A Remote Intelligent Management and Control Method and System for a Photovoltaic Power Station

Abstract

The present invention discloses a method and system for remote intelligent control of a photovoltaic power station, belonging to the technical field of photovoltaic power station control; this method collects the historical operation data of the key parameters of the photovoltaic power station system, establishes a prediction model of the photovoltaic power station system based on a neural network, and optimizes the parameters of the PID controller by using an adaptive control algorithm of the photovoltaic power station system optimized by ITAE; through mining the historical data by a deep learning model and combining with an adaptive PID control strategy, the intelligent remote control of the photovoltaic power station is realized, and the power generation efficiency and operation and maintenance management level are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station management and control, and particularly relates to a method and system for remote intelligent management and control of a photovoltaic power station. Background Art

[0002] At present, the proportion of large-scale photovoltaic power stations in the power system is continuously increasing, and their safe and stable operation has an increasingly greater impact on the power grid. However, the traditional control system of photovoltaic power stations mainly uses fixed PID control parameters and cannot adjust the control strategy in a timely manner according to the dynamic changes of environmental conditions, resulting in a lag in system response and affecting power generation efficiency.

[0003] Photovoltaic power generation has the characteristics of intermittency and volatility, and its output power changes with external conditions such as light intensity and environmental temperature, which poses challenges to the precise control of the power station. At the same time, the photovoltaic power station needs to match the load characteristics of the power grid to achieve grid-friendly grid connection operation.

[0004] Therefore, how to improve the control accuracy and intelligent level of photovoltaic power stations and achieve the efficient operation of power stations has become an urgent technical problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for remote intelligent management and control of a photovoltaic power station, which is used to solve the problems of lagging response and low control accuracy of the traditional photovoltaic power station control system, and achieve the purpose of intelligent remote management and control and efficient operation of the photovoltaic power station.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] In the first aspect, the present invention provides a method for remote intelligent management and control of a photovoltaic power station, which is used to improve the power generation efficiency and operation and maintenance management level of the photovoltaic power station. The photovoltaic power station uses a PID controller to regulate the power output of the inverter and the angle of the photovoltaic array to achieve matching adjustment of the power output of the photovoltaic power station and the power grid load.

[0008] The method includes the following steps:

[0009] Step 1, collect historical operation data of key parameters of the photovoltaic power station system, where the key parameters include: power output of the inverter, angle of the photovoltaic array, light intensity, environmental temperature, and power grid load.

[0010] Step 2, establish a prediction model of the photovoltaic power station system based on a neural network, and give the power setting of the inverter and the optimal angle of the photovoltaic array under the current light and load response according to the prediction model.

[0011] Step 3: Optimize the proportional, integral, and derivative coefficients of the PID controller using the ITAE-optimized adaptive control algorithm for the photovoltaic power station system. Based on the established prediction model and the optimized PID controller, adjust the inverter power output and the photovoltaic array angle in real time.

[0012] Further, the prediction model consists of an input layer, a one-dimensional convolutional layer, a pooling layer, a bidirectional memory recurrent layer, a Dropout layer, a fully connected layer, and an output layer connected in sequence.

[0013] The one-dimensional convolutional layer extracts the temporal features of the historical operation data of the photovoltaic power station, including the periodic change features of light intensity and ambient temperature and the dynamic change features of grid load; the pooling layer simplifies the data dimension after one-dimensional convolution and passes the data to the bidirectional gated recurrent layer; the bidirectional gated recurrent layer uses bidirectional GRU to model the long-term and short-term dynamic characteristics of the photovoltaic power generation system, extracts the temporal correlation features of power output and photovoltaic array angle adjustment, and performs a non-linear transformation to determine the internal logical relationship between light, temperature, load input, inverter power output, and photovoltaic array angle.

[0014] After the data is subjected to secondary feature extraction by the bidirectional memory recurrent layer, some nodes of the data are randomly discarded in the Dropout layer to prevent overfitting and the processed data is passed to the fully connected layer. The fully connected layer maps the output features to the label space of the samples through non-linear combination, and the output layer outputs the preset power output adapted to the current state of the photovoltaic power station through linear regression operation and the preset photovoltaic array angle predicted values.

[0015] Further, divide the historical operation data into a training set and a feature set. At time, use to represent the state of the input layer, to represent the state of the output layer, to represent the hidden layer state during the transfer process in the bidirectional GRU layer. Then:

[0016] ;

[0017] In the formula, represents the feature state learned by the forward layer during the unidirectional transfer process, is the feature state learned by the backward layer during the unidirectional transfer process; and are the weights from the forward layer and the backward layer to the output layer in sequence; then represents the bias vector added in the output layer; Import the training set into the neural network model to obtain the parameters of the network model.

[0018] Furthermore, compare the prediction results output by the prediction model of the photovoltaic power station system with the measured data in the test set, and use the goodness-of-fit index to describe the prediction performance of the model, When , the model training stop condition is satisfied. At this time, the parameters of the model are the optimal parameters of the neural network model structure. If not satisfied, use the backpropagation algorithm to adjust the deviation of the model and continue to loop.

