Equipment load data processing method and electronic equipment

Abstract

The invention provides an equipment load data processing method and electronic equipment, and relates to the technical field of data processing, and the method comprises the steps: obtaining equipment load data in a power grid, arranging the equipment load data in a data queue according to a time sequence, and determining a plurality of fluctuation data groups in the data queue; constructing a feature vector of each fluctuation data group, clustering all the obtained feature vectors, determining a target feature vector cluster in a clustering result, determining the fluctuation data group corresponding to each feature vector in the target feature vector cluster as a target fluctuation data group, and sending the target fluctuation data group to a server; the target fluctuation data set comprises high-load data meeting a high-load condition; and carrying out smoothing processing on the high-load data in each target fluctuation data set, and removing noise data to obtain a plurality of low-load data sets. According to the invention, the low-load data set without the influence of high-load data can be obtained.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a device load data processing method and electronic equipment. Background Art

[0002] To ensure reliable power grid operation, it's crucial to accurately identify and monitor the status of load devices. However, low-load devices like small household appliances cause relatively weak fluctuations in grid parameters. High-load devices like high-power motors can cause significant fluctuations during operation, often masking the characteristic data of low-load devices. This can lead to widespread under-detection and misdetection of low-load device status data. Summary of the Invention

[0003] In view of this, the purpose of the present application is to provide a device load data processing method and electronic device to accurately extract low-load data from the device load data.

[0004] Based on the above objectives, this application provides a device load data processing method, including:

[0005] Obtaining device load data in the power grid, arranging the device load data into a data queue in chronological order, and determining a plurality of fluctuation data groups in the data queue;

[0006] Constructing a feature vector for each fluctuation data group, clustering all obtained feature vectors, determining a target feature vector cluster from the clustering results, and determining the fluctuation data group corresponding to each feature vector in the target feature vector cluster as a target fluctuation data group, wherein the target fluctuation data group includes high-load data that meets the high-load condition;

[0007] The high-load data in each target fluctuation data group is smoothed and the noise data is removed to obtain multiple low-load data groups.

[0008] Based on the same inventive concept, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0009] As can be seen from the above, the device load data processing method and the electronic device provided by the present application, wherein the method includes: obtaining device load data in the power grid, arranging the device load data in a data queue in chronological order, and determining multiple fluctuation data groups in the data queue. The fluctuation data group contains complete fluctuation characteristics, providing a data basis for subsequent feature extraction and clustering analysis; constructing a feature vector for each fluctuation data group, clustering all the obtained feature vectors, determining a target feature vector cluster in the clustering result, and determining the fluctuation data group corresponding to each feature vector in the target feature vector cluster as the target fluctuation data group. Each feature vector in the target feature vector cluster is a feature vector containing low-load data characteristics and high-load data characteristics. Therefore, the high-load data in the target fluctuation data group is data containing the change state of the low-load data. After smoothing the high-load data in each target fluctuation data group and removing the noise data, a low-load data group free from the influence of the high-load data can be obtained. The low-load data group can be used for monitoring and analyzing the state of low-load devices, and can more accurately display the operation problems that occur in the low-load devices, avoiding the problem that the load data of high-load devices masks the load data of low-load devices, resulting in difficulty in identifying the load data of low-load devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following will briefly introduce the drawings required for use in the embodiments or related technology descriptions. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0011] Figure 1 It is a flowchart of the device load data processing method according to an embodiment of the present application;

[0012] Figure 2 It is a schematic diagram of the device load data processing device according to an embodiment of the present application;

[0013] Figure 3 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] To make the objectives, technical solutions, and advantages of the present application clearer, the following further elaborates on the present application in detail with reference to specific embodiments and the accompanying drawings.

