Distribution network medium-voltage power-cut plan time consumption prediction method based on engineering quantitative data

Abstract

The invention discloses a power distribution network medium-voltage power outage plan time consumption prediction method based on engineering quantitative data. Comprising a data acquisition module, a data preprocessing module, a prediction model training module, a total time consumption prediction module, a result output and adjustment optimization and data collection module, a data preprocessing module, a prediction model training module, a prediction module, an adjustment and optimization module and a display and feedback module. According to the invention, on one hand, the accuracy of the power-off plan is improved: through quantitative data analysis, the consumed time of the power-off process can be accurately predicted, and excessive power-off or too short-time power-off is avoided, so that the operation and maintenance work of the power distribution network is better coordinated; and on the other hand, resource configuration is optimized, power failure time consumption prediction can help a power company reasonably configure manpower, material resources and equipment in a power failure plan, efficient utilization of the resources is ensured, and the operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of distribution networks, and particularly to a method for predicting the duration of medium-voltage power outage plans in distribution networks based on engineering quantification data. Background Art

[0002] During the operation and maintenance of distribution networks, power outage plans are one of the common operation means, mainly used for equipment maintenance, fault troubleshooting, equipment replacement and other work.

[0003] However, power outages not only affect the stability and power supply reliability of the power system, but also cause inconvenience to users. Especially in medium- and low-voltage distribution networks, the scope of power outages is wide and the duration is long.

[0004] Therefore, how to accurately predict the duration of power outages and reasonably plan the power outage time has become an important task in distribution network management. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems in the above technologies to some extent.

[0006] To achieve the above object, a first aspect of the present invention proposes a method for predicting the duration of medium-voltage power outage plans in distribution networks based on engineering quantification data, including:

[0007] S1. Data collection: Collect engineering quantification data in medium-voltage power outage plans of distribution networks, including information such as line length, substation load, equipment type, work difficulty, number of operating personnel, weather conditions, historical power outage data, etc. in the power outage area;

[0008] S2. Data preprocessing: Preprocess the collected engineering quantification data, remove noise data, and fill or correct missing values;

[0009] S3. Prediction model training: According to the preprocessed data, use machine learning algorithms to establish a duration prediction model, and the algorithms include but are not limited to regression analysis, support vector machine, neural network, etc.;

[0010] S4. Predict the total duration: Input the engineering quantification data into the duration prediction model to predict the total duration of the medium-voltage power outage plan in the distribution network;

[0011] S5. Output results and adjustment and optimization: Output the prediction results, and adjust and optimize the power outage plan according to actual needs to reduce the power outage time.

[0012] In addition, a method for predicting the duration of medium-voltage power outage plans in distribution networks based on engineering quantification data proposed by the present invention as above may also have the following additional technical features:

[0013] Further, the engineering quantification data further includes geographical information of the power outage scope, load types within the power outage area, maintenance or replacement cycles of power distribution equipment, and equipment status information during the power outage.

[0014] Further, the machine learning algorithm optimizes the accuracy of the prediction model by training historical power outage data and performing cross-validation.

[0015] Further, the preprocessing steps include data standardization, normalization, and handling of outliers.

[0016] Further, the prediction model is based on a neural network algorithm, trained using a multi-layer perceptron (MLP), and the parameters of the model are optimized through a backpropagation algorithm.

[0017] Further, the output of the time-consuming prediction model includes not only the total time-consuming prediction result but also the time predictions for each stage, including the preparation stage, construction stage, restoration stage, etc.

[0018] Further, the model optimization steps include introducing intelligent optimization algorithms such as genetic algorithms and particle swarm optimization algorithms to optimize the parameters of the model.

[0019] Further, the prediction results are updated through real-time data and dynamically adjusted in combination with changes in engineering quantification data to further improve the accuracy and real-time performance of the prediction.

[0020] Further, the prediction model is used for decision support in the distribution network operation and maintenance department, helping to formulate a more scientific and reasonable power outage plan and reducing the impact of power outages on users.