[0019] Goodness-of-fit index The calculation formula of is:

[0020] ; In the formula, represents the actual power output value of the th sample, is the predicted power output value corresponding to the th sample, is the average value of the power output; represents the actual photovoltaic array angle value of the th sample, is the predicted photovoltaic array angle value corresponding to the th sample, is the average value of the photovoltaic array angle; is the total number of samples; and are weight coefficients and satisfy , used to balance the importance of power output and angle prediction. The preset values are: , .

[0021] Furthermore, the control transfer function of the PID controller is:

[0022] ;

[0023] Among them, is the inverter power output after taking the Laplace transform, is the Laplace transform value of the photovoltaic array angle, and are the Laplace transform values of the power deviation and the angle deviation respectively, is the time variable; , and are the proportional, integral, and differential coefficients of the PID controller in the power control channel respectively, , , ; Among them, is the relative deviation of the inverter power output, is the relative deviation of the power control channel PID controller stroke; , and are the proportional, integral, and derivative coefficients of the angle control channel PID controller respectively; , , ; where, is the relative deviation of angle control, is the relative deviation of the angle control channel PID controller stroke.

[0024] Furthermore, select index as the fitness function of the optimization algorithm , where, is the simulation time.

[0025] Furthermore, compare the ITAE index values calculated from the system states at the previous moment S - 1 and the current moment S and make a comparison. The ITAE index value at the previous moment is denoted as , and the ITAE index value at the current moment is denoted as .

[0026] When ITAE(S - 1) ≥ ITAE(S), it indicates that the system performance is improving. At this time, keep the current PID controller parameters unchanged; according to the relative deviations of the controlled variables of the power and angle channels and the relative deviation of the PID controller stroke at the current moment; adjust the inverter power output and the photovoltaic array angle to make them reach the preset power output and the preset photovoltaic array angle .

[0027] When ITAE(S - 1) < ITAE(S), it indicates that the system performance is deteriorating. At this time, restore the relative deviations of the controlled variables of the power and angle channels and the relative deviation of the PID controller stroke to the values at the previous moment, recalculate the PID controller parameters; adjust the inverter power output and the photovoltaic array angle to make them reach the preset power output and the preset photovoltaic array angle .

[0028] Furthermore, the method further includes the following steps:

[0029] Step 4, as the operation data accumulates continuously, update the prediction model parameters and PID controller parameters regularly; the frequency of the regular update is maintained at 15 - 30 days.

[0030] Further, step 1 further includes preprocessing the historical operation data by a mean filtering method to remove noise and outliers; for each point in the historical operation data, the average value of this point and the two points before and after it is taken as the output.

[0031] The specific method of the mean filtering is as follows:

[0032]

[0033] where is the number of points within the filtering window, N = 5, and the original value is the value of the th point within the filtering window.

[0034] In a second aspect, the present invention provides a remote intelligent control and management system for a photovoltaic power station, which is used to execute the method of the first aspect. The system includes, connected in sequence: a data acquisition module, a data processing module, and a parameter adjustment module.

[0035] The data acquisition module is used to collect the historical operation data of the key parameters of the photovoltaic power station system. The key parameters include: inverter power output, photovoltaic array angle, light intensity, ambient temperature, and grid load.

[0036] The data processing module is used to establish a prediction model of the photovoltaic power station system based on a neural network, and give the inverter power setting and the optimal angle of the photovoltaic array under the current light and load responses according to the prediction model.

[0037] The parameter adjustment module is used to optimize the proportional, integral, and differential coefficients of the PID controller by using an ITAE-optimized adaptive control algorithm for the photovoltaic power station system. Based on the established prediction model and the optimized PID controller, the inverter power output and the photovoltaic array angle are adjusted in real time.

[0038] Further, the system further includes:

[0039] A remote communication unit, which is used to realize remote transmission of system data, remote monitoring of system status, and remote alarm for abnormal situations.

[0040] A data storage unit, which is used to store the historical operation data of the photovoltaic power station system, the neural network model parameters, and the PID controller parameters.

[0041] A human-computer interaction unit, including a display module and a control module; wherein, the display module is used to display in real time the power generation power, array angle, environmental data, and system operation status of the photovoltaic power station; the control module is used to receive the control instructions of the operator and adjust the system operation parameters.

