Adaptive reclosing optimization method and system for power distribution network

Abstract

The invention relates to the technical field of reclosing, in particular to a self-adaptive reclosing optimization method and system for a power distribution network, and the method comprises the following steps: S1, collecting the historical fault data of the power distribution network, and carrying out the preprocessing of the historical fault data, and generating three-dimensional time series data; s2, according to the three-dimensional time sequence data, extracting key features by using a multi-scale convolutional neural network, and processing the key features to obtain input features; s3, establishing a Transform network model, classifying the input features to obtain samples, analyzing relation information of the samples to obtain an optimization model, classifying fault areas, generating classification labels, and predicting fault duration; and S4, for a non-permanent fault, dynamically adjusting reclosing delay time and an action time sequence by adopting the optimization model. According to the method, fault data are analyzed through deep learning, and the time and the time sequence of the reclosing action are optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of reclosing technology, and more specifically, to a distribution network adaptive reclosing optimization method and system. Background Art

[0002] In the distribution network, the reclosing device is a key device to ensure power supply continuity and system stability. Its core function is to quickly cut off the current and try to restore power supply after a fault occurs. Traditional reclosing technology mainly relies on mechanical relays and fixed timing logic to handle transient faults (such as lightning strikes and tree branch short circuits) through preset reclosing times and delay times (such as 0.5 seconds, 15 seconds, etc.).

[0003] However, with the expansion of the distribution network, the increase in the proportion of new energy access and the diversification of load types, traditional technologies have a significant defect of misjudging fault types, that is, they are unable to distinguish between permanent faults (such as equipment breakdown) and non-permanent faults (such as instantaneous arcs), resulting in repeated reclosing under permanent faults, increasing the risk of equipment damage. Although the existing technology can distinguish faults, it lacks a process for optimizing the time and sequence of reclosing actions according to the fault type. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art of misjudgment of reclosing fault types, and to propose a distribution network adaptive reclosing optimization method and system, which can accurately judge the fault type and optimize the time and sequence of reclosing.

[0005] To achieve the above object, a distribution network adaptive reclosing optimization method of the present invention comprises the following steps: S1: Collecting historical fault data of the distribution network, and preprocessing the historical fault data to generate three-dimensional time series data, wherein the historical fault data includes waveform data of voltage, current, and power factor collected from multiple sensors of the distribution network during historical faults; S2: extracting key features using a multi-scale convolutional neural network according to the three-dimensional time series data, and processing the key features to obtain input features, wherein the key features include fluctuation frequency and amplitude change; S3: Establish a Transformer network model, classify the input features to obtain samples, analyze the relationship information of the samples to obtain an optimized model and classify the faults into permanent faults and non-permanent faults, generate classification labels and predict the fault duration; S4: For non-permanent faults: dynamically adjust the reclosing delay time using the optimization model to optimize the reclosing action time; divide the timing window, and adaptively adjust the reclosing action timing based on the load intensity and the optimization model to optimize the reclosing action timing. In this technical solution, historical fault data is collected from multiple sensors (current transformers, voltage transformers, etc.) of the distribution network, the data is cleaned, abnormal data is processed to improve the accuracy of subsequent judgments, different types of faults are manually judged and labeled (permanent and non-permanent) to prepare for deep learning, and the data is flattened and spliced ​​into three-dimensional time series data after processing. The three-dimensional time series data is: data with three dimensions (number of samples, time steps, number of features) arranged in chronological order, which reflects the changes of historical faults in the distribution network over time. The three-dimensional time series data can be processed by a deep learning model, and a convolution operation is performed on the three-dimensional time series data to extract features to obtain input and output features, establish a Transformer network model, classify the input features to obtain samples, analyze the relationship information between the samples to obtain an optimization model, and use the optimization model to classify the fault type. If it is a non-permanent fault, the reclosing operation is triggered and the optimal delay time is set and the reclosing action timing is optimized to improve the reclosing success rate. If it is a permanent fault, the reclosing restart is avoided to reduce unnecessary system disturbances.

[0006] As a preferred solution, step S1 includes: S11: Collecting historical record data of each reclosing operation; the waveform data includes current waveform, voltage waveform, and duration; S12: Cleaning the waveform data and the historical record data of each reclosing operation, and processing abnormal data; S13: label different types of faults at the time of power outage; S14: The processed data is flattened and spliced ​​into the three-dimensional time series data.