[0021] To achieve the above object, the first aspect of the present invention proposes a prediction system for the time-consuming of medium-voltage power outage plans in a distribution network based on engineering quantification data, including:

[0022] A data collection module for collecting engineering quantification data of power outage plans;

[0023] A data preprocessing module for preprocessing engineering quantification data to remove noise and missing values;

[0024] A prediction model training module for training a prediction model using a machine learning algorithm;

[0025] A prediction module for inputting engineering quantification data and outputting a time-consuming prediction result of the power outage plan;

[0026] An adjustment and optimization module for adjusting and optimizing the power outage plan according to the prediction result;

[0027] A display and feedback module for displaying the prediction result and providing decision support information.

[0028] The beneficial effects of the present invention are as follows. On the one hand, it improves the accuracy of the power outage plan: through quantitative data analysis, it can accurately predict the time consumed during the power outage process, avoid excessive power outages or power outages for too short a time, and thus better coordinate the operation and maintenance work of the distribution network. On the other hand, it optimizes resource allocation: predicting the power outage duration can help power companies reasonably allocate manpower, material resources, and equipment in the power outage plan, ensure the efficient use of resources, and reduce operating costs.

[0029] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and / or additional aspects and advantages of the present invention will become apparent and easy to understand from the following description of the embodiments in conjunction with the drawings, in which:

[0031] Figure 1 is a schematic diagram of a method for predicting the duration of a medium-voltage power outage plan in a distribution network based on engineering quantitative data according to an embodiment of the present invention;

[0032] Figure 2 is a schematic diagram of a system for predicting the duration of a medium-voltage power outage plan in a distribution network based on engineering quantitative data according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0034] A method for predicting the duration of a medium-voltage power outage plan in a distribution network based on engineering quantitative data according to an embodiment of the present invention will be described below in conjunction with the drawings.

[0035] As Figure 1 shown, a method for predicting the duration of a medium-voltage power outage plan in a distribution network based on engineering quantitative data according to an embodiment of the present invention may include.

[0036] Specifically, S1. Data collection: Collect engineering quantitative data in the medium-voltage power outage plan of the distribution network, including information such as the line length of the power outage area, substation load, equipment type, work difficulty, number of operating personnel, weather conditions, historical power outage data, etc.;

[0037] S2. Data preprocessing: Preprocess the collected engineering quantitative data, remove noise data, and fill or correct missing values;

[0038] S3. Prediction model training: Based on the preprocessed data, a time-consuming prediction model is established using machine learning algorithms, including but not limited to regression analysis, support vector machines, neural networks, etc.;

[0039] S4. Predict the total time-consuming: Input the engineering quantification data into the time-consuming prediction model to predict the total time-consuming of the medium-voltage power outage plan in the distribution network;

[0040] S5. Output results and adjustment and optimization: Output the prediction results, and adjust and optimize the power outage plan according to actual needs to reduce the power outage time.

[0041] It should be noted that the engineering quantification data further includes the geographical information of the power outage scope, the load types within the power outage area, the repair or replacement cycle of distribution equipment, and the equipment status information during the power outage.

[0042] It should be noted that the machine learning algorithm optimizes the accuracy of the prediction model by training historical power outage data and performing cross-validation.

[0043] It should be noted that the preprocessing steps include data standardization, normalization, and the handling of outliers.

[0044] It should be noted that the prediction model is based on a neural network algorithm, trained using a multi-layer perceptron (MLP), and the parameters of the model are optimized through the backpropagation algorithm.

[0045] It should be noted that the output of the time-consuming prediction model includes not only the total time-consuming prediction result but also the time prediction for each stage, including the preparation stage, the construction stage, the restoration stage, etc.

[0046] It should be noted that the model optimization steps include introducing intelligent optimization algorithms such as genetic algorithms and particle swarm optimization algorithms to optimize the parameters of the model.

[0047] It should be noted that the prediction results are updated through real-time data and dynamically adjusted in combination with changes in engineering quantification data to further improve the accuracy and real-time performance of the prediction.

[0048] It should be noted that the prediction model is used for decision-making support in the distribution network operation and maintenance department to help formulate a more scientific and reasonable power outage plan and reduce the impact of power outages on users.

[0049] As Figure 2 shown, a time-consuming prediction system for medium-voltage power outage plans in the distribution network based on engineering quantification data according to an embodiment of the present invention may include.

[0050] Specifically, a data collection module for collecting engineering quantification data of power outage plans;

[0051] A data preprocessing module for preprocessing engineering quantization data to remove noise and missing values;

[0052] A prediction model training module for training a prediction model using machine learning algorithms;

[0053] A prediction module for inputting engineering quantization data and outputting the time-consuming prediction result of the power outage plan;

[0054] An adjustment and optimization module for adjusting and optimizing the power outage plan according to the prediction result;

[0055] A display and feedback module for displaying the prediction result and providing decision support information.

