A carbon emission monitoring management method and system for a substation

Abstract

The application discloses a carbon emission monitoring management method and system for a transformer substation, which utilizes various electrical equipment operation efficiency information and convolutional neural network technology to monitor and manage the state of large different climate and environment urban power supply areas and adjust different regional population changes; the method comprises collecting carbon emission related information of the transformer substation of the urban power supply area, wherein the carbon emission related information of the transformer substation comprises different urban power supply area different power consumption data of different power groups and electrical equipment operation efficiency information of different power groups in the urban power supply area within a preset time before the population change of different regions occurs; and the electrical equipment operation efficiency information of different power groups in the urban power supply area is classified according to the statistical situation of the electrical equipment operation efficiency information, so that the seasonal safety is ensured and the electrical equipment operation efficiency information of the urban power supply area is accurately monitored per unit time.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of urban carbon emission monitoring and management, and particularly relates to a carbon emission monitoring and management method and system for a substation. BACKGROUND

[0002] As an important hub of power transmission and distribution, the energy efficiency and emission level of substations directly affect the overall carbon emission performance of the urban power supply area. Therefore, for real-time monitoring and management of substation carbon emissions, not only accurate data collection and analysis are needed, but also deep integration with the overall operation status of the urban power supply area is needed to ensure the accuracy of monitoring and the comprehensiveness of management. However, existing substation carbon emission monitoring methods are usually limited to carbon emission estimation of a single device or a local area, and do not take into account the dynamic changes of the entire urban power supply network.

[0003] The existing carbon emission monitoring technology mainly relies on data collection of local equipment and carbon emission calculation based on emission factors, which has obvious limitations. First, the monitoring method mostly relies on the operation data of a single device, such as the energy consumption of a transformer or a switching device, but the carbon emissions of these devices only account for a part of the emissions of the entire substation or urban power supply system. Second, the power load, energy structure, external climate, and other factors of the urban power supply area are also changing, and if these factors are not fully collected and considered, the accuracy of the monitoring results will be greatly reduced. For example, during peak electricity consumption, the load of the substation may fluctuate sharply, causing significant changes in its carbon emission level, and this dynamic change is not effectively monitored, affecting the true reflection of the emission data.

[0004] In addition, the existing monitoring system has serious deficiencies in data collection and cannot comprehensively obtain the operation status of the substation and its surrounding area. For example, some systems only focus on energy consumption data, ignoring environmental factors, device operation efficiency, system scheduling strategies, and other key factors. The incompleteness of these data leads to inaccuracy in carbon emission monitoring and cannot effectively reflect the carbon emission level of the substation under different loads and different operating conditions. Therefore, the existing technology needs to be improved, and a more comprehensive monitoring method should be adopted to integrate more operating data and environmental factors to provide more accurate basis for carbon emission management of substations. SUMMARY

[0005] To solve the above technical problems, the purpose of the present application is to provide a state monitoring and management method for large-scale different climate and environment urban power supply areas, which utilizes multiple electrical equipment operation efficiency information and convolutional neural network technology, realizes the monitoring and management of large-scale different climate and environment urban power supply area status, adjusts the population change of different regions, ensures the seasonal safety, and accurately monitors the electrical equipment operation efficiency information of the large-scale different climate and environment urban power supply area per unit time.

[0006] The first aspect of the present application provides a carbon emission monitoring management method for a substation, comprising the following steps:

[0007] Collecting carbon emission related information of substations in a city power supply area, wherein the carbon emission related information of the substations includes different regional power consumption data of different power consumption groups in different city power supply areas and electrical equipment operation efficiency information of different power consumption groups in different city power supply areas within a preset time before the change of the population in different regions;

[0008] The electrical equipment operation efficiency information of different power consumption groups in different city power supply areas includes load rate, power factor, equipment loss, operation time, equipment health status, load change and power quality during operation of the city power supply area;

[0009] Among them, the load rate and power factor are collected per unit time, and the equipment loss, operation time, equipment health status, load change and power quality are collected according to the distribution of the preset city area;

[0010] According to the statistical situation of the electrical equipment operation efficiency information, the electrical equipment operation efficiency information of different power consumption groups in different city power supply areas is classified to obtain different climate, environmental electrical equipment operation efficiency information types, emission source types and greenhouse gas concentrations in the statistical area, wherein the different climate, environmental electrical equipment operation efficiency information types include load rate and power factor, and the emission source types and greenhouse gas concentrations include equipment loss, operation time, equipment health status, load change and power quality;

[0011] The different climate, environmental electrical equipment operation efficiency information types, emission source types and greenhouse gas concentrations in the statistical area and the corresponding different regional power consumption data of different power consumption groups in different city power supply areas are uploaded to a graph convolutional neural network model to establish a meteorological condition electrical equipment operation efficiency fluctuation management algorithm and a different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0012] Among them, the input of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm is the different climate, environmental electrical equipment operation efficiency information types in the statistical area, and the output is the management emission factor of the different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the input of the different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm is the emission source type, greenhouse gas concentration and determined management emission factor, and the output is the different regional power consumption data of the city power supply area;

[0013] In practical applications, the information types of the operation efficiency of electrical equipment in different climates and environments in the statistical area of the urban power supply area are collected in a unit of time and input into the meteorological condition electrical equipment operation efficiency fluctuation management algorithm to obtain the management emission factor of the electrical equipment operation efficiency fluctuation management algorithm of different regions and emission source distribution;

[0014] The management emission factor of the electrical equipment operation efficiency fluctuation management algorithm of different regions and emission source distribution is compared with the preset emission factor types:

[0015] When the management emission factor types are less than the preset emission factor types, the emission source type and the greenhouse gas concentration do not need to be set, and the collection and analysis of the information types of the operation efficiency of electrical equipment in different climates and environments in the statistical area are continued;

[0016] When the management emission factor types are equal to or greater than the preset emission factor types, the emission source type and the greenhouse gas concentration are set, and the emission source type, the greenhouse gas concentration, and the management emission factor are input into the electrical equipment operation efficiency fluctuation management algorithm of different regions and emission source distribution to obtain the different regional power consumption data of the urban power supply area.