[0007] As a preferred solution, step S2 includes: S21: using a multi-scale convolutional neural network to perform a convolution operation on the waveform data and extract key features; the key features are the fluctuation frequency and amplitude changes in the reclosing waveform diagram; S22: Adding a time series convolution layer to the multi-scale convolutional neural network to obtain a time series model, inputting key features into the time series model to obtain multi-time step sequence features to describe the dynamic change characteristics when a reclosing fault occurs; S23: applying convolution kernels of different scales to the sequence features of the multiple time steps to obtain features in different time windows to form multi-scale features; S24: adding position coding to the multi-scale features to provide position information and obtain input features.

[0008] As a preferred solution, in step S23, the calculation formula of the multi-scale feature is:

[0009] Where: is a multi-scale feature, is the feature concatenation operation, , and For input Perform convolutions of different scales.

[0010] As a preferred solution, step S3 includes: S31: Establish a Transformer network model, classify the input features based on a multi-head self-attention mechanism to obtain different samples, calculate the relationship scores between different samples, and determine the similarity between samples. The relationship scores between samples of the same category are higher, while the relationship scores between samples of different categories are lower. The relationship information between samples is captured through the self-attention mechanism, which can effectively capture the correlation between different time steps. The Transformer network model learns fault features by encoding the correlation between different time points, thereby improving the accuracy of fault classification and the robustness of the model. S32: Based on the cross attention mechanism, the Transformer network model is optimized according to the following formula for the dependency relationship between different time steps to obtain an optimized model:

[0011] Where: represents the input data at different time steps, represents the query matrix, Represents the learnable weight matrix , represents the key matrix, Represents the learnable weight matrix , represents the value matrix, Represents the learnable weight matrix ; S33: Use the multi-layer perceptron of the optimized model to distinguish permanent from non-permanent faults, generate classification labels and predict fault duration.

[0012] As a preferred solution, in step S4, the process of optimizing the reclosing action time is: according to the fault classification result, the reclosing delay time is dynamically adjusted using the characteristics and prediction results of the optimization model; if it is judged to be a non-permanent fault, the reclosing delay time is adjusted to ensure that the reclosing operation is performed after the arc is completely dissociated, thereby improving the success rate, wherein the calculation formula of the adaptive reclosing delay time is:

[0013] Where: is the adaptive reclosing delay time, is the basic delay time, Based on the fault type The control function of is the adjustment factor.

[0014] As a preferred solution, in step S4, the process of optimizing the timing of the reclosing action is: defining multiple time windows to ensure that the reclosing action in each window has the best activation and delay timing, and setting the duration and delay time of multiple reclosing attempts according to the load intensity through the prediction parameters of the optimization model, wherein the calculation formula for optimizing the timing of the reclosing action is:

[0015] Where: is the action time of the i-th reclosing switch, is the basic delay of the i-th time window, is the delay sequence calculated according to different windows, is the adjustment factor.

[0016] As a preferred solution, it also includes step S5: adaptively optimizing the reclosing strategy by updating the parameters of the optimization model through real-time data stream. This step can update the deep learning data online to achieve adaptive tuning.

[0017] As a preferred solution, step S5 includes: incrementally updating the parameters of the optimization model according to the new fault data, adaptively optimizing the reclosing delay time and action timing strategy, and the optimization model adopts an adaptive control strategy, which can update the data in real time to adapt to the power load fluctuations and environmental changes in the distribution network.

[0018] To achieve the above object, a distribution network adaptive reclosing optimization system of the present invention is used to implement the above distribution network adaptive reclosing optimization method, including: Data acquisition module: used to collect historical fault data of the distribution network, and pre-process the historical fault data to generate three-dimensional time series data; Feature extraction module: used to extract key features from the three-dimensional time series data, and process the key features to obtain input features; Feature classification module: used to establish a network model, classify the input features to obtain samples, analyze the relationship information of the samples to obtain an optimized model and classify faults; Action parameter optimization module: used to dynamically optimize the reclosing action time according to the fault classification result and using the optimization model, and adaptively adjust the reclosing action timing based on the load intensity and the optimization model.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention extracts features by performing convolution operations on fault data to improve the accuracy of fault classification, optimizes the model using the self-attention mechanism, accurately classifies faults into permanent and non-permanent, and then optimizes the reclosing strategy based on the judgment results, effectively improving the flexibility and accuracy of the reclosing and avoiding equipment damage caused by repeated reclosing under permanent faults.

[0020] 2. By optimizing the features and prediction results provided by the model, the reclosing delay time is dynamically adjusted according to the fault classification results to achieve adaptive reclosing action time optimization, improve the reclosing success rate under non-permanent faults, and effectively reduce the impact of faults on power supply.

