Power grid line loss rate PINN real-time prediction method and system based on PDE dynamic following

Abstract

The invention provides a PDE dynamic following power grid line loss rate PINN real-time prediction method and system, and the method comprises the steps: constructing a power grid PINN line loss rate prediction model which comprises a BiGRU model and a dynamic PDE model, dividing the historical data of a power grid into a long-term data set, a short-term data set and a real-time data set, inputting the long-term data set into the prediction model for training, and carrying out the training of the short-term data set; the method comprises the following steps: training a BiGRU model to determine a network parameter of the BiGRU model, a weight ratio of a loss function and an initial value of a dynamic key parameter in a dynamic PDE model, inputting a recent data set into a trained prediction model to obtain a loss function output value, if the output value is greater than an inspection value, optimizing and updating the dynamic key parameter, and if the output value is greater than the inspection value, updating the dynamic key parameter. And finally, inputting the real-time data set into the updated prediction model to obtain a power grid line loss rate prediction result. According to the method, the PINN dynamically follows the change of the power grid through the investigation-update function of the PDE model, so that the real-time prediction precision of the line loss rate is greatly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid control, and in particular relates to a method and system for real-time prediction of power grid line loss rate PINN with PDE dynamic following. Background Art

[0002] Grid line loss refers to the energy loss generated in the transmission, transformation, and distribution of electricity during the transmission of electricity in the grid. The ratio of line loss to total input electricity is usually defined as line loss rate. Line loss rate is a key indicator for measuring the operation quality, management level, and economic benefits of power grids. With the rapid development of my country's social economy, residential and industrial electricity consumption is increasing day by day. At present, the line loss of low-voltage distribution networks accounts for about 40% of the total power grid loss, resulting in a decline in the economic efficiency of grid operation. Therefore, reducing the line loss rate of the power grid can effectively achieve low-carbon emission reduction, energy saving and loss reduction.

[0003] Accurately predicting the line loss rate of the power grid can provide data support in the event of a measurement failure in the power grid. It can also reversely verify the credibility and accuracy of the measurement system data and promptly detect abnormal measurement values ​​and faulty measurement devices. The predicted line loss rate data can estimate the changes in the line loss of the power grid in the future, and provide auxiliary indicators for the technical transformation of the power grid, the adjustment of the operation mode, and the implementation of energy-saving and loss-reduction measures. The prediction results of the power grid line loss rate can also assist the planning and design of the power system and the reconstruction of the network, which has important guiding significance for the energy saving and loss reduction, structural optimization, and improvement of the economic benefits of the power grid.

[0004] Since the line loss of the power grid is affected by many characteristics, such as input power, output power, line length, temperature, load size, and power grid operation mode, etc. Using the traditional power balance method, the line loss rate is only predicted by the changes in input power and output power, which makes it difficult to accurately predict the line loss rate of a complex power grid. The empirical formula method can infer the future line loss rate based on the previous load rate-line loss rate relationship. However, in the modern society where the power grid is rapidly updated, this method is difficult to make an accurate estimate of the future line loss rate. Through the artificial intelligence neural network, historical line loss data, load data, meteorological data and many other factors are used as input neurons, and the trained neural network model can predict the future line loss rate.

[0005] In order to further improve the prediction accuracy of the neural network model for line loss rate and enhance the ability of the neural network model to process time series data, a recurrent unit can usually be introduced to form a recurrent neural network (RNN). Common ones include bidirectional recurrent neural networks (Bidirectional RNN, Bi-RNN) and long short-term memory networks (Long Short-Term Memory networks, LSTM). The Chinese patent document with publication number CN110659779 B discloses a distribution system network loss prediction method based on long short-term memory networks. The Chinese patent document with publication number CN 110598854 A discloses a substation line loss rate prediction method based on the GRU model. This shows that the use of the RNN model can be used to predict the line loss rate of the power grid.

[0006] These methods are all based on pure data-driven neural network prediction methods, which are highly dependent on the quantity and accuracy of historical data. When predicting the line loss rate of the power grid, they are prone to overfitting problems. Using historical data to predict future line loss rates can only be used in long-term fixed power grids. These pure data-driven neural network prediction methods have poor generalization capabilities and cannot predict the impact of changes in the power grid structure on future line loss rates, making it difficult to provide reference prediction data for power grid modification.

