Self-encoder static power distribution network state estimation method and system

Abstract

The invention relates to a self-encoder static power distribution network state estimation method and system, and belongs to the field of power systems. The method comprises the following steps: when partial data is missing, collecting simulation data of a static power distribution network system, and generating a repair model; based on the repair model, a target domain model is obtained through transfer learning fine tuning; and repairing the actually measured data with partial data missing through the repair model to obtain complete data, and performing state estimation of the static power distribution network system by using the target domain model. The method can accurately predict the operation state of the power system.

Description

Technical Field

[0001] The present invention belongs to the field of electric power systems, and in particular relates to an autoencoder static distribution network state estimation method and system. Background Art

[0002] Power system state estimation is the basis of power system monitoring and dispatching, and can provide key real-time information for the safe and stable operation of the power system. Therefore, power system state estimation has always been one of the important areas of power system research. Traditional power system state estimation methods mainly include least squares estimation, weighted least squares method and Kalman filtering. The least squares estimation method requires that the measured data is accurate and error-free. It is easy to produce estimation errors in the face of noise or data loss, resulting in inaccurate state estimation results; the weighted least squares method improves the anti-interference ability of noise by introducing weights, but the selection of weights depends on prior knowledge and it is difficult to cope with the situation of poor data quality under actual working conditions; the Kalman filtering method has a good effect in processing dynamic power system state estimation, but it has a strong dependence on the initial state and is easily affected by external interference, resulting in large estimation deviations.

[0003] In addition, with the expansion of the scale and complexity of power systems, traditional state estimation methods face problems such as high computational complexity and difficulty in data synchronization. In modern smart grids, the sources of power system data are more diverse, the amount of data has also increased significantly, and sensors may experience noise, data loss, delays, etc., making it difficult for traditional state estimation methods to meet real-time and accuracy requirements. Especially in the context of large-scale distributed energy access and multi-source heterogeneous data fusion, the requirements for data quality in power system state estimation have become more stringent. How to achieve efficient and accurate state estimation in the presence of noise, data loss and delay has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for estimating the state of an autoencoder static distribution network in view of the problems in the prior art.

[0005] To achieve the above object, the technical solution of the present invention is: a method for estimating the state of a static distribution network using an autoencoder, comprising:

[0006] When part of the input data is missing, the static distribution network system simulation model is input for simulation, the simulation data of the static distribution network system simulation model is collected, and a repair model is generated based on the simulation data of the static distribution network system simulation model;

[0007] Based on the repair model, the target domain model is obtained through transfer learning fine-tuning;

[0008] Based on the actual input data where some data is missing in the actual static distribution network system, the repair model is used to repair the complete input data. Based on the complete input data, the target domain model is used to estimate the operating status of the actual static distribution network system.

[0009] In one embodiment of the present invention, part of the data is missing, including setting the active power P and the reactive power Q in the input data to zero simultaneously.

[0010] In one embodiment of the present invention, the repair model is generated in the following manner:

[0011] In the framework of federated learning, the simulation data of the static distribution network system is clustered by Gaussian mixture model GMM, and the simulation data of the static distribution network system is divided into multiple subsets. The data of each subset is assigned to different federated learning clients, and each federated learning client independently trains the autoencoder model. The weights of the trained autoencoder model are sent to the central server. The central server aggregates the weights of the autoencoder models of all federated learning clients by weighted averaging to generate a repair model.

[0012] In one embodiment of the present invention, the encoder of the autoencoder model is composed of four fully connected layers, which gradually compresses the dimension of the input data to a low-dimensional representation; the decoder of the autoencoder model reconstructs the reconstructed data with the same dimension as the input data by expanding the compressed low-dimensional representation layer by layer.

[0013] In one embodiment of the present invention, the training method of the autoencoder model is as follows:

[0014] The encoder of the autoencoder model converts the input data x into hidden variables z, which can be expressed as:

[0015] z=f(w (1) x+b (1) )

[0016] In the formula, w (1) represents the weight matrix; b (1) represents the bias vector; f() represents the activation function;

[0017] The decoder of the autoencoder model reconstructs the reconstructed data that is similar to the input data x based on the hidden variable z , expressed as:

[0018]

[0019] In the formula, w (2) represents the weight matrix; b (2) represents the bias vector;

[0020] The optimization goal of the autoencoder model is to ensure the reconstruction of the data As close as possible to the input data x; given a set of input data x (n) ∈R (D) ,1≤n≤N, the reconstruction error is expressed as:

[0021]

[0022] In the formula, Represents reconstructed data;

[0023] By minimizing the reconstruction error, the network parameters of the autoencoder model are learned as θ = {w (1) ,b (1) ,w (2) ,b (2)}.