[0042] The monitoring execution unit is used to monitor the key system parameters according to a preset frequency and execute exception handling, and the monitoring frequency is not less than once every 5 minutes; when an anomaly is detected, an alarm message is sent to the remote communication unit.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] By adopting a prediction model based on neural network and an adaptive PID control strategy optimized by ITAE, the present invention can dynamically optimize the system control parameters according to real-time conditions such as light intensity and ambient temperature, improving the power generation efficiency and control accuracy of the photovoltaic power station; realizing intelligent remote monitoring and management of the photovoltaic power station, improving the operation and maintenance efficiency, and reducing the operation and maintenance cost. Description of the Drawings

[0045] Figure 1 It is a flowchart of a remote intelligent control method for a photovoltaic power station according to the present invention;

[0046] Figure 2 It is a schematic diagram of the composition of a remote intelligent control system for a photovoltaic power station according to the present invention. Detailed Embodiments

[0047] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0048] It should be noted that the present invention deploys a distributed data acquisition system at the photovoltaic power station site. In terms of the acquisition of the inverter power output, a power meter with an accuracy of 0.2 level is selected, and the sampling frequency is 100Hz to ensure that the rapid fluctuation characteristics of the power can be captured. The photovoltaic array angle adopts a high-precision angle sensor with a resolution of 0.1°, and the inclination angle change of the array is monitored in real time. The light intensity measurement uses a professional photovoltaic meteorological station, which includes 12 illuminometers distributed in different areas of the power station, and the sampling frequency is 1Hz to form the spatial distribution data of the light intensity; in addition to collecting the air temperature, an infrared thermometer is arranged to monitor the surface temperature of the photovoltaic modules for the environmental temperature, comprehensively reflecting the temperature field distribution; the grid load data is obtained through the real-time communication interface with the grid dispatching system, including electrical parameters such as active power and reactive power.

[0049] Embodiment 1

[0050] As Figure 1As shown in the figure, it is a flowchart of a remote intelligent control method for a photovoltaic power station of the present invention, which is used to improve the power generation efficiency and operation and maintenance management level of the photovoltaic power station. The photovoltaic power station applies a PID controller to regulate the power output of the inverter and the angle of the photovoltaic array, so as to realize the matching adjustment of the power output of the photovoltaic power station and the grid load.

[0051] The method includes the following steps:

[0052] Step 1: Collect the historical operation data of the key parameters of the photovoltaic power station system. The key parameters include: the power output of the inverter, the angle of the photovoltaic array, the light intensity, the ambient temperature, and the grid load.

[0053] By configuring a data acquisition module, the key parameters during the operation of the photovoltaic power station are recorded in real time at a sampling frequency of not less than once every 5 minutes. Among them, the power output of the inverter is measured by a wattmeter, the angle of the photovoltaic array is obtained through an angle sensor, the light intensity is measured by a luxmeter, the ambient temperature is collected by a temperature sensor, and the grid load data is obtained from the grid dispatching system.

[0054] The present invention adopts a hierarchical distributed data acquisition architecture. At the field layer, each photovoltaic square array is configured with an independent data acquisition unit, including a high-precision luxmeter (accuracy ±1%, range 0-2000W / m²), a PT100 temperature sensor (accuracy ±0.1°C, range -30°C to +80°C), an angle sensor (accuracy ±0.1°, range 0-90°), etc. The power output of the inverter is measured by a 0.5S-class high-precision watt-hour meter, and the sampling frequency is 1Hz. All acquisition devices are connected to the local controller through the RS485 bus and communicate using the Modbus-RTU protocol to ensure the real-time and reliable transmission of data.

[0055] Before mean filtering, the original data is first subjected to outlier detection, and a data validity judgment standard based on principles is set:

[0056] 1. Effective range of light intensity: 0-1200W / m²; 2. Effective range of ambient temperature: (μ is the average value of historical data, σ is the standard deviation); 3. Effective range of power data: 0-1.2 times the installed capacity.

[0057] Data points outside the range are marked as outliers. For continuous outliers, if the duration is less than 1 minute, the linear interpolation method is used for correction; if the duration exceeds 1 minute, an alarm signal is triggered and manual confirmation is required.

[0058] Preprocess the historical operation data through the mean filtering method to remove noise and outliers; for each point in the historical operation data, take the average value of this point and its neighboring points, that is, the points within the filtering window, as the output.

[0059] The specific method of the mean filtering is as follows:

[0060]

[0061] where is the number of points within the filtering window, and the original value is the value of the th point within the filtering window.

[0062] Select the filtering window size N = 5, that is, take the average value of 5 points including 2 points before and after each data point as the filtered value of this point. This method can effectively eliminate the data noise caused by factors such as equipment jitter and electromagnetic interference. For example, the light intensity data continuously collected 5 times at a certain moment is: 850 W / m², 890 W / m², 870 W / m², 860 W / m², 880 W / m². The light intensity value at this moment after mean filtering is 870 W / m², avoiding the deviation that may be brought by single sampling.

[0063] In mean filtering processing, different sizes of filtering windows are used for different types of data: for the light intensity data with fast changes, a small window with N = 5 is selected to retain the fast-changing characteristics; for parameters with slow changes such as temperature, a large window with N = 9 is used to further suppress noise; for grid load data, a medium window with N = 7 is adopted to balance the response speed and filtering effect; at the same time, an adaptive window mechanism is introduced. When a data mutation is detected (the deviation between adjacent two points exceeds the set threshold), the filtering window size is automatically reduced to improve the system's response ability to mutations. For example, in the working condition where the light intensity suddenly drops from 1000 W / m² to 200 W / m², the window size automatically adjusts from N = 5 to N = 3, enabling the system to quickly track this change.

