Thermal power coupling battery energy storage control device

Through the AI ​​model, the power grid and temperature data are integrated to generate accurate peak-to-frequency modulation instructions, which solves the problem of low prediction timeliness of battery energy storage control in the prior art, and achieves high-accurate battery energy storage management and grid power supply stability.

CN119029969AInactive Publication Date: 2024-11-26GUODIAN NANJING ELECTRIC POWER TEST RES CO LTD

Patent Information

Application Number
CN202410996755.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing thermal power coupled energy storage control methods lack effective data analysis methods, resulting in low prediction timeliness and large errors of battery energy storage output by temperature changes, and it is impossible to accurately adjust battery energy storage.

Method used

Using AI model combined with real-time and historical data, a data module is built through a fully connected neural network, integrating grid load, power generation and temperature data, generating accurate peak and frequency regulation instructions, and optimizing battery energy storage control.

Benefits of technology

It improves the timeliness and accuracy of battery energy storage control, can directly predict battery energy storage control instructions based on temperature changes, optimize the access and maintenance of the battery pack, and improve the stability of the power supply in the power grid.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119029969A_ABST
    Figure CN119029969A_ABST
Patent Text Reader

Abstract

The invention provides a thermal power coupling battery energy storage control device, and relates to the technical field of electric power energy storage, the thermal power coupling battery energy storage control device comprises a generator set, a transformer I and a power grid, the residual electric energy generated by the generator set is transmitted to a PCS energy storage converter through a transformer II, and the transformer II is connected with a peak regulation and frequency modulation coordination control center through a direct current switch; the peak and frequency modulation coordination control center accesses the data of the AI model, and the AI model accesses the data of the data module. According to the method, the AI model is constructed on the basis of multiple historical data, so that the constructed AI model can be trained according to a large amount of basic data, the over-fitting between the air temperature data and the power consumption data is avoided, and the air temperature critical value during power transmission quantity adjustment is analyzed; therefore, a user can directly predict a battery energy storage control instruction required to be performed according to the temperature change, so that the control of battery energy storage has timeliness and relatively high accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy storage, and in particular to a thermal power coupled battery energy storage control device. Background Art

[0002] Thermal power coupled with energy storage is a technology that combines traditional thermal power generation with energy storage technology. It aims to improve the peak-shaving capacity, thermal-electric decoupling capacity and system operation efficiency of thermal power plants. The control method of thermal power coupled with energy storage generally adopts flexibility transformation, joint frequency regulation system, multi-objective optimization load frequency control, etc., to achieve more efficient energy management and improve the regulation capability of the power grid.

[0003] The control of thermal power coupled energy storage is generally based on the actual grid load conditions. The release of battery energy storage is adjusted according to the power generation of thermal power generating units. It is mainly completed by the peak-shaving and frequency-regulating coordination control center. This battery energy storage control method is generally based on data only based on grid load data, or predicts adjustment instructions based on past adjustment data and operation analysis results. This method has few data sources, simple analysis methods, and does not take temperature changes into consideration, so it is easy to cause low accuracy of predicted adjustment instructions.

[0004] There is a close correlation between temperature and electricity consumption. As the temperature changes, people's electricity consumption behavior will also change accordingly, especially under extreme temperatures, the change is more significant. Depending on the different proportions of civil, commercial and industrial electricity consumption in the power supply area, the actual correlation between temperature and electricity consumption in different power supply areas is different.

[0005] However, there is currently no good data analysis method for adjusting the output of battery energy storage according to the temperature. The only way to make basic predictions is through analysis of data from previous years. As a result, the prediction results produced by this method have low timeliness and large errors, and there is room for improvement. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcomings existing in the prior art and alleviate the fact that the current method of adjusting the output of battery energy storage according to the temperature does not have a good data analysis method, and can only make basic predictions through data analysis in previous years, resulting in the prediction results produced by this method having low timeliness and large errors. There is room for improvement.