[0007] In other prediction fields, physical information model neural networks (PINNs) can usually be used to improve the poor generalization ability of pure data-driven neural network prediction methods and reduce dependence on data. However, the circuit topology of the power grid is very complex, and it is difficult to establish a suitable physical model, which is a problem faced by PINN in the field of power grid line loss rate prediction. Secondly, in the traditional PINN prediction field, it is assumed that the physical process or physical model will not change, but the power grid topology is constantly changing. New lines, line network changes, and line aging will cause significant changes in the physical properties and structure of the power grid. Therefore, when using the existing PINN for real-time prediction of power grid line loss rate, it is impossible to accurately describe the physical properties and structure of the current power grid, which will lead to serious lack of accuracy in real-time prediction. It is impossible to provide timely and effective reference data for power grid transactions. Summary of the invention

[0008] The purpose of the present invention is to provide a method and system for real-time prediction of power grid line loss rate PINN with dynamic following of PDE in view of the above-mentioned problems existing in the prior art.

[0009] To achieve the above objectives, the technical solution of the present invention is as follows:

[0010] In a first aspect, the present invention proposes a real-time prediction method for a power line loss rate PINN with dynamic PDE following, comprising:

[0011] S1. Build a power grid PINN line loss rate prediction model including BiGRU model and dynamic PDE model; obtain historical data of the power grid, and divide the historical data into long-term data set, short-term data set and real-time data set according to N days ago, 1-N days and within 1 day respectively;

[0012] S2. Input the long-term data set into the constructed prediction model for training to determine the network parameters of the BiGRU model, the weight ratio parameters of the loss function, and the initial values ​​of the dynamic key parameters in the dynamic PDE model;

[0013] S3, input the recent data set into the trained prediction model to obtain the output value m of the loss function;

[0014] S4, compare the output value m with its observation value m0, if m>m0, optimize the dynamic key parameters in the dynamic PDE model until m≤m0, and enter S5 after updating the dynamic key parameters; if m≤m0, directly enter S5;

[0015] S5. Input the real-time data set into the updated prediction model to obtain the power grid line loss rate prediction result.

[0016] In S1, the dynamic PDE model is:

[0017]

[0018]

[0019]

[0020] In the above formula, L (l，t) , C (l，t) , R ( l ，t) , G (l，t) are dynamic key parameters, representing distributed inductance, distributed capacitance, distributed resistance and distributed conductance respectively. l and t are the total length and time of the power grid line respectively. I and U are the current and voltage respectively.

[0021] The S2 includes:

[0022] S21, using algorithms to optimize the network parameters of the BiGRU model;

[0023] S22, based on the BiGRU model optimized by the algorithm, the weight ratio parameter of the loss function is adjusted with the goal of minimizing the loss function, where the loss function for:

[0024]

[0025]

[0026]

[0027]

[0028] In the above formula, are prediction error, physical error, and λ data , PDE are the predicted weight ratio and physical weight ratio respectively, μ^ is the true value of the power grid line loss rate, μ d is the line loss rate prediction value of the BiGRU model, μ p is the line loss rate value calculated by physical formula, t0, t x are the start and end time respectively, U0 and I0 are the voltage and current at the grid end respectively, U l ,I l They are the voltage and current at the outgoing network end respectively;

[0029] S23, based on the BiGRU model after the weight ratio parameter is adjusted, the dynamic key parameters in the dynamic PDE model are adjusted with the goal of minimizing the loss function to obtain the initial values ​​of the dynamic key parameters;

[0030] S24, determine whether the loss function has reached the minimum, if not, return to S22 to optimize the network parameters again until the loss function is minimized.

[0031] In S3, the output value m is calculated according to the following formula:

[0032]

[0033] In the above formula, λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the recent data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and n is the number of data points in the recent data set;

[0034] In S4, the investigation value m0 is calculated according to the following formula:

[0035]

[0036] In the above formula, δ is the tolerance factor with a value range of [0, 2], λ data , PED are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the long-term data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and k is the number of data points in the long-term data set.

[0037] The S21 uses a Bayesian optimization algorithm to optimize the network parameters of the BiGRU model, including the number of hidden units, the maximum number of training rounds, the initial learning rate, the L2 regularization parameter, the gradient threshold, the Dropout rate, and the learning rate adjustment factor;

[0038] The S4 uses a particle swarm optimization algorithm to optimize dynamic key parameters in the dynamic PDE model.

