Hydropower station bus voltage regulation control method based on big data self-learning

Abstract

The invention relates to a hydropower station bus voltage regulation control method based on big data self-learning, and the method comprises the steps: calculating the average value of the voltage regulation coefficients of a hydropower station in the same period in the previous year, and the average value of the voltage regulation coefficients in the current time period; searching a bus voltage regulation control process in a similar control scene from the big data, and calculating to obtain an average value of voltage regulation coefficients of the hydropower station in the same type of control scene; calculating to obtain a voltage regulation coefficient for real-time regulation and control of the bus voltage of the hydropower station; calculating a reactive power target value by using an automatic voltage control system of the hydropower station according to the obtained voltage regulation coefficient; and distributing the reactive power target value to each starting-up unit through an automatic voltage control system of the hydropower station, and carrying out closed-loop control adjustment on the bus voltage. According to the method, a big data analysis method and an AI model are combined, the accurate voltage regulation coefficient is obtained through real-time calculation, the bus voltage can be quickly regulated to the target value under the current working condition, and the response speed of the bus voltage is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of hydropower generation control, and in particular relates to a bus voltage regulation and control method for a hydropower station based on big data self-learning. Background Art

[0002] In order to ensure the quality of electric energy, improve transmission efficiency, reduce grid losses, and achieve stable and economical operation of the grid, it is necessary to perform automatic voltage control (AVC) on the grid. The bus voltage of each power station needs to operate according to the voltage curve specified by the grid dispatch. The voltage curve is generally issued once a quarter, and the bus voltage is adjusted according to the daily grid load law. The bus voltage of a hydropower station is mainly regulated by adjusting the reactive power of the turbine generator set. The reactive power required to adjust the bus voltage of the hydropower station is calculated by the voltage regulation coefficient, and then approximate regulation is performed. The voltage regulation coefficient is usually calculated when the hydropower station is put into operation. With the change of grid capacity, the original voltage regulation coefficient calculation method can no longer fully match the current operating conditions of the hydropower station, which will affect the bus voltage regulation performance. Summary of the invention

[0003] The purpose of the present invention is to address the above-mentioned problems and provide a bus voltage regulation and control method for a hydropower station based on big data self-learning. By combining big data analysis methods and AI models, an accurate voltage regulation coefficient is obtained based on the average value of the voltage regulation coefficients of similar control scenarios in the same period of previous years and historical periods of the hydropower station, so as to achieve rapid adjustment of AVC to the target value and improve the bus voltage response speed.

[0004] In order to achieve the above object, the technical solution of the present invention is: The bus voltage regulation control method of a hydropower station based on big data self-learning includes the following steps: Step 1: Calculate the average value of the voltage regulation coefficient of the hydropower station in the same period of previous years , and the average value of the voltage regulation coefficient H hours before the current time point ; Step 2: Search the bus voltage regulation control process of similar control scenarios from the big data historical data, and calculate the average value of the voltage regulation coefficient of the hydropower station under the same control scenario ; Step 3: Determine , , The weight value of Step 4: Calculate the voltage regulation coefficient used for real-time regulation and control of the bus voltage of the hydropower station according to the average value of the voltage regulation coefficient calculated in step 1 and step 2 and the weight value obtained in step 3; Step 5: Calculate the reactive power target value using the automatic voltage control system of the hydropower station according to the voltage regulation coefficient obtained in step 3; Step 6: Allocate the reactive power target value to each operating unit through the hydropower station automatic voltage control system to perform closed-loop control and adjustment of the bus voltage.

[0005] Preferably, in step 1, the value range of H is [1,3].

[0006] Preferably, step 2 comprises the following sub-steps: Step 2.1: Collect a large amount of hydropower station operation data from the big data platform or historical database, including voltage regulation factor, load demand, head and flow; Step 2.2: Use the correlation algorithm to analyze the correlation between the operating data of different bus voltage regulation control processes, and find out the historical operating data similar to the bus voltage regulation control process under the current working condition; Step 2.3: Perform cluster analysis on the collected operation data and classify the control scenarios of the bus voltage regulation control process with similar operation characteristics into the same category; Step 2.4: Calculate the average value of the voltage regulation coefficient under the same type of control scenario.