[0007] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a thermal power coupling battery energy storage control device, comprising a generator set, a transformer one and a power grid, the electric energy generated by the generator set is supplied to the power grid through the transformer one, the surplus electric energy generated by the generator set is transmitted to the PCS energy storage converter through the transformer two, the PCS energy storage converter is transmitted to the energy storage battery group through the DC switch, the transformer two is connected to the peak-shaving and frequency-modulation coordination control center through the DC switch, the peak-shaving and frequency-modulation coordination control center controls the start and stop of the AC switch, the transformer two transmits the electric energy of the energy storage battery group to the transformer one through the AC switch, the peak-shaving and frequency-modulation coordination control center accesses the data of the AI ​​model, the AI ​​model accesses the data of the data module, and the data module receives the data from the real-time data monitoring module and the historical data information recording module; The real-time data monitoring module includes a battery monitoring module for real-time monitoring of the energy storage battery pack, a power generation data monitoring module for real-time monitoring of the power generation of the generator set, and a power grid load monitoring module for real-time monitoring of the load data of the power grid; The historical data recording module includes a battery data recording module for storing energy storage battery data, a DC switch start / stop signal recording module for storing DC switch signal data, a transformer 2 adjustment recording module for recording transformer 2 adjustment data, an AC switch start / stop signal recording module for recording AC switch start / stop signal data, and a peak / frequency regulation data recording module for recording coordination data of a peak / frequency regulation coordination control center; The data module includes historical data and real-time data. The historical data includes a training set for training the AI ​​module and a verification set for verifying the AI ​​module. The real-time data includes real-time battery pack data obtained through the battery pack monitoring module, real-time power consumption data obtained through the power grid load monitoring module, and real-time power generation data obtained through the power generation data monitoring module.

[0008] As a preferred implementation, the training set includes historical power grid data, historical temperature data of the corresponding area obtained through the Internet, DC switch start and stop signal data obtained through a DC switch start and stop signal recording module, transformer two adjustment signal data obtained through a transformer two adjustment signal recording module, AC switch start and stop signal data obtained through an AC switch start and stop signal recording module, and peak and frequency modulation data obtained through a peak and frequency modulation data recording module.

[0009] As a preferred implementation, the verification set includes battery pack output history data and battery pack charging history data acquired through a battery pack data recording module.

[0010] As a preferred embodiment, it also includes a control system based on a real-time data monitoring module, a historical data recording module, an AI model and a data module, and the construction steps of the control system include: S1. Basic data arrangement: Since all items of historical data have time characteristics, we can use time characteristics as the connection point to classify the data in the same time in the training set, and associate the training set and the validation set with time characteristics as the connection point; S2. Model construction: Based on the fully connected neural network, an AI model is constructed, and the AI ​​model is trained using the training set to obtain the correlation between the temperature data and the peak and frequency regulation instructions; S3. Preliminary verification: Based on the verification set, the peak-shaving and frequency-regulating instructions output by the AI ​​model are compared with the historical output data of the battery pack and the historical battery charge data to verify the output results of the AI ​​model.

[0011] As a preferred implementation, the control method of the control system specifically includes: A1. Real-time data collation: Analyze the time characteristics of real-time battery data, real-time power consumption data and real-time power generation data, and associate the real-time battery data, real-time power consumption data and real-time power generation data according to the time characteristics; A2. Control data generation: Input real-time temperature data into the AI ​​model, and use the AI ​​model to generate simulated power consumption data and simulated battery pack adjustment data; A3. Control data adjustment: Compare the difference between simulated power consumption data and real-time power consumption data, adjust the simulated battery pack adjustment data, use the simulated battery pack adjustment data, and generate new simulated power consumption data through the AI ​​model; A4. Determine control data: Compare the difference between simulated power consumption data and real-time power consumption data. When the error is within the set threshold, the simulated battery pack adjustment data can be regarded as a usable adjustment result.

[0012] As a preferred implementation, the peak-shaving and frequency-modulation data are based on the historical data of the power grid, and the result data of the peak-shaving and frequency-modulation are the DC switch start-stop signal data, the transformer 2 adjustment signal data and the AC switch start-stop signal data. Therefore, the AI ​​model can take the historical data of the power grid within a unit time point as the starting point, analyze the correlation between the power supply change data and the peak-shaving and frequency-modulation data in the historical data of the power grid, and then analyze the correlation between the power supply change data and the peak-shaving and frequency-modulation data at different time points and the correlation with the temperature data, thereby deriving the correlation between the temperature data and the peak-shaving and frequency-modulation instructions.