[0039] In the second aspect, the present invention proposes a PDE dynamic following power grid line loss rate PINN real-time prediction system, including a prediction model construction module, a data partitioning module, a prediction model training module, a prediction model inspection module, a dynamic parameter update module, and a real-time prediction module;

[0040] The prediction model building module is used to build a power grid PINN line loss rate prediction model including a BiGRU model and a dynamic PDE model;

[0041] The data partitioning module is used to obtain historical data of the power grid, and to divide the historical data into a long-term data set, a short-term data set and a real-time data set according to N days ago, 1-N days and within 1 day respectively;

[0042] The prediction model training module is used to input the long-term data set into the constructed prediction model for training to determine the network parameters of the BiGRU model, the weight ratio parameters of the loss function, and the initial values ​​of the dynamic key parameters in the dynamic PDE model;

[0043] The prediction model inspection module is used to input the recent data set into the trained prediction model, obtain the output value m of the loss function, and compare the output value m with the inspection value m0. If m>m0, the dynamic parameter update module is started;

[0044] The dynamic parameter updating module is used to optimize the dynamic key parameters in the dynamic PDE model until m≤m0, and update the dynamic key parameters;

[0045] The real-time prediction module is used to input the real-time data set into the updated prediction model to obtain the power grid line loss rate prediction result.

[0046] The prediction model building module is used to build the following dynamic PDE model:

[0047]

[0048]

[0049]

[0050] In the above formula, L (l，t) , C (l，t) , R (l，t) , G (l，t) are dynamic key parameters, representing distributed inductance, distributed capacitance, distributed resistance and distributed conductance respectively. l and t are the total length and time of the power grid line respectively. I and U are the current and voltage respectively.

[0051] The prediction model training module includes a network parameter optimization unit, a weight ratio parameter adjustment unit, a dynamic key parameter adjustment unit, and a judgment unit;

[0052] The network parameter optimization unit is used to optimize the network parameters of the BiGRU model using an algorithm;

[0053] The weight ratio parameter adjustment unit is used to adjust the weight ratio parameter of the loss function based on the BiGRU model optimized by the algorithm with the goal of minimizing the loss function, wherein the loss function for:

[0054]

[0055]

[0056]

[0057]

[0058] In the above formula, are prediction error, physical error, and λ data , PDE are the predicted weight ratio and physical weight ratio respectively, μ^ is the true value of the power grid line loss rate, μ d is the line loss rate prediction value of the BiGRU model, μ p is the line loss rate value calculated by physical formula, t0, t x are the start and end time respectively, U0 and I0 are the voltage and current at the grid end respectively, U l ,I l They are the voltage and current at the outgoing network end respectively;

[0059] The dynamic key parameter adjustment unit is used to adjust the dynamic key parameters in the dynamic PDE model based on the BiGRU model after the weight ratio parameter is adjusted, with the loss function as the minimum, to obtain the initial value of the dynamic key parameter;

[0060] The judgment unit is used to judge whether the loss function has reached the minimum. If not, the network parameter optimization unit is started to optimize the network parameters again until the loss function is minimized.

[0061] The prediction model inspection module calculates the output value m according to the following formula

[0062]

[0063] In the above formula, λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the recent data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and n is the number of data points in the recent data set;

[0064] The investigation value m0 is calculated according to the following formula:

[0065]

[0066] In the above formula, δ is the tolerance factor with a value range of [0, 2], λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the long-term data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and k is the number of data points in the long-term data set.

[0067] The network parameter optimization unit uses a Bayesian optimization algorithm to optimize the network parameters of the BiGRU model, including the number of hidden units, the maximum number of training rounds, the initial learning rate, the L2 regularization parameter, the gradient threshold, the Dropout rate, and the learning rate adjustment factor;