[0024] In one embodiment of the present invention, the activation function adopts the ReLU function:

[0025] f(Z)=max(0,Z)

[0026] Z represents input.

[0027] In one embodiment of the present invention, the central server aggregates the weights of the autoencoder models of all federated learning clients by weighted averaging as follows:

[0028] Suppose there are K federated learning clients, and their local data are represented as D 1 ,D 2 ,…,D k ,…,D K , for the dataset D of the kth federated learning client k , the collected loss function is:

[0029]

[0030] In the formula, f j (w) is f(x j ,y j ), x j represents the input variable of the jth sample; y j represents the output variable of the jth sample; the loss function defined on the dataset set of all federated learning clients is:

[0031]

[0032] In the formula, |D k | indicates D k The number of samples in |D| represents the total number of samples in all federated learning clients.

[0033] The global aggregation parameter set w(t) of the central server at time t is expressed as follows:

[0034]

[0035] Where μ is the learning rate; ▽F(·) is the local gradient of the loss function; w k (t) is the local parameter set of the kth federated learning client at time t, expressed as:

[0036] w k (t) = w k (t-1)-μ▽F k (w k (t-1))

[0037] The central server obtains the local gradient ▽F of the loss function of the kth federated learning client at time t k (w k (t-1)), and w(t) is calculated.

[0038] In one embodiment of the present invention, based on the repair model, the specific implementation method of obtaining the target domain model through transfer learning fine-tuning is:

[0039] In transfer learning, let the subscripts S and T represent the source task and the target task respectively, D S and D T They are the source domain and the target domain respectively, and the corresponding domains are constructed using the feature vector space X and the probability distribution function P(X), namely:

[0040]

[0041] Let Y s and Y t are the label vector spaces of the source domain and the target domain respectively, and f s and f t are the mapping functions of the source domain and the target domain respectively, then the tasks T in the source domain and the target domain s and T t They are described as:

[0042]

[0043] Assuming that the source domain and the target domain have the same feature distribution but different label spaces, the goal of transfer learning is to learn the mapping function f t :X t →X s In D T The expected error on is the smallest and satisfies X t =X s , Y t =Y s and P(Yt |X t )≠P(Y s |X s );

[0044] The repair model is used as the source domain model. Through transfer learning, the feature representation and parameters of the repair model are transferred to the target domain model. The parameters on the target domain model are fine-tuned to make the parameters on the target domain model adapt to the characteristics of the target domain data. The target domain model with fine-tuned parameters is trained on the target domain data to obtain the final target domain model. The specific process is as follows:

[0045] (1) Source domain data collection: collecting node voltage (v), phase angle (θ), active power (p) and reactive power (q) data;

[0046] (2) Source domain model training: Train a high-precision state estimation model on the source domain data. This model usually uses a large amount of labeled source domain data and has good generalization ability. The goal of the source domain model is to capture the characteristics and change patterns of the source domain power system state data as much as possible;

[0047] (3) Feature representation transfer: Transfer the feature representation of the source domain model (i.e., the extracted intermediate layer features or feature space) to the target domain model;

[0048] (4) Parameter migration and fine-tuning: Migrate some or all parameters of the source domain model to the target domain model. Fine-tune the parameters on the target domain data to further adjust the migrated parameters so that the model adapts to the characteristics of the target domain.

[0049] (5) Target domain model training: Continue to train the model on the target domain data to adapt to the state estimation task in the target domain. Through target domain training, the model can better capture the state characteristics of the target domain power system and have higher estimation accuracy;

[0050] (6) State estimation: Use the fine-tuned transfer learning model to estimate the state of the power system in the target domain. Predict the voltage, frequency, power and other states of each node in the system and identify potential abnormal or unstable conditions. Evaluate the estimation accuracy of the model to ensure that the state estimation results are sufficiently accurate and robust in the target domain.

[0051] The present invention also provides an autoencoder static distribution network state estimation system based on federated learning and transfer learning, comprising:

[0052] The simulation data acquisition module inputs the static distribution network system simulation model for simulation when part of the input data is missing, and collects simulation data of the static distribution network system simulation model;

[0053] A repair model generation module generates a repair model based on simulation data of a static distribution network system simulation model;

[0054] The transfer learning module obtains the target domain model through transfer learning fine-tuning based on the repair model;

[0055] The state estimation module uses the repair model to repair the actual input data with some missing data in the actual static distribution network system to obtain complete input data. Based on the complete input data, the target domain model is used to estimate the operating state of the actual static distribution network system.