[0064] Step 2, establish a prediction model of the photovoltaic power station system based on the neural network, and give the inverter power setting and the optimal angle of the photovoltaic array under the current light and load responses according to the prediction model.

[0065] The prediction model consists of an input layer, a one-dimensional convolutional layer, a pooling layer, a bidirectional memory recurrent layer, a Dropout layer, a fully connected layer, and an output layer connected in sequence.

[0066] The one-dimensional convolutional layer extracts the temporal features of the historical operation data of the photovoltaic power station, including the periodic change features of light intensity and ambient temperature and the dynamic change features of grid load; the pooling layer simplifies the data dimension after one-dimensional convolution and passes the data to the bidirectional gated recurrent layer; the bidirectional gated recurrent layer uses bidirectional GRU to model the long-term and short-term dynamic characteristics of the photovoltaic power generation system, extracts the temporal correlation features of power output and photovoltaic array angle adjustment, and performs non-linear transformation to determine the internal logical relationship between light, temperature, load input and inverter power output and photovoltaic array angle.

[0067] After the data is subjected to secondary feature extraction by the bidirectional memory recurrent layer, some nodes of the data are randomly discarded in the Dropout layer to prevent overfitting and the processed data is passed to the fully connected layer. The fully connected layer maps the output features to the label space of the samples through non-linear combination, and outputs the preset power output adapted to the current state of the photovoltaic power station through the linear regression operation of the output layer and the preset photovoltaic array angle of the predicted value.

[0068] The specific structural parameters of the neural network model are as follows: Input layer: Receives 5×24-dimensional temporal data (5 parameters, 24 historical moments); One-dimensional convolutional layer: Consists of three cascaded structures: The first layer: 64 convolutional kernels, kernel size 3, stride 1, ReLU activation; The second layer: 128 convolutional kernels, kernel size 3, stride 1, ReLU activation; The third layer: 256 convolutional kernels, kernel size 3, stride 1, ReLU activation; Pooling layer: Adopts max pooling, window size 2, to achieve feature dimensionality reduction; Bidirectional GRU layer: Consists of two layers: The first layer: 256 hidden units, tanh activation function, The second layer: 128 hidden units, tanh activation function; Dropout layer: Adopts a dropout rate of 0.3 to prevent overfitting; Fully connected layer: Consists of three structures: The first layer: 256 neurons, ReLU activation; The second layer: 128 neurons, ReLU activation; The third layer: 64 neurons, ReLU activation; Output layer: 2 neurons, respectively outputting the power and angle predicted values.

[0069] The historical operation data is divided into a training set and a feature set. At time, represents the state of the input layer, represents the state of the output layer, represents the hidden layer state during the transfer in the bidirectional GRU layer, then:

[0070] ;

[0071] In the formula, represents the feature state learned by the forward layer during the unidirectional transmission, is the feature state learned by the backward layer during the unidirectional transmission; and are the weights from the forward layer and the backward layer to the output layer in sequence; represents the bias vector added to the output layer; The training set is imported into the neural network model to obtain the parameters of the network model.

[0072] At time t, the input data xt contains 5 key parameter values at the current moment; Through the forward propagation process, the GRU layer models the past time series data; Through the backward propagation process, the change trend of future time series data is captured. The final output layer obtains the prediction result through linear combination; For example, for a certain sample, when inputting parameters such as the current light intensity of 900 W / m², the environmental temperature of 25°C, and the grid load of 80%, the model can predict that the optimal inverter power output should be 450kW, and the photovoltaic array angle should be adjusted to 32°.

[0073] The network structure of the prediction model is specifically set as follows: The input layer receives 5 key parameters as input features; The one-dimensional convolutional layer uses 64 convolutional kernels, the kernel size is 3, and the stride is 1; The pooling layer uses max pooling, and the pooling window size is 2; The bidirectional GRU layer contains 128 hidden units; The dropout rate of the Dropout layer is set to 0.3; The fully connected layer contains 64 neurons and uses the ReLU activation function; The output layer outputs two prediction values of power and angle; It can effectively capture the time series features and nonlinear relationships of the data.

[0074] During model training, the dataset is divided as follows: 70% training set, 15% validation set, 15% test set; The Adam optimizer is used, the initial learning rate is 0.001, and it decays by 10% every 50 epochs; The batch size is set to 64, and the maximum number of training epochs is 1000; The early stopping strategy is adopted, and training stops when the validation set loss has not improved for 10 consecutive epochs; L2 regularization (coefficient 0.0001) is used to suppress overfitting.

