Abstract: Various embodiments of the teachings herein include a method for deploying power quality monitoring (PQM) devices. The method may include: determining a maximum number of PQM devices and historical power data of candidate deployment points, wherein the number of the candidate deployment points is greater than the maximum number of the PQM devices; clustering the historical power data of the candidate deployment points, wherein a target number of categories is determined on the basis of a silhouette coefficient of each candidate number of categories and the maximum number of the PQM devices; and determining PQM device deployment points based on the center of each category in the target number of categories.

Abstract: Various embodiments of the teachings herein include a method for deploying power quality monitoring (PQM) devices. The method may include: determining a maximum number of PQM devices and historical power data of candidate deployment points, wherein the number of the candidate deployment points is greater than the maximum number of the PQM devices; clustering the historical power data of the candidate deployment points, wherein a target number of categories is determined on the basis of a silhouette coefficient of each candidate number of categories and the maximum number of the PQM devices; and determining PQM device deployment points based on the center of each category in the target number of categories.

Abstract: A power load data prediction method and device, and a storage medium are disclosed. In an embodiment, the he method comprises: acquiring historical power load data of a one-dimensional time sequence, the historical power load data including values of corresponding time points; mapping the values of corresponding time points to a coordinate system in which a horizontal axis is a set time period, and a vertical axis is time points within the time period, and performing marking at each mapping point by using predetermined pixel values corresponding to the values to obtain a mapping image, wherein different values correspond to different pixel values; and inputting the pixel values of the mapping image to a trained data prediction model, and acquiring a power load data prediction value output by the data prediction model. The method and device and the storage medium can improve the prediction accuracy of the power load data.

Abstract: Various embodiments of the teachings herein include a method for deploying power quality monitoring (PQM) devices. The method may include: determining a maximum number of PQM devices and historical power data of candidate deployment points, wherein the number of the candidate deployment points is greater than the maximum number of the PQM devices; clustering the historical power data of the candidate deployment points, wherein a target number of categories is determined on the basis of a silhouette coefficient of each candidate number of categories and the maximum number of the PQM devices; and determining PQM device deployment points based on the center of each category in the target number of categories.

Abstract: Provided are a method, apparatus and system for storing fault data, an embodiment of the fault data storage method including: acquiring fault data of a target electrical device; sending a consensus request for the fault data, usable to request that consensus personnel who use the consensus client reach a consensus for the reason why the target electrical device is faulty, to at least one consensus client; respectively receiving a consensus result from each consensus client, the consensus result being formed by the consensus client according to the triggering of the consensus personnel; determining, according to each received consensus result, whether the reason for why the target electrical device is faulty is due to device quality; generating, upon the reason for why the target electrical device is faulty being due to device quality, a first data block which contains the fault data; and storing the first data block into a blockchain.

Abstract: Disclosed are a power grid user classification method and device, and a computer-readable storage medium. The method includes: determining user power consumption data of each time period within a time interval, the user power consumption data of each time period including user power consumption data of each time granularity within the time period; generating a power consumption pattern image of a user within the time interval based upon the user power consumption data of each time period within the time interval; and classifying the user based upon an image recognition result of the power consumption pattern image. A user is classified by performing image recognition on a power consumption pattern image, and file information does not need to be manually inputted, thereby reducing a manual workload. In addition, a completion defect caused by incomplete file information is avoided, thereby improving the accuracy of classification.

Abstract: A power load data prediction method and device, and a storage medium are disclosed. In an embodiment, the he method comprises: acquiring historical power load data of a one-dimensional time sequence, the historical power load data including values of corresponding time points; mapping the values of corresponding time points to a coordinate system in which a horizontal axis is a set time period, and a vertical axis is time points within the time period, and performing marking at each mapping point by using predetermined pixel values corresponding to the values to obtain a mapping image, wherein different values correspond to different pixel values; and inputting the pixel values of the mapping image to a trained data prediction model, and acquiring a power load data prediction value output by the data prediction model. The method and device and the storage medium can improve the prediction accuracy of the power load data.

Abstract: The present application provides a method and apparatus for evaluating the health state of a distribution transformer, and a medium and a program. In an embodiment, the method for evaluating the health state of a distribution transformer includes: extracting features from electric power parameters of a plurality of distribution transformers; clustering the plurality of distribution transformers into M subsets based on the extracted features, M being a natural number greater than 1 and less than a number of the distribution transformers; and respectively executing processing for each of the M subsets. In an embodiment, the processing includes determining a cluster center of the subset as a reference transformer for the subset; calculating the similarity between each of the distribution transformers in the subset and the reference transformer therein; and sorting the distribution transformers in the subset according to the calculated similarity.