[0021] 3. Adjust the reclosing strategy in real time under different loads and environments to enhance the stability and safety of the power grid in complex scenarios. By optimizing the reclosing action sequence, it accelerates fault isolation and recovery of non-fault areas, significantly reduces the power supply interruption time for users, and improves the overall power grid service level. At the same time, it can avoid unnecessary current shocks, reduce the possibility of secondary faults, and ensure the safety of the system.

[0022] 4. The parameters of the optimization model are updated incrementally by new fault data, and the reclosing delay time and action sequence are adaptively optimized to adapt to power load fluctuations and environmental changes in the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of the adaptive reclosing optimization method for distribution network of the present invention; Figure 2 It is a flow chart of data processing of the present invention.

[0024] Figure 3 It is a schematic diagram of the distribution network adaptive reclosing optimization system of the present invention. DETAILED DESCRIPTION

[0025] The drawings are only for illustrative purposes and cannot be construed as limiting the present invention. To better illustrate the present embodiment, some parts of the drawings may be omitted, enlarged, or reduced, and do not represent the size of the actual product. For those skilled in the art, it is understandable that some well-known structures and their descriptions may be omitted in the drawings. The positional relationships described in the drawings are only for illustrative purposes and cannot be construed as limiting the present invention.

[0026] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "long", "short" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0027] The technical solution of the present invention is further described in detail below through specific embodiments and in conjunction with the accompanying drawings: Embodiment 1: like Figure 1 , 2 As shown, this embodiment provides a distribution network adaptive reclosing optimization method, comprising the following steps: S1: Collecting historical fault data of the distribution network, and preprocessing the historical fault data to generate three-dimensional time series data, wherein the historical fault data includes waveform data of voltage, current, and power factor collected from multiple sensors of the distribution network during historical faults; S2: extracting key features using a multi-scale convolutional neural network according to the three-dimensional time series data, and processing the key features to obtain input features, wherein the key features include fluctuation frequency and amplitude change; S3: Establish a Transformer network model, classify the input features to obtain samples, analyze the relationship information of the samples to obtain an optimized model and classify the faults into permanent faults and non-permanent faults, generate classification labels and predict the fault duration; S4: For non-permanent faults: dynamically adjust the reclosing delay time using the optimization model to optimize the reclosing action time; divide the timing window, and adaptively adjust the reclosing action timing based on the load intensity and the optimization model to optimize the reclosing action timing.

[0028] In this embodiment, after a fault occurs, the optimization model can quickly determine the type of fault. If it is a non-permanent fault, the reclosing operation is triggered and the optimal delay time and action sequence are set to improve the success rate of the reclosing. If it is a permanent fault, the reclosing restart is avoided to reduce unnecessary system disturbances.

[0029] Specifically, step S1 includes: S11: Collecting historical record data of each reclosing operation; the waveform data includes current waveform, voltage waveform, and duration; S12: Cleaning the waveform data and the historical record data of each reclosing operation, and processing abnormal data; S13: label different types of faults at the time of power outage; S14: The processed data is flattened and spliced ​​into the three-dimensional time series data.

[0030] In this embodiment, the three-dimensional time series data is: data with three dimensions (number of samples, time steps, number of features) arranged in chronological order.

[0031] Specifically, step S2 includes: S21: using a multi-scale convolutional neural network to perform a convolution operation on the waveform data and extract key features; S22: Add a time series convolution layer to the multi-scale convolutional neural network to obtain a time series model, and input key features into the time series model to obtain multi-time step sequence features; S23: applying convolution kernels of different scales to the sequence features of the multiple time steps to obtain features in different time windows to form multi-scale features; S24: adding position encoding to the multi-scale features to obtain input features.

[0032] In this embodiment, the input formula of the multi-scale convolutional neural network model is:

[0033] Where: For input data, is a real matrix, is the number of time steps, is the spatial resolution, is the number of channels.

[0034] In this embodiment, the calculation formula of the multi-scale feature is:

[0035] Where: is a multi-scale feature, is the feature concatenation operation, , and For input Perform convolutions of different scales.

[0036] In this embodiment, after adding the position code, the position where the fault occurs can be marked in the fault feature to form a new optimization model input, wherein the calculation formula of the input is:

[0037] Where: Represents multi-scale features, represents the position code, Represents the input after adding the location information.

[0038] In this embodiment, the intelligent reclosing switch can be connected to the distribution automation system (DAS) and work in conjunction with the SCADA system to achieve centralized monitoring and remote control. It can automatically select the reclosing mode and time according to the fault location, equipment status and load properties, effectively improving the flexibility and accuracy of the reclosing switch.