[0068] The dynamic parameter updating module uses a particle swarm optimization algorithm to optimize the dynamic key parameters in the dynamic PDE model.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] The present invention discloses a PINN real-time prediction method for power line loss rate with dynamic PDE following, firstly constructs a power line loss rate prediction model including a BiGRU model and a dynamic PDE model, obtains historical data of the power grid, and divides the historical data into a long-term data set, a short-term data set and a real-time data set according to N days ago, 1-N days and within 1 day, respectively. Then, the long-term data set is input into the constructed prediction model for training to determine the network parameters of the BiGRU model, the weight ratio parameters of the loss function and the initial values ​​of the dynamic key parameters in the dynamic PDE model. Then, the short-term data set is input into the trained prediction model to obtain the output value m of the loss function, and the output value m is compared with the observation value m0. If m>m0, the dynamic key parameters in the dynamic PDE model are optimized until m≤m0, and the dynamic key parameters are updated. Finally, the real-time data set is input into the updated prediction model to obtain the prediction result of the power line loss rate. This method introduces a dynamic PDE model with adjustable key parameters, establishes a dynamic update mode of the PDE model, and realizes the inspection-update function of the PDE model. On the one hand, this inspection-update function helps the PINN neural network to dynamically follow the latest changes in the power grid, thereby greatly improving the accuracy of real-time prediction of the power grid line loss rate; on the other hand, the PDE model update step will only be started when the power grid structure has undergone major changes and exceeded the inspection value, avoiding the PINN model from calculating and iterating the network structure, loss function weights and key parameters every time it runs, greatly saving the computing power of the intelligent server; at the same time, this method can be used for real-time changes in line loss rate after power grid transformation, providing timely effect evaluation for power grid transformation, without waiting for the power grid to run for a long time again and obtaining a large amount of data before conducting data analysis and effect evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a flowchart of the method described in Example 1.

[0072] Figure 2 This is a schematic diagram of the 10kV distribution circuit structure in Example 1.

[0073] Figure 3 Schematic diagram of the BiGRU model in Example 1.

[0074] Figure 4 This is a flow chart of the Bayesian optimization algorithm in Example 1.

[0075] Figure 5 Schematic diagram of forecast error on weekdays.

[0076] Figure 6 Schematic diagram of forecast error on non-working days.

[0077] Figure 7 The structure diagram of the system of the present invention is shown in FIG. DETAILED DESCRIPTION

[0078] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0079] Embodiment 1:

[0080] This embodiment takes the actual 10kV distribution circuit structure of a township power grid area (including a 110 / 10kV substation with a capacity of 2*100MVA, a total of 39 substations in the planning area, including 58 10kV lines) as the research object, and implements the power grid line loss rate PINN real-time prediction method with PDE dynamic following described in the present invention, such as Figure 1 As shown, the specific steps are as follows:

[0081] 1. Collect the power grid's input and sales data, and conduct 24-hour forecast sampling of the power distribution network's losses, input voltage U0, and input current I0. The data sampling frequency is once every 20 minutes, and there are 72 sampling points for 24 hours. Obtain one year of historical data, and divide the data before 30 days into long-term data sets, the data within 1 day to 30 days into short-term data sets, and the data within 1 day into real-time data sets.

[0082] 2. Preprocess the above data, including supplementing blank values, correcting abnormal data, normalizing data, and constructing the time series of corresponding feature quantities. The missing value processing formula is:

[0083]

[0084] In the above formula, D(X) is the missing value, n is the length of the missing time series data, and Y i is the function value of the known data point, L i (x) is the Lagrangian basis function;

[0085] In order to avoid the problem of large numerical differences, the Min-Max Normalization method is used to normalize the input power and sales power data and construct the time series of the corresponding characteristic quantities.

[0086] 3. Construct a PINN line loss rate prediction model for the power grid, including:

[0087] 1) Use the Tensorflow library to build a BiGRU model in Python, such as Figure 2 As shown. This model sets 4 layers of BiGRU with 128 units. In the initial Bi-GRU network model, the output information at a certain time t is the sum of the outputs of the forward hidden layer and the backward hidden layer. The specific calculation formula is as follows:

[0088]

[0089] In the above formula, GRU(·) is a gated recurrent unit, are the outputs of the forward and backward hidden layers respectively, is the hidden state of the forward hidden state at the previous moment, is the hidden state of the backward hidden state at the next moment, w t 、v t are the weights corresponding to the forward hidden layer state and the backward hidden layer state of Bi-GRU at time t, respectively. t is the bias value corresponding to the hidden layer state at time t.

[0090] 2) Constructing a dynamic PDE model

[0091] In the power grid distribution system, the number of transmission lines is huge, the connection method is very complex, and the number of components such as transformers is difficult to estimate. In order to simplify the physical structure of the power grid, this embodiment simplifies the influence of these factors on the power distribution network transmission line into the influence of unit inductance, resistance, capacitance and conductance on a transmission line with a length of l, that is, the power grid transmission line circuit is simplified to a single transmission line circuit. The following dynamic PDE model is obtained:

[0092]

[0093]

[0094]

[0095] In the above formula, L (l，t) , C (l，t) , R (l，t) , G (l，t) are dynamic key parameters, representing distributed inductance, distributed capacitance, distributed resistance and distributed conductance respectively, which are functions that change with the total length of the grid line l (determined according to the total length of the township power grid) and time t. I and U are current and voltage respectively.