[0075] Compare the prediction results output by the prediction model of the photovoltaic power station system with the measured data in the test set, and use the goodness-of-fit index to describe the prediction performance of the model, , when , the model training stop condition is satisfied. At this time, the parameters of the model are the optimal parameters of the neural network model structure. If not satisfied, the deviation of the model is adjusted using the backpropagation algorithm and the loop continues.

[0076] The goodness-of-fit index is calculated as:

[0077] ; where represents the actual power output value of the th sample, is the predicted power output value corresponding to the th sample, is the average value of the power output; represents the actual photovoltaic array angle value of the th sample, is the predicted photovoltaic array angle value corresponding to the th sample, is the average value of the photovoltaic array angle; is the total number of samples; and are weight coefficients and satisfy , which is used to balance the importance of power output and angle prediction, and the preset value is: , .

[0078] The settings of the weight coefficients w1 and w2 take into account that the power output has a greater impact on the system efficiency, so a higher weight of 0.55 is given, while the weight of angle prediction is set to 0.45; when R²≥0.95, it indicates that the deviation between the model prediction result and the actual value is within an acceptable range; if the condition is not met, the Adam optimizer is used for backpropagation, the learning rate is set to 0.001, the batch size is 64, and the maximum number of iterations is 1000 times.

[0079] Step 3: Use the ITAE-optimized adaptive control algorithm for the photovoltaic power station system to optimize the proportional, integral, and derivative coefficients of the PID controller. Based on the established prediction model and the optimized PID controller, adjust the inverter power output and the photovoltaic array angle in real time.

[0080] During the tuning process of the PID controller parameters, first determine the initial parameter values according to the Ziegler-Nichols method, and then fine-tune them through the ITAE optimization algorithm; the PID parameters of the power control channel and the angle control channel are optimized independently, but the coupling relationship between the two is established through the ITAE index to achieve coordinated control.

[0081] Initial parameters of the PID controller: Power control channel: Kp1 = 0.5, Ti1 = 2.0 s, Td1 = 0.1 s; Angle control channel: Kp2 = 0.3, Ti2 = 5.0 s, Td2 = 0.2 s; ITAE optimization process: Set the simulation time st = 100 s, use the particle swarm optimization algorithm for optimization, population size 50, maximum number of iterations 100; Parameter search range: Kp1 ∈ [0.1, 1.0], Ti1 ∈ [1.0, 5.0], Td1 ∈ [0.05, 0.5]; Kp2 ∈ [0.1, 0.8], Ti2 ∈ [2.0, 8.0], Td2 ∈ [0.1, 0.8].

[0082] The control transfer function of the PID controller is:

[0083] ;

[0084] Where, is the inverter power output after taking the Laplace transform, is the Laplace transform value of the photovoltaic array angle, and are the Laplace transform values of the power deviation and angle deviation respectively, is the time variable; 、 and are the proportional, integral and differential coefficients of the PID controller in the power control channel respectively, , , ; Where, is the relative deviation of the inverter power output, is the relative deviation of the stroke of the PID controller in the power control channel; 、 and are the proportional, integral and differential coefficients of the PID controller in the angle control channel respectively; , , ; Where, is the relative angle control deviation, is the relative deviation of the stroke of the PID controller in the angle control channel.

[0085] Select index as the fitness function of the optimization algorithm , where, is the simulation time.

[0086] Compare the system states at the previous moment S - 1 and the current moment S to calculate and compare the ITAE index values. The ITAE index value at the previous moment is denoted as , and the ITAE index value at the current moment is denoted as 。

[0087] When ITAE(S - 1) ≥ ITAE(S), it indicates that the system performance is improving. At this time, keep the current PID controller parameters unchanged; according to the relative deviation of the controlled variables of the power and angle channels and the relative deviation of the PID controller stroke at the current moment; adjust the power output of the inverter and the angle of the photovoltaic array to make it reach the preset power output given by the prediction model and the preset angle of the photovoltaic array 。

[0088] When ITAE(S - 1) < ITAE(S), it indicates that the system performance is deteriorating. At this time, restore the relative deviation of the controlled variables of the power and angle channels and the relative deviation of the PID controller stroke to the values of the previous moment, recalculate the PID controller parameters; adjust the power output of the inverter and the angle of the photovoltaic array to make it reach the preset power output given by the prediction model and the preset angle of the photovoltaic array 。

[0089] Taking a 100MW photovoltaic power station as an example, after adopting the remote intelligent management and control method of the present invention, under typical sunny conditions, the power generation efficiency of the power station has increased by 3.2%; when there is a sudden change in light intensity (such as suddenly dropping from 1000 W / m² to 600 W / m²), the system can complete power regulation within 2 seconds, and the response time is shortened by 60% compared with the traditional fixed - parameter PID control; at the same time, the average power prediction error within 24 hours a day is reduced to 3.5%, which is significantly improved compared with 7.8% of the traditional method; this shows that the present invention can effectively improve the operation efficiency and control performance of the photovoltaic power station.