[0007] Preferably, in step 3, the weight vector is calculated using the LSTM model W , W =[w1, w2, w3], , , Respectively , , The corresponding weights, the input of the LSTM model includes the water head of the hydropower station, the unit output, and the bus voltage target value V 目标 , bus voltage current value V 当前 And the voltage regulation coefficient vector K , , the output of the LSTM model is the weight vector W .

[0008] Furthermore, in step 4, the voltage regulation coefficient for real-time regulation and control of the bus voltage of the hydropower station is calculated by the formula:

[0009] In the formula It indicates the voltage regulation coefficient of the busbar voltage regulation control of the hydropower station. , , Respectively , , The corresponding weight.

[0010] Preferably, in step 5, the calculation formula of the reactive power target value is: Q 目标 = Q 当前 + k ×( V 目标 - V 当前 ) In the formula Q 目标 Represents the reactive power target value, Q 当前 Indicates the current reactive power of the hydropower station; V 目标 Indicates the target value of the bus voltage of the hydropower station; V 当前 Indicates the current value of the bus voltage of the hydropower station.

[0011] Compared with the prior art, the beneficial effects of the present invention include: 1) The present invention obtains an accurate voltage regulation coefficient by calculating the average value of the voltage regulation coefficient of the hydropower station in the same period of previous years, the current time period and the same control scenario in the historical period, so as to realize the rapid adjustment of the bus voltage to the target value under the current working conditions, and effectively improve the bus voltage response speed.

[0012] 2) The present invention uses a dynamic voltage regulation coefficient calculation method to obtain the voltage regulation coefficient that best suits the actual situation at any time according to the change of the power grid capacity, so that the AVC regulation feature can track the change of the power grid capacity in a timely manner.

[0013] 3) The present invention searches for similar bus voltage regulation and control processes from big data historical data, uses an association algorithm to analyze the correlation between the operating data of different bus voltage regulation and control processes, and finds out historical operating data similar to the bus voltage regulation and control process of the current operating condition; uses a cluster analysis method to classify the control scenarios of the bus voltage regulation and control process with similar operating characteristics into the same category, and calculates the real-time dynamic voltage regulation coefficient of the current operating condition based on the voltage regulation coefficient of the same control scenario, thereby improving the accuracy and scientificity of the real-time dynamic voltage regulation coefficient.

[0014] 4) The present invention adopts the LSTM model as the voltage regulation coefficient weight prediction model, which can effectively capture the time series characteristics in big data and historical data, and uses the hydropower station head, unit output, bus voltage target value, and bus voltage current value as input data of the voltage regulation coefficient weight prediction model, thereby improving the accuracy of the voltage regulation coefficient weight value and further improving the accuracy of the real-time voltage regulation coefficient.

[0015] 5) The system of the present invention realizes the real-time dynamic and accurate calculation of the voltage regulation coefficient of the current working condition, communicates with the automatic voltage control system of the hydropower station, and effectively improves the bus voltage regulation performance of the hydropower station. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0017] Figure 1 The present invention is a flowchart of a method for controlling bus voltage regulation in a hydropower station based on big data self-learning according to an embodiment of the present invention.

[0018] Figure 2 It is a schematic diagram of the system modules of the bus voltage regulation control method of a hydropower station according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] like Figure 1 As shown, the bus voltage regulation control method of a hydropower station based on big data self-learning includes the following steps: Step 1: Calculate the average value of the voltage regulation coefficient of the hydropower station in the same period of previous years , and the average value of the voltage regulation coefficient H hours before the current time point ; In the embodiment, the value of H is 2, that is, It is the average value of the voltage regulation coefficient 2 hours before the current time point.