[0096] The BiGRU model and the dynamic PDE model constitute the power grid PINN line loss rate prediction model.

[0097] 4. The Bayesian optimization algorithm (BO algorithm) is used to optimize the network parameters of the BiGRU model, including the number of hidden units, the maximum number of training rounds, the initial learning rate, the L2 regularization parameter, the gradient threshold, the Dropout rate, and the learning rate adjustment factor.

[0098] The BO algorithm maximizes or minimizes a black box objective function based on probability models such as Bayesian theorem and Gaussian process. It gradually converges to the global optimal solution by continuously selecting the next sampling point in the search space and then estimating the optimal value of the function based on the existing sampling data. Its expression is:

[0099]

[0100] In the above formula, f(h) is the prior distribution model, h * is the optimal parameter value of the constraint domain of f(h), and H is the candidate set.

[0101] Compared with grid search and random search, the Bayesian optimization algorithm can achieve satisfactory optimization results with fewer iterations. The specific workflow of the BO algorithm is as follows: Figure 3 shown.

[0102] The optimized network parameters in this embodiment are: the number of neurons in the hidden layer is 30, the time window size is 50, the learning rate is 0.001, and the drop rate is 0.1.

[0103] 5. Based on the BiGRU model optimized by the BO algorithm, the weight ratio parameter of the loss function is adjusted with the goal of minimizing the loss function. The loss function for:

[0104]

[0105]

[0106]

[0107]

[0108] μ^=(W in -W out ) / W in

[0109] In the above formula, are prediction error, physical error, and λ data , PDE are the predicted weight ratio and physical weight ratio respectively, μ^ is the true value of the power grid line loss rate, μ d is the line loss rate prediction value of the BiGRU model, μ p is the line loss rate value calculated by physical formula, t0, t x are the start and end time respectively, U0 and I0 are the voltage and current at the grid end respectively, U l ,I l are the voltage and current at the outgoing network end, W in , W outThey are respectively the input electricity and the sold electricity.

[0110] The adjusted weight ratio parameter obtained in this embodiment is: data =0.7,λ PDE =0.3.

[0111] 6. Based on the BiGRU model after the weight ratio parameters are adjusted, the dynamic key parameters in the dynamic PDE model are adjusted with the goal of minimizing the loss function to obtain the initial values ​​of the dynamic key parameters.

[0112] The initial value of the dynamic key parameter obtained in this embodiment is: L (l，t) =10mH / km, C (l，t) =600nF / km, R (l，t) =2Ω / km, G (l，t) =10 -6 S / km.

[0113] 7. Determine whether the loss function has reached the minimum. If not, return to step 4 and optimize the network parameters again until the loss function is minimized.

[0114] 8. Enter the PDE equation dynamic update module, input the recent data set into the trained prediction model, and calculate the output value m of the loss function according to the following formula, where the formula is as follows:

[0115]

[0116] In the above formula, λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the recent data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and n is the number of data points in the recent data set;

[0117] The output value m obtained in this embodiment is 0.82.

[0118] 9. Calculate the inspection value m0 according to the following formula:

[0119]

[0120] In the above formula, δ is a tolerance factor in the range of [0, 2], which represents the tolerance degree of the output value m, and λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the long-term data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and k is the number of data points in the long-term data set.

[0121] The investigated value m0 obtained in this embodiment is 0.5.

[0122] 10. Compare the output value m with its observation value m0. If m≤m0, it means that the dynamic key parameters set based on the long-term data set still meet the expectations for the boundary restriction effect on the recent data set, and the aforementioned prediction model can be directly used for real-time prediction; if m>m0, it means that the dynamic key parameters set based on the long-term data set cannot meet the expectations for the boundary restriction effect on the recent data set, that is, the recent changes in the power grid make the PDE model no longer able to accurately reflect the physical information of the current power grid, and the dynamic key parameters need to be reset. At this time, the particle swarm optimization algorithm is used to optimize the dynamic key parameters in the dynamic PDE model until m≤m0, and update the dynamic key parameters.

