Energy storage frequency modulation method, device and equipment based on thermal power generating unit and medium

Abstract

The invention relates to the field of power system frequency modulation, in particular to an energy storage frequency modulation method, device and equipment based on a thermal power generating unit and a medium. The method comprises the following steps: determining the power grid frequency deviation corresponding to the current power grid state by acquiring the current power grid state corresponding to the current transformer area and the future environment data, and accurately obtaining the frequency deviation by monitoring the power grid frequency in real time and comparing the power grid frequency with the standard frequency; and based on the future environment data, the current power grid state and the power grid frequency deviation, predicting a power grid frequency change trend in a future period, generating an energy storage frequency modulation instruction according to the predicted power grid frequency change trend, and sending the instruction to an energy storage device corresponding to the current transformer area to realize dynamic response between the energy storage device and the power grid. Therefore, the energy storage device can perform charging and discharging operation according to the actual demand of the power grid, thereby effectively adjusting the frequency of the power grid.

Description

Technical Field

[0001] The present application relates to the field of power system frequency regulation, and in particular to a method, device, equipment and medium for energy storage frequency regulation based on thermal power units. Background Art

[0002] The power system is one of the important infrastructures for modern industrial and social operations. Its stability and reliability directly affect the development of social economy and the quality of people's lives. With the large-scale access of renewable energy and the widespread application of distributed power sources, the load fluctuation of the power grid has intensified, bringing new challenges to the safe and stable operation of the power grid. In order to meet these challenges, energy storage technology, as an effective means of regulation, plays an important role in improving the flexibility and stability of the power grid.

[0003] In the existing power system, in order to solve the problem of grid frequency deviation, the system's active power balance is usually maintained by adjusting the generator output, or using energy storage equipment for short-term energy storage and smooth power output. However, the above traditional methods have some shortcomings. Due to the lack of effective prediction of future environmental factors, the scheduling strategy is not accurate enough, which in turn affects the overall frequency regulation efficiency. Therefore, how to formulate a more scientific and reasonable energy storage frequency regulation strategy has become an urgent problem to be solved. Summary of the invention

[0004] In order to improve the accuracy of energy storage frequency regulation strategy, the present application provides an energy storage frequency regulation method, device, equipment and medium based on thermal power units.

[0005] In the first aspect, the present application provides an energy storage frequency regulation method based on a thermal power unit, which adopts the following technical solution: A method for frequency regulation based on energy storage of thermal power units, comprising: Obtaining the current grid state and future environmental data corresponding to the current substation, wherein the current grid state includes grid voltage and grid current, and the future environmental data is a curve of the change of ambient temperature over time in a future period; Determining a grid frequency deviation corresponding to the current grid state; Based on the future environmental data, the current grid state and the grid frequency deviation, predicting a grid frequency change trend in a future period; Based on the power grid frequency change trend, an energy storage frequency modulation instruction is generated, and the energy storage frequency modulation instruction is sent to the energy storage device corresponding to the current substation.

[0006] By adopting the above technical solution, the current grid state and future environmental data corresponding to the current substation are obtained, and the grid frequency deviation corresponding to the current grid state is determined. By real-time monitoring of the grid frequency and comparing it with the standard frequency, the frequency deviation can be accurately obtained, providing a precise target for subsequent frequency modulation operations. Based on future environmental data, the current grid state, and the grid frequency deviation, the trend of grid frequency changes in future cycles is predicted, thereby ensuring that the energy storage device can be prepared before the grid frequency fluctuates and can effectively respond to frequency modulation needs. According to the predicted trend of grid frequency changes, energy storage frequency modulation instructions are generated, and these instructions are sent to the energy storage device corresponding to the current substation, so as to achieve dynamic response between the energy storage device and the grid, so that the energy storage device can perform charging and discharging operations according to the actual needs of the grid, thereby effectively adjusting the grid frequency.

[0007] In a possible implementation manner, determining a grid frequency deviation corresponding to the current grid state includes: Obtaining a voltage cycle corresponding to the grid voltage and a current cycle corresponding to the grid current; Based on the voltage cycle and the current cycle, determining an actual grid frequency corresponding to the current area; Obtaining the rated frequency corresponding to the current station area; Based on the actual grid frequency and the rated frequency, a grid frequency deviation corresponding to the current grid state is determined.

[0008] By adopting the above technical solution, the voltage cycle corresponding to the grid voltage and the current cycle corresponding to the grid current are obtained. The voltage cycle and the current cycle are important parameters reflecting the characteristics of the grid AC power, and their changes can directly reflect the fluctuation of the grid frequency. Based on the voltage cycle and the current cycle, the actual grid frequency corresponding to the current substation can be accurately determined. The rated frequency corresponding to the current substation is obtained. The rated frequency is the basis for the stable operation of the grid. By comparing with the actual frequency, it can be determined whether there is a frequency deviation in the grid, as well as the size and direction of the deviation. Based on the actual grid frequency and the rated frequency, the grid frequency deviation corresponding to the current grid state can be accurately determined, so as to accurately know the size and direction of the frequency deviation, and lay the foundation for the subsequent formulation of an effective frequency modulation strategy to ensure the stable operation of the grid.

