Load-prediction-based control method and apparatus for energy storage apparatus, and terminal device and storage medium

Abstract

Disclosed in the present invention are a load-prediction-based control method and apparatus for an energy storage apparatus, and a terminal device and a storage medium. The method comprises: using a preset load prediction model to perform prediction on the basis of real-time operation data, so as to obtain a predicted load value of a micro-grid within a future time period; then, on the basis of a power generation capacity and the predicted load value, determining whether there is surplus electricity after the current power generation capacity of the micro-grid satisfies a future load demand; if so, controlling an energy storage apparatus to be charged, so as to avoid the waste of electric energy; and if not, controlling the energy storage apparatus to supply power to the micro-grid, so as to ensure that the micro-grid can satisfy the future load demand, thereby effectively ensuring the stable power supply of the micro-grid.

Description

Control methods, devices, terminal equipment, and storage media for energy storage devices based on load forecasting Technical Field

[0001] This invention relates to the field of mobile energy storage technology, and in particular to a control method, device, terminal equipment, and storage medium for an energy storage device based on load forecasting. Background Technology

[0002] With strong government support for new energy power generation technologies, photovoltaic and wind power units are gradually being integrated into microgrids. However, new energy power generation is often affected by time and space, resulting in unstable output, which causes fluctuations and uncertainties in microgrid load. Furthermore, user-side electricity consumption is also uncertain, especially with the promotion of electric vehicles, which can easily lead to extreme situations like overcrowded charging and no charging at all. Therefore, energy storage in microgrids is essential.

[0003] Electrochemical energy storage devices, characterized by fast charging / discharging speeds and small footprints, have been widely used in microgrids. However, current electrochemical energy storage systems generally require the microgrid to provide feedback on its load before proceeding with further scheduling operations—that is, determining whether to supply power to the microgrid or absorb excess energy. Because future loads cannot be known in advance, energy storage devices may fail to supply energy to the microgrid in a timely manner. This can result in the microgrid's own power generation being insufficient to meet current load demands, or the inability to absorb and store excess energy, leading to energy waste. Summary of the Invention

[0004] This invention provides a load forecast-based energy storage device control method, device, terminal equipment, and storage medium. By predicting the load of the microgrid in advance for a future period of time, the charging and discharging of the energy storage device can be controlled, which can effectively ensure the stable power supply of the microgrid and effectively avoid energy waste.

[0005] An embodiment of the present invention provides a control method for an energy storage device based on load forecasting, comprising:

[0006] Obtain real-time operating data and power generation of the microgrid;

[0007] The real-time operating data is input into a preset load forecasting model so that the load forecasting model can predict the load forecast value of the microgrid in a future time period based on the real-time operating data.

[0008] Based on the power generation and the load forecast, it is determined whether the microgrid will experience a power surplus in the future.

[0009] If so, the energy storage device is controlled to charge, absorbing surplus electricity from the microgrid;

[0010] If not, the energy storage device is controlled to supply power to the microgrid.

[0011] Furthermore, the energy storage device control method based on load forecasting described in the above embodiments of the invention further includes:

[0012] The historical operating data of the microgrid and the historical load data corresponding to each of the historical operating data are obtained; wherein, the historical operating data includes: current, voltage, and power generation.

[0013] The historical operating data and the corresponding historical load data are used as training samples to construct a training dataset;

[0014] Construct an initial prediction model using a BP neural network structure;

[0015] The initial prediction model is trained using the training dataset. During the training process, a preset loss function is used to evaluate the initial prediction model based on its output and the historical load data, and an evaluation result is generated.

[0016] When the evaluation result converges and is minimized, the initial prediction model is determined to be trained successfully, and the trained initial prediction model is used as the load prediction model.

[0017] Furthermore, the initial prediction model is evaluated using a preset loss function based on its output and the historical load data, and an evaluation result is generated, including:

[0018] The initial prediction model is evaluated using the following loss function, based on its output and the historical load data:

[0019] Where LOSS represents the evaluation result, n is the total number of training samples in the training dataset, and y i The output of the initial prediction model, based on historical data from the i-th training sample. The initial prediction model is based on historical load data from the i-th training sample.