[0090] The method further includes the following steps:

[0091] Step 4, as the operation data accumulates continuously, regularly update the prediction model parameters and PID controller parameters; the frequency of the regular update is maintained at 15 - 30 days.

[0092] For example: select to update the system parameters once every 20 days; the update process is carried out during the low - load period in the early morning. Update the neural network model parameters through incremental learning, and at the same time re - optimize the PID controller parameters based on the latest operation data; this regular update mechanism ensures that the system can adapt to the influence brought by seasonal changes and equipment performance degradation.

[0093] Embodiment 2

[0094] Such as Figure 2As shown in the figure, it is a schematic diagram of the composition of a remote intelligent management and control system for a photovoltaic power station according to the present invention. The system includes, connected in sequence: a data acquisition module, a data processing module, and a parameter adjustment module; data interaction between the system modules is carried out through an industrial Ethernet, and the TCP / IP protocol stack is adopted to ensure the real-time performance and reliability of data transmission.

[0095] The data acquisition module is used to collect historical operation data of key parameters of the photovoltaic power station system. The key parameters include: inverter power output, photovoltaic array angle, light intensity, ambient temperature, and grid load.

[0096] The data acquisition module adopts a hierarchical distributed architecture. Multiple data acquisition units are deployed at the field layer to collect historical operation data of key parameters of the photovoltaic power station system; for power data acquisition, a 0.5S-class high-precision intelligent electricity meter is used, with a sampling frequency of 1Hz and a measurement range of 0 - 120% of the rated power, and data is transmitted through an RS485 interface; for angle data acquisition, a high-precision encoder with a resolution of 0.1° is used, with a measurement range of 0 - 90°, and has a temperature compensation function; for light intensity acquisition, 12 distributed illuminometers are used, with an accuracy of ±1% and a range of 0 - 2000W / m² to form a spatial distribution map of light intensity; for ambient temperature acquisition, a PT100 temperature sensor (accuracy ±0.1°C) and an infrared thermometer are configured to comprehensively monitor the ambient temperature and the surface temperature of components; grid load data communicates with the grid dispatching system in real time through the standard IEC 60870-5-104 protocol.

[0097] The data processing module is used to establish a prediction model of the photovoltaic power station system based on a neural network, and give the inverter power setting and the optimal angle of the photovoltaic array under the current light and load responses according to the prediction model.

[0098] The data processing module is built based on an industrial-grade server, configured with a dual-core Intel Xeon processor and 32GB of memory, and adopts a real-time operating system to perform the following functions: for data preprocessing, a mean filtering algorithm is used to remove data noise, the window size is configurable (5 - 9 points), outlier detection and processing are carried out based on the 3σ principle, and data normalization processing is performed to uniformly map various types of data to the [0,1] interval; for the operation of the neural network model, the model framework is implemented using PyTorch, supports GPU accelerated computing, the real-time calculation response time < 100ms, and the model parameters are updated regularly (15 - 30 days); the output prediction power resolution is 0.1kW, and the prediction angle resolution is 0.1°.

[0099] The parameter adjustment module is used to optimize the proportional, integral, and differential coefficients of the PID controller by using an adaptive control algorithm for the photovoltaic power station system optimized by ITAE. Based on the established prediction model and the optimized PID controller, the inverter power output and the photovoltaic array angle are adjusted in real time.

[0100] The parameter adjustment module is implemented by a real-time controller with a configurable control period, and the typical setting is 100 ms. The self-tuning range of PID parameters is reasonably designed. The parameter ranges of the power control channel are: Kp1 (0.1 - 1.0), Ti1 (1.0 - 5.0 s), Td1 (0.05 - 0.5 s); the parameter ranges of the angle control channel are: Kp2 (0.1 - 0.8), Ti2 (2.0 - 8.0 s), Td2 (0.1 - 0.8 s). The control accuracy requirements are strict, with the power control accuracy reaching ±0.5% and the angle control accuracy reaching ±0.2°. The system responds quickly, with the power regulation response time less than 2 s and the angle regulation response time less than 5 s, meeting the requirements of rapid regulation of the power station.

[0101] The system further includes:

[0102] A remote communication unit for realizing remote transmission of system data, remote monitoring of system status, and remote alarm for abnormal situations; the remote communication unit adopts a redundant design, supports multiple interfaces such as 4G / 5G wireless communication, Gigabit Ethernet, and fiber optic communication, and the communication protocol covers mainstream industrial protocols such as Modbus TCP / IP and IEC 60870-5-104, and supports encrypted data transmission. The communication performance is excellent, with the data transmission delay controlled within 100 ms and the system reliability exceeding 99.99%. This unit has functions such as remote parameter configuration, remote program update, and remote fault diagnosis, providing strong support for the remote operation and maintenance of the system.