[0123] The goal of Particle Swarm Optimization (PSO) is to find the global optimal solution of the fitness function in D-dimensional space, that is, the optimal parameter combination. The position x and velocity v of each particle in the particle swarm describe its behavior in space. The position of the particle is a 4-dimensional vector,

[0124] x={x1,x2,x3,x4}={L (l，t) , C (l，t) , R (l，t) , G (l，t)}

[0125] During the search process, the particle swarm tracks the local optimal solution P best and the global optimal solution G best , update the position x and velocity v. Its expression is:

[0126] v i (t+1)=ω×v i (t)+c1×r1×(P best_id -x i (t))+c2×r2×(G best_id -x i (t))

[0127] x i (t+1=x i (t)+v i (t+1)

[0128] In the above formula, x i (t), v i (t) are the current position and current speed, respectively, P best_idis the local optimal solution of the i-th particle, G best_id is the global optimal solution of the i-th particle, c1 and c2 are acceleration constants, r1 and r2 are random numbers, and ω is the inertia weight, which affects the convergence of the PSO algorithm. The larger the ω value, the weaker the particle's local optimization ability and the stronger the global search ability, and vice versa. Therefore, the ω value is set larger at the beginning of the iteration and gradually reduced during the iteration process. Its attenuation formula is:

[0129]

[0130] In the above formula, ω max ,ω min are the maximum and minimum values ​​of the inertia weight, n is the current number of iterations, and n max is the total number of iterations.

[0131] In this embodiment, m>m0, so the particle swarm optimization algorithm is used to optimize the dynamic key parameters. After optimization, m=0.33 is calculated, which satisfies m≤m0. The dynamic key parameters are updated to: L (l，t) =8.3mH / km, C (l，t) =657nF / km, R (l，t) =3.4Ω / km, G (l，t) =10.26 -6 S / km.

[0132] 11. Enter the real-time prediction module, input the real-time data set into the prediction model after updating the dynamic key parameters, and obtain the prediction results of the power line loss rate on working days and non-working days, as shown below: Figure 5 , Figure 6 shown.

[0133] It can be seen that the line loss rate prediction value obtained by this method is very close to the changing pattern of the true value.

[0134] Embodiment 2:

[0135] A real-time prediction of power line loss rate PINN with dynamic following of PDE, such as Figure 7 As shown, it includes a prediction model building module, a data partitioning module, a prediction model training module, a prediction model inspection module, a dynamic parameter updating module, and a real-time prediction module.

[0136] The prediction model building module is used to build a power grid PINN line loss rate prediction model including a BiGRU model and a dynamic PDE model, wherein the dynamic PDE model is:

[0137]

[0138]

[0139]

[0140] In the above formula, L (l，t) , C (l，t) , R (l，t) , G (l，t) are dynamic key parameters, representing distributed inductance, distributed capacitance, distributed resistance and distributed conductance respectively. l and t are the total length and time of the power grid line respectively. I and U are the current and voltage respectively.

[0141] The data partitioning module is used to obtain historical data of the power grid, and to divide the historical data into a long-term data set, a short-term data set and a real-time data set according to N days ago, 1-N days and within 1 day respectively.

[0142] The prediction model training module is used to input the long-term data set into the constructed prediction model for training to determine the network parameters of the BiGRU model, the weight ratio parameters of the loss function, and the initial values ​​of the dynamic key parameters in the dynamic PDE model, including a network parameter optimization unit, a weight ratio parameter adjustment unit, a dynamic key parameter adjustment unit, and a judgment unit;

[0143] The network parameter optimization unit is used to optimize the network parameters of the BiGRU model using a Bayesian optimization algorithm, including the number of hidden units, the maximum number of training rounds, the initial learning rate, the L2 regularization parameter, the gradient threshold, the Dropout rate, and the learning rate adjustment factor;

[0144] The weight ratio parameter adjustment unit is used to adjust the weight ratio parameter of the loss function based on the BiGRU model optimized by the algorithm with the goal of minimizing the loss function, wherein the loss function for:

[0145]

[0146]

[0147]

[0148]

[0149] In the above formula, are prediction error, physical error, and λ data , PDE are the predicted weight ratio and physical weight ratio respectively, μ^ is the true value of the power grid line loss rate, μ d is the line loss rate prediction value of the BiGRU model, μ p is the line loss rate value calculated by physical formula, t0, t x are the start and end time respectively, U0 and I0 are the voltage and current at the grid end respectively, Ul ,I l They are the voltage and current at the outgoing network end respectively;

[0150] The dynamic key parameter adjustment unit is used to adjust the dynamic key parameters in the dynamic PDE model based on the BiGRU model after the weight ratio parameter is adjusted, with the loss function as the minimum, to obtain the initial value of the dynamic key parameter;

[0151] The judgment unit is used to judge whether the loss function has reached the minimum. If not, the network parameter optimization unit is started to optimize the network parameters again until the loss function is minimized.

