy storage converter access point is not zero, traversing the predicted power consumption sequence according to the current moment to obtain the predicted power consumption at the next moment, presetting a comparison threshold, and comparing the predicted power consumption at the next moment according to the comparison threshold and the predicted power consumption at the next moment, and outputting a grid-connected diagnostic result if the predicted power consumption at the next moment is greater than the threshold, and outputting an off-grid diagnostic result if the predicted power consumption at the next moment is less than the threshold;

[0038] The on-grid and off-grid module is used for the intelligent terminal to generate an on-grid and off-grid transition signal according to the on-grid and off-grid diagnosis result, and the energy storage converter performs on-grid and off-grid operations according to the on-grid and off-grid transition signal.

[0039] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the energy storage converter control method based on intelligent integrated energy management as described above is implemented.

[0040] A storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the energy storage converter control method based on intelligent integrated energy management as described above.

[0041] The beneficial effects of the present invention are:

[0042] (1) By setting up a time series prediction model, the power consumption of the plant area on the previous day is calculated through the time series prediction model to obtain the predicted power consumption at each moment of the next day. The planned island time node is calculated based on the predicted power consumption through the diagnostic model, which improves the energy storage inverter's timely on-grid and off-grid response, effectively avoiding the need for real-time monitoring of power consumption by manpower, and reducing the consumption of manpower, financial resources and energy.

[0043] (2) The current at the grid-connected access point is obtained through external data collection equipment, and the current is determined by the diagnostic model to determine whether the energy storage inverter is in an unplanned island state. The grid-connected and off-grid transition signals are transmitted to the energy storage inverter through 5G high-state flow real-time communication technology. This can improve the response time of the energy storage inverter and avoid unplanned island detection through the internal detection components of the energy storage inverter, which may cause damage to the energy storage inverter components and loads due to long detection time. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0045] Figure 1 It is a flow chart of a method for controlling an energy storage converter based on intelligent integrated energy management according to the present invention. DETAILED DESCRIPTION

[0046] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0047] See also Figure 1 , a control method of energy storage converter based on intelligent integrated energy management,

[0048] Obtain basic electricity consumption data, add a timestamp to the basic electricity consumption data to obtain time series electricity consumption data, construct a feature triplet sequence based on the time series electricity consumption data, and calculate a predicted electricity consumption sequence based on the feature triplet sequence through a time series prediction model;

[0049] It should be noted that the base electricity consumption data refers to the factory's electricity consumption data from the previous day.

[0050] Acquire current data of the energy storage converter access point, and calculate the on-grid and off-grid diagnosis results through the diagnosis model according to the current data of the energy storage converter access point and the predicted power consumption sequence; the on-grid and off-grid diagnosis results include on-grid diagnosis results and off-grid diagnosis results;

[0051] The intelligent terminal generates an on-grid and off-grid transition signal according to the on-grid and off-grid diagnosis result, and the energy storage converter performs on-grid and off-grid operations according to the on-grid and off-grid transition signal.

[0052] The feature triplet sequence is obtained by dividing the time series power consumption according to the time granularity to obtain the hourly power consumption, constructing the hourly feature triplet according to the hourly power consumption, and aggregating the hourly feature triplet to obtain the feature triplet sequence; the time granularity is one hour.

[0053] The triple expression of the feature at each time is:

[0054] ,

[0055] in, U i is the feature triplet at each time, m i For the date, d i For the moment, c i For electricity consumption.

[0056] Specifically, the time series prediction model includes an encoding model and a decoding model. The encoder encodes the feature triple sequence to obtain feature codes, and the decoder calculates the predicted power consumption sequence based on the feature codes.

[0057] The coding model includes a fully connected layer, a position coding layer, an encoder, and a normalization layer. The specific calculation steps are:

[0058] Specifically, the coding model includes a fully connected layer, a position coding layer, an encoder, and a normalization layer. The specific calculation steps are:

[0059] S401: performing high-dimensional space mapping through the fully connected layer according to the feature triple sequence to obtain an extended feature sequence;

[0060] S402: Obtaining a coding vector through sinusoidal position coding according to the extended feature sequence;

[0061] S403: the encoder performs encoding according to the encoding vector by using a Layer Norm method to obtain an initial encoding;

[0062] S404: The normalization layer performs normalization according to the initial code to obtain the feature code.

[0063] Specifically, the decoding model includes a memory unit and a fully connected layer, and the specific calculation steps are as follows:

[0064] S501: Obtain context coding by calculating through the memory unit according to the feature coding;

[0065] S502: Calculating predicted power consumption through the fully connected layer according to the context coding, obtaining a judgment parameter value, and performing an addition operation on the judgment parameter value to obtain a new judgment parameter value;

[0066] S503: judging according to the new judgment parameter value, if the new judgment parameter value is equal to twenty-four, executing S504; if the new judgment parameter value is less than twenty-four, adding the predicted power consumption to the predicted power consumption sequence, presetting a sliding window, intercepting the predicted power consumption sequence according to the sliding window to obtain a new power consumption sequence, and repeating the steps S401-S404 and the steps S501-S503 according to the new power consumption sequence; the sliding window size is 24;

[0067] S504: Aggregate each of the predicted power consumption to obtain the predicted power consumption sequence.