[0103] A data storage unit for storing historical operation data of the photovoltaic power station system, neural network model parameters, and PID controller parameters; the data storage unit adopts a distributed storage architecture, with 256 GB SSD configured locally for data caching and the remote database capacity of 10 TB. The stored content includes real-time operation data, historical trend data, alarm event records, and model parameter backups, etc. This unit realizes automatic data backup, data compression storage, and hierarchical storage strategy, uses RAID5 disk array to ensure data security, and at the same time implements strict data encryption storage and access permission control mechanisms.

[0104] A human-machine interaction unit, including a display module and a control module; among them, the display module is used to display the power generation power, array angle, environmental data, and system operation status of the photovoltaic power station in real time; the control module is used to receive control instructions from the operator and adjust the system operation parameters.

[0105] The human-machine interaction unit is designed with a B / S architecture. The display module supports functions such as multi-screen real-time display, trend curve analysis, automatic report generation, and 3D visualization display; the control module realizes functions such as online parameter adjustment, operation mode switching, remote operation authorization, and emergency control. The system interface supports multi-resolution adaptation and mobile access, and provides a multi-language switching function. The operation permissions adopt a hierarchical management method, support the traceability of operation records, and implement a confirmation mechanism for key operations.

[0106] The monitoring and execution unit is used to monitor the key parameters of the system at a preset frequency and perform exception handling. The monitoring frequency is not less than once every 5 minutes; when an abnormality is detected, an alarm message is sent to the remote communication unit.

[0107] The monitoring and execution unit has perfect real-time monitoring and fault handling capabilities. The monitoring functions include equipment operation status monitoring, performance index calculation, fault early warning analysis, and system diagnosis and evaluation; the execution functions cover automatic regulation control, fault protection actions, emergency handling responses, and optimization control execution. The system sets the monitoring frequency according to different time scales: general parameters once every 5 minutes, key parameters once every 10 seconds, and protection parameters once every 100 ms. The exception handling mechanism adopts a four-level alarm system to realize functions such as automatic fault isolation, standby plan switching, and automatic fault recovery.

[0108] The overall performance indicators of the system are excellent. The screen refresh time is less than 1 s, the control response time is less than 2 s, and the alarm response time is less than 1 s. The annual operation reliability of the system exceeds 99.9%, and the average trouble-free operation time exceeds 5000 hours. The system has good scalability, supports capacity expansion, function upgrade, and interface expansion; the economic benefits are remarkable, and it can achieve a 3-5% increase in power generation efficiency and a 30% reduction in operation and maintenance costs.

[0109] The specific implementation manners described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only the specific implementation manners of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A remote intelligent control method for a photovoltaic power station, used to improve the power generation efficiency and operation and maintenance management level of the photovoltaic power station, wherein the photovoltaic power station uses a PID controller to control the inverter power output and the photovoltaic array angle to achieve matching adjustment of the power output of the photovoltaic power station with the grid load; characterized in that: The method comprises the following steps: Step 1, collecting historical operating data of key parameters of the photovoltaic power station system, wherein the key parameters include: inverter power output, photovoltaic array angle, light intensity, ambient temperature and grid load; Step 2, establishing a prediction model of the photovoltaic power station system based on a neural network, and providing the inverter power setting and the optimal angle of the photovoltaic array under the current light and load response according to the prediction model; The prediction model consists of an input layer, a one-dimensional convolutional layer, a pooling layer, a bidirectional memory loop layer, a Dropout layer, a fully connected layer and an output layer connected in sequence; The one-dimensional convolution layer extracts the time series characteristics of the historical operation data of the photovoltaic power station, including the periodic change characteristics of the light intensity and the ambient temperature and the dynamic change characteristics of the grid load; the pooling layer simplifies the data dimension after the one-dimensional convolution and passes the data to the bidirectional memory loop layer; the bidirectional memory loop layer uses the bidirectional GRU to model the long-term and short-term dynamic characteristics of the photovoltaic power generation system, extracts the time series correlation characteristics of the power output and the photovoltaic array angle adjustment, and performs nonlinear transformation to determine the intrinsic logical relationship between the light, temperature, load input and the inverter power output and the photovoltaic array angle; After the data is subjected to secondary feature extraction by the bidirectional memory loop layer, some nodes of the data are randomly discarded in the Dropout layer to prevent overfitting and the processed data is passed to the fully connected layer. The fully connected layer maps the output features to the label space of the sample through nonlinear combination, and the output layer outputs the preset power output adapted to the current state of the photovoltaic power station through linear regression operation. and preset PV array angle The predicted value of The historical operation data is divided into a training set and a feature set. time, use represents the state of the input layer, represents the output layer state, represents the hidden layer state during the bidirectional GRU layer transmission process, then: ； In the formula, Represents the feature state learned by the forward layer during one-way transmission. It is the feature state learned by the backward layer during the one-way transmission process; and It is the weight of the forward layer, the backward layer and the output layer in sequence; represents the bias vector added in the output layer; importing the training set into the neural network model to obtain the parameters of the network model; Step 3: Use the ITAE optimized photovoltaic power station system adaptive control algorithm to optimize the proportional, integral and differential coefficients of the PID controller, and adjust the inverter power output and photovoltaic array angle in real time based on the established prediction model and the optimized PID controller; The control transfer function of the PID controller is: ； in, is the inverter power output after Laplace transformation, is the Laplace transform value of the PV array angle, and are the Laplace transform values ​​of power deviation and angle deviation respectively, is the time variable; , and are the proportional, integral and differential coefficients of the power control channel PID controller, , , ;in, is the relative deviation of inverter power output, It is the relative deviation of the PID controller stroke of the power control channel; , and They are the proportional, integral and differential coefficients of the PID controller of the angle control channel respectively; , , ;in, To control the relative deviation for the angle, It is the relative deviation of the PID controller stroke of the angle control channel; choose The indicator is used as the fitness function of the optimization algorithm , where is the simulation time; Compare the system status at the previous moment S-1 and the current moment S to calculate the ITAE index value and compare them. The ITAE index value at the previous moment is recorded as , the ITAE index value at the current moment is recorded as ; When ITAE(S-1)≥ITAE(S), it indicates that the system performance is improving. At this time, keep the current PID controller parameters unchanged; according to the relative deviation of the controlled parameters of the power and angle channels at the current moment and the relative deviation of the PID controller stroke; adjust the inverter power output and the PV array angle to achieve the preset power output given by the prediction model. and preset PV array angle ; When ITAE(S - 1) < ITAE(S), it indicates that the system performance is deteriorating. At this time, the relative deviation of the controlled parameters of the power and angle channels and the relative deviation of the PID controller stroke are restored to the values of the previous moment, and the PID controller parameters are recalculated; the inverter power output and the photovoltaic array angle are adjusted to reach the preset power output given by the prediction model and the preset photovoltaic array angle .