[0039] Specifically, step S3 includes: S31: Establish a Transformer network model, classify the input features based on a multi-head self-attention mechanism to obtain different samples, calculate the relationship scores between different samples, and determine the similarity between samples, wherein the relationship scores between samples of the same category are higher, while the relationship scores between samples of different categories are lower. The relationship information between samples is captured through a multi-head self-attention mechanism to improve classification accuracy and model robustness; S32: Based on the cross attention mechanism, the Transformer network model is optimized according to the following formula for the dependency relationship between different time steps to obtain an optimized model:

[0040] Where: represents the input data at different time steps, represents the query matrix, Represents the learnable weight matrix , represents the key matrix, Represents the learnable weight matrix , represents the value matrix, Represents the learnable weight matrix ; S33: Use the multi-layer perceptron of the optimized model to distinguish permanent from non-permanent faults, generate classification labels and predict fault duration.

[0041] In this embodiment, in step S34, the calculation formula for query, key and value in the cross attention is:

[0042] Where: represents the input data at different time steps, represents the query matrix, Represents the learnable weight matrix , represents the key matrix, Represents the learnable weight matrix , represents the value matrix, Represents the learnable weight matrix .

[0043] In this embodiment, the calculation formula of self-attention in the encoder is: Where: represents the output of the attention calculation, is the similarity score of the two matrices, is a nonlinear activation function, is the dimension of the Key vector.

[0044] In this embodiment, the output passes through the fully connected layer and finally passes through the classifier to obtain the output:

[0045] Where: For output, It is a fully connected layer, which is mapped to the output space of the target task through the MLP layer for classification.

[0046] Specifically, in step S4, the process of optimizing the reclosing action time is: according to the fault classification result, the characteristics and prediction results of the optimization model are used to dynamically adjust the reclosing delay time to ensure that the reclosing operation is performed after the arc is completely dissociated, thereby improving the success rate.

[0047] In this embodiment, the calculation formula of the adaptive reclosing delay time is:

[0048] Where: is the adaptive reclosing delay time, is the basic delay time, Based on the fault type The control function of is the adjustment factor.

[0049] Specifically, in step S4, the process of optimizing the timing of the reclosing action is: defining multiple time windows to ensure that the reclosing action in each window has the best activation and delay timing, and setting the duration and delay time of multiple reclosing attempts according to the load intensity through the prediction parameters of the optimization model, wherein the calculation formula for optimizing the timing of the reclosing action is:

[0050] Where: is the action time of the i-th reclosing switch, is the basic delay of the i-th time window, is the delay sequence calculated according to different windows, is the adjustment factor.

[0051] Embodiment 2: This embodiment is similar to Embodiment 1, except that, in this embodiment, Figure 1 As shown, the method further includes step S5: incrementally updating the parameters of the optimization model according to the new fault data, and adaptively optimizing the reclosing delay time and the action timing strategy.

[0052] Specifically, the step S5 includes: incrementally updating the parameters of the optimization model according to the new fault data, and adaptively optimizing the reclosing delay time and action timing strategy.

[0053] In this embodiment, through online updating and adaptive tuning, the reclosing delay time and action timing strategy can be adjusted and optimized in real time to adapt to power load fluctuations and environmental changes in the distribution network.

[0054] Embodiment 3: like Figure 3 As shown, this embodiment provides a distribution network adaptive reclosing optimization system, which is used to implement the above-mentioned distribution network adaptive reclosing optimization method, including: Data acquisition module: used to collect historical fault data of the distribution network, and pre-process the historical fault data to generate three-dimensional time series data; Feature extraction module: used to extract key features from the three-dimensional time series data, and process the key features to obtain input features; Feature classification module: used to establish a network model, classify the input features to obtain samples, analyze the relationship information of the samples to obtain an optimized model and classify faults; Action parameter optimization module: used to dynamically optimize the reclosing action time according to the fault classification result and using the optimization model, and adaptively adjust the reclosing action timing based on the load intensity and the optimization model.

[0055] In this embodiment, during the operation of the distribution network adaptive reclosing optimization system, the optimized model parameters are updated in real time and input into the power system distribution network model containing the reclosing device to achieve adaptive optimization.