[0068] In this embodiment, the memory unit is a bridge between the encoding model and the decoding model, and the memory unit uses the feature code output by the encoding model as memory content to guide the operation of the decoding model;

[0069] The memory unit calculation expression is:

[0070] ,

[0071] in, W 1 i ，W 2 i ，W 3 i ，W 4 , v Fixed parameters for memory modules, g is the dimension of the high-dimensional space, M is the memory matrix, n is a variable parameter, indicating that n Head attention, i is a variable parameter, output Encode the context.

[0072] Specifically, the diagnostic model includes first making a judgment based on the current data of the energy storage inverter access point. If the current data of the energy storage inverter access point is zero, an off-grid diagnostic result is output. If the current data of the energy storage inverter access point is not 0, the predicted power consumption sequence is traversed according to the current moment to obtain the predicted power consumption at the next moment, a preset comparison threshold is set, and the comparison is made according to the comparison threshold and the predicted power consumption at the next moment. If the predicted power consumption at the next moment is greater than the threshold, a grid-connected diagnostic result is output. If the predicted power consumption at the next moment is less than the threshold, an off-grid diagnostic result is output.

[0073] Specifically, the on-grid and off-grid operation includes on-grid to off-grid operation and off-grid to on-grid operation. The on-grid to off-grid operation is to switch the power outer loop to the voltage outer loop, and the off-grid to on-grid operation is to switch the voltage outer loop to the power outer loop.

[0074] In this embodiment, smooth grid-connected to off-grid operation can be achieved through the following steps: obtaining the active power outer loop output voltage and the reactive power outer loop output voltage, using the active power outer loop output voltage as the output of the d-axis voltage loop controller, and using the reactive power outer loop output voltage as the integral value of the q-axis voltage loop controller, so that the given current inner loop at the switching moment will not change suddenly; obtaining the phase of the phase-locked loop at the switching moment, and using the phase as the initial phase value in the off-grid mode, so as to ensure that the voltage phase at the switching moment does not change suddenly; obtaining the d-axis voltage at the switching moment, and using the d-axis voltage as the initial voltage value of the d-axis voltage loop in the off-grid mode, so as to ensure that the output of the voltage loop will not have large oscillations.

[0075] A storage converter control system based on intelligent integrated energy management, comprising: a data acquisition module, a data processing module, and a grid-connected and off-grid module;

[0076] The data acquisition module is used to acquire basic power consumption data of the factory area, add a timestamp to the basic power consumption data to obtain time series power consumption data, construct a feature triple sequence according to the time series power consumption data, and calculate a predicted power consumption sequence according to the feature triple sequence through a time series prediction model;

[0077] The data processing module is used to obtain the current data of the energy storage converter access point, and calculate the on-grid and off-grid diagnosis result through the diagnosis model according to the current data of the energy storage converter access point and the predicted power consumption sequence;

[0078] The on-grid and off-grid module is used for the intelligent terminal to generate an on-grid and off-grid transition signal according to the on-grid and off-grid diagnosis result, and the energy storage converter performs on-grid and off-grid operations according to the on-grid and off-grid transition signal.

[0079] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the energy storage converter control method based on intelligent integrated energy management as described above is implemented.

[0080] A storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the energy storage converter control method based on intelligent integrated energy management as described above.

[0081] In this embodiment, the intelligent terminal performs island detection on the energy storage inverter through external detection technology, and transmits the isolation conversion signal to the energy storage inverter through 5G high state stream real-time communication technology, thereby avoiding damage to the internal components of the energy storage inverter due to the inability to adjust the control strategy in time when the energy storage inverter performs island detection when a power grid fails.

[0082] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0083] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0084] The program code included in the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written with one or more programming languages ​​or their combination, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0085] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for controlling an energy storage converter based on intelligent integrated energy management, characterized in that: include: Obtain basic electricity consumption data, add a timestamp to the basic electricity consumption data to obtain time series electricity consumption data, construct a feature triplet sequence based on the time series electricity consumption data, and calculate a predicted electricity consumption sequence based on the feature triplet sequence through a time series prediction model; The characteristic triplet sequence is obtained by dividing the time series power consumption according to the time granularity to obtain the hourly power consumption, constructing the hourly characteristic triplet according to the hourly power consumption, and aggregating the hourly characteristic triplet to obtain the characteristic triplet sequence; The triple expression of each time feature is: , in, U i is the feature triplet at each time, m i For the date, d i For the moment, c i For electricity consumption; Acquire current data of the energy storage converter access point, and calculate the on-grid and off-grid diagnosis result through the diagnosis model according to the current data of the energy storage converter access point and the predicted power consumption sequence; The diagnostic model includes firstly making a judgment according to the current data of the energy storage converter access point, and outputting an off-grid diagnostic result if the current data of the energy storage converter access point is zero; if the current data of the energy storage converter access point is not zero, traversing the predicted power consumption sequence according to the current moment to obtain the predicted power consumption at the next moment, presetting a comparison threshold, and comparing the predicted power consumption at the next moment according to the comparison threshold and the predicted power consumption at the next moment, and outputting a grid-connected diagnostic result if the predicted power consumption at the next moment is greater than the threshold, and outputting an off-grid diagnostic result if the predicted power consumption at the next moment is less than the threshold; The intelligent terminal generates an on-grid and off-grid transition signal according to the on-grid and off-grid diagnosis result, and the energy storage converter performs on-grid and off-grid operations according to the on-grid and off-grid transition signal.