[0020] Furthermore, the energy storage device control method based on load forecasting described in the above embodiments of the invention further includes:

[0021] Obtain the actual load value of the microgrid over a future time period;

[0022] Calculate the error between the predicted load value and the actual load value;

[0023] When the error exceeds a preset error threshold, the real-time running data and the actual load value are saved as model update training samples to a preset model training database.

[0024] When the number of model update training samples exceeds a preset threshold, several model update training samples are obtained from the model training database to train the load prediction model and generate a new load prediction model.

[0025] Furthermore, determining whether the microgrid will experience a power surplus in the future based on the power generation and the load forecast includes:

[0026] Compare the power generation with the load forecast value;

[0027] When the power generation is greater than the load forecast value, it is determined that the microgrid will have a power surplus in the future period of time;

[0028] When the power generation is less than the load forecast, it is determined that the microgrid will experience a power shortage in the future.

[0029] Another embodiment of the present invention provides a control device for an energy storage device based on load forecasting, comprising:

[0030] The data acquisition module is used to acquire real-time operating data and power generation of the microgrid;

[0031] The load forecasting module is used to input the real-time operating data into a preset load forecasting model, so that the load forecasting model can predict the load forecast value of the microgrid in a future time period based on the real-time operating data.

[0032] The power assessment module is used to determine whether the microgrid will have a power surplus in the future period of time based on the power generation and the load forecast value.

[0033] The first control module is used to control the energy storage device to charge if the condition is met, so as to absorb the surplus power from the microgrid.

[0034] The second control module is used to control the energy storage device to supply power to the microgrid if not otherwise specified.

[0035] Furthermore, the energy storage device control device based on load forecasting described in the above embodiments of the invention further includes:

[0036] Model training module;

[0037] The model training module is used to acquire historical operating data of the microgrid, as well as historical load data corresponding to each historical operating data; wherein, the historical operating data includes: current, voltage, power generation, and weather data;

[0038] The historical operating data and the corresponding historical load data are used as training samples to construct a training dataset;

[0039] Construct an initial prediction model using a BP neural network structure;

[0040] The initial prediction model is trained using the training dataset. During the training process, a preset loss function is used to evaluate the initial prediction model based on its output and the historical load data, and an evaluation result is generated.

[0041] When the evaluation result converges and is minimized, the initial prediction model is determined to be trained successfully, and the trained initial prediction model is used as the load prediction model.

[0042] Furthermore, the energy storage device control device based on load forecasting described in the above embodiments of the invention further includes:

[0043] Model update module;

[0044] The model update module is used to obtain the actual load value of the microgrid in a future time period;

[0045] Calculate the error between the predicted load value and the actual load value;

[0046] When the error exceeds a preset error threshold, the real-time running data and the actual load value are saved as model update training samples to a preset model training database.

[0047] When the number of model update training samples exceeds a preset threshold, several model update training samples are obtained from the model training database to train the load prediction model and generate a new load prediction model.

[0048] Another embodiment of the present invention provides a terminal device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a load forecast-based energy storage device control method as described in any of the embodiments.

[0049] Another embodiment of the present invention provides a storage medium, characterized in that the storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the storage medium is located to perform a load forecast-based energy storage device control method as described in any of the above embodiments.

[0050] The following benefits can be obtained by implementing the present invention:

[0051] This invention discloses a control method, device, terminal equipment, and storage medium for an energy storage device based on load forecasting. The method uses a preset load forecasting model to predict the load forecast value of the microgrid within a future time period based on real-time operating data. Then, based on the power generation and the load forecast value, it determines whether there is a surplus of power generation in the current microgrid after meeting future load demand. If so, the method controls the energy storage device to charge to avoid wasting energy. If not, the method controls the energy storage device to supply power to the microgrid to ensure that the microgrid can meet future load demand and effectively guarantee the stable power supply of the microgrid. Attached Figure Description

[0052] Figure 1 is a schematic flowchart of a load forecast-based energy storage device control method according to an embodiment of the present invention.