[0056] The present invention also provides a computer-readable storage medium, on which computer program instructions that can be executed by a processor are stored. When the processor executes the computer program instructions, the method steps described above can be implemented.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] (1) The present invention uses an improved autoencoder structure using a federated learning framework to train a repair model, and the data repair result has higher accuracy.

[0059] (2) The present invention obtains the target domain model for state estimation through transfer learning fine-tuning, which does not require retraining the model and is more efficient.

[0060] (3) The present invention takes into account the problem of missing data under weak communication conditions, preprocesses the measurement data, including data cleaning, completion, calibration, etc., obtains the statistical distribution characteristics of the data, and proposes a corresponding repair model. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 The figure is a flow chart of the method of the present invention.

[0062] Figure 2 The effect of patching on the P (active power) and Q (reactive power) data is shown.

[0063] Figure 3 Estimated effects in the case of missing data are shown. DETAILED DESCRIPTION

[0064] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0065] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0066] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0067] In the state estimation of power systems, it is necessary to introduce more robust and intelligent algorithms that can effectively deal with noise, data loss, delay and other problems, and improve the reliability and accuracy of state estimation. At the same time, with the development of artificial intelligence and machine learning technologies, data-driven intelligent state estimation methods, such as deep learning, autoencoders, and federated learning, have gradually become a potential direction for solving these problems, providing new technical approaches and solutions for the state estimation of power systems.

[0068] To this end, the present invention provides a method for estimating the state of an autoencoder static distribution network, comprising:

[0069] When part of the input data is missing, the static distribution network system simulation model is input for simulation, the simulation data of the static distribution network system simulation model is collected, and a repair model is generated based on the simulation data of the static distribution network system simulation model;

[0070] Based on the repair model, the target domain model is obtained through transfer learning fine-tuning;

[0071] Based on the actual input data where some data is missing in the actual static distribution network system, the repair model is used to repair the complete input data. Based on the complete input data, the target domain model is used to estimate the operating status of the actual static distribution network system.

[0072] The following is the specific implementation process of the present invention.

[0073] like Figure 1 As shown, this embodiment provides a method for estimating the state of a static distribution network from an autoencoder, such as Figure 1 As shown, the following steps are included:

[0074] S1, data collection, collects simulation data of static distribution network system under the condition of partial data missing;

[0075] S2. Model construction. In the framework of federated learning, Gaussian mixture model (GMM) is used to cluster the simulation data and divide the simulation data into multiple subsets with strong homogeneity. The data of each subset is assigned to different federated learning clients. Each client independently trains the autoencoder model on its assigned data subset and sends the trained model weights to the central server. The central server aggregates the model weights of all clients by weighted average to generate a repair model.

[0076] For the input data x, the encoding process of the autoencoder is expressed as follows:

[0077] z=f(w (1) x+b (1) )

[0078] In the formula, x represents input data; z represents hidden variables; w (1) represents the weight matrix; b (1) represents the bias vector; f() represents the activation function, usually the ReLU function:

[0079] f(z)=max(0,z)

[0080] Through this mapping, the encoder transforms high-dimensional input data x into a low-dimensional latent representation z, which contains the main features of the input data.

[0081] The decoding process is expressed as:

[0082]

[0083] In the formula, represents reconstructed data; z represents hidden variables; w (2) represents the weight matrix; b (2) represents the bias vector; f() represents the activation function, which also uses the ReLU function.

[0084] The autoencoder converts the input data into hidden variables z and reconstructs the reconstructed data that is close to the original input through the decoder. Therefore, ensuring that the output of the decoder can restore the original data as much as possible is the optimization goal of the autoencoder, that is, reconstructing the data As close as possible to the input data x. Given a set of data x (n) ∈R (D) ,1≤n≤N, then the reconstruction error can be expressed as:

[0085]

[0086] In the formula, x (n) Represents input data; Represents reconstructed data.

[0087] The most typical reconstruction error indicator is usually measured by mean square error (MSE):

[0088]

[0089] By minimizing the reconstruction error, the network parameters θ = {w (1) ,b (1) ,w (2) ,b (2)}.