[0152] The prediction model inspection module is used to input the recent data set into the trained prediction model to obtain the output value m of the loss function, and compare the output value m with the inspection value m0. If m>m0, the dynamic parameter update module is started to perform dynamic parameter update, wherein the output value m is calculated according to the following formula:

[0153]

[0154] In the above formula, λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the recent data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and n is the number of data points in the recent data set;

[0155] The investigation value m0 is calculated according to the following formula:

[0156]

[0157] In the above formula, δ is the tolerance factor with a value range of [0, 2], λ data , PDF are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the long-term data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and k is the number of data points in the long-term data set.

[0158] The dynamic parameter updating module is used to optimize the dynamic key parameters in the dynamic PDE model by using a particle swarm optimization algorithm until m≤m0, and to update the dynamic key parameters.

[0159] The real-time prediction module is used to input the real-time data set into the updated prediction model to obtain the power grid line loss rate prediction result.

Claims

1. A real-time prediction method for power line loss rate PINN with PDE dynamic following, characterized in that: The method comprises: S1. Build a power grid PINN line loss rate prediction model including BiGRU model and dynamic PDE model; obtain historical data of the power grid, and divide the historical data into long-term data set, short-term data set and real-time data set according to N days ago, 1-N days and within 1 day respectively; S2. Input the long-term data set into the constructed prediction model for training to determine the network parameters of the BiGRU model, the weight ratio parameters of the loss function, and the initial values ​​of the dynamic key parameters in the dynamic PDE model; S3, input the recent data set into the trained prediction model to obtain the output value m of the loss function; S4, compare the output value m with its observation value m0, if m>m0, optimize the dynamic key parameters in the dynamic PDE model until m≤m0, and enter S5 after updating the dynamic key parameters; if m≤m0, directly enter S5; S5. Input the real-time data set into the updated prediction model to obtain the power grid line loss rate prediction result.

2. The method for real-time prediction of power line loss rate PINN with dynamic PDE following according to claim 1 is characterized in that: In S1, the dynamic PDE model is: In the above formula, L (l，t) , C (l，t) , R (l，t) , G (l，t) are dynamic key parameters, representing distributed inductance, distributed capacitance, distributed resistance and distributed conductance respectively. l and t are the total length and time of the power grid line respectively. I and U are the current and voltage respectively.

3. The method for real-time prediction of power line loss rate PINN with dynamic PDE following according to claim 2 is characterized in that: The S2 includes: S21, using algorithms to optimize the network parameters of the BiGRU model; S22, based on the BiGRU model optimized by the algorithm, the weight ratio parameter of the loss function is adjusted with the goal of minimizing the loss function, where the loss function for: In the above formula, are prediction error, physical error, and λ data , PDE are the predicted weight ratio and physical weight ratio respectively, μ^ is the true value of the power grid line loss rate, μ d is the line loss rate prediction value of the BiGRU model, μ p is the line loss rate value calculated by physical formula, t0, t x are the start and end time respectively, U0 and I0 are the voltage and current at the grid end respectively, U l ,I l They are the voltage and current at the outgoing network end respectively; S23, based on the BiGRU model after the weight ratio parameter is adjusted, the dynamic key parameters in the dynamic PDE model are adjusted with the goal of minimizing the loss function to obtain the initial values ​​of the dynamic key parameters; S24, determine whether the loss function has reached the minimum, if not, return to S22 to optimize the network parameters again until the loss function is minimized.

4. The method for real-time prediction of power line loss rate PINN with dynamic PDE following according to claim 1 or 2, characterized in that: In S3, the output value m is calculated according to the following formula: In the above formula, λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the recent data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and n is the number of data points in the recent data set; In S4, the investigation value m0 is calculated according to the following formula: In the above formula, δ is the tolerance factor with a value range of [0, 2], λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the long-term data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and k is the number of data points in the long-term data set.

5. The method for real-time prediction of power line loss rate PINN with dynamic PDE following according to claim 3 is characterized in that: The S21 uses a Bayesian optimization algorithm to optimize the network parameters of the BiGRU model, including the number of hidden units, the maximum number of training rounds, the initial learning rate, the L2 regularization parameter, the gradient threshold, the Dropout rate, and the learning rate adjustment factor; The S4 uses a particle swarm optimization algorithm to optimize dynamic key parameters in the dynamic PDE model.