[0020] Step 2: Search the bus voltage regulation control process of similar control scenarios from the big data historical data, and calculate the average value of the voltage regulation coefficient of the hydropower station under the same control scenario ; Step 2.1: Collect a large amount of hydropower station operation data from the big data platform or historical database, including voltage regulation factor, load demand, head and flow; Step 2.2: Analyze the correlation between the operating data of different bus voltage regulation control processes, and find out the historical operating data similar to the bus voltage regulation control process under the current working condition; Step 2.3: Perform cluster analysis on the collected operation data and classify the control scenarios of the bus voltage regulation control process with similar operation characteristics into the same category; Step 2.4: Calculate the average value of the voltage regulation coefficient under the same type of control scenario.

[0021] Step 3: Determine , , The corresponding weight value , , ; In the embodiment, the weight vector is calculated using the LSTM model W , W =[w1, w2, w3], the input of the LSTM model includes the water head of the hydropower station, the unit output, and the bus voltage target value V 目标 , bus voltage current value V 当前 And the voltage regulation coefficient vector K , , the output of the LSTM model is the weight vector W .

[0022] Step 4: Calculate the voltage regulation coefficient k used for real-time regulation and control of the bus voltage of the hydropower station according to the average value of the voltage regulation coefficients calculated in steps 1 and 2 and the weight value obtained in step 3;

[0023] In the formula It indicates the voltage regulation coefficient of the busbar voltage regulation control of the hydropower station. , , Respectively , , The corresponding weight.

[0024] Step 5: Calculate the reactive power target value using the automatic voltage control system of the hydropower station according to the voltage regulation coefficient obtained in step 3; The calculation formula of reactive power target value is: Q 目标 = Q 当前 + k ×( V 目标 - V 当前 ) In the formula Q 目标 Represents the reactive power target value, Q 当前 Indicates the current reactive power of the hydropower station; V 目标 Indicates the target value of the bus voltage of the hydropower station; V 当前 Indicates the current value of the bus voltage of the hydropower station.

[0025] Step 6: Allocate the reactive power target value to each operating unit through the hydropower station automatic voltage control system to perform closed-loop control and adjustment of the bus voltage.

[0026] like Figure 2As shown, the system of the above-mentioned hydropower station bus voltage regulation control method includes the following modules: The voltage regulation coefficient calculation module of the same period in previous years is used to calculate the average value of the voltage regulation coefficient of the hydropower station in the same period in previous years; The current time period voltage regulation coefficient average value calculation module is used to calculate the voltage regulation coefficient average value within the time range before the current time point; The pressure regulation coefficient calculation module for the same control scenario calculates the average value of the pressure regulation coefficient under the same control scenario of the current working condition based on big data; The voltage regulation coefficient weight calculation module is used to calculate the weight value of the average voltage regulation coefficient of the hydropower station in the same period of previous years, the current time period, and the same control scenario; The real-time voltage regulation coefficient calculation module calculates the real-time voltage regulation coefficient under the current working conditions based on the average voltage regulation coefficients and corresponding weight values ​​of the hydropower station in the same period of previous years, the current time period, and the same control scenarios; The reactive power calculation module is used to calculate the reactive power target value of the hydropower station according to the real-time voltage regulation coefficient output by the real-time voltage regulation coefficient calculation module.

[0027] The command sending module is connected to the automatic voltage control system of the hydropower station for communication, and distributes the reactive power target value to each operating unit through the automatic voltage control system of the hydropower station.

[0028] In another embodiment of the present invention, the current time period voltage regulation coefficient average value calculation module calculates the average value of the voltage regulation coefficient of the current time period by calculating the average value of the voltage regulation coefficient of N instruction cycles, where N is the number of instruction cycles and the value of N is 10 in the embodiment.