[0009] In a possible implementation, determining the actual grid frequency corresponding to the current area based on the voltage cycle and the current cycle includes: Based on the voltage cycle, determining the voltage zero-crossing time, and based on the current cycle, determining the current zero-crossing time; Calculating the voltage time interval corresponding to every two adjacent voltage zero-crossing moments, and calculating the current time interval corresponding to every two adjacent current zero-crossing moments; Based on the voltage time interval and the current time interval, an actual grid frequency corresponding to the current substation is determined.

[0010] By adopting the above technical solution, the zero-crossing moments of voltage and current are captured, the time intervals between adjacent zero-crossing moments are measured, and the actual frequency of the power grid is calculated accordingly. This not only improves the accuracy and reliability of power grid frequency measurement, but also enables real-time monitoring of changes in power grid frequency to promptly detect and correct frequency deviations, thereby ensuring safe and stable operation of the power system.

[0011] In a possible implementation, predicting a grid frequency change trend in a future period based on the future environmental data, the current grid state, and the grid frequency deviation includes: Acquire historical power grid data corresponding to the current substation, wherein the historical power grid data includes historical voltage, historical current and historical network frequency deviation corresponding to a historical period; Based on the historical power grid data, establishing a correlation feature, wherein the correlation feature is a correlation relationship between power grid power and power grid frequency deviation; Based on the future environmental data, the historical power grid data, the associated features, the current power grid state and the power grid frequency deviation, a power grid frequency change trend in a future period is predicted.

[0012] By adopting the above technical solution, the historical power grid data corresponding to the current substation is obtained. The historical power grid data contains the operation status of the power grid in the past period of time, including historical voltage, historical current and historical frequency deviation. These data provide an important reference for establishing a prediction model. Based on the historical power grid data, the correlation characteristics are established, that is, the correlation between the power grid power and the frequency deviation of the power grid. The future environmental data, historical power grid data, correlation characteristics, current power grid status and power grid frequency deviation are combined to predict the change trend of the power grid frequency in the future cycle. By considering the current operation status of the power grid and the change trend of the future environment, the accuracy and reliability of the prediction are improved.

[0013] In a possible implementation, predicting a grid frequency change trend in a future period based on the historical grid data, the associated features, the current grid state, and the grid frequency deviation includes: Extracting time features from the historical power grid data, and extracting temperature features from the future environmental data; Determining an influencing parameter corresponding to the grid frequency deviation based on the association feature, the temperature feature, and the time feature; Obtaining an electric energy generation plan corresponding to a thermal power unit in a future period, wherein the electric energy generation plan represents the planned amount of electric energy generated in a certain period of time; Based on the electric energy generation plan, the influencing parameters and the current grid state, a grid frequency variation trend in the future period is predicted.

[0014] By adopting the above technical solution, by extracting time characteristics and temperature characteristics, determining the influencing parameters, and combining the power generation plan and the current power grid status, an accurate prediction of the future power grid frequency change trend is achieved, which not only improves the accuracy and reliability of the prediction, but also can more effectively formulate frequency regulation strategies to ensure the safe and stable operation of the power system and meet the electricity needs of users. In a possible implementation, generating an energy storage frequency regulation instruction based on the power grid frequency change trend includes: Based on the power grid frequency change trend, determine the working time corresponding to the energy storage device in the future cycle and the working mode corresponding to each working time, the working time is the time when the energy storage device switches the working mode, and the working mode is a charging mode or a discharging mode; Based on the working moments corresponding to the energy storage device in the future cycle and the working mode corresponding to each working moment, a working instruction corresponding to each working moment is generated to obtain an energy storage frequency modulation instruction.

[0015] By adopting the above technical solution, the working time and working mode of the energy storage device are determined, and corresponding working instructions are generated, thereby achieving efficient use of the energy storage device in power grid frequency regulation.

[0016] In the second aspect, the present application provides an energy storage frequency regulation device based on a thermal power unit, which adopts the following technical solution: An energy storage frequency regulation device based on a thermal power unit, comprising: An acquisition module is used to acquire the current grid state and future environmental data corresponding to the current substation, wherein the current grid state includes grid voltage and grid current, and the future environmental data is a curve of the change of ambient temperature over time in a future period; A determination module, used to determine a grid frequency deviation corresponding to the current grid state; A prediction module, configured to predict a grid frequency variation trend in a future period based on the future environmental data, the current grid state, and the grid frequency deviation; A generation module is used to generate an energy storage frequency modulation instruction based on the power grid frequency change trend, and send the energy storage frequency modulation instruction to the energy storage device corresponding to the current substation.

[0017] In a possible implementation manner, when determining the grid frequency deviation corresponding to the current grid state, the determination module is specifically configured to: Obtaining a voltage cycle corresponding to the grid voltage and a current cycle corresponding to the grid current; Based on the voltage cycle and the current cycle, determining an actual grid frequency corresponding to the current area; Obtaining the rated frequency corresponding to the current station area; Based on the actual grid frequency and the rated frequency, a grid frequency deviation corresponding to the current grid state is determined.

[0018] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the energy storage frequency regulation method of a thermal power unit described in the first aspect above.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the energy storage frequency regulation method of a thermal power unit described in the first aspect.