6. A PDE dynamic following power grid line loss rate PINN real-time prediction system, characterized in that: The system includes a prediction model construction module, a data partitioning module, a prediction model training module, a prediction model inspection module, a dynamic parameter updating module, and a real-time prediction module; The prediction model building module is used to build a power grid PINN line loss rate prediction model including a BiGRU model and a dynamic PDE model; The data partitioning module is used to obtain historical data of the power grid, and to divide the historical data into a long-term data set, a short-term data set and a real-time data set according to N days ago, 1-N days and within 1 day respectively; The prediction model training module is used to input the long-term data set into the constructed prediction model for training to determine the network parameters of the BiGRU model, the weight ratio parameters of the loss function, and the initial values ​​of the dynamic key parameters in the dynamic PDE model; The prediction model inspection module is used to input the recent data set into the trained prediction model, obtain the output value m of the loss function, and compare the output value m with the inspection value m0. If m>m0, the dynamic parameter update module is started; The dynamic parameter updating module is used to optimize the dynamic key parameters in the dynamic PDE model until m≤m0, and update the dynamic key parameters; The real-time prediction module is used to input the real-time data set into the updated prediction model to obtain the power grid line loss rate prediction result.

7. A PDE dynamic following power grid line loss rate PINN real-time prediction system according to claim 6, characterized in that: The prediction model building module is used to build the following dynamic PDE model: In the above formula, L (l，t) , C (l，t) , R (l，t) , G (l，t) are dynamic key parameters, representing distributed inductance, distributed capacitance, distributed resistance and distributed conductance respectively. l and t are the total length and time of the power grid line respectively. I and U are the current and voltage respectively.

8. The PDE dynamic following power grid line loss rate PINN real-time prediction system according to claim 7 is characterized in that: The prediction model training module includes a network parameter optimization unit, a weight ratio parameter adjustment unit, a dynamic key parameter adjustment unit, and a judgment unit; The network parameter optimization unit is used to optimize the network parameters of the BiGRU model using an algorithm; The weight ratio parameter adjustment unit is used to adjust the weight ratio parameter of the loss function based on the BiGRU model optimized by the algorithm with the goal of minimizing the loss function, wherein the loss function for: In the above formula, are prediction error, physical error, and λ data , PDE are the predicted weight ratio and physical weight ratio respectively, μ^ is the true value of the power grid line loss rate, μ d is the line loss rate prediction value of the BiGRU model, μ p is the line loss rate value calculated by physical formula, t0, t x are the start and end time respectively, U0 and I0 are the voltage and current at the grid end respectively, U l ,I l They are the voltage and current at the outgoing network end respectively; The dynamic key parameter adjustment unit is used to minimize the loss function based on the BiGRU model after the weight ratio parameter is adjusted. Adjust the dynamic key parameters in the dynamic PDE model for the target and obtain the initial values ​​of the dynamic key parameters; The judgment unit is used to judge whether the loss function has reached the minimum. If not, the network parameter optimization unit is started to optimize the network parameters again until the loss function is minimized.

9. A PDE dynamic following power grid line loss rate PINN real-time prediction system according to claim 6 or 7, characterized in that: The prediction model inspection module calculates the output value m according to the following formula In the above formula, λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the recent data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and n is the number of data points in the recent data set; The investigation value m0 is calculated according to the following formula: In the above formula, δ is the tolerance factor with a value range of [0, 2], λ data , PDE are the predicted weight ratio and the physical weight ratio respectively. is the true value of the power line loss rate calculated from the i-th data point in the long-term data set, are the power grid line loss rate values ​​of the i-th data point in the recent data set predicted by the BiGRU network and calculated by the physical formula, respectively, and k is the number of data points in the long-term data set.

10. The PDE dynamic following power grid line loss rate PINN real-time prediction system according to claim 8 is characterized in that: The network parameter optimization unit uses a Bayesian optimization algorithm to optimize the network parameters of the BiGRU model, including the number of hidden units, the maximum number of training rounds, the initial learning rate, the L2 regularization parameter, the gradient threshold, the Dropout rate, and the learning rate adjustment factor; The dynamic parameter updating module uses a particle swarm optimization algorithm to optimize the dynamic key parameters in the dynamic PDE model.

Images