2. The energy storage converter control method based on intelligent integrated energy management according to claim 1 is characterized in that: The time series prediction model includes a coding model and a decoding model. The coding model is used to encode the feature triple sequence to obtain a feature code, and the decoding model is used to calculate the predicted power consumption sequence based on the feature code.

3. The energy storage converter control method based on intelligent integrated energy management according to claim 2 is characterized in that: The coding model includes a fully connected layer, a position coding layer, an encoder, and a normalization layer. The specific calculation steps are: S401: performing high-dimensional space mapping through the fully connected layer according to the feature triple sequence to obtain an extended feature sequence; S402: Obtaining a coding vector through sinusoidal position coding according to the extended feature sequence; S403: the encoder performs encoding according to the encoding vector by using a Layer Norm method to obtain an initial encoding; S404: The normalization layer performs normalization according to the initial code to obtain the feature code.

4. The energy storage converter control method based on intelligent integrated energy management according to claim 3 is characterized in that: The decoding model includes a memory unit and a fully connected layer. The specific calculation steps are as follows: S501: Obtain context coding by calculating through the memory unit according to the feature coding; S502: Calculating predicted power consumption through the fully connected layer according to the context coding, obtaining a judgment parameter value, and performing an addition operation on the judgment parameter value to obtain a new judgment parameter value; S503: judging according to the new judgment parameter value, if the new judgment parameter value is equal to twenty-four, executing S504; if the new judgment parameter value is less than twenty-four, adding the predicted power consumption to the predicted power consumption sequence, presetting a sliding window, intercepting the predicted power consumption sequence according to the sliding window to obtain a new power consumption sequence, and repeating the steps S401-S404 and the steps S501-S503 according to the new power consumption sequence; S504: Aggregate each of the predicted power consumption to obtain the predicted power consumption sequence.

5. The energy storage converter control method based on intelligent integrated energy management according to claim 1 is characterized in that: The on-grid and off-grid operation includes on-grid to off-grid operation and off-grid to on-grid operation. The on-grid to off-grid operation is to switch the power outer loop to the voltage outer loop, and the off-grid to on-grid operation is to switch the voltage outer loop to the power outer loop.

6. A storage converter control system based on intelligent integrated energy management, characterized in that: include: Data acquisition module, data processing module, and on-grid and off-grid module; The data acquisition module is used to acquire basic power consumption data, add a timestamp to the basic power consumption data to obtain time series power consumption data, construct a feature triple sequence based on the time series power consumption data, and calculate a predicted power consumption sequence based on the feature triple sequence through a time series prediction model; The characteristic triplet sequence is obtained by dividing the time series power consumption according to the time granularity to obtain the hourly power consumption, constructing the hourly characteristic triplet according to the hourly power consumption, and aggregating the hourly characteristic triplet to obtain the characteristic triplet sequence; The triple expression of each time feature is: , in, U i is the feature triplet at each time, m i For the date, d i For the moment, c i For electricity consumption; The data processing module is used to obtain the current data of the energy storage converter access point, and calculate the on-grid and off-grid diagnosis result through the diagnosis model according to the current data of the energy storage converter access point and the predicted power consumption sequence; The diagnostic model includes firstly making a judgment according to the current data of the energy storage converter access point, and outputting an off-grid diagnostic result if the current data of the energy storage converter access point is zero; if the current data of the energy storage converter access point is not zero, traversing the predicted power consumption sequence according to the current moment to obtain the predicted power consumption at the next moment, presetting a comparison threshold, and comparing the predicted power consumption at the next moment according to the comparison threshold and the predicted power consumption at the next moment, and outputting a grid-connected diagnostic result if the predicted power consumption at the next moment is greater than the threshold, and outputting an off-grid diagnostic result if the predicted power consumption at the next moment is less than the threshold; The on-grid and off-grid module is used for the intelligent terminal to generate an on-grid and off-grid transition signal according to the on-grid and off-grid diagnosis result, and the energy storage converter performs on-grid and off-grid operations according to the on-grid and off-grid transition signal.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the energy storage converter control method based on intelligent integrated energy management as described in any one of claims 1-5.

8. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the energy storage converter control method based on intelligent integrated energy management as described in any one of claims 1 to 5.

Images