[0020] In summary, this application includes the following beneficial technical effects: By obtaining the current grid status and future environmental data corresponding to the current substation, the grid frequency deviation corresponding to the current grid status is determined. By real-time monitoring of the grid frequency and comparing it with the standard frequency, the frequency deviation can be accurately obtained, providing a precise target for subsequent frequency modulation operations. Based on future environmental data, the current grid status, and the grid frequency deviation, the trend of grid frequency changes in future cycles is predicted to ensure that the energy storage device is ready before the grid frequency fluctuates and can effectively respond to frequency modulation needs. Based on the predicted trend of grid frequency changes, energy storage frequency modulation instructions are generated and sent to the energy storage device corresponding to the current substation to achieve dynamic response between the energy storage device and the grid, so that the energy storage device can perform charging and discharging operations according to the actual needs of the grid, thereby effectively adjusting the grid frequency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of an energy storage frequency modulation method for a thermal power unit provided in an embodiment of the present application; Figure 2 It is a block diagram of an energy storage frequency modulation device of a thermal power unit provided in an embodiment of the present application; Figure 3 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following is combined with Figure 1 -Attached Figure 3 This application is described in further detail.

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] The present application embodiment provides a method for frequency regulation based on energy storage of thermal power units, such as Figure 1 As shown, the method provided in the embodiment of the present application is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S104, wherein: Step S101: Obtain the current grid status and future environmental data corresponding to the current substation.

[0025] Among them, the current grid status includes grid voltage and grid current, and the future environmental data is the curve of ambient temperature change over time in the future period. The substation is a local power supply area in the power system, usually composed of one or more transformers and their low-voltage lines and users. It is the basic unit of power distribution and management, which facilitates the monitoring, control and maintenance of power distribution and use. The power required by the load in the substation is provided by thermal power units and energy storage devices (including distributed energy if there is distributed energy).

[0026] Specifically, for the current power grid device, the electronic device can obtain the power grid voltage and power grid current signals through the voltage transformer and current transformer connected to the power grid of the substation. For future environmental data, the electronic device establishes a network connection with the database of the weather forecast system or environmental monitoring agency, obtains the environmental temperature change data over time in the future period (such as the next 24 hours) according to a preset time period (for example, updated once every hour), and establishes an environmental temperature change curve over time.

[0027] Step S102: Determine the grid frequency deviation corresponding to the current grid state.

[0028] The grid frequency deviation refers to the difference between the actual operating frequency and the rated frequency of the grid, which can reflect the balance state of the grid's active power. When the frequency deviation is zero, the grid is in an ideal power balance state; when the frequency deviation is not zero, it indicates that there is an excess or shortage of active power in the grid, and corresponding adjustments are required to maintain the stable operation of the grid.

[0029] Specifically, the collected grid voltage or current signal can be processed by a discrete Fourier transform (DFT) algorithm to determine the grid frequency deviation corresponding to the current grid state. More specifically, the collected grid voltage and grid current can be sorted into a voltage sequence and a current sequence, respectively, and the voltage sequence and the current sequence are respectively subjected to DFT operations to obtain the spectrum of the voltage signal and the spectrum of the current signal. Further, the fundamental frequency component (corresponding to the actual frequency of the grid) is found in the spectrum, and it is subtracted from the preset grid rated frequency (such as 50Hz or 60Hz) to obtain the grid frequency deviation. More specifically, when the fundamental frequency component corresponding to the spectrum of the voltage signal is consistent with the fundamental frequency component corresponding to the spectrum of the current signal, the fundamental frequency component is directly subtracted from the preset grid rated frequency to obtain the grid frequency deviation; when the fundamental frequency component corresponding to the spectrum of the voltage signal is inconsistent with the fundamental frequency component corresponding to the spectrum of the current signal, the average value of the two fundamental frequency components is used, and the average value is subtracted from the preset grid rated frequency to obtain the grid frequency deviation.

[0030] Step S103: predicting the grid frequency change trend in the future period based on the future environmental data, the current grid state and the grid frequency deviation.

[0031] Among them, the grid frequency change trend represents the direction and approximate change amplitude of the grid frequency rising, falling or maintaining stability in the future period of time, which can be expressed in the form of a curve, and the embodiments of the present application are not limited to this.

[0032] After obtaining the future environmental data, the current power grid state and the power grid frequency deviation, the prediction module can be used to predict the power grid frequency change trend in the future cycle, so as to facilitate the generation of the subsequent energy storage frequency regulation strategy. Specifically, the long short-term memory network (LSTM) model based on the trained deep learning can be used for prediction, and the voltage, current data, frequency deviation data in the current power grid state and the ambient temperature data in the future environmental data are used as input features, which are input into the trained LSTM model, and the power grid frequency change curve over time in the future cycle output by the LSTM model is obtained, thereby obtaining the power grid frequency change trend in the future cycle. Among them, the LSTM model is trained on a large number of power grid frequency change curve samples, voltage samples, current data samples, frequency deviation samples and ambient temperature data samples in the future environmental data. The trained LSTM model can capture the complex nonlinear relationship between these data and the power grid frequency change, thereby predicting the power grid frequency change trend in the future cycle (such as the frequency value per hour in the next 24 hours).

[0033] Step S104: Generate an energy storage frequency modulation instruction based on the power grid frequency change trend, and send the energy storage frequency modulation instruction to the energy storage device corresponding to the current substation.