[0017] Further, the establishing step of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm is:

[0018] According to the carbon emission related information of the transformer substation, the information types of the operation efficiency of electrical equipment of different power consumption groups in the urban power supply area and the corresponding different regional power consumption data are sorted out;

[0019] The information types of the operation efficiency of electrical equipment in different climates and environments in the statistical area are processed and spatio-temporal convolution is performed to convert the original data into practical features for use by the graph convolutional neural network model;

[0020] Using the graph convolutional neural network model, the prepared ReLU function calculation data is used to perform model ReLU function calculation using the selected algorithm, and the model is parameter adjusted;

[0021] After the ReLU function calculation is completed, the related parameters of the model are extracted as the output of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm.

[0022] Further, the establishing step of the electrical equipment operation efficiency fluctuation management algorithm of different regions and emission source distribution is:

[0023] According to the carbon emission related information of the transformer substation, the emission source type, the greenhouse gas concentration, and the corresponding different regional power consumption data of the urban power supply area are sorted out;

[0024] The emission source type and the greenhouse gas concentration are taken as independent variables, the power consumption data of different regions are taken as nodes, data graph structure modeling is carried out by using a convolutional neural network model, and ReLU function calculation is carried out on the model;

[0025] After the ReLU function calculation is completed, different regional power consumption data of the city power supply area is predicted by using a different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0026] The carbon emission related information of the transformer substation is subjected to convolutional neural network calculation, and the statistical deviation between the different regional power consumption data and the actual different regional power consumption data is calculated.

[0027] Further, the data acquisition method of the emission source type and the greenhouse gas concentration comprises:

[0028] The device loss of the city power supply area is monitored and collected by using a temperature monitoring device; the running time of the city power supply area is monitored and collected based on a power equipment monitoring platform; the power quality of the city power supply area is monitored and collected, and the peak value and fluctuation interval of the device loss change are analyzed; the device health condition signal generated by the city power supply area is monitored and collected by using a remote sensing system; and the load change around the city power supply area is collected by using a management system, and the influence generated by different load changes is counted.

[0029] Further, the preset influence causes of the preset emission factor category include energy consumption types, technical and management measures, differences between standardization and local policies, data accuracy and availability, and device production and transportation emission periods.

[0030] On the other hand, the application also provides a carbon emission monitoring and management system for a transformer substation, comprising:

[0031] A carbon emission related information acquisition module of a transformer substation is used to acquire carbon emission related information of a transformer substation of a city power supply area, wherein the carbon emission related information of the transformer substation includes different regional power consumption data of different power consumption groups of the city power supply area and electrical equipment operation efficiency information of the different power consumption groups of the city power supply area within a preset time before a change in the population of the city power supply area;

[0032] The electrical equipment operation efficiency information of the different power consumption groups of the city power supply area includes a load rate, a power factor, a device loss, a running time, a device health condition, a load change and power quality of the city power supply area during operation; the device loss, the running time, the device health condition, the load change and the power quality are collected according to a preset city area distribution;

[0033] The power information monitoring module is used for receiving power consumption data of different power consumption groups in different regions and electrical equipment operation efficiency information of different power consumption groups, classifying the electrical equipment operation efficiency information of different power consumption groups in the urban power supply region based on the statistical situation of the electrical equipment operation efficiency information, and obtaining different climate and environment electrical equipment operation efficiency information types, emission source types and greenhouse gas concentrations in the statistical region; the different climate and environment electrical equipment operation efficiency information types include load rate and power factor, and the emission source types and greenhouse gas concentrations include equipment loss, operation time, equipment health status, load change and power quality;

[0034] The graph convolutional neural network model module is used for receiving the different climate and environment electrical equipment operation efficiency information types, the emission source types and the greenhouse gas concentrations in the statistical region and uploading them to the graph convolutional neural network model, establishing a meteorological condition electrical equipment operation efficiency fluctuation management algorithm and a different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0035] The input of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm is the different climate and environment electrical equipment operation efficiency information types in the statistical region, and the output is a management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the input of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm is the emission source types, the greenhouse gas concentrations and the determined management emission factor, and the output is the different region power consumption data of the urban power supply region.

[0036] The emission factor management module is used for receiving the meteorological condition electrical equipment operation efficiency fluctuation management algorithm and the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the different climate and environment electrical equipment operation efficiency information types in the statistical region are collected in a unit time and input into the meteorological condition electrical equipment operation efficiency fluctuation management algorithm, so as to obtain the management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm.

[0037] The different region household population change analysis module is used for receiving the management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm, comparing the management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm with a preset emission factor type.

[0038] When the management emission factor type is less than the preset emission factor type, the emission source types and the greenhouse gas concentrations do not need to be set, and the collection and analysis of the different climate and environment electrical equipment operation efficiency information types in the statistical region are continued.

[0039] When the management emission factor category is equal to or greater than the preset emission factor category, the emission source type and the greenhouse gas concentration are set, and the emission source type and the greenhouse gas concentration are input into the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm to obtain the different area power consumption data of the urban power supply area.