[0013] As a preferred implementation, during the preliminary verification process, since the peak-shaving and frequency modulation instructions include instructions for battery pack output and charging, directly analyzing the results of comparing the peak-shaving and frequency modulation instructions with the battery pack output historical data and historical battery power charging data can verify the accuracy of the peak-shaving and frequency modulation instructions output by the AI ​​model.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: 1. The present invention constructs an AI model based on a number of historical data, so that the constructed AI model can be trained based on a large amount of basic data to avoid overfitting between temperature data and power consumption data, and then analyze the critical temperature value when the transmission power is adjusted, so that the user can directly predict the required battery energy storage control instructions according to the temperature change, so that the control of battery energy storage is not only timely, but also has high accuracy; 2. The present invention predicts the control instructions for battery energy storage through the AI ​​model, so that the present invention can adjust the number of connected battery groups according to the power generation surplus when only battery energy storage is used; 3. The present invention predicts the control instructions of battery energy storage through the AI ​​model, so that users can adjust the connected battery packs according to the health of the batteries, select the battery packs that do not need to be put into use, and perform maintenance; 4. The present invention can also combine the control instructions of battery energy storage predicted by the AI ​​model with the battery health data to select the battery packs to be discharged first according to the health of the battery packs, and perform maintenance on the battery packs that need maintenance after they are fully discharged. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention proposes a structural schematic diagram of a thermal power coupled battery energy storage control device; Figure 2 A data module schematic diagram of a thermal power coupled battery energy storage control device is proposed for the present invention; Figure 3 A control system construction flow chart of a thermal power coupled battery energy storage control device is proposed for the present invention; Figure 4 The present invention proposes a control method flow chart of a thermal power coupled battery energy storage control device. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0017] like Figure 1 and Figure 2 As shown, the present invention provides a technical solution: a thermal power coupling battery energy storage control device, comprising a generator set, a transformer one and a power grid, the electric energy generated by the generator set is supplied to the power grid through the transformer one, the surplus electric energy generated by the generator set is transmitted to the PCS energy storage converter through the transformer two, the PCS energy storage converter is transmitted to the energy storage battery group through the DC switch, the transformer two is connected to the peak-shaving and frequency-modulation coordination control center through the DC switch, the peak-shaving and frequency-modulation coordination control center controls the start and stop of the AC switch, the transformer two transmits the electric energy of the energy storage battery group to the transformer one through the AC switch, the peak-shaving and frequency-modulation coordination control center accesses the data of the AI ​​model, the AI ​​model accesses the data of the data module, and the data module receives the data from the real-time data monitoring module and the historical data information recording module; The real-time data monitoring module includes a battery monitoring module for real-time monitoring of the energy storage battery pack, a power generation data monitoring module for real-time monitoring of the power generation of the generator set, and a power grid load monitoring module for real-time monitoring of the load data of the power grid; In the above design, the data monitoring module can obtain the health data and power data of the energy storage battery group, and can also obtain the real-time power generation data of the generator group and the real-time load data of the power grid. This data item can fully reflect the real-time power grid status, power generation status and energy storage status, making it convenient for users to adjust power generation and energy storage according to the power grid status; Further, the historical data recording module includes a battery data recording module for storing energy storage battery data, a DC switch start / stop signal recording module for storing DC switch signal data, a transformer 2 adjustment recording module for recording transformer 2 adjustment data, an AC switch start / stop signal recording module for recording AC switch start / stop signal data, and a peak / frequency regulation data recording module for recording coordination data of a peak / frequency regulation coordination control center; In the above content, the large amount of data stored in the historical data recording module can provide data support for the training and verification of the AI ​​model, so as to make the constructed AI model more accurate and reliable.

[0018] Furthermore, the data module includes historical data and real-time data, the historical data includes a training set for training the AI ​​module and a verification set for verifying the AI ​​module, and the real-time data includes real-time battery data obtained by the battery monitoring module, real-time power consumption data obtained by the power grid load monitoring module, and real-time power generation data obtained by the power generation data monitoring module; The training set includes historical power grid data, historical temperature data of the corresponding area obtained through the Internet, DC switch start / stop signal data obtained through a DC switch start / stop signal recording module, transformer 2 adjustment signal data obtained through a transformer 2 adjustment signal recording module, AC switch start / stop signal data obtained through an AC switch start / stop signal recording module, and peak / frequency modulation data obtained through a peak / frequency modulation data recording module; Furthermore, the verification set includes battery pack output history data and battery pack charging history data acquired through a battery pack data recording module; In the above content, the data in the training set provide the basic data for training the AI ​​model, and the peak and frequency modulation instructions output by the AI ​​model are verified for accuracy through the data in the verification set.