[0034] Among them, the energy storage frequency modulation instruction is a control command sent by the electronic device to the energy storage device. It can be a charging instruction or a discharging instruction. It is used to guide the working state of the energy storage device during the grid frequency modulation process, so that it can perform charging and discharging operations in a timely and accurate manner according to the changes in the grid frequency, thereby effectively adjusting the active power balance of the grid and maintaining the stability of the grid frequency.

[0035] Specifically, based on the predicted trend of grid frequency changes, the energy storage frequency modulation instruction is generated in combination with the preset energy storage frequency modulation strategy. More specifically, if it is predicted that the grid frequency will decrease in a certain period of time in the future, and the decrease exceeds the set threshold, the electronic device generates a discharge instruction to discharge the energy storage device to increase the active power of the grid; if the frequency is predicted to increase, a charging instruction is generated to charge the energy storage device to absorb excess active power. Furthermore, the electronic device sends these instructions to the controller of the energy storage device in a specific communication protocol (such as Modbus protocol) through a communication interface (such as industrial Ethernet, wireless communication module, etc.), and the controller of the energy storage device controls the charging and discharging operations of the energy storage device according to the received instructions.

[0036] The embodiment of the present application provides an energy storage frequency regulation method based on a thermal power unit. By obtaining the current grid state and future environmental data corresponding to the current substation, the grid frequency deviation corresponding to the current grid state is determined. By real-time monitoring of the grid frequency and comparing it with the standard frequency, the frequency deviation can be accurately obtained to provide a precise target for subsequent frequency regulation operations. Based on future environmental data, the current grid state, and the grid frequency deviation, the trend of grid frequency changes in future cycles is predicted, thereby ensuring that the energy storage device can be prepared before the grid frequency fluctuates and can effectively respond to frequency regulation needs. According to the predicted trend of grid frequency changes, energy storage frequency regulation instructions are generated, and these instructions are sent to the energy storage device corresponding to the current substation, so as to achieve a dynamic response between the energy storage device and the grid, so that the energy storage device can perform charging and discharging operations according to the actual needs of the grid, thereby effectively adjusting the grid frequency.

[0037] In a possible implementation of the embodiment of the present application, in the above step S103, determining the grid frequency deviation corresponding to the current grid state includes: Obtaining a voltage cycle corresponding to the grid voltage and a current cycle corresponding to the grid current; Based on the voltage cycle and current cycle, determine the actual grid frequency corresponding to the current area; Get the rated frequency corresponding to the current station area; Based on the actual grid frequency and the rated frequency, a grid frequency deviation corresponding to the current grid state is determined.

[0038] Specifically, the electronic device can collect analog signals of the grid voltage and grid current through high-precision voltage sensors and current sensors, and then use an analog-to-digital converter (ADC) to convert these analog signals into digital signal sequences. For the acquisition of the voltage cycle, the electronic device can use the zero-crossing detection method, that is, by writing a program, it is allowed to continuously compare the voltage digital signal with the zero level. When the voltage signal passes through the zero point from the positive half cycle to the negative half cycle, or from the negative half cycle to the positive half cycle, these zero-crossing moments are recorded, and the time interval between adjacent zero-crossing moments is calculated. This time interval is the voltage cycle. Similarly, for the current cycle, the same zero-crossing detection method is also used to process the current digital signal and obtain the time interval between adjacent zero-crossing moments as the current cycle. Among them, the voltage cycle refers to the time required for the grid voltage signal to complete a complete periodic change. It is inversely related to the grid frequency and is an important parameter that reflects the law of change of the grid voltage signal over time. For example, in a common 50Hz grid, the voltage cycle is 0.02 seconds (1÷50Hz), that is, the voltage signal completes a complete change process from positive to negative and then to positive every 0.02 seconds. The current cycle is similar to the voltage cycle, which is the time it takes for the grid current signal to complete a complete periodic change. Furthermore, after obtaining the voltage cycle and current cycle, their corresponding frequency values ​​are calculated respectively. Specifically, the frequency corresponding to the voltage is calculated by the formula "frequency = 1 ÷ voltage cycle"; for the frequency corresponding to the current cycle, the formula "frequency = 1 ÷ current cycle" is used to calculate the frequency corresponding to the current, and the average value is calculated by the voltage cycle and the current cycle to obtain the actual grid frequency corresponding to the current substation.

[0039] Furthermore, the rated frequency value corresponding to the grid area is obtained from the database corresponding to the current substation, and the grid frequency deviation is determined by calculation. Specifically, the formula "grid frequency deviation = actual grid frequency - rated frequency" is used to calculate to obtain the grid frequency deviation. For example, if the actual grid frequency is 50.2Hz and the rated frequency is 50Hz, then the grid frequency deviation is 50.2-50=0.2Hz. This deviation value can be positive or negative. A positive value indicates that the actual frequency is higher than the rated frequency, and a negative value indicates that the actual frequency is lower than the rated frequency.

[0040] A possible implementation of the embodiment of the present application, in the above embodiment, based on the voltage cycle and the current cycle, determining the actual grid frequency corresponding to the current area includes: Based on the voltage cycle, determine the voltage zero-crossing time, and based on the current cycle, determine the current zero-crossing time; Calculate the voltage time interval corresponding to every two adjacent voltage zero-crossing moments, and calculate the current time interval corresponding to every two adjacent current zero-crossing moments; Based on the voltage time interval and the current time interval, the actual grid frequency corresponding to the current substation is determined.