[0040] Beneficial effects:

[0041] The present application provides a carbon emission monitoring management method and system for a substation, which can comprehensively understand the operation state of the urban power supply area by collecting these data; the method uses a graph convolutional neural network model to establish a meteorological condition electrical equipment operation efficiency fluctuation management algorithm and a different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm, calculates and trains the carbon emission related information of the substation and the corresponding different area power consumption data through a ReLU function, and the model can identify and classify different urban power supply area different area power consumption data; according to the comparison of the management emission factor and the preset emission factor category, it can be determined whether the emission source type and the greenhouse gas concentration need to be set, the different area power consumption data of the urban power supply area can be found in time, and through the application of a variety of electrical equipment operation efficiency information and the graph convolutional neural network model, the adjustment accuracy of the different area household population change of the urban power supply area can be improved, not only the different area power consumption data can be judged, but also the different area household population change prediction and trend analysis can be carried out according to different electricity group data.

[0042] The method of the present application utilizes various electrical equipment operation efficiency information and convolutional neural network technology to realize monitoring and management of large-scale different climate and environment urban power supply area states and adjustment of different regional population changes, ensuring seasonal safety and accurate monitoring of electrical equipment operation efficiency information of urban power supply area per unit time. The present application provides more efficient and accurate carbon emission monitoring means than traditional monitoring methods by comprehensively integrating substation equipment operation state, regional load change, energy structure and environmental factors and other multi-dimensional data. The system not only relies on energy consumption data of a single device, but also dynamically captures and analyzes factors such as power load fluctuation and equipment operation efficiency change, thereby evaluating carbon emission levels in real time. By using intelligent data collection technology and big data analysis algorithms, the system can realize accurate prediction and management of carbon emissions of substations and their power supply areas, effectively improving the accuracy of emission monitoring. More importantly, the method supports joint analysis based on historical data and real-time data, can automatically identify abnormal loads and equipment failures, and timely adjust operation strategies to reduce unnecessary energy waste and carbon emissions. In addition, the system also has flexible scalability and can be customized and optimized according to different regional power demand and energy structure changes to ensure the effectiveness of substation carbon emission management in different situations. This comprehensive and dynamic management method provides a more forward-looking and efficient carbon emission monitoring solution for substations and urban power supply systems. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is a flowchart of a carbon emission monitoring and management method for substations;

[0044] Figure 2 is a module composition diagram of a carbon emission monitoring and management system for substations. DETAILED DESCRIPTION

[0045] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict, and the present application will be further described in detail below with specific embodiments in conjunction with the drawings.

[0046] As shown in Figure 1 , a carbon emission monitoring and management method for substations includes the following steps:

[0047] A1, collect carbon emission related information of substations in urban power supply areas, the carbon emission related information of the substations includes different urban power supply area different electricity group different regional power consumption data and different regional population change before the occurrence of the urban power supply area different electricity group electrical equipment operation efficiency information within a preset time;

[0048] In order to realize the state monitoring management of large-scale different climate, environment and city power supply area, first of all, the carbon emission related information of the substation of the city power supply area needs to be collected. These data can provide information about the performance of the city power supply area in the running process, different regional power consumption data and related electrical equipment operation efficiency information, which provides the basis for subsequent state evaluation and different regional population change adjustment;

[0049] The electrical equipment operation efficiency information of different power groups in the city power supply area includes:

[0050] Load rate and power factor: collect the load rate and power factor of the city power supply area, and analyze the fluctuation of the load rate and power factor; The fluctuation of load rate and power factor can reflect the stability of the city power supply area. The load rate and power factor parameters of the city power supply area need to be collected in unit time, and the fluctuation is recorded.

[0051] Device loss: based on the temperature monitoring device to monitor and collect the device loss of the city power supply area, including the maximum, average and variance of the device loss, etc. The change of device loss can reflect the mechanical operation state of the city power supply area and the change of the population of different regions.

[0052] Running time: use the power equipment monitoring platform to monitor and collect the running time change of the city power supply area, including the running time inside and outside the device. The abnormal change of running time can indicate that the city power supply area has overload, poor heat dissipation and other changes of the population of different regions.

[0053] Device health status: based on the remote sensing system to monitor and collect the device health status signal generated by the city power supply area, and analyze it. The device health status signal can provide the state information inside the city power supply area.

[0054] Load change: based on the household management system to collect the load change around the city power supply area, and count the influence change caused by different load changes, and count the abnormal change of the influence caused by different load changes.

[0055] Power quality: monitor and collect the power quality of the city power supply area, analyze the peak value and fluctuation interval of the device loss change, and the test result of the power quality can provide information about the insulation performance.

[0056] By collecting and recording the electrical equipment operation efficiency information of these different power consumption groups, an information library of the urban power supply area is established for subsequent data analysis, correlation analysis and model ReLU function calculation. The load rate and power factor are collected in unit time, and the equipment loss, operation time, equipment health status, load change and power quality are collected according to the preset urban area distribution. By collecting the carbon emission related information of the transformer substation in the urban power supply area, the basic data of the performance and different regional power consumption data of the urban power supply area in the operation process can be provided, which provides an important basis for subsequent state evaluation, different regional household population change adjustment and performance optimization.

[0057] By analyzing the carbon emission related information of the transformer substation, the stability, mechanical operation state, insulation performance and potential different regional household population change of the urban power supply area can be revealed. In addition to the fluctuation data of the load rate and power factor, the urban power supply area is comprehensively monitored and managed through various detection means such as air temperature monitoring device, power equipment monitoring platform, equipment health status detection, household management system and power quality detection. The state information of the urban power supply area is collected from different angles to improve the accuracy of different regional household population change detection and adjustment.

[0058] By collecting the carbon emission related information of the transformer substation in the urban power supply area and the electrical equipment operation efficiency information, the performance, different regional power consumption data and electrical equipment operation efficiency information of the urban power supply area can be comprehensively understood, and the basic data and basis for subsequent state evaluation, different regional household population change adjustment and performance optimization are provided.

[0059] A2、According to the electrical equipment operation efficiency information statistics, the electrical equipment operation efficiency information of different power consumption groups in the urban power supply area is classified to obtain the statistical area different climate, environmental electrical equipment operation efficiency information species, emission source type and greenhouse gas concentration. The statistical area different climate, environmental electrical equipment operation efficiency information species include load rate and power factor, and the emission source type and greenhouse gas concentration include equipment loss, operation time, equipment health status, load change and power quality.