Abstract: The present disclosure relates to a power management method and apparatus, a computing device, a medium, and a product. The power management method includes a monitoring step, a prediction step, an error calculation step and an adjustment step including adjusting power supply plan or a power demand of a user when at least one of a first error is greater than a first predetermined threshold or a second error is greater than a second predetermined threshold.

Abstract: Provided are a method, apparatus and system for storing fault data, an embodiment of the fault data storage method including: acquiring fault data of a target electrical device; sending a consensus request for the fault data, usable to request that consensus personnel who use the consensus client reach a consensus for the reason why the target electrical device is faulty, to at least one consensus client; respectively receiving a consensus result from each consensus client, the consensus result being formed by the consensus client according to the triggering of the consensus personnel; determining, according to each received consensus result, whether the reason for why the target electrical device is faulty is due to device quality; generating, upon the reason for why the target electrical device is faulty being due to device quality, a first data block which contains the fault data; and storing the first data block into a blockchain.

Abstract: An abnormal electricity use method is disclosed. An embodiment includes: classifying a transformer into a public transformer or a dedicated transformer, the public transformer corresponding to a plurality of first users; the dedicated transformer corresponding to one second user; recognizing a first abnormal user from the first users based upon the smart meter reading of the public transformer and the smart meter reading of the first user; or recognizing the first abnormal user from the first users based upon the smart meter reading of the first user; and recognizing a second abnormal user from the second user based upon the smart meter reading of the second user or the smart meter reading of the dedicated transformer. Respective personalized anomaly recognition policies are used for the public transformer having a plurality of first users and the dedicated transformer having only one second user, to improve the recognition accuracy and speed.

Abstract: The present disclosure relates to a power management method and apparatus, a computing device, a medium, and a product. The power management method includes a monitoring step, a prediction step, an error calculation step and an adjustment step including adjusting power supply plan or a power demand of a user when at least one of a first error is greater than a first predetermined threshold or a second error is greater than a second predetermined threshold.

Abstract: A power load prediction method, apparatus, and storage medium are disclosed. The method includes: acquiring historical power load data of a one-dimensional time series satisfying a set time length, composed of data corresponding to each time point; converting the historical power load data of a one-dimensional time series into a three-dimensional matrix composed of set time scales, the dads included in each time scale and the time points included in each day; based upon the size of each tiny e scale, dividing the historical power load data of the three-dimensional matrix into at least one operating mode; in each operating mode, using the time scale as a unit, based upon the historical power load data in each tune scale, deriving the value band of each day of power load data of the next time scale to be predicted in the operating mode. An embodiment can improve power load prediction accuracy.

Abstract: A method includes: obtaining a first measurement data set of a plurality of transformers configured with power quality monitoring systems; obtaining a second measurement data set of a plurality of transformers configured with no power quality monitoring systems; respectively clustering the plurality of transformers configured with power quality monitoring systems and the plurality of transformers configured with no power quality monitoring systems based upon values of common data types in the first measurement set and the second measurement data set to respectively obtain r groups; establishing a similar mapping relation between the groups; and assessing states of health of the transformers in each group configured with no power quality monitoring systems using the first measurement data set of the transformers in the group having the similar mapping relation with said group, thereby implementing assessing the states of health of the transformers without power quality monitoring systems.

Abstract: Disclosed are a power grid user classification method and device, and a computer-readable storage medium. The method includes: determining user power consumption data of each time period within a time interval, the user power consumption data of each time period including user power consumption data of each time granularity within the time period; generating a power consumption pattern image of a user within the time interval based upon the user power consumption data of each time period within the time interval; and classifying the user based upon an image recognition result of the power consumption pattern image. A user is classified by performing image recognition on a power consumption pattern image, and file information does not need to be manually inputted, thereby reducing a manual workload. In addition, a completion defect caused by incomplete file information is avoided, thereby improving the accuracy of classification.

Abstract: The present application provides a method and apparatus for evaluating the health state of a distribution transformer, and a medium and a program. In an embodiment, the method for evaluating the health state of a distribution transformer includes: extracting features from electric power parameters of a plurality of distribution transformers; clustering the plurality of distribution transformers into M subsets based on the extracted features, M being a natural number greater than 1 and less than a number of the distribution transformers; and respectively executing processing for each of the M subsets. In an embodiment, the processing includes determining a cluster center of the subset as a reference transformer for the subset; calculating the similarity between each of the distribution transformers in the subset and the reference transformer therein; and sorting the distribution transformers in the subset according to the calculated similarity.