[0090] The autoencoder architecture designed in this paper takes into full account the characteristics of power system data. The encoder consists of four fully connected layers, which gradually compresses the dimension of the input data from 81×16 to a compact low-dimensional representation. The decoder reconstructs a data matrix of the same dimension as the original input by expanding this low-dimensional representation layer by layer.

[0091] Suppose there are K federated learning clients, and their local data are represented as D 1 ,D 2 ,…,D k ,…,D K , for the dataset D of the kth federated learning client k , the collected loss function is:

[0092]

[0093] In the formula, f j (w) is f(x j ,y j ), x j represents the input variable of the jth sample; y j represents the output variable of the jth sample; the loss function defined on the dataset set of all federated learning clients is:

[0094]

[0095] In the formula, |D k | indicates D k The number of samples in |D| represents the total number of samples in all federated learning clients. The inpainting model is trained to minimize a loss function, for example using gradient descent, to find the best set of parameters to learn with the goal of minimizing the loss function F k (w):

[0096] w * =argminF k (w)

[0097] Since the original data is distributed on different clients, federated learning cannot find the gradient directly on the central server like centralized machine learning. If the gradient descent method is used to minimize the global loss function, that is:

[0098]

[0099] Where μ is a small positive number, i.e., the learning rate; ▽F(·) is the local gradient of the loss function; w(t) is the global aggregation parameter set of the central server at time; w k (t) is the local parameter set of client k at time t, which can be expressed as:

[0100] w k (t) = w k (t-1)-μ▽F k (w k (t-1))

[0101] After that, as long as the local gradient ▽F is obtained k (w k (t-1)), the central server can calculate w(t). Therefore, only the local gradient needs to be sent to the central server, which can save communication resources. In particular, when gradient compression is used, the amount of gradient data transmitted can be reduced to a certain extent.

[0102] S3, model migration, migrate the repair model obtained by training in S2 to the target domain, use the data of the target domain for fine-tuning, retain the important features in the source domain, and adapt to the new data features in the target domain to obtain the target domain model.

[0103] In transfer learning, let the subscripts S and T represent the source task and the target task respectively, D S and D T They are the source domain and the target domain respectively, and the corresponding domains are constructed using the feature vector space X and the probability distribution function P(X), namely:

[0104]

[0105] Let Y s and Y t are the label vector spaces of the source domain and the target domain respectively, and f s and f t are the mapping functions of the source domain and the target domain respectively, then the tasks T in the source domain and the target domain s and T t Can be described as:

[0106]

[0107] Assuming that the source domain and the target domain have the same feature distribution but different label spaces, the goal of transfer learning is to learn the mapping function f t :X t →X s In D T The expected error on is the smallest and satisfies X t =X s , Y t =Y s and P(Y t |X t )≠P(Y s |X s );

[0108] Repair the model and fine-tune it through transfer learning to obtain the target domain model. The specific process is as follows:

[0109] (1) Source domain data collection: collecting node voltage (v), phase angle (θ), active power (p) and reactive power (q) data;

[0110] (2) Source domain model training: Train a high-precision state estimation model on the source domain data. This model usually uses a large amount of labeled source domain data and has good generalization ability. The goal of the source domain model is to capture the characteristics and change patterns of the source domain power system state data as much as possible;

[0111] (3) Feature representation transfer: Transfer the feature representation of the source domain model (i.e., the extracted intermediate layer features or feature space) to the target domain model;

[0112] (4) Parameter migration and fine-tuning: Migrate some or all parameters of the source domain model to the target domain model. Fine-tune the parameters on the target domain data to further adjust the migrated parameters so that the model adapts to the characteristics of the target domain.

[0113] (5) Target domain model training: Continue to train the model on the target domain data to adapt to the state estimation task in the target domain. Through target domain training, the model can better capture the state characteristics of the target domain power system and have higher estimation accuracy;

[0114] (6) State estimation: Use the fine-tuned transfer learning model to estimate the state of the power system in the target domain. Predict the voltage, frequency, power and other states of each node in the system and identify potential abnormal or unstable conditions. Evaluate the estimation accuracy of the model to ensure that the state estimation results are sufficiently accurate and robust in the target domain.

[0115] S4, state estimation, repairs the measured data with some missing data through the repair model, and then uses the repaired data to perform state estimation on the target domain data through the fine-tuned model to ensure that the model can accurately predict the operating status of the power system.

[0116] The method of the present invention first sets the P and Q parts to zero to obtain system simulation data, and then uses the Gaussian mixture model (GMM) to cluster the source domain data under the federated learning framework. GMM divides the source domain data into multiple subsets with strong homogeneity through the expectation maximization (EM) algorithm. The data of each subset is allocated to different federated learning clients.