[0019] In this embodiment, the peak-shaving and frequency-regulating instructions are generated by the designed AI model, and the basis for generating the instructions is the grid load, power generation and storage capacity. The temperature data as the feature vector is the start signal for the instruction generation, which links the calling of the energy storage battery group with the temperature change, making the control of the battery energy storage faster and the power supply of the grid more stable. Example

[0020] like Figure 1 , Figure 2 and Figure 3 As shown, it also includes a control system based on a real-time data monitoring module, a historical data recording module, an AI model and a data module. The construction steps of the control system include: S1. Basic data arrangement: Since all items of historical data have time characteristics, we can use time characteristics as the connection point to classify the data in the same time in the training set, and associate the training set and the validation set with time characteristics as the connection point; S2. Model construction: Based on the fully connected neural network, an AI model is constructed, and the AI ​​model is trained using the training set to obtain the correlation between the temperature data and the peak and frequency regulation instructions; S3. Preliminary verification: Based on the verification set, the peak-shaving and frequency-regulating instructions output by the AI ​​model are compared with the historical output data of the battery pack and the historical battery charge data to verify the output results of the AI ​​model.

[0021] Among them, in the model construction: the peak-shaving and frequency regulation data are based on the historical data of the power grid, and the result data of the peak-shaving and frequency regulation are the DC switch start and stop signal data, the transformer two adjustment signal data and the AC switch start and stop signal data. Therefore, the AI ​​model can take the historical data of the power grid within a unit time point as the starting point, analyze the correlation between the power supply change data and the peak-shaving and frequency regulation data in the historical data of the power grid, and then analyze the correlation between the power supply change data and the peak-shaving and frequency regulation data at different time points and the correlation with the temperature data, so as to obtain the correlation between the temperature data and the peak-shaving and frequency regulation instructions.

[0022] In this embodiment, the AI ​​model based on the fully connected neural network can build a complex nonlinear model to fit the relationship between temperature and power consumption by adjusting the network structure and parameters, and avoid overfitting by using the training data of multiple terms and multiple time dimensions in the training set, so as to fully calculate the relationship between temperature and peak and frequency regulation instructions; Furthermore, by analyzing the relationship between the temperature and the peak-shaving and frequency-modulation instructions, the direct relationship between the change in the peak-shaving and frequency-modulation instructions and the change in the temperature can be analyzed, so that the user can set the temperature threshold according to the relationship, and then the control system can adjust the power transmission of the energy storage battery group according to the temperature critical value; In addition, the data in the training set are segmented according to the time characteristics and distributed along the time axis. When the AI ​​model retrieves data, it can directly retrieve the corresponding data with the time point as the data anchor point, so as to analyze the correlation between the peak-shaving and frequency-modulation data at a unit time point and the historical data of the power grid. Then, the correlation between the temperature data and the peak-shaving and frequency-modulation data at different unit times is combined with the correlation between the peak-shaving and frequency-modulation data and the historical data of the power grid, and the correlation between the temperature data and the peak-shaving and frequency-modulation data is analyzed. In addition, due to the addition of the correlation data of the historical data of the power grid, the correlation between the temperature data and the peak-shaving and frequency-modulation data obtained by analysis is more reliable. Example

[0023] like Figure 1 , Figure 2 and Figure 4 As shown, the control method of the control system specifically includes: A1. Real-time data collation: Analyze the time characteristics of real-time battery data, real-time power consumption data and real-time power generation data, and associate the real-time battery data, real-time power consumption data and real-time power generation data according to the time characteristics; A2. Control data generation: Input real-time temperature data into the AI ​​model, and use the AI ​​model to generate simulated power consumption data and simulated battery pack adjustment data; A3. Control data adjustment: Compare the difference between simulated power consumption data and real-time power consumption data. When the error is greater than the set threshold, generate new simulated power consumption data through the AI ​​model based on the error; A4. Determine control data: Compare the difference between simulated power consumption data and real-time power consumption data. When the error is within the set threshold, the simulated battery pack adjustment data can be regarded as a usable adjustment result.