[0053] Figure 2 is a schematic diagram of the structure of an energy storage device control device based on load prediction according to an embodiment of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] Unless otherwise defined, 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 pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0056] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0057] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0058] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0059] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0060] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0061] Referring to Figure 1, it is a schematic flowchart of a load forecast-based energy storage device control method according to an embodiment of the present invention, including:

[0062] S1. Obtain real-time operating data and power generation of the microgrid;

[0063] In a preferred embodiment of the present invention, the real-time operating data includes: current, voltage, and power generation. It is understood that when there are new energy generators such as photovoltaic and wind power units in the microgrid, the real-time operating data also includes: real-time weather data. The power generation is the sum of the power generation of all generator units in the microgrid at that moment.

[0064] S2. Input the real-time operating data into a preset load forecasting model so that the load forecasting model can predict the load forecast value of the microgrid in a future time period based on the real-time operating data.

[0065] In a preferred embodiment of the present invention, in order to improve the accuracy of prediction, the real-time operating data is preprocessed by removing outliers and normalizing before being input into the load prediction model.

[0066] Preferably, the training process of the load prediction model includes:

[0067] S01. Obtain historical operating data of the microgrid, and historical load data corresponding to each of the historical operating data; wherein, the historical operating data includes: current, voltage, and power generation.

[0068] S02. Use the historical operating data and the corresponding historical load data as training samples to construct a training dataset;

[0069] S03. Construct the initial prediction model of the BP neural network structure;

[0070] S04. The initial prediction model is trained using the training dataset. During the training process, the initial prediction model is evaluated using a preset loss function based on the output of the initial prediction model and the historical load data, and an evaluation result is generated.

[0071] Preferably, the step of evaluating the initial prediction model using a preset loss function based on the output of the initial prediction model and the historical load data, and generating an evaluation result, includes:

[0072] The initial prediction model is evaluated using the following loss function, based on its output and the historical load data:

[0073] Where LOSS represents the evaluation result, n is the total number of training samples in the training dataset, and y i The output of the initial prediction model, based on historical data from the i-th training sample. The initial prediction model is based on historical load data from the i-th training sample.

[0074] S05. When the evaluation result converges and is minimized, the initial prediction model is determined to be trained and the trained initial prediction model is used as the load prediction model.

[0075] In a preferred embodiment of the present invention, the data in the training dataset is randomly divided into training data and test data, with the ratio of training data to test data being 60% and 40%, respectively.

[0076] Furthermore, the initial prediction model consists of an input layer, a hidden layer, and an output layer, and the node connections between layers are represented by weights. During training, training data is input into the initial prediction model, and iterative updates are performed to obtain an initial prediction model that minimizes the loss function.

[0077] It should be further explained that the initial prediction model uses the Sigmoid function as the activation function, as shown below:

[0078] Where x is the input value.

[0079] S3. Based on the power generation and the load forecast, determine whether the microgrid will have a power surplus in the future.

[0080] Preferably, determining whether the microgrid will experience a power surplus in the future period based on the power generation and the load forecast includes:

[0081] S31. Compare the power generation with the load forecast value;

[0082] S32. When the power generation is greater than the load forecast value, it is determined that the microgrid will have a power surplus in the future period of time.

[0083] S33. When the power generation is less than the load forecast value, it is determined that the microgrid will experience insufficient power supply in the future.

[0084] S4. If so, control the energy storage device to charge and absorb the surplus power from the microgrid.

[0085] S5. If not, control the energy storage device to supply power to the microgrid.

[0086] In a preferred embodiment of the present invention, the energy storage device can be various electrochemical energy storage devices such as lead-acid batteries, lithium batteries, sodium-sulfur batteries, and flow batteries. When the microgrid has a power surplus, the electrochemical energy storage device charges to accommodate the excess power of the microgrid; when the microgrid's power supply is insufficient, the electrochemical energy storage device discharges to provide power to the microgrid.