[0015] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of this application should have the ordinary meanings understood by those of ordinary skill in the field to which this application belongs. The "first", "second" and similar terms used in the embodiments of this application do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right", etc. are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0016] In the related art, there are various load devices in the power grid system, including high-power motors for industrial use and small household appliances for household use, etc. During the startup, stop and operation processes of these load devices, fluctuations in power grid parameters will be caused, affecting the stability and performance of the power grid. To ensure the reliable operation of the power grid, it is particularly important to accurately identify and monitor the states of these load devices. However, there are many deficiencies and defects in the existing technologies in this regard. The power grid environment is complex, and the operation state signals of load devices are easily interfered by various background noises. When dealing with these noises, the existing technologies often have difficulty in effectively distinguishing the noises from the device state signals, resulting in a low recognition rate. Especially in a high-noise environment, it is more difficult to extract and identify the device state signals. For low-load devices such as small household appliances, the fluctuations in power grid parameters caused by them are weak. During the operation of high-load devices such as high-power motors, significant fluctuations in power grid parameters will be caused. These fluctuation signals often mask the characteristic signals of low-load devices, creating an identification blind spot, and resulting in a relatively common phenomenon of missed detection and false detection of the state signals of low-load devices, which not only affects the monitoring effect of the power grid, but also may lead to the failure to timely detect the abnormal operation of low-load devices.

[0017] Based on the above problems, the applicant found that: obtaining the device load data in the power grid, arranging the device load data in a data queue in chronological order, and determining multiple fluctuating data groups in the data queue; constructing the feature vectors of each fluctuating data group, clustering all the obtained feature vectors, determining the target feature vector cluster in the clustering result, and determining the fluctuating data group corresponding to each feature vector in the target feature vector cluster as the target fluctuating data group, where the target fluctuating data group includes high-load data that meets the high-load condition; smoothing the high-load data in each target fluctuating data group and removing the noise data to obtain multiple low-load data groups. The low-load data groups can be used for monitoring and analyzing the low-load device status, and can more accurately display the operation problems that occur in the low-load devices, avoiding the load data of high-load devices covering the load data of low-load devices and causing an identification blind spot.

[0018] The following will describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0019] In some embodiments, as Figure 1 shown, a method for processing device load data, which is executed by a data processor. In the following embodiments, the data processor is taken as an example for illustration. The method includes:

[0020] S101. Obtain the device load data in the power grid, arrange the device load data in a data queue in chronological order, and determine multiple fluctuating data groups in the data queue;

[0021] Specifically, sensors and data acquisition devices can be used to collect device load data from the power grid in real time. The load data usually includes parameters such as three-phase voltage, three-phase current, active power, reactive power, and power factor. These data can be collected through devices such as smart meters, data collectors, and monitoring systems to ensure the real-time and accuracy of the data. Each data point contains a timestamp and the corresponding load parameter value. Sort the collected device load data according to the timestamp to form an ordered data queue. The purpose of arranging in chronological order is to ensure the continuity and traceability of the data, which is convenient for subsequent analysis and processing. In the data queue arranged in chronological order, check each data point one by one through the sliding window technology, identify the fluctuating data in the data queue, and determine the fluctuating data groups. The fluctuating data groups will serve as the basis for subsequent feature extraction and clustering analysis, providing support for the accurate identification of device status.

[0022] S102. Construct the feature vectors of each fluctuating data group, cluster all the obtained feature vectors, determine the target feature vector cluster in the clustering result, and determine the fluctuating data group corresponding to each feature vector in the target feature vector cluster as the target fluctuating data group, where the target fluctuating data group includes high-load data that meets the high-load condition;

[0023] In specific implementation, for each fluctuation data group, its eigenvalue is extracted to form an eigenvector. Commonly used features include mean value, standard deviation, peak-to-peak value, fluctuation density, etc. These features can effectively describe the dynamic changes and characteristics of the fluctuation data group. The extracted eigenvalues are combined into an eigenvector. Each fluctuation data group has a corresponding eigenvector. An appropriate clustering algorithm is used to perform clustering analysis on all eigenvectors. Commonly used clustering algorithms include K-means, DBSCAN, etc. In this embodiment, the DBSCAN algorithm can be selected. This algorithm can effectively process data with noise and can identify clusters of any shape. By setting the distance threshold ε and the minimum number of samples min_samples, density clustering is performed. Mark all data points as unvisited, randomly select an unvisited data point, mark it as visited, take this data point as the center, and calculate all data points within its ε neighborhood. If the number of data points within the ε neighborhood is greater than or equal to min_samples, then take this data point as the core to form a cluster, and mark all data points within the ε neighborhood as visited. For the data points newly added to the cluster, repeat the above process until the cluster no longer expands. Repeat the above process for all data points until all data points are visited. After clustering, each eigenvector is assigned a cluster label. The cluster label indicates the cluster to which the eigenvector belongs. According to the clustering result, the target eigenvector cluster is determined. The cluster label of the target eigenvector cluster is the mixed load level (the cluster labels of the clustering results are usually set with low load level, high load level, and mixed load level, where the mixed load level indicates that the fluctuation data group includes high-load data and low-load data). The fluctuation data group corresponding to each eigenvector in the target eigenvector cluster is determined as the target fluctuation data group. The target fluctuation data group contains high-load data that meets the high-load conditions. High-load data refers to the operation data of the device under high-load conditions, usually manifested as relatively high load values. The high-load conditions can be determined by setting a load threshold. When the device load data exceeds this load threshold, the device load data is considered high-load data. Smooth the high-load data in the target fluctuation data group. After smoothing, remove the noise from the data to ensure the reliability and accuracy of the remaining data, and obtain multiple low-load data groups. The low-load data groups mainly contain the operation status data of low-load devices.