[0024] Among them, during the preliminary verification process, since the peak-shaving and frequency modulation instructions include instructions for battery pack output and charging, directly analyzing the results of comparing the peak-shaving and frequency modulation instructions with the battery pack output historical data and historical battery power charging data can verify the accuracy of the peak-shaving and frequency modulation instructions output by the AI ​​model.

[0025] In this embodiment, on the basis of verifying the AI ​​model with the verification set, when using the AI ​​model to generate simulated peak-shaving and frequency modulation instructions according to real-time data, using real-time data to verify the simulated peak-shaving and frequency modulation instructions in real time can further improve the accuracy of the simulated peak-shaving and frequency modulation instructions, and avoid the situation where the simulated peak-shaving and frequency modulation instructions generated by the AI ​​model and the peak-shaving and frequency modulation instructions actually required have large errors due to the difference between the actual data and the training set and the verification set; At the same time, the verification of AI models by real-time data can also realize continuous training of AI models, so that the accuracy of AI models increases with the increase of running time.

[0026] Working principle: like Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown, the present invention builds an AI model based on power grid historical data, temperature historical data, DC switch start / stop signal data, transformer 2 adjustment signal data, AC switch start / stop signal data, peak-shaving and frequency-modulation data, battery pack output historical data, and battery pack charging historical data, so that the constructed AI model can be trained based on a large amount of basic data to avoid overfitting between temperature data and power consumption data; In actual use, real-time data is used as the basic data. Since there is a certain time difference between temperature changes and electricity consumption data changes, the simulated electricity consumption data calculated by the AI ​​model based on real-time temperature data can reflect the actual electricity consumption data at a certain point in the future. By comparing the simulated electricity consumption data with the real-time electricity consumption data, the simulation accuracy of the AI ​​model can be verified. When the difference between the simulated electricity consumption data and the real-time electricity consumption data is greater than the set threshold, new simulated electricity consumption data is generated by the AI ​​model, and then compared with the real-time electricity consumption data until the difference between the simulated electricity consumption data and the real-time electricity consumption data is within the set error threshold. At this time, the simulated battery group adjustment data generated by the AI ​​model can be used as available data, and peak-shaving and frequency-regulation instructions are generated based on this data, so that the peak-shaving and frequency-regulation coordination control center controls the AC switch, thereby realizing the adjustment of the power supply to the power grid; The AI ​​model designed in the present invention can calculate the rules of temperature changes and power supply demand changes, so the user can select a time period according to the rules to perform access, inspection and maintenance of the energy storage battery pack.

[0027] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A thermal power coupled battery energy storage control device, comprising a generator set, a transformer 1 and a power grid, wherein the electric energy generated by the generator set is supplied to the power grid through the transformer 1, and is characterized in that: The surplus electric energy generated by the generator set is transmitted to the PCS energy storage converter through transformer 2, and the PCS energy storage converter is transmitted to the energy storage battery group through the DC switch. The transformer 2 is connected to the peak-shaving and frequency-modulation coordination control center through the DC switch, and the peak-shaving and frequency-modulation coordination control center controls the start and stop of the AC switch. The transformer 2 transmits the electric energy of the energy storage battery group to the transformer 1 through the AC switch, and the peak-shaving and frequency-modulation coordination control center accesses the data of the AI ​​model, and the AI ​​model accesses the data of the data module, and the data module receives the data from the real-time data monitoring module and the historical data recording module; The real-time data monitoring module includes a battery monitoring module for real-time monitoring of the energy storage battery pack, a power generation data monitoring module for real-time monitoring of the power generation of the generator set, and a power grid load monitoring module for real-time monitoring of the load data of the power grid; The historical data recording module includes a battery data recording module for storing energy storage battery data, a DC switch start / stop signal recording module for storing DC switch signal data, a transformer 2 adjustment recording module for recording transformer 2 adjustment data, an AC switch start / stop signal recording module for recording AC switch start / stop signal data, and a peak / frequency regulation data recording module for recording coordination data of a peak / frequency regulation coordination control center; The data module includes historical data and real-time data. The historical data includes a training set for training the AI ​​module and a verification set for verifying the AI ​​module. The real-time data includes real-time battery pack data obtained through the battery pack monitoring module, real-time power consumption data obtained through the power grid load monitoring module, and real-time power generation data obtained through the power generation data monitoring module.