[0060] In this step, according to the electrical equipment operation efficiency information statistics, the electrical equipment operation efficiency information of different power consumption groups in the urban power supply area is classified, and the electrical equipment operation efficiency information of different power consumption groups is divided into two different information, i.e. statistical area different climate, environmental electrical equipment operation efficiency information species, emission source type and greenhouse gas concentration.

[0061] The load rate and power factor are included in the information of the electrical equipment operation efficiency in different climates and environments in the statistical area. The data can be collected by monitoring and collecting the load rate and power factor parameters of the city power supply area per unit time;

[0062] The emission source type and greenhouse gas concentration include equipment wear and tear, operation time, equipment health, load change, and power quality, which are used to monitor and collect the state of equipment wear and tear, operation time, equipment health, load change, and power quality during operation in the city power supply area;

[0063] The classification basis of the information of the electrical equipment operation efficiency in different climates and environments in the statistical area, the emission source type, and the greenhouse gas concentration is:

[0064] Different types of different regional population changes correspond to different electrical equipment operation efficiency information. By classifying the load rate and power factor separately from other multiple characteristic data, different types of different regional population changes can be more targeted for judgment and analysis. Load rate and power factor fluctuations are more easily related to different climates and different regional population changes, while equipment wear and tear, operation time, sound, and other data are more easily related to mechanical or insulating different regional population changes. Load rate and power factor are more convenient to collect in unit time monitoring and management. Through these data, preliminary different regional population changes can be quickly judged;

[0065] The emission source type and greenhouse gas concentration involve more sensor collection and detection equipment, which requires a certain amount of time and cost for collection. Therefore, by pre-setting a pre-set emission factor type, if the management emission factor of the information of the electrical equipment operation efficiency in different climates and environments in the statistical area is less than the pre-set emission factor type, the emission source type and greenhouse gas concentration can be avoided from being frequently set, thereby improving the management effect.

[0066] By dividing the electrical equipment operation efficiency information into two information, different types of different regional population changes can be more targeted for judgment and analysis. By pre-setting a pre-set emission factor type, if the management emission factor of the information of the electrical equipment operation efficiency in different climates and environments in the statistical area is less than the pre-set emission factor type, the emission source type and greenhouse gas concentration can be avoided from being frequently set, thereby improving the management effect. By classifying different types of electrical equipment operation efficiency information, more accurate judgment and adjustment results can be obtained by comprehensively analyzing the relevance between different characteristic data.

[0067] A3, upload the information of different climate, environmental electrical equipment operation efficiency, information types, emission source types, greenhouse gas concentrations and corresponding different regional power consumption data of different power consumption groups in the city power supply area to the graph convolutional neural network model, establish meteorological condition electrical equipment operation efficiency fluctuation management algorithm and different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0068] The establishment steps of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm are:

[0069] According to the carbon emission related information of the city power supply area substation collected in step A1, the information types of different power consumption groups of electrical equipment operation efficiency in the city power supply area and the corresponding different regional power consumption data are sorted out;

[0070] The information types of different climate, environmental electrical equipment operation efficiency in the statistical area are processed and spatio-temporal convolution is performed to convert the original data into practical features for use by the graph convolutional neural network model;

[0071] According to the problem description, select a graph convolutional neural network model suitable for this scenario, use the selected algorithm to calculate the model ReLU function, and adjust the parameters of the model;

[0072] After the ReLU function calculation is completed, the relevant parameters of the model are extracted as the output of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm.

[0073] The establishment steps of the different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm are:

[0074] According to the carbon emission related information of the city power supply area substation collected in step A1, the information types of different power consumption groups of electrical equipment operation efficiency in the city power supply area and the corresponding different regional power consumption data are sorted out;

[0075] Use the convolutional neural network model for training, use the emission source type and greenhouse gas concentration as the independent variable, and use the different regional power consumption data as the node to perform data graph structure modeling, and perform ReLU function calculation on the model;

[0076] After the ReLU function calculation is completed, the different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm is used to predict the different regional power consumption data of the city power supply area,

[0077] The different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm uses the convolutional neural network model for training,

[0078] Convolutional neural network model architecture

[0079] A convolutional neural network (CNN) is used to extract key features of electrical equipment operational efficiency. Here is a typical architecture of a CNN model:

[0080] Input Layer: The input data is usually multi-dimensional features of equipment operation, such as voltage, current, temperature, etc., which can be represented as a matrix (e.g., each row represents a timestamp and each column represents a device feature).

[0081] Convolutional Layer: The convolutional layer is used to extract local features from the input data. For example, a set of filters (convolution kernels) is applied to the device's operational data to extract feature maps.

[0082] Activation Layer: The ReLU (Rectified Linear Unit) activation function is commonly used to introduce non-linear transformations, improving the model's fitting ability.

[0083] Pooling Layer: Pooling operations are used for downsampling, reducing the size and computational load of feature maps while preserving key information.

[0084] Fully Connected Layer: The extracted features are classified or regressed through the fully connected layer, outputting the predicted value of the device's operational efficiency.

[0085] Data Formatting and Input: Assuming the input data is x, its shape is m x n, where m is the number of data samples and n is the dimension of the features. For a convolutional neural network, the data is organized into a three-dimensional matrix, with each input sample having dimensions h x w x c (where h and w are the height and width of the feature map, and c is the number of input channels). If it is time series data, it can be converted into a time window or sliding window form.