[0041] Specifically, to determine the voltage zero-crossing moment, the value of the voltage digital signal can be compared with the zero level. When the voltage digital signal changes from a positive value to a negative value (i.e., from the positive half cycle through the zero point to the negative half cycle) or from a negative value to a positive value (from the negative half cycle through the zero point to the positive half cycle), the corresponding timestamp is recorded, and the moment marked by this timestamp is the voltage zero-crossing moment. Similarly, to determine the current zero-crossing moment, the current digital signal is compared with the zero level. When the current digital signal changes from positive to negative, the corresponding timestamp is recorded as the current zero-crossing moment.

[0042] Furthermore, after obtaining the voltage zero-crossing moment and the current zero-crossing moment, these moments can be sorted and stored in chronological order to obtain an array of voltage zero-crossing moments, and the array storing the voltage zero-crossing moment is traversed, and the difference obtained by subtracting the previous voltage zero-crossing moment from the next voltage zero-crossing moment is the voltage time interval corresponding to the two adjacent voltage zero-crossing moments. Similarly, for the current time interval, the array storing the current zero-crossing moment is traversed in the same manner, and the previous current zero-crossing moment is subtracted from the next current zero-crossing moment to calculate the current time interval between every two adjacent current zero-crossing moments.

[0043] Furthermore, after obtaining the voltage time interval and the current time interval, a weighted average method can be used to comprehensively utilize the voltage time interval and the current time interval to determine the actual grid frequency. Specifically, according to the reciprocal relationship between frequency and period, for each voltage time interval, the corresponding voltage frequency value is calculated by the formula "voltage frequency = 1 ÷ voltage time interval"; similarly, for each current time interval, the corresponding current frequency value is calculated using the formula "current frequency = 1 ÷ current time interval". Further, the weights corresponding to the voltage frequency and the current frequency are obtained from the database corresponding to the current substation, and the weighted average formula "actual grid frequency = voltage frequency × voltage frequency weight + current frequency × current frequency weight" is used to calculate to obtain the actual grid frequency corresponding to the current substation. Among them, the weights corresponding to the voltage frequency and the current frequency can be obtained based on past experience data or a large amount of historical data, and the embodiments of the present application are not limited to this.

[0044] A possible implementation of the embodiment of the present application is that in the above step S103, based on the future environmental data, the current power grid state and the power grid frequency deviation, the power grid frequency change trend in the future period is predicted, including: Obtain the historical power grid data corresponding to the current substation, which includes the historical voltage, historical current and historical network frequency deviation corresponding to the historical period; Based on historical power grid data, correlation features are established, and the correlation features are the correlation between power grid power and power grid frequency deviation. Based on future environmental data, historical power grid data, correlation features, current power grid status and power grid frequency deviation, the power grid frequency change trend in the future period is predicted.

[0045] Among them, historical power grid data refers to the various parameter data recorded during the operation of the power grid in the current substation within a certain period of time in the past, including voltage, current and power grid frequency deviation corresponding to the historical period (different time stages in the past, such as the past day, month, etc.), and other information, which is stored in the database corresponding to the current substation. Electronic equipment can directly obtain the historical power grid data corresponding to the current substation from the database corresponding to the current substation.

[0046] Furthermore, after obtaining the historical power grid data, the corresponding historical power data can be calculated using the acquired historical voltage and historical current data according to the power calculation formula (P = UIcosθ, where P is power, U is voltage, I is current, and cosθ is power factor) (the power factor can be set to a reasonable value through historical data or based on experience). Furthermore, the calculated historical power data is integrated with the corresponding historical grid frequency deviation data, for example, stored in the form of data pairs (each data pair contains a power value and a corresponding frequency deviation value). Using data analysis methods, the historical power is used as the independent variable and the historical grid frequency deviation is used as the dependent variable for model training. The trained model is used to characterize the correlation between the grid power and the grid frequency deviation. This model reflects the correlation features that need to be established. Among them, the correlation feature refers to an intrinsic connection feature between the grid power and the grid frequency deviation.

[0047] Specifically, the process of constructing the correlation feature can be as follows: arrange the historical power data in chronological order to obtain the power data sequence P(t), and use the first-order difference method to calculate the power change rate r(t) of two adjacent time periods t and t+1, and calculate it through the formula The time series data of power change rate is obtained, which reflects the speed of power change over time and has a potential correlation with frequency deviation, because power changes often cause changes in the active power balance of the power grid, thereby affecting the power grid frequency.

[0048] Furthermore, the historical environmental data of each historical period corresponding to the current substation is obtained, and the corresponding power grid load changes under different historical environmental data are obtained. The deep network learning model is trained through historical environmental data samples and power grid load change samples to obtain a trained deep network learning model.

[0049] Specifically, based on future environmental data, historical power grid data, associated features, current power grid status and power grid frequency deviation, the power grid frequency change trend in the future period is predicted, including: extracting time features in historical power grid data, and extracting temperature features in future environmental data; based on associated features, temperature features and time features, determining the influencing parameters corresponding to the power grid frequency deviation; obtaining the power generation plan corresponding to the thermal power units in the future period, the power generation plan representing the planned power generation within a certain time period; based on the power generation plan, influencing parameters and current power grid status, the power grid frequency change trend in the future period is predicted.