Claims

1. A method for regulating and controlling bus voltage of a hydropower station based on big data self-learning, characterized in that: The following steps are involved: Step 1: Calculate the average value of the voltage regulation coefficient of the hydropower station in the same period of previous years , and the average value of the voltage regulation coefficient H hours before the current time point ; Step 2: Search the bus voltage regulation control process of similar control scenarios from the big data historical data, and calculate the average value of the voltage regulation coefficient of the hydropower station under the same control scenario ; Step 3: Determine , , The weight value of Step 4: Calculate the voltage regulation coefficient used for real-time regulation and control of the bus voltage of the hydropower station according to the average value of the voltage regulation coefficient calculated in step 1 and step 2 and the weight value obtained in step 3; Step 5: Calculate the reactive power target value using the automatic voltage control system of the hydropower station according to the voltage regulation coefficient obtained in step 3; Step 6: Allocate the reactive power target value to each operating unit through the hydropower station automatic voltage control system to perform closed-loop control and adjustment of the bus voltage.

2. The method for controlling bus voltage of a hydropower station based on big data self-learning according to claim 1 is characterized in that: In step 1, the value range of H is [1,3].

3. The method for controlling bus voltage regulation of a hydropower station based on big data self-learning according to claim 1 is characterized in that: The step 2 includes the following sub-steps: Step 2.1: Collect a large amount of hydropower station operation data from the big data platform or historical database, including voltage regulation factor, load demand, head and flow; Step 2.2: Analyze the correlation between the operating data of different bus voltage regulation control processes, and find out the historical operating data similar to the bus voltage regulation control process under the current working condition; Step 2.3: Perform cluster analysis on the collected operation data and classify the control scenarios of the bus voltage regulation control process with similar operation characteristics into the same category; Step 2.4: Calculate the average value of the voltage regulation coefficient under the same type of control scenario.

4. The bus voltage regulation and control method for a hydropower station based on big data self-learning according to claim 1, 2 or 3, characterized in that: In step 3, the weight vector is calculated using the LSTM model. W , W =[w1, w2, w3], , , Respectively , , The corresponding weights, the input of the LSTM model includes the water head of the hydropower station, the unit output, and the bus voltage target value V 目标 , bus voltage current value V 当前 And the voltage regulation coefficient vector K , , the output of the LSTM model is the weight vector W .

5. The method for controlling bus voltage regulation of a hydropower station based on big data self-learning according to claim 4 is characterized in that: In step 4, the voltage regulation coefficient for real-time regulation and control of the bus voltage of the hydropower station is calculated as follows: ； In the formula It represents the voltage regulation coefficient of the busbar voltage regulation control of the hydropower station. , , Respectively , , The corresponding weight.

6. The method for controlling bus voltage regulation of a hydropower station based on big data self-learning according to claim 5 is characterized in that: In step 5, the reactive power target value is calculated as: Q 目标 = Q 当前 + k ×（ V 目标 - V 当前 ）； In the formula Q 目标 Represents the reactive power target value, Q 当前 Indicates the current reactive power of the hydropower station; V 目标 Indicates the target value of the bus voltage of the hydropower station; V 当前 Indicates the current value of the bus voltage of the hydropower station.

7. The system of the bus voltage regulation control method of a hydropower station according to claim 1, 2, 3, 5 or 6, characterized in that: include: The voltage regulation coefficient calculation module of the same period in previous years is used to calculate the average value of the voltage regulation coefficient of the hydropower station in the same period in previous years; The current time period voltage regulation coefficient average value calculation module is used to calculate the voltage regulation coefficient average value within the time range before the current time point; The pressure regulation coefficient calculation module for the same control scenario calculates the average value of the pressure regulation coefficient under the same control scenario of the current working condition based on big data; The voltage regulation coefficient weight calculation module is used to calculate the weight value of the voltage regulation coefficient of the hydropower station in the same period of previous years, the current time period, and the same control scenario; The real-time voltage regulation coefficient calculation module calculates the real-time voltage regulation coefficient under the current working conditions based on the average voltage regulation coefficients and corresponding weight values ​​of the hydropower station in the same period of previous years, the current time period, and the same control scenarios; The reactive power calculation module is used to calculate the reactive power target value of the hydropower station according to the real-time voltage regulation coefficient output by the real-time voltage regulation coefficient calculation module. The voltage regulation instruction sending module distributes the reactive power target value to each operating unit through the automatic voltage control system of the hydropower station.

Images