[0086] Forward Propagation of the Model: The convolutional neural network extracts data features through a series of convolution operations and activation functions. Assuming the input data is X and the convolution kernel used by the convolutional layer is W, the output of the convolution operation is: Z = X * W + b

[0087] where * represents the convolution operation, b is the bias term, and Z is the output of the convolutional layer. Non-linear transformation is performed through the activation function f (such as ReLU): A = f(Z)

[0088] Pooling layers are usually used to reduce computational complexity and reduce overfitting, and their operations can be max pooling (MaxPooling) or average pooling (Average Pooling). For max pooling operations, assuming the input feature map A is h x w in size, the output of the pooling operation is:

[0089] P = MaxPool(A)

[0090] This operation selects the maximum value in each window, reducing the size of the feature map.

[0091] After convolution and pooling operations, the network passes these feature vectors to fully connected layers for prediction. The fully connected layers map high-dimensional features to the target output space, such as the operational efficiency prediction of electrical equipment. Assuming F is the input feature of the fully connected layer, W f is the weight matrix, and b f is the bias term, then:

[0092] Y = FW f + b f

[0093] where Y is the predicted value of the output layer, representing the operational efficiency of electrical equipment.

[0094] A loss function is used to measure the gap between the predicted value and the actual value. For regression problems, the commonly used loss function is Mean Squared Error (MSE):

[0095]

[0096] where y i is the actual value, is the model predicted value, and N is the number of samples. An optimization algorithm (such as gradient descent or Adam optimizer) is used to minimize the loss function, adjusting the network's weights W and biases b, and the update process is as follows:

[0097]

[0098] where η is the learning rate, and are the gradients of the loss function with respect to the weights and biases.

[0099] The summary of the training process includes:

[0100] Data preparation: Collect and preprocess the operational data of electrical equipment.

[0101] Model design: Build a CNN model, including convolution layers, pooling layers, and fully connected layers.

[0102] Forward propagation: Input data into the model, extract features through convolution operations and pooling operations, and finally predict the device operational efficiency through fully connected layers.

[0103] Loss function calculation and optimization: Calculate the prediction error through the loss function, and adjust the model parameters using the optimization algorithm.

[0104] Training and evaluation: Use the training data for multiple iterations of training, and use the validation set to evaluate the performance of the model.

[0105] The trained model can monitor the operation efficiency of the equipment in real time, predict the efficiency fluctuation of the equipment according to the input real-time data, and provide support for the operation and maintenance decision of the substation or other electrical facilities, such as adjusting the load and optimizing the equipment operation strategy.

[0106] Through the convolutional neural network (CNN) for training and management of electrical equipment operation efficiency fluctuation, effective features can be automatically extracted from multi-dimensional input data, and the efficiency change of the equipment can be accurately predicted. Through the loss function optimization in the training process, CNN can gradually improve the accuracy of prediction, and provide effective support for the management of electrical equipment.

[0107] The different regional power consumption data is corresponded with the actual different regional power consumption data; specifically, the corresponding relationship between the different regional power consumption data and the actual different regional power consumption data is obtained by performing ReLU function calculation and model training on the carbon emission related information of the substation, and the statistical deviation between the different regional power consumption data and the actual different regional power consumption data is calculated by performing classification and regression on the carbon emission related information of the substation and the graph convolutional neural network model.

[0108] The input of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm is the statistical regional different climate, environment electrical equipment operation efficiency information type, and the output is the management emission factor of the different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the input of the different regional, emission source distribution electrical equipment operation efficiency fluctuation management algorithm is the emission source type, greenhouse gas concentration and the determined management emission factor, and the output is the different regional power consumption data of the urban power supply area.

[0109] This step can obtain complete input information by sorting and processing the different power consumption groups electrical equipment operation efficiency information type and different regional power consumption data of the urban power supply area, so that the electrical equipment operation efficiency fluctuation management algorithm can more accurately judge the state of the equipment and the different regional power consumption data; the selected graph convolutional neural network model is calculated by using the prepared ReLU function calculation data, and the model parameters are adjusted, which can improve the accuracy and performance of the model by continuously optimizing the model parameters and algorithm selection; by outputting the management emission factor, the importance of each feature to the judgment of the different regional power consumption data can be understood, so as to better understand the relationship between the electrical equipment operation efficiency fluctuation and the different regional power consumption data.

[0110] In summary, the electrical equipment operation efficiency fluctuation management algorithm can more accurately evaluate the state of the urban power supply area and the different regional power consumption data, and provide effective decision support and different regional household population change exclusion guidance for the braking personnel.

[0111] A4, collect different climate, environmental electrical equipment operation efficiency information categories in the statistical area of the urban power supply area per unit time, and input into the meteorological condition electrical equipment operation efficiency fluctuation management algorithm to obtain the management emission factor of the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0112] In this step, before data input, the data is preprocessed, including data desensitization, arrangement, normalization, etc., to ensure the quality and consistency of the data input into the model;

[0113] The different climate, environmental electrical equipment operation efficiency information categories collected per unit time in the statistical area are input as input to the meteorological condition electrical equipment operation efficiency fluctuation management algorithm for spatio-temporal convolution and state evaluation, providing management emission factors for the subsequent different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm; The management emission factor reflects the current state and performance of the urban power supply area, and through the management emission factor, the operation status of the urban power supply area can be preliminarily judged and evaluated;

[0114] In this step, through the preprocessing steps of data desensitization, arrangement and normalization, the quality and consistency of the data input into the model can be ensured, and problems such as abnormal values, noise and inconsistent sampling rates in the data can be excluded, improving the accuracy and reliability of the monitoring algorithm;

[0115] The management emission factor obtained by the meteorological condition electrical equipment operation efficiency fluctuation management algorithm can reflect the current state and performance of the urban power supply area, and these management emission factors can be used for preliminary judgment and evaluation of the urban power supply area, providing important input for the subsequent different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0116] By continuously monitoring and evaluating the state of the urban power supply area, potential changes in the different area household population or abnormal conditions can be discovered in time, so that maintenance measures can be taken in advance to avoid the impact of different area household population changes on different climate, environmental supply. Through unit time analysis and evaluation of the state of the urban power supply area, the electrical equipment operation strategy can be optimized, and the operation efficiency and energy utilization efficiency of the urban power supply area can be improved.