[0024] S103. Smooth the high-load data in each target fluctuation data group and remove the noise data to obtain multiple low-load data groups.

[0025] In specific implementation, in the target fluctuation data group, high-load data usually shows significant fluctuations and large numerical changes. The main purpose of smoothing is to reduce the random fluctuations and noise in the high-load data, so that the high-load data becomes more stable and is convenient for subsequent analysis and processing. After smoothing the high-load data in each target fluctuation data group, it is necessary to remove the noise data, which usually appears as outliers significantly different from the surrounding data points. After smoothing the high-load data in each target fluctuation data group and removing the noise data, multiple low-load data groups can be obtained. The low-load data groups mainly contain data groups of the operating states of low-load devices. The fluctuations in the low-load data groups are small and the numerical changes are relatively stable, which can reflect the operating states of the low-load devices in the power grid.

[0026] In this embodiment, by constructing the feature vectors of each fluctuation data group and clustering all the obtained feature vectors, each fluctuation data group corresponding to each feature vector in the obtained target feature vector cluster is determined as the target fluctuation data group. Then, the high-load data in each target fluctuation data group is smoothed and the noise data is removed to obtain multiple low-load data groups. The low-load data groups can be used for monitoring and analyzing the states of low-load devices, and can more accurately display the operating problems of low-load devices, avoiding the load data of high-load devices covering the load data of low-load devices and causing identification blind spots.

[0027] In some embodiments, determining multiple fluctuation data groups in the data queue includes:

[0028] Determining a data fluctuation threshold according to the device load data within the sliding window of the data queue, and determining whether the target data is fluctuation data based on the data fluctuation threshold, where the target data is the device load data corresponding to the next position of the sliding window of the data queue;

[0029] In specific implementation, the sliding window is used to gradually move the window in the time series data and perform calculations and analyses at each position. The size of the sliding window (i.e., the number of data points included in the window) is usually set according to the specific application scenario. For example, the window size can be set to 5 data points. At each sliding window position, a data fluctuation threshold is determined according to the device load data within the sliding window. And based on the data fluctuation threshold, it is determined whether the target data is fluctuation data. The target data refers to the device load data corresponding to the next position of the sliding window in the data queue. When the target data is identified as fluctuation data, the fluctuation data and a preset number of adjacent device load data need to be determined as a fluctuation data group to ensure that the fluctuation data group contains complete fluctuation characteristics.

[0030] In response to determining that the target data is fluctuating data, the fluctuating data and a preset number of device load data adjacent to the fluctuating data are determined as a fluctuating data group.

[0031] In specific implementation, when the target data is identified as fluctuating data, it is necessary to determine the fluctuating data and a preset number of device load data adjacent to it as a fluctuating data group (exemplarily, the preset number can be set to 5). The purpose is to ensure that the complete change process before and after the fluctuation is captured, so as to more accurately describe the fluctuation characteristics of the device load data.

[0032] In this embodiment, by determining that the target data is fluctuating data and determining the fluctuating data and the device load data adjacent to the fluctuating data as a fluctuating data group, the complete fluctuation characteristics of the device load data can be effectively captured. Effectively identifying and extracting the fluctuating data group can provide a data basis for subsequent feature extraction and clustering analysis, ensuring the accuracy and reliability of device status identification.

[0033] In some embodiments, determining the data fluctuation threshold according to the device load data within the sliding window of the data queue includes:

[0034] Determine the mean value of all device load data within the sliding window, and determine the standard deviation of all device load data according to the mean value;

[0035] Determine the product of the standard deviation and a preset fluctuation coefficient as the data fluctuation threshold.