[0050] In this embodiment, the stored historical power grid data is identified through a data processing program to identify the time-related information columns therein, and the corresponding time features are extracted. Specifically, the time information can be decomposed into features of multiple dimensions, such as extracting hourly features (taking 24 hours a day as a category feature, with a value range of 0-23, representing different hourly periods), daily features (7 days a week, with a value range of 0-6, representing different days of the week), monthly features (with a value range of 1-12, representing different months) and seasonal features (divided into 4 categories according to spring, summer, autumn and winter, and can be classified and assigned by judging the season to which the month belongs) to obtain time features. These time features of different dimensions can help capture the laws of power grid operation in different time periods, such as the laws of peak and trough electricity consumption in certain periods of time.

[0051] Extract key temperature features from the acquired future environmental data. Specifically, the average temperature, maximum temperature, minimum temperature, and temperature change rate (i.e., the ratio of the temperature difference in adjacent time intervals to the time interval, which is used to reflect the speed of temperature change) in different time periods in the future cycle can be calculated to obtain temperature features. These temperature features can reflect the possible impact of future ambient temperature on power grid operation, because temperature changes are usually closely related to changes in power load.

[0052] Furthermore, the feature fusion method in machine learning can be used to integrate the associated features, the extracted temperature features and the time features as input data, and the input data is input into the trained model to obtain the influencing parameters output by the trained model, so as to obtain the influencing parameters corresponding to the grid frequency deviation. Among them, the model is trained with a large amount of historical sample data (the corresponding actual frequency deviation in the historical grid data and the power, temperature and time characteristics at that time) to obtain a trained model. The trained model can output the corresponding grid frequency deviation influencing parameters according to the input associated features, the current temperature features and the time features. These parameters characterize the specific degree and direction of influence that the grid frequency deviation may be subject to under the combined influence of these factors at present (for example, a certain parameter indicates that when the temperature rises to a certain degree, the frequency deviation will increase or decrease accordingly).

[0053] By establishing a communication connection with the power grid dispatching system, a request is sent to it to obtain the power generation plan of the thermal power unit in the future period (for example, the next 24 hours or the next week, etc.). After receiving the request, the power grid dispatching system will search and return the corresponding plan data, which contains the planned output power values ​​of different thermal power units in each time period (such as one hour or half an hour as a time period) (the unit is generally megawatt-hour, MWh). Furthermore, the total power supply power change trend of the thermal power units in the future period is calculated according to the power generation plan, and combined with the influencing parameters corresponding to the previously determined power grid frequency deviation, the comprehensive impact of the changes in the power generation plan and the influencing parameters on the power grid frequency deviation in different time periods is analyzed. Specifically, for each time period in the power generation plan, the total planned power for the time period is obtained by adding the planned power generated by all thermal power units in the time period. Then, according to the power calculation formula (where P is power, W is electric energy, and t is time). Since the time interval is known, the total planned electric energy is divided by the corresponding time interval to calculate the total electric energy supply power value of the thermal power unit in each time period. The calculated electric energy supply power values ​​of each time period are arranged in chronological order, and the power values ​​of adjacent time periods are compared to determine whether the power is rising, falling, or remaining unchanged. For example, if the power value of the latter time period is greater than that of the previous time period, it means that the electric energy supply power is on an upward trend; otherwise, it is on a downward trend. Further, for each time period, according to the change of the electric energy supply power in the current time period relative to the previous time period (known from the power change trend calculated previously), combined with the corresponding influencing parameters, the impact value of the change of the electric energy supply power on the grid frequency deviation is calculated. Based on the impact value of the change of the electric energy supply power corresponding to each time period on the grid frequency deviation and the total electric energy supply power value of the thermal power unit, the grid frequency change trend corresponding to each time period is obtained, thereby obtaining the grid frequency change trend corresponding to the future cycle.

[0054] A possible implementation of the embodiment of the present application, in the above embodiment, based on the power grid frequency change trend, generating the energy storage frequency regulation instruction includes: Based on the frequency change trend of the power grid, the working time corresponding to the energy storage device in the future cycle and the working mode corresponding to each working time are determined. The working time is the moment when the energy storage device switches the working mode, and the working mode is the charging mode or the discharging mode. Based on the working time corresponding to the energy storage device in the future cycle and the working mode corresponding to each working time, the working instruction corresponding to each working time is generated to obtain the energy storage frequency modulation instruction.

[0055] The frequency threshold range is obtained from the database corresponding to the current substation to determine the timing of switching the working mode of the energy storage device. Specifically, when the grid frequency change trend shows that the frequency is lower than the lower limit threshold of the frequency threshold range, it is determined that the energy storage device needs to enter the discharge mode to supplement the grid and increase the grid frequency; when the grid frequency is higher than the upper limit threshold of the frequency threshold range, it is determined that the energy storage device should switch to the charging mode to absorb excess grid energy and stabilize the grid frequency.

[0056] Furthermore, along the time axis of the future cycle, according to the frequency threshold set above and the power grid frequency change trend data, judgments are made at each time point. When it is found that at a certain time point, the predicted value of the power grid frequency crosses the set threshold for the first time (from above the threshold to below the threshold, or vice versa), the time point is marked as the working moment of the energy storage device, and the corresponding working mode is determined at the same time (whether it is a charging mode or a discharging mode is determined according to whether the upper or lower threshold is crossed). By traversing the frequency prediction data in the entire future cycle in this way, all working moments and corresponding working modes that require the energy storage device to switch working modes are determined.