2. A thermal power coupled battery energy storage control device according to claim 1, characterized in that: The training set includes historical power grid data, historical temperature data of the corresponding area obtained through the Internet, DC switch start and stop signal data obtained through a DC switch start and stop signal recording module, transformer two adjustment signal data obtained through a transformer two adjustment signal recording module, AC switch start and stop signal data obtained through an AC switch start and stop signal recording module, and peak-shaving and frequency modulation data obtained through a peak-shaving and frequency modulation data recording module.

3. A thermal power coupled battery energy storage control device according to claim 1, characterized in that: The verification set includes battery output history data and battery charging history data acquired through a battery data recording module.

4. A thermal power coupled battery energy storage control device according to claim 1, characterized in that: It also includes a control system based on a real-time data monitoring module, a historical data recording module, an AI model and a data module. The construction steps of the control system include: S1. Basic data arrangement: Since all items of historical data have time characteristics, we can use time characteristics as the connection point to classify the data in the same time in the training set, and associate the training set and the validation set with time characteristics as the connection point; S2. Model construction: Based on the fully connected neural network, an AI model is constructed, and the AI ​​model is trained using the training set to obtain the correlation between the temperature data and the peak and frequency regulation instructions; S3. Preliminary verification: Based on the verification set, the peak-shaving and frequency-regulating instructions output by the AI ​​model are compared with the historical output data of the battery pack and the historical battery charge data to verify the output results of the AI ​​model.

5. A thermal power coupled battery energy storage control device according to claim 4, characterized in that: The control method of the control system specifically includes: A1. Real-time data collation: Analyze the time characteristics of real-time battery data, real-time power consumption data and real-time power generation data, and associate the real-time battery data, real-time power consumption data and real-time power generation data according to the time characteristics; A2. Control data generation: Input real-time temperature data into the AI ​​model, and use the AI ​​model to generate simulated power consumption data and simulated battery pack adjustment data; A3. Control data adjustment: Compare the difference between simulated power consumption data and real-time power consumption data, adjust the simulated battery pack adjustment data, use the simulated battery pack adjustment data, and generate new simulated power consumption data through the AI ​​model; A4. Determine control data: Compare the difference between simulated power consumption data and real-time power consumption data. When the error is within the set threshold, the simulated battery pack adjustment data can be regarded as a usable adjustment result.

6. A thermal power coupled battery energy storage control device according to claim 4, characterized in that: In the model construction: the peak-shaving and frequency regulation data are based on the historical data of the power grid, and the result data of the peak-shaving and frequency regulation are the DC switch start and stop signal data, the transformer two adjustment signal data and the AC switch start and stop signal data. Therefore, the AI ​​model can take the historical data of the power grid within a unit time point as the starting point, analyze the correlation between the power supply change data and the peak-shaving and frequency regulation data in the historical data of the power grid, and then analyze the correlation between the power supply change data and the peak-shaving and frequency regulation data at different time points and the correlation with the temperature data, so as to obtain the correlation between the temperature data and the peak-shaving and frequency regulation instructions.

7. A thermal power coupled battery energy storage control device according to claim 4, characterized in that: During the preliminary verification process: Since the peak-shaving and frequency modulation instructions include instructions for battery pack output and charging, directly analyzing the results of comparing the peak-shaving and frequency modulation instructions with the battery pack output historical data and historical battery power charging data can verify the accuracy of the peak-shaving and frequency modulation instructions output by the AI ​​model.

Citation Information

Patent Citations

  • Multicomponent coupling energy-storage system

    CN107516905A

  • Power load scheduling method and system based on big data

    CN116646933A

  • Energy storage system control method and device based on artificial intelligence

    CN117060456A

  • Electric power peak regulation method in high-capacity energy storage system

    CN117713172A

  • Electric power peak regulation system based on Internet of Things

    CN117833319A

Cited By

  • Thermal power generation battery energy storage cooperative control method

    CN122118979A

  • Thermal power generation cell energy storage collaborative control method

    CN122118979B