[0087] Preferably, the energy storage device control method based on load forecasting described in the above embodiments further includes:

[0088] S6. Obtain the actual load value of the microgrid in a future time period;

[0089] S7. Calculate the error between the predicted load value and the actual load value;

[0090] S8. When the error is greater than a preset error threshold, the real-time running data and the actual load value are saved as model update training samples to a preset model training database.

[0091] S9. When the number of model update training samples is greater than a preset threshold, obtain several model update training samples from the model training database to train the load prediction model and generate a new load prediction model.

[0092] In a preferred embodiment of the present invention, considering the continuous development and changes in the power system, the load characteristics will also change. Therefore, this embodiment updates the neural network model to adapt to the new load characteristics.

[0093] This embodiment provides a load forecast-based energy storage device control method. By using a preset load forecast model to predict the load forecast value of the microgrid in the future time period based on real-time operating data, and then judging whether there is a surplus of electricity after the current power generation of the microgrid meets the future load demand based on the power generation and the load forecast value, if so, the energy storage device is controlled to charge to avoid wasting electricity; if not, the energy storage device is controlled to supply power to the microgrid to ensure that the microgrid can meet the future load demand, effectively ensuring the stable power supply of the microgrid.

[0094] Referring to Figure 2, it is a schematic diagram of the structure of an energy storage device control device based on load forecasting according to an embodiment of the present invention, including:

[0095] The data acquisition module is used to acquire real-time operating data and power generation of the microgrid;

[0096] The load forecasting module is used to input the real-time operating data into a preset load forecasting model, so that the load forecasting model can predict the load forecast value of the microgrid in a future time period based on the real-time operating data.

[0097] The power assessment module is used to determine whether the microgrid will have a power surplus in the future period of time based on the power generation and the load forecast value.

[0098] The first control module is used to control the energy storage device to charge if the condition is met, so as to absorb the surplus power from the microgrid.

[0099] The second control module is used to control the energy storage device to supply power to the microgrid if not otherwise specified.

[0100] Preferably, the energy storage device control device based on load forecasting further includes:

[0101] Model training module;

[0102] The model training module is used to acquire historical operating data of the microgrid, as well as historical load data corresponding to each historical operating data; wherein, the historical operating data includes: current, voltage, power generation, and weather data;

[0103] The historical operating data and the corresponding historical load data are used as training samples to construct a training dataset;

[0104] Construct an initial prediction model using a BP neural network structure;

[0105] The initial prediction model is trained using the training dataset. During the training process, a preset loss function is used to evaluate the initial prediction model based on its output and the historical load data, and an evaluation result is generated.

[0106] When the evaluation result converges and is minimized, the initial prediction model is determined to be trained successfully, and the trained initial prediction model is used as the load prediction model.

[0107] Preferably, the energy storage device control device based on load forecasting further includes: a model update module;

[0108] The model update module is used to obtain the actual load value of the microgrid in a future time period;

[0109] Calculate the error between the predicted load value and the actual load value;

[0110] When the error exceeds a preset error threshold, the real-time running data and the actual load value are saved as model update training samples to a preset model training database.

[0111] When the number of model update training samples exceeds a preset threshold, several model update training samples are obtained from the model training database to train the load prediction model and generate a new load prediction model.

[0112] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0113] Those skilled in the art will clearly understand that, for convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0114] Another preferred embodiment of the present invention provides a terminal device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a load forecast-based energy storage device control method as described in any of the above embodiments.

[0115] The terminal device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0116] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0117] The memory can be used to store the computer program. The processor implements various functions of the terminal device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0118] Another preferred embodiment of the present invention provides a storage medium, which is a computer-readable storage medium. A computer program is stored in the computer-readable storage medium, and when executed by a processor, the computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0119] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A control method for an energy storage device based on load forecasting, characterized in that, include: Obtain real-time operating data and power generation of the microgrid; The real-time operating data is input into a preset load forecasting model so that the load forecasting model can predict the load forecast value of the microgrid in a future time period based on the real-time operating data. Based on the power generation and the load forecast, it is determined whether the microgrid will experience a power surplus in the future. If so, the energy storage device is controlled to charge, absorbing surplus electricity from the microgrid; If not, the energy storage device is controlled to supply power to the microgrid.