[0117] Each client independently trains an autoencoder model on its assigned data subset. The autoencoder model extracts low-dimensional feature representations from the input data through an encoder-decoder structure and attempts to reconstruct the input data. After each round of training, each client sends the trained model weights to the central server.

[0118] The central server aggregates the model weights of all clients by weighted average to generate a repair model. This repair model combines the learning results of different clients and has the ability to generalize in multiple scenarios.

[0119] Data patching is performed directly through the repair model after federated learning. For target domain data with missing P and Q data, these data are directly input into the global model, and the decoder part of the model generates the complete patched data. The patching process utilizes the feature representation learned by the global model in multiple scenarios in the source domain, which can effectively restore the missing data.

[0120] The repaired data is used to further perform state estimation of the power system. The repaired model is transferred to the target domain and fine-tuned using the data from the target domain. During the fine-tuning process, only the parameters of some model layers are adjusted to adapt to the specific data distribution of the target domain.

[0121] Use the fine-tuned model to perform state estimation on the target domain data to ensure that the model can accurately predict the operating state of the power system. State estimation includes the prediction of key states of the power system (such as abnormal or emergency states).

[0122] In order to intuitively demonstrate the performance of the autoencoder model based on federated learning in power system data patching, the present invention randomly selected a group of masked data from the validation set and compared its predicted values ​​with the true values. Figure 2 The patching effect of P (active power) and Q (reactive power) data is shown. Figure 2 It is clear to see the accuracy and performance of the model when patching missing data. To evaluate the patching effect, the present invention uses the true values ​​of randomly selected P and Q data to compare with the predicted values ​​after patching. The blue points in the figure represent the true values, and the green points represent the patched values ​​predicted by the model. We compare the masked data points and show their patching effects.

[0123] In the state estimation effect verification, the present invention randomly selected some samples containing missing data from the verification set, and compared the estimated values ​​of active power (P), reactive power (Q), voltage (V) and phase angle (θ) with the true values. By drawing the comparison chart, we intuitively show the estimation effect of the model in the case of missing data, such as Figure 3 Each figure compares the true value of the masked data (blue) and the model estimate (red), and the results show that the model performs well in the estimation of P and Q, V and θ.

[0124] The present invention also provides an autoencoder static distribution network state estimation system based on federated learning and transfer learning, comprising:

[0125] The simulation data acquisition module inputs the static distribution network system simulation model for simulation when part of the input data is missing, and collects simulation data of the static distribution network system simulation model;

[0126] A repair model generation module generates a repair model based on simulation data of a static distribution network system simulation model;

[0127] The transfer learning module obtains the target domain model through transfer learning fine-tuning based on the repair model;

[0128] The state estimation module uses the repair model to repair the actual input data with some missing data in the actual static distribution network system to obtain complete input data. Based on the complete input data, the target domain model is used to estimate the operating state of the actual static distribution network system.

[0129] The present invention also provides a computer-readable storage medium, on which computer program instructions that can be executed by a processor are stored. When the processor executes the computer program instructions, the method steps described above can be implemented.

[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0131] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

Claims

1. A method for estimating the state of a static distribution network using an autoencoder, characterized in that: include: When part of the input data is missing, the static distribution network system simulation model is input for simulation, the simulation data of the static distribution network system simulation model is collected, and a repair model is generated based on the simulation data of the static distribution network system simulation model; Based on the repair model, the target domain model is obtained through transfer learning fine-tuning; Based on the actual input data where some data is missing in the actual static distribution network system, the repair model is used to repair the complete input data. Based on the complete input data, the target domain model is used to estimate the operating status of the actual static distribution network system.

2. The method for estimating the state of an autoencoder static distribution network according to claim 1, characterized in that: Some data are missing, including setting both the active power P and the reactive power Q in the input data to zero.

3. The method for estimating the state of an autoencoder static distribution network according to claim 1, characterized in that: The repair model is generated as follows: In the framework of federated learning, the simulation data of the static distribution network system is clustered by Gaussian mixture model GMM, and the simulation data of the static distribution network system is divided into multiple subsets. The data of each subset is assigned to different federated learning clients, and each federated learning client independently trains the autoencoder model. The weights of the trained autoencoder model are sent to the central server. The central server aggregates the weights of the autoencoder models of all federated learning clients by weighted averaging to generate a repair model.