2. A photovoltaic power station remote intelligent management and control method according to claim 1, characterized in that: The prediction results output by the prediction model of the photovoltaic power station system are compared with the measured data in the test set, and the fit index is used To describe the predictive performance of the model, ,when When , the model training stop condition is met. At this time, the model parameters are the optimal parameters of the neural network model structure. If not, the back propagation algorithm is used to adjust the model deviation and continue the cycle; Goodness of fit index The calculation formula is: ; In the formula, Representative The actual power output value of the samples, For the The power output prediction value corresponding to the samples is: is the average value of power output; Representative The actual PV array angle value of samples, For the The predicted value of the photovoltaic array angle corresponding to the sample, is the average value of the photovoltaic array angle; is the total number of samples; and is the weight coefficient and satisfies , used to balance the importance of power output and angle prediction, the default value is: , .

3. A photovoltaic power station remote intelligent management and control method according to claim 1, characterized in that: The method further comprises the following steps: Step 4: As the operation data continues to accumulate, the prediction model parameters and PID controller parameters are regularly updated; The frequency of regular updates is maintained at 15 to 30 days.

4. A photovoltaic power station remote intelligent management and control method according to claim 1, characterized in that: The step 1 also includes preprocessing the historical operation data by a mean filtering method to remove noise and outliers; for each point in the historical operation data, the average value of the point and the two points before and after it is taken as the output; The method of mean filtering is specifically as follows: in is the number of points in the filter window, N=5, the original value The first The value of a point.

5. A remote intelligent management and control system for a photovoltaic power station, used to execute the method described in any one of claims 1 to 4, characterized in that: The system comprises: a data acquisition module, a data processing module and a parameter adjustment module connected in sequence; The data acquisition module is used to collect historical operating data of key parameters of the photovoltaic power station system, and the key parameters include: inverter power output, photovoltaic array angle, light intensity, ambient temperature and grid load; The data processing module is used to establish a prediction model of the photovoltaic power station system based on a neural network, and to provide the inverter power setting and the optimal angle of the photovoltaic array under the current light and load response according to the prediction model; The parameter adjustment module is used to optimize the proportional, integral and differential coefficients of the PID controller using the ITAE optimized photovoltaic power station system adaptive control algorithm, and to adjust the inverter power output and photovoltaic array angle in real time based on the established prediction model and the optimized PID controller.

6. A photovoltaic power station remote intelligent management and control system according to claim 5, characterized in that: The system further comprises: Remote communication unit, used to achieve remote transmission of system data, remote monitoring of system status, and remote alarm of abnormal situations; A data storage unit, used to store historical operation data of the photovoltaic power station system, neural network model parameters and PID controller parameters; The human-computer interaction unit includes a display module and a control module; wherein the display module is used to display the power generation, array angle, environmental data and system operation status of the photovoltaic power station in real time; and the control module is used to receive the operator's control instructions and adjust the system operation parameters; The monitoring execution unit is used to monitor the key parameters of the system and perform exception processing at a preset frequency, and the monitoring frequency shall not be less than once every 5 minutes; when an abnormality is detected, an alarm message is sent to the remote communication unit.

Images