[0057] Furthermore, for each determined working moment and its corresponding working mode, a specific working instruction is generated. For each working moment, the working instruction needs to clarify the key information of the power regulation parameters of the energy storage device. Specifically, if the working mode is the discharge mode, the appropriate discharge power value can be calculated according to the magnitude of the grid frequency deviation (calculated by the difference between the current frequency and the rated frequency), the current load of the grid, and the remaining power of the energy storage device itself (for example, a pre-set power allocation strategy is adopted, and the specific value is determined in combination with the maximum discharge power allowed by the remaining power of the energy storage device according to the principle that the greater the frequency deviation, the greater the discharge power). And this discharge power value, the start discharge time (that is, the corresponding working moment), the discharge duration (which can be set according to the subsequent frequency change trend prediction and experience, such as how long it is expected that the frequency will return to the normal range, and the corresponding discharge duration is set) and other information are integrated into a discharge work instruction, and the instruction format may be similar to the following: {"working moment": time point 1, "working mode": "discharge mode", "discharge power": XX megawatts, "discharge duration": XX minutes}. Similarly, when the working mode is charging mode, the charging power value, charging start time (working time) and charging duration are determined by considering factors such as grid frequency deviation and current power generation conditions, and a charging work instruction is generated in the following format: {"working time": time point 2, "working mode": "charging mode", "charging power": XX MW, "charging duration": XX minutes}.

[0058] The above embodiment introduces a method for energy storage and frequency regulation based on a thermal power unit from the perspective of a method flow, and the following embodiment introduces an energy storage and frequency regulation device based on a thermal power unit from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0059] See also Figure 2 The energy storage frequency regulation device 20 based on the thermal power unit may specifically include: an acquisition module 201, a determination module 202, a prediction module 203 and a generation module 204, wherein: An energy storage frequency modulation device 20 based on a thermal power unit comprises: The acquisition module 201 is used to acquire the current grid state and future environmental data corresponding to the current substation, the current grid state includes grid voltage and grid current, and the future environmental data is a curve of the change of ambient temperature over time in a future period; A determination module 202 is used to determine a grid frequency deviation corresponding to a current grid state; Prediction module 203, used to predict the grid frequency change trend in the future period based on future environmental data, current grid state and grid frequency deviation; The generation module 204 is used to generate energy storage frequency modulation instructions based on the power grid frequency change trend, and send the energy storage frequency modulation instructions to the energy storage device corresponding to the current substation.

[0060] In a possible implementation of the embodiment of the present application, when determining the grid frequency deviation corresponding to the current grid state, the determination module 202 is specifically used to: Obtaining a voltage cycle corresponding to the grid voltage and a current cycle corresponding to the grid current; Based on the voltage cycle and current cycle, determine the actual grid frequency corresponding to the current area; Get the rated frequency corresponding to the current station area; Based on the actual grid frequency and the rated frequency, a grid frequency deviation corresponding to the current grid state is determined.

[0061] In a possible implementation of the embodiment of the present application, when the determination module 202 determines the actual grid frequency corresponding to the current area based on the voltage cycle and the current cycle, it is specifically used to: Based on the voltage cycle, determine the voltage zero-crossing time, and based on the current cycle, determine the current zero-crossing time; Calculate the voltage time interval corresponding to every two adjacent voltage zero-crossing moments, and calculate the current time interval corresponding to every two adjacent current zero-crossing moments; Based on the voltage time interval and the current time interval, the actual grid frequency corresponding to the current substation is determined.

[0062] In a possible implementation of the embodiment of the present application, the prediction module 203 is specifically used to predict the power grid frequency change trend in the future period based on the future environmental data, the current power grid state and the power grid frequency deviation: Obtain the historical power grid data corresponding to the current substation, which includes the historical voltage, historical current and historical network frequency deviation corresponding to the historical period; Based on historical power grid data, correlation features are established, and the correlation features are the correlation between power grid power and power grid frequency deviation. Based on future environmental data, historical power grid data, correlation features, current power grid status and power grid frequency deviation, the power grid frequency change trend in the future period is predicted.

[0063] In a possible implementation of the embodiment of the present application, the prediction module 203 is specifically used to: extract time features from historical power grid data, and extract temperature features from future environmental data when predicting the power grid frequency change trend in a future period based on historical power grid data, associated features, current power grid status, and power grid frequency deviation; Determine the influencing parameters corresponding to the grid frequency deviation based on the correlation characteristics, temperature characteristics and time characteristics; Obtaining the power generation plan corresponding to the thermal power units in the future period, where the power generation plan represents the planned amount of power generated within a certain period of time; Based on the power generation plan, influencing parameters and the current grid status, the grid frequency change trend in the future period is predicted.

[0064] In a possible implementation of the embodiment of the present application, when the generation module 204 generates the energy storage frequency modulation instruction based on the power grid frequency change trend, it is specifically used to: Based on the changing trend of the grid frequency, determine the corresponding working time of the energy storage device in the future cycle and the working mode corresponding to each working time. The working time is the time when the energy storage device switches the working mode, and the working mode is the charging mode or the discharging mode; Based on the working moments corresponding to the energy storage device in the future cycle and the working mode corresponding to each working moment, a working instruction corresponding to each working moment is generated to obtain an energy storage frequency modulation instruction.