[0056] In summary, a prediction system for the time-consuming of medium-voltage power outage plans in a distribution network based on engineering quantization data according to an embodiment of the present invention effectively improves the accuracy of power outage plans on the one hand and optimizes resource allocation on the other hand.

[0057] In the description of this specification, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of these features. In the description of this application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0058] In the description of this specification, the description referring to terms such as "an embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0059] Although the embodiments of this application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting this application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A prediction method for the time-consuming of medium-voltage power outage plan in distribution network based on engineering quantification data, characterized in that, Including: S1. Data collection: Collect the engineering quantification data in the medium-voltage power outage plan of the distribution network, including information such as the line length of the outage area, substation load, equipment type, work difficulty, number of operating personnel, weather conditions, historical outage data, etc.; S2. Data preprocessing: Preprocess the collected engineering quantification data, remove noise data, and fill or correct missing values; S3. Prediction model training: According to the preprocessed data, use machine learning algorithms to establish a time-consuming prediction model, and the algorithms include but are not limited to regression analysis, support vector machine, neural network, etc.; S4. Predict the total time-consuming: Input the engineering quantification data into the time-consuming prediction model to predict the total time-consuming of the medium-voltage power outage plan of the distribution network; S5. Output results and adjustment and optimization: Output the prediction results, and adjust and optimize the power outage plan according to actual needs to reduce the power outage time.

2. The method for predicting the time consumption of the medium-voltage power outage plan in the distribution network based on engineering quantification data according to claim 1, wherein The engineering quantification data further includes the geographical information of the outage scope, the load type within the outage area, the repair or replacement cycle of distribution equipment, and the equipment status information during the power outage.

3. A method for predicting the time-consuming of medium-voltage power outage plan in a distribution network based on engineering quantification data according to claim 1, characterized in that, The machine learning algorithm optimizes the accuracy of the prediction model by training historical outage data and performing cross-validation.

4. A method for predicting the time consumption of medium-voltage power outage plans in a distribution network based on engineering quantification data according to claim 1, characterized in that The preprocessing step includes data standardization, normalization, and the handling of outliers.

5. A method for predicting the time consumption of medium-voltage power outage plans in a distribution network based on engineering quantification data according to claim 1, characterized in that, The prediction model is based on the neural network algorithm, trained using a multi-layer perceptron (MLP), and the parameters of the model are optimized through the backpropagation algorithm.

6. The method for predicting the time-consuming of medium-voltage power outage plan in a distribution network based on engineering quantification data according to claim 1, wherein The output of the time-consuming prediction model includes not only the total time-consuming prediction result but also the time prediction of each stage, including the preparation stage, construction stage, restoration stage, etc.

7. A method for predicting the time-consuming of medium-voltage power outage plan in distribution network based on engineering quantification data according to claim 1, characterized in that, The model optimization step includes introducing intelligent optimization algorithms such as genetic algorithm and particle swarm optimization algorithm to optimize the parameters of the model.

8. A method for predicting the time-consuming of medium-voltage power outage plan in a distribution network based on engineering quantification data according to claim 1, characterized in that, The prediction result is updated through real-time data and dynamically adjusted in combination with the changes in the engineering quantification data to further improve the accuracy and real-time performance of the prediction.

9. A method for predicting the time consumption of medium-voltage power outage plans in a distribution network based on engineering quantification data according to claim 1, wherein, The prediction model is used for decision support in the distribution network operation and maintenance department to help formulate a more scientific and reasonable power outage plan and reduce the impact of power outages on users.

10. A medium-voltage power outage plan duration prediction system for distribution networks based on engineering quantification data, characterized in that, Including: A data collection module for collecting the engineering quantification data of the power outage plan; A data preprocessing module for preprocessing the engineering quantification data to remove noise and missing values; A prediction model training module for training a prediction model using machine learning algorithms; A prediction module for inputting the engineering quantification data and outputting the time-consuming prediction result of the power outage plan; An adjustment and optimization module for adjusting and optimizing the power outage plan according to the prediction result; A display and feedback module for displaying the prediction result and providing decision support information.

Images