[0056] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

[0057] Obviously, the above embodiments of the present invention are only examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A distribution network adaptive reclosing optimization method, characterized in that: The following steps are involved: S1: Collecting historical fault data of the distribution network, and preprocessing the historical fault data to generate three-dimensional time series data, wherein the historical fault data includes waveform data of voltage, current, and power factor collected from multiple sensors of the distribution network during historical faults; S2: extracting key features using a multi-scale convolutional neural network according to the three-dimensional time series data, and processing the key features to obtain input features, wherein the key features include fluctuation frequency and amplitude change; S3: Establish a Transformer network model, classify the input features to obtain samples, analyze the relationship information of the samples to obtain an optimized model and classify the faults into permanent faults and non-permanent faults, generate classification labels and predict the fault duration; S4: For non-permanent faults: dynamically adjust the reclosing delay time using the optimization model to optimize the reclosing action time; The timing window is divided, and the reclosing action timing is adaptively adjusted based on the load intensity and the optimization model to optimize the reclosing action timing.

2. A distribution network adaptive reclosing optimization method according to claim 1, characterized in that: Step S1 includes: S11: Collecting historical record data of each reclosing operation; the waveform data includes current waveform, voltage waveform, and duration; S12: Cleaning the waveform data and the historical record data of each reclosing operation, and processing abnormal data; S13: label different types of faults at the time of power outage; S14: The processed data is flattened and spliced ​​into the three-dimensional time series data.

3. A distribution network adaptive reclosing optimization method according to claim 2, characterized in that: Step S2 includes: S21: using a multi-scale convolutional neural network to perform a convolution operation on the waveform data and extract key features; S22: Add a time series convolution layer to the multi-scale convolutional neural network to obtain a time series model, and input key features into the time series model to obtain multi-time step sequence features; S23: applying convolution kernels of different scales to the sequence features of the multiple time steps to obtain features in different time windows to form multi-scale features; S24: adding position encoding to the multi-scale features to obtain input features.

4. A distribution network adaptive reclosing optimization method according to claim 3, characterized in that: In step S23, the calculation formula of the multi-scale feature is: Where: is a multi-scale feature, is the feature concatenation operation, , and For input Perform convolutions of different scales.

5. A distribution network adaptive reclosing optimization method according to claim 1, characterized in that: Step S3 includes: S31: Establish a Transformer network model, classify the input features based on a multi-head self-attention mechanism to obtain different samples, calculate the relationship scores between different samples, and determine the similarity between the samples; S32: Based on the cross attention mechanism, the Transformer network model is optimized according to the following formula for the dependency relationship between different time steps to obtain an optimized model: Where: represents the input data at different time steps, represents the query matrix, Represents the learnable weight matrix , represents the key matrix, Represents the learnable weight matrix , represents the value matrix, Represents the learnable weight matrix ; S33: Use the multi-layer perceptron of the optimized model to distinguish permanent from non-permanent faults, generate classification labels and predict fault duration.

6. A distribution network adaptive reclosing optimization method according to claim 1, characterized in that: In step S4, the process of optimizing the reclosing action time is: according to the fault classification result, the reclosing delay time is dynamically adjusted using the characteristics and prediction results of the optimization model, wherein the calculation formula of the adaptive reclosing delay time is: Where: is the adaptive reclosing delay time, is the basic delay time, Based on the fault type The control function of is the adjustment factor.

7. A distribution network adaptive reclosing optimization method according to claim 1, characterized in that: In step S4, the process of optimizing the reclosing action sequence is: defining multiple time windows, and setting the duration and delay time of multiple reclosing attempts according to the load intensity and the prediction parameters of the optimization model, wherein the calculation formula for optimizing the reclosing action sequence is: Where: is the action time of the i-th reclosing switch, is the basic delay of the i-th time window, is the delay sequence calculated according to different windows, is the adjustment factor.

8. A distribution network adaptive reclosing optimization method according to any one of claims 1 to 7, characterized in that: The method further comprises step S5: adaptively optimizing the reclosing strategy by updating the parameters of the optimization model through real-time data stream.

9. A distribution network adaptive reclosing optimization method according to claim 8, characterized in that: The step S5 comprises: incrementally updating the parameters of the optimization model according to the new fault data, and adaptively optimizing the reclosing delay time and the action timing strategy.

10. A distribution network adaptive reclosing optimization system, characterized in that: A method for optimizing the adaptive reclosing of a distribution network according to any one of claims 1 to 9, comprising: Data acquisition module: used to collect historical fault data of the distribution network, and pre-process the historical fault data to generate three-dimensional time series data; Feature extraction module: used to extract key features from the three-dimensional time series data, and process the key features to obtain input features; Feature classification module: used to establish a network model, classify the input features to obtain samples, analyze the relationship information of the samples to obtain an optimized model and classify faults; Action parameter optimization module: used to dynamically optimize the reclosing action time according to the fault classification result and using the optimization model, and adaptively adjust the reclosing action timing based on the load intensity and the optimization model.

Images