[0117] A5, compare the management emission factor of the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm with the preset emission factor category: when the management emission factor category is less than the preset emission factor category, there is no need to set the emission source type and greenhouse gas concentration, and the collection and analysis of the different climate, environmental electrical equipment operation efficiency information categories in the statistical area continue;

[0118] A6、In the case of the management emission factor category being equal to or greater than the preset emission factor category, the emission source type and the greenhouse gas concentration are set, and the emission source type and the greenhouse gas concentration are input into the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm together with the management emission factor to obtain the different area power consumption data of the urban power supply area.

[0119] In the case of the management emission factor category being less than the preset emission factor category, the emission source type and the greenhouse gas concentration do not need to be set, and the collection and analysis of the different climate, environment electrical equipment operation efficiency information category in the statistical area are continued to be maintained;

[0120] In the case of the management emission factor category being equal to or greater than the preset emission factor category, the emission source type and the greenhouse gas concentration are set, and the emission source type and the greenhouse gas concentration are input into the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm together with the management emission factor to obtain the different area power consumption data of the urban power supply area.

[0121] The preset emission factor category refers to a fixed value or range used to determine whether the emission source type and the greenhouse gas concentration need to be set, which is preset based on the following factors: energy consumption type, technology and management measures, differences between standardized and local policies, and data accuracy and availability, equipment production and transportation emission period.

[0122] Further, the preset of the preset emission factor category is a dynamic process, which needs to be adjusted and optimized according to the actual situation. By continuously observing and analyzing the system operation state, the different area household population change data and the maintenance record, the preset emission factor category needs to be continuously optimized to improve the accuracy and reliability of the state monitoring management.

[0123] In the case of the management emission factor category being less than the preset emission factor category, the meteorological condition state evaluation result of the urban power supply area indicates that it is in a normal state. In this case, the emission source type and the greenhouse gas concentration do not need to be set, and the collection and analysis of the initial force electrical equipment operation efficiency information category can be continued to be maintained to help monitor and collect the basic operation state of the urban power supply area;

[0124] If the management emission factor is equal to or greater than the preset emission factor category, the meteorological condition state evaluation result of the urban power supply area indicates that there is a potential different area household population change or abnormal situation. In this case, the emission source type and the greenhouse gas concentration need to be set, and they are input into the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm together with the meteorological condition management emission factor to obtain the different area power consumption data of the urban power supply area;

[0125] The different region, emission source distribution electric equipment operation efficiency fluctuation management algorithm will comprehensively consider the different climate, environmental electric equipment operation efficiency information type, emission source type, greenhouse gas concentration in the statistical region and the preset management emission factor, and perform ReLU function calculation and analysis by using the convolutional neural network algorithm, so that the different region power consumption data of the urban power supply region is determined;

[0126] By comparing the management emission factor with the preset emission factor type, it can be quickly judged whether the urban power supply region is in a normal state, so as to decide whether to set the emission source type and the greenhouse gas concentration. If the management emission factor is less than the preset emission factor type, additional data collection and analysis can be avoided, time and resources can be saved;

[0127] When the management emission factor is equal to or greater than the preset emission factor type, the emission source type and the greenhouse gas concentration are set, and they are input into the different region, emission source distribution electric equipment operation efficiency fluctuation management algorithm together with the management emission factor, which can provide accurate different region power consumption data judgment. By comprehensively considering multiple data information and preset parameters, ReLU function calculation and analysis are performed by using the convolutional neural network algorithm, so that the different region power consumption data of the urban power supply region can be accurately determined;

[0128] The determination of the preset emission factor type is based on multiple factors. By comprehensively considering these factors, the preset emission factor type suitable for the specific urban power supply region is formulated, the accuracy and reliability of the state monitoring management are improved; by observing and analyzing the system operation state, the different region household population change data and the maintenance record, the preset emission factor type can be continuously optimized, the actual operation of the urban power supply region is adapted, and the accuracy and reliability of the monitoring algorithm are improved.

[0129] As shown in Figure 2 The carbon emission monitoring management system for the substation is realized by different control modules, including;

[0130] The carbon emission related information acquisition module of the substation is used for acquiring the carbon emission related information of the substation in the urban power supply region. The carbon emission related information of the substation includes different region power consumption data of different power consumption groups in different urban power supply regions and electric equipment operation efficiency information of different power consumption groups in the urban power supply region within a preset time before the occurrence of different region household population change;

[0131] The city power supply area different electricity group electrical equipment operation efficiency information includes load rate, power factor, equipment loss, operation time, equipment health condition, load change and power quality in the running process of the city power supply area; the load rate and power factor are collected per unit time, and the equipment loss, operation time, equipment health condition, load change and power quality are collected according to the preset city area distribution;

[0132] The power information monitoring module is used for receiving different electricity group different area power consumption data and different electricity group electrical equipment operation efficiency information, classifying the city power supply area different electricity group electrical equipment operation efficiency information based on the electrical equipment operation efficiency information statistics, and obtaining different climate, environment electrical equipment operation efficiency information types, emission source types and greenhouse gas concentrations in the statistical area; the different climate, environment electrical equipment operation efficiency information types in the statistical area include load rate and power factor, and the emission source types and greenhouse gas concentrations include equipment loss, operation time, equipment health condition, load change and power quality;