[0036] In specific implementation, at each sliding window position, calculate the mean value of all device load data within the window and determine the standard deviation of all device load data according to the mean value. The mean value is the average value of all device load data within the sliding window, reflecting the central tendency of the data. The standard deviation is the degree of dispersion of all device load data within the sliding window, reflecting the fluctuation of the data. The preset fluctuation coefficient is a preset parameter used to adjust the sensitivity of the data fluctuation threshold. It is usually set to 2 - 3. The data fluctuation threshold is the product of the standard deviation and the preset fluctuation coefficient, reflecting the degree of data fluctuation. The smaller the fluctuation coefficient, the lower the fluctuation threshold, and the more sensitive the identification of fluctuating data.

[0037] In this embodiment, by calculating the standard deviation of all device load data at each sliding window position and determining the product of the standard deviation and the preset fluctuation coefficient as the data fluctuation threshold, the fluctuation of the data can be effectively reflected, ensuring that when processing device load data, the fluctuation of the data can be accurately identified, providing a basis for subsequent identification and feature extraction of fluctuating data.

[0038] In some embodiments, determining whether the target data is fluctuating data based on the data fluctuation threshold includes:

[0039] Determine the first difference between the target data in the data queue and the device load data corresponding to its previous position;

[0040] In response to determining that the first difference is greater than or equal to the data fluctuation threshold, determine that the target data is fluctuating data.

[0041] Specifically, in implementation, the first difference is the difference between the target data and the device load data corresponding to its previous position, which reflects the change of the target data relative to the data at the previous position. To ensure that the first difference is a positive value, the absolute value of the first difference can be taken. The data fluctuation threshold is used to determine whether the data has significant fluctuations. By comparing the first difference with the data fluctuation threshold, it is judged whether the target data is fluctuating data. If the first difference is greater than or equal to the data fluctuation threshold, it indicates that the target data has a large fluctuation, and the target data is determined to be fluctuating data.

[0042] In this embodiment, the first difference between the target data and the data at its previous position is calculated, and the first difference is compared with the data fluctuation threshold to determine whether the target data is fluctuating data. This ensures that when processing device load data, the fluctuation situation of the data can be accurately identified, providing a basis for subsequent identification and feature extraction of fluctuating data.

[0043] In some embodiments, the smoothing process for the high-load data in each target fluctuating data group includes:

[0044] Determine the high-load fluctuating data from the high-load data of the target fluctuating data group, perform linear interpolation correction on the high-load fluctuating data to obtain the fluctuating data to be processed;

[0045] Perform baseline correction on the fluctuating data to be processed.

[0046] In specific implementation, the high-load fluctuation data refers to the device load data with significant load changes and large loads in the target fluctuation data group, usually manifested as obvious spikes or mutations, reflecting the operation of the device under high-load conditions. Linear interpolation is a commonly used smoothing method. By using the linear relationship between adjacent data points, the high-load fluctuation data is corrected to eliminate outliers and mutations. Linear interpolation can smooth the data, making the data change more continuously and smoothly. The high-load fluctuation data corrected by linear interpolation is used to obtain the to-be-processed fluctuation data. Baseline correction is used to eliminate the long-term trend and baseline drift in the data, making the baseline of the data more stable. Commonly used baseline correction methods include local polynomial fitting and smoothing filtering, etc. Local polynomial fitting is to smooth the data by fitting a polynomial curve in a local range. Perform local polynomial fitting on the to-be-processed fluctuation data, and the fitting formula is: [y_t=a_0+a_1t+a_2t^2] where (y_t) is the data point after fitting, (t) is the time point, and (a_0, a_1, a_2) are the fitting parameters. Use the least squares method to calculate the fitting parameters (a_0, a_1, a_2) to minimize the deviation of the data points of the fitting curve. Perform baseline correction on the to-be-processed fluctuation data to eliminate the long-term trend in the data. Realize the smoothing processing of the high-load data.

[0047] In this embodiment, by identifying the high-load fluctuation data points in the target fluctuation data group, linear interpolation correction is performed on the high-load fluctuation data points to generate the to-be-processed fluctuation data. Perform baseline correction on the to-be-processed fluctuation data to eliminate the long