[0065] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0066] See also Figure 3 , the embodiment of the present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0067] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0068] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0069] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0070] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0071] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be servers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0072] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0073] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0074] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for energy storage frequency modulation based on a thermal power unit, characterized in that: include: Obtaining the current grid state and future environmental data corresponding to the current substation, wherein the current grid state includes grid voltage and grid current, and the future environmental data is a curve of the change of ambient temperature over time in a future period; Determining a grid frequency deviation corresponding to the current grid state; Based on the future environmental data, the current grid state and the grid frequency deviation, predicting a grid frequency change trend in a future period; Based on the power grid frequency change trend, an energy storage frequency modulation instruction is generated, and the energy storage frequency modulation instruction is sent to the energy storage device corresponding to the current substation.

2. The energy storage frequency modulation method based on a thermal power unit according to claim 1 is characterized in that: The determining the grid frequency deviation corresponding to the current grid state includes: Obtaining a voltage cycle corresponding to the grid voltage and a current cycle corresponding to the grid current; Based on the voltage cycle and the current cycle, determining an actual grid frequency corresponding to the current area; Obtaining the rated frequency corresponding to the current station area; Based on the actual grid frequency and the rated frequency, a grid frequency deviation corresponding to the current grid state is determined.

3. The energy storage frequency modulation method based on a thermal power unit according to claim 2 is characterized in that: The determining, based on the voltage cycle and the current cycle, an actual grid frequency corresponding to the current area includes: Based on the voltage cycle, determining the voltage zero-crossing time, and based on the current cycle, determining the current zero-crossing time; Calculating the voltage time interval corresponding to every two adjacent voltage zero-crossing moments, and calculating the current time interval corresponding to every two adjacent current zero-crossing moments; Based on the voltage time interval and the current time interval, an actual grid frequency corresponding to the current substation is determined.

4. The energy storage frequency modulation method based on a thermal power unit according to claim 1 is characterized in that: The predicting of the grid frequency change trend in a future period based on the future environmental data, the current grid state and the grid frequency deviation includes: Acquire historical power grid data corresponding to the current substation, wherein the historical power grid data includes historical voltage, historical current and historical network frequency deviation corresponding to a historical period; Based on the historical power grid data, establishing a correlation feature, wherein the correlation feature is a correlation relationship between power grid power and power grid frequency deviation; Based on the future environmental data, the historical power grid data, the associated features, the current power grid state and the power grid frequency deviation, a power grid frequency change trend in a future period is predicted.

5. The energy storage frequency modulation method based on thermal power units according to claim 4 is characterized in that: The predicting of the grid frequency change trend in a future period based on the historical grid data, the associated features, the current grid state, and the grid frequency deviation includes: Extracting time features from the historical power grid data, and extracting temperature features from the future environmental data; Determining an influencing parameter corresponding to the grid frequency deviation based on the association feature, the temperature feature, and the time feature; Obtaining an electric energy generation plan corresponding to a thermal power unit in a future period, wherein the electric energy generation plan represents the planned amount of electric energy generated in a certain period of time; Based on the electric energy generation plan, the influencing parameters and the current grid state, a grid frequency variation trend in the future period is predicted.

6. The energy storage frequency modulation method based on thermal power units according to claim 5 is characterized in that: The generating of energy storage frequency modulation instructions based on the power grid frequency change trend includes: Based on the power grid frequency change trend, determine the working time corresponding to the energy storage device in the future cycle and the working mode corresponding to each working time, the working time is the time when the energy storage device switches the working mode, and the working mode is a charging mode or a discharging mode; Based on the working moments corresponding to the energy storage device in the future cycle and the working mode corresponding to each working moment, a working instruction corresponding to each working moment is generated to obtain an energy storage frequency modulation instruction.

7. An energy storage frequency modulation device based on a thermal power unit, characterized in that: include: An acquisition module is used to acquire the current grid state and future environmental data corresponding to the current substation, wherein the current grid state includes grid voltage and grid current, and the future environmental data is a curve of the change of ambient temperature over time in a future period; A determination module, used to determine a grid frequency deviation corresponding to the current grid state; A prediction module, used for predicting the frequency change trend of the power grid in a future period based on the future environmental data, the current power grid state and the power grid frequency deviation; A generation module is used to generate an energy storage frequency modulation instruction based on the power grid frequency change trend, and send the energy storage frequency modulation instruction to the energy storage device corresponding to the current substation.

8. The energy storage frequency modulation device based on a thermal power unit according to claim 7, characterized in that: When determining the grid frequency deviation corresponding to the current grid state, the determination module is specifically used to: Obtaining a voltage cycle corresponding to the grid voltage and a current cycle corresponding to the grid current; Based on the voltage cycle and the current cycle, determining an actual grid frequency corresponding to the current area; Obtaining the rated frequency corresponding to the current station area; Based on the actual grid frequency and the rated frequency, a grid frequency deviation corresponding to the current grid state is determined.

9. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the energy storage frequency regulation method based on a thermal power unit as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the energy storage frequency regulation method based on a thermal power unit as described in any one of claims 1 to 7.

Images