[0133] The graph convolutional neural network model module is used for receiving the different climate, environment electrical equipment operation efficiency information types, emission source types and greenhouse gas concentrations in the statistical area and uploading them to the graph convolutional neural network model, establishing meteorological condition electrical equipment operation efficiency fluctuation management algorithm and different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0134] The meteorological condition electrical equipment operation efficiency fluctuation management algorithm is inputted with the different climate, environment electrical equipment operation efficiency information types in the statistical area, and outputted with the management emission factor of the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm is inputted with the emission source types, greenhouse gas concentrations and the determined management emission factor, and outputted with the different area power consumption data of the city power supply area;

[0135] The emission factor management module is used for receiving the meteorological condition electrical equipment operation efficiency fluctuation management algorithm and the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the different climate, environment electrical equipment operation efficiency information types in the statistical area are collected per unit time and inputted into the meteorological condition electrical equipment operation efficiency fluctuation management algorithm, so as to obtain the management emission factor of the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm;

[0136] The different area household population change analysis module is used for receiving the management emission factor of the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm, comparing the management emission factor of the different area, emission source distribution electrical equipment operation efficiency fluctuation management algorithm with the preset emission factor types;

[0137] When the management emission factor category is less than the preset emission factor category, the emission source type and the greenhouse gas concentration are not set, and the collection and analysis of the different climate and environmental electrical equipment operation efficiency information in the statistical area are continued;

[0138] When the management emission factor category is equal to or greater than the preset emission factor category, the emission source type and the greenhouse gas concentration are set, and the emission source type and the greenhouse gas concentration are input into the different area and emission source distribution electrical equipment operation efficiency fluctuation management algorithm to obtain the different area power consumption data of the urban power supply area.

[0139] The system realizes comprehensive monitoring and management of the state of the urban power supply area by collecting different area power consumption data of different power consumption groups and electrical equipment operation efficiency information of different power consumption groups in the urban power supply area, and performing information monitoring and graph convolutional neural network model, thereby realizing comprehensive monitoring and management of the state of the urban power supply area. Compared with the traditional method of only monitoring and managing the load rate and power factor parameters, the system considers more electrical equipment operation efficiency information and provides more comprehensive state evaluation;

[0140] The system uses the meteorological condition electrical equipment operation efficiency fluctuation management algorithm and the different area and emission source distribution electrical equipment operation efficiency fluctuation management algorithm to evaluate the state of the urban power supply area. The meteorological condition electrical equipment operation efficiency fluctuation management algorithm evaluates the state by collecting different climate and environmental electrical equipment operation efficiency information in the statistical area per unit time, which is more timely and rapid. The different area and emission source distribution electrical equipment operation efficiency fluctuation management algorithm evaluates the state by comprehensively considering different area power consumption data of different power consumption groups and electrical equipment operation efficiency information of different power consumption groups, which is more accurate and reliable;

[0141] By comparing the management emission factor of the different area and emission source distribution electrical equipment operation efficiency fluctuation management algorithm with the preset emission factor category, the different area power consumption data of the urban power supply area can be determined. Since the system comprehensively considers different area power consumption data of different power consumption groups and electrical equipment operation efficiency information of different power consumption groups and uses a hierarchical evaluation method, the accuracy of the judgment of the different area power consumption data can be improved, and the possibility of false positives and false negatives can be reduced;

[0142] In summary, the method uses multiple electrical equipment operation efficiency information and convolutional neural network technology to realize monitoring and management of the state of large different climate and environmental urban power supply areas and adjustment of different area population changes, ensuring seasonal safety and accurate monitoring of electrical equipment operation efficiency information per unit time in the urban power supply area.

[0143] The various changed modes and specific embodiments of the state monitoring management method of the large different climate and environment city power supply area in the foregoing embodiment one are also applicable to the state monitoring management system of the large different climate and environment city power supply area in the present embodiment. Through the foregoing detailed description of the state monitoring management method of the large different climate and environment city power supply area, those skilled in the art can clearly know the implementation method of the state monitoring management system of the large different climate and environment city power supply area in the present embodiment. Therefore, in order to make the description brief, the state monitoring management system of the large different climate and environment city power supply area in the present embodiment will not be described in detail here.

[0144] Although embodiments of the present application have been shown and described, it would be appreciated by those of ordinary skill in the art that a variety of equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A carbon emission monitoring management method for a substation, characterized by, The method comprises the following steps: A1, collecting carbon emission related information of substations in the urban power supply area, the carbon emission related information of the substations including different regional power consumption data of different power consumption groups in different urban power supply areas and electrical equipment operation efficiency information of different power consumption groups in different urban power supply areas within a preset time before the change of the population of different regions; A2, classifying the electrical equipment operation efficiency information of different power consumption groups in different urban power supply areas according to the statistical situation of the electrical equipment operation efficiency information, and obtaining the types of electrical equipment operation efficiency information, emission source types and greenhouse gas concentrations in different climates and environments in the statistical region; A3, uploading the types of electrical equipment operation efficiency information, emission source types and greenhouse gas concentrations in different climates and environments in the statistical region and the corresponding different regional power consumption data of different power consumption groups in different urban power supply areas to a graph convolutional neural network model, and establishing meteorological condition electrical equipment operation efficiency fluctuation management algorithms and different regional and emission source distribution electrical equipment operation efficiency fluctuation management algorithms; A4, collecting the types of electrical equipment operation efficiency information in different climates and environments in the statistical region of the urban power supply area per unit time, and inputting them into the meteorological condition electrical equipment operation efficiency fluctuation management algorithm to obtain the management emission factors of the different regional and emission source distribution electrical equipment operation efficiency fluctuation management algorithm; A5, comparing the management emission factors of the different regional and emission source distribution electrical equipment operation efficiency fluctuation management algorithm with the preset emission factor types: when the types of management emission factors are less than the types of preset emission factors, the emission source types and greenhouse gas concentrations do not need to be set, and the collection and analysis of the types of electrical equipment operation efficiency information in different climates and environments in the statistical region continue to be maintained; A6, when the types of management emission factors are equal to or greater than the types of preset emission factors, the emission source types and greenhouse gas concentrations are set, and the emission source types and greenhouse gas concentrations and the management emission factors are input into the different regional and emission source distribution electrical equipment operation efficiency fluctuation management algorithm to obtain the different regional power consumption data of the urban power supply area.