4. The method for estimating the state of an autoencoder static distribution network according to claim 3, characterized in that: The encoder of the autoencoder model consists of four fully connected layers, which gradually compresses the dimension of the input data to a low-dimensional representation; the decoder of the autoencoder model reconstructs the reconstructed data with the same dimension as the input data by expanding the compressed low-dimensional representation layer by layer.

5. A method for estimating the state of an autoencoder static distribution network according to claim 3 or 4, characterized in that: The autoencoder model is trained as follows: The encoder of the autoencoder model converts the input data x into hidden variables z, which can be expressed as: z=f(w (1) x+b (1) ) In the formula, w (1) represents the weight matrix; b (1) represents the bias vector; f() represents the activation function; The decoder of the autoencoder model reconstructs the reconstructed data that is similar to the input data x based on the hidden variable z The formula is: In the formula, w (2) represents the weight matrix; b (2) represents the bias vector; The optimization goal of the autoencoder model is to ensure that the reconstructed data As close as possible to the input data x; given a set of input data x (n) ∈R (D) ,1≤n≤N, the reconstruction error is expressed as: In the formula, Represents reconstructed data; By minimizing the reconstruction error, the network parameters of the autoencoder model are learned as θ = {w (1) ,b (1) ,w (2) ,b (2) }.

6. The method for estimating the state of an autoencoder static distribution network according to claim 5, characterized in that: The activation function uses the ReLU function: f(Z)=max(0,Z) Z represents input.

7. The method for estimating the state of an autoencoder static distribution network according to claim 3, characterized in that: The central server aggregates the weights of the autoencoder models of all federated learning clients by weighted averaging as follows: Suppose there are K federated learning clients, whose local data are represented as D1, D2, …, D k ,…,D K , for the dataset D of the kth federated learning client k , the collected loss function is: In the formula, f j (w) is f(x j ,y j ), x j represents the input variable of the jth sample; y j represents the output variable of the jth sample; the loss function defined on the dataset set of all federated learning clients is: In the formula, |D k | indicates D k The number of samples in |D| represents the total number of samples in all federated learning clients. The global aggregation parameter set w(t) of the central server at time t is expressed as follows: Where μ is the learning rate; ▽F(·) is the local gradient of the loss function; w k (t) is the local parameter set of the kth federated learning client at time t, expressed as: w k (t)=w k (t-1)-μ▽F k (w k (t-1)) The central server obtains the local gradient ▽F of the loss function of the kth federated learning client at time t k (w k (t-1)), and w(t) is calculated.

8. The method for estimating the state of an autoencoder static distribution network according to claim 1, characterized in that: Based on the repair model, the specific implementation method of obtaining the target domain model through transfer learning fine-tuning is as follows: In transfer learning, let the subscripts S and T represent the source task and the target task respectively, D S and D T They are the source domain and the target domain respectively, and the corresponding domains are constructed using the feature vector space X and the probability distribution function P(X), namely: Let Y s and Y t are the label vector spaces of the source domain and the target domain respectively, and f s and f t are the mapping functions of the source domain and the target domain respectively, then the tasks T in the source domain and the target domain s and T t They are described as: Assuming that the source domain and the target domain have the same feature distribution but different label spaces, the goal of transfer learning is to learn the mapping function f t :X t →X s In D T The expected error on is the smallest and satisfies X t =X s , Y t =Y s and P(Y t |X t )≠P(Y s |X s ); The repair model is used as the source domain model. Through transfer learning, the feature representation and parameters of the repair model are transferred to the target domain model. The parameters are fine-tuned on the target domain model so that the parameters on the target domain model adapt to the characteristics of the target domain data. The target domain model with fine-tuned parameters is trained on the target domain data to obtain the final target domain model.

9. An autoencoder static distribution network state estimation system, characterized in that: include: The simulation data acquisition module inputs the static distribution network system simulation model for simulation when part of the input data is missing, and collects simulation data of the static distribution network system simulation model; A repair model generation module generates a repair model based on simulation data of a static distribution network system simulation model; The transfer learning module obtains the target domain model through transfer learning fine-tuning based on the repair model; The state estimation module uses the repair model to repair the actual input data with some missing data in the actual static distribution network system to obtain complete input data. Based on the complete input data, the target domain model is used to estimate the operating state of the actual static distribution network system.

10. A computer-readable storage medium having stored thereon computer program instructions that can be executed by a processor, and when the processor executes the computer program instructions, the method steps according to any one of claims 1 to 8 can be implemented.

Images