2. The energy storage device control method based on load forecasting as described in claim 1, characterized in that, Also includes: The historical operating data of the microgrid and the historical load data corresponding to each of the historical operating data are obtained; wherein, the historical operating data includes: current, voltage, and power generation. The historical operating data and the corresponding historical load data are used as training samples to construct a training dataset; Construct an initial prediction model using a BP neural network structure; The initial prediction model is trained using the training dataset. During the training process, a preset loss function is used to evaluate the initial prediction model based on its output and the historical load data, and an evaluation result is generated. When the evaluation result converges and is minimized, the initial prediction model is determined to be trained successfully, and the trained initial prediction model is used as the load prediction model.

3. The energy storage device control method based on load forecasting as described in claim 2, characterized in that, The method employs a preset loss function to evaluate the initial prediction model based on its output and the historical load data, and generates an evaluation result, including: The initial prediction model is evaluated using the following loss function, based on its output and the historical load data: Where LOSS represents the evaluation result, n is the total number of training samples in the training dataset, and y i The output of the initial prediction model, based on historical data from the i-th training sample. The initial prediction model is based on historical load data from the i-th training sample.

4. The energy storage device control method based on load forecasting as described in claim 1, characterized in that, Also includes: Obtain the actual load value of the microgrid over a future time period; Calculate the error between the predicted load value and the actual load value; When the error exceeds a preset error threshold, the real-time running data and the actual load value are saved as model update training samples to a preset model training database. When the number of model update training samples exceeds a preset threshold, several model update training samples are obtained from the model training database to train the load prediction model and generate a new load prediction model.

5. The energy storage device control method based on load forecasting as described in claim 1, characterized in that, The step of determining whether the microgrid will experience a power surplus in the future based on the power generation and the load forecast includes: Compare the power generation with the load forecast value; When the power generation is greater than the load forecast value, it is determined that the microgrid will have a power surplus in the future period of time; When the power generation is less than the load forecast, it is determined that the microgrid will experience a power shortage in the future.

6. A control device for an energy storage device based on load forecasting, characterized in that, include: The data acquisition module is used to acquire real-time operating data and power generation of the microgrid; The load forecasting module is used to input the real-time operating data into a preset load forecasting model, so that the load forecasting model can predict the load forecast value of the microgrid in a future time period based on the real-time operating data. The power assessment module is used to determine whether the microgrid will have a power surplus in the future period of time based on the power generation and the load forecast value. The first control module is used to control the energy storage device to charge if the condition is met, so as to absorb the surplus power from the microgrid. The second control module is used to control the energy storage device to supply power to the microgrid if not otherwise specified.

7. The energy storage device control device based on load forecasting as described in claim 1, characterized in that, It also includes: a model training module; The model training module is used to acquire historical operating data of the microgrid, as well as historical load data corresponding to each historical operating data; wherein, the historical operating data includes: current, voltage, power generation, and weather data; The historical operating data and the corresponding historical load data are used as training samples to construct a training dataset; Construct an initial prediction model using a BP neural network structure; The initial prediction model is trained using the training dataset. During the training process, a preset loss function is used to evaluate the initial prediction model based on its output and the historical load data, and an evaluation result is generated. When the evaluation result converges and is minimized, the initial prediction model is determined to be trained successfully, and the trained initial prediction model is used as the load prediction model.

8. The energy storage device control device based on load forecasting as described in claim 6, characterized in that, Also includes: Model update module; The model update module is used to obtain the actual load value of the microgrid in a future time period; Calculate the error between the predicted load value and the actual load value; When the error exceeds a preset error threshold, the real-time running data and the actual load value are saved as model update training samples to a preset model training database. When the number of model update training samples exceeds a preset threshold, several model update training samples are obtained from the model training database to train the load prediction model and generate a new load prediction model.

9. A terminal device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements a load forecast-based energy storage device control method as described in any one of claims 1 to 5.

10. A storage medium, characterized in that, The storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the storage medium to perform a load forecast-based energy storage device control method as described in any one of claims 1 to 5.

Images