2. A carbon emission monitoring management method for a substation according to claim 1, characterized in that, The electrical equipment operation efficiency information of different power consumption groups in the urban power supply area includes load rate, power factor, equipment loss, operation time, equipment health status, load change and power quality during the operation of the urban power supply area; the load rate and power factor are collected per unit time, and the equipment loss, operation time, equipment health status, load change and power quality are collected according to the preset urban area distribution.

3. A carbon emission monitoring management method for a substation according to claim 1, characterized in that, The types of electrical equipment operation efficiency information in different climates and environments in the statistical region include load rate and power factor, and the emission source types and greenhouse gas concentrations include equipment loss, operation time, equipment health status, load change and power quality.

4. A carbon emission monitoring management method for a substation according to claim 1, characterized in that, The input of the different regional and emission source distribution electrical equipment operation efficiency fluctuation management algorithm is the emission source types, greenhouse gas concentrations and determined management emission factors, and the output is the different regional power consumption data of the urban power supply area.

5. A carbon emission monitoring management method for a substation according to claim 1, characterized in that, The establishment steps of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm are: According to the carbon emission related information of the transformer substation, the efficiency information of the electrical equipment of different power consumption groups in the urban power supply area is sorted and the corresponding power consumption data of different regions is obtained; the efficiency information of the electrical equipment in different climates and environments in the statistical area is processed and spatio-temporal convolution is performed to convert the original data into practical features for the graph convolutional neural network model; Using the graph convolutional neural network model, the prepared ReLU function calculation data is used to calculate the model ReLU function using the selected algorithm, and the parameters of the model are adjusted; after the ReLU function calculation is completed, the related parameters of the model are extracted as the output of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm.

6. A carbon emission monitoring management method for a substation according to claim 1, characterized in that, The establishment steps of the electrical equipment operation efficiency fluctuation management algorithm of different regions and emission sources are: According to the carbon emission related information of the transformer substation, the type of emission source, the concentration of greenhouse gas and the corresponding power consumption data of different regions in the urban power supply area are sorted; Using the convolutional neural network model for training, the type of emission source and the concentration of greenhouse gas are used as independent variables, and the power consumption data of different regions are used as nodes for data graph structure modeling, and ReLU function calculation is performed on the model; After the ReLU function calculation is completed, the power consumption data of different regions in the urban power supply area is predicted by the electrical equipment operation efficiency fluctuation management algorithm of different regions and emission sources, and the carbon emission related information of the transformer substation is convolved by the neural network to calculate the statistical deviation between the power consumption data of different regions and the actual power consumption data of different regions.

7. A carbon emission monitoring management method for a substation according to claim 1, characterized by, The data collection method of the type of emission source and the concentration of greenhouse gas includes: monitoring and collecting the equipment loss of the urban power supply area by using a temperature monitoring device; monitoring and collecting the running time of the urban power supply area based on a power equipment monitoring platform; monitoring and collecting the power quality of the urban power supply area, analyzing the peak value and fluctuation interval of the equipment loss change; monitoring and collecting the equipment health condition signal generated by the urban power supply area by using a remote sensing system; collecting the load change around the urban power supply area by using a management system, and counting the influence caused by different load changes.

8. A carbon emission monitoring management method for a substation according to claim 1, characterized by, The preset influence reasons of the preset emission factor type include energy consumption type, technology and management measures, standardization and local policy difference, data accuracy and availability, and equipment production and transportation emission period.

9. A carbon emission monitoring management system for a substation, characterized by, It includes: The carbon emission related information collection module of the transformer substation is used to collect the carbon emission related information of the transformer substation in the urban power supply area, which includes the power consumption data of different regions of different power consumption groups in different cities and the efficiency information of the electrical equipment of different power consumption groups in the urban power supply area before the change of the population of different regions occurs within a preset time; The power information monitoring module is used for receiving power consumption data of different power consumption groups in different regions and electrical equipment operation efficiency information of different power consumption groups, classifying the electrical equipment operation efficiency information of different power consumption groups in the urban power supply region based on the statistical situation of the electrical equipment operation efficiency information, and obtaining different climate and environment electrical equipment operation efficiency information types, emission source types and greenhouse gas concentrations in the statistical region; the different climate and environment electrical equipment operation efficiency information types include load rate and power factor, and the emission source types and greenhouse gas concentrations include equipment loss, operation time, equipment health status, load change and power quality; The graph convolutional neural network model module is used for uploading the different climate and environment electrical equipment operation efficiency information types, emission source types and greenhouse gas concentrations in the statistical region to the graph convolutional neural network model, establishing meteorological condition electrical equipment operation efficiency fluctuation management algorithms and different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithms; wherein the input of the meteorological condition electrical equipment operation efficiency fluctuation management algorithm is the different climate and environment electrical equipment operation efficiency information types in the statistical region, and the output is a management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the input of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm is the emission source type, greenhouse gas concentration and determined management emission factor, and the output is the different region power consumption data of the urban power supply region; The emission factor management module is used for receiving the meteorological condition electrical equipment operation efficiency fluctuation management algorithm and the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm; the different climate and environment electrical equipment operation efficiency information types in the statistical region are collected in a unit time and input into the meteorological condition electrical equipment operation efficiency fluctuation management algorithm to obtain the management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm; The different region household population change analysis module is used for receiving the management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm, and comparing the management emission factor of the different region and emission source distribution electrical equipment operation efficiency fluctuation management algorithm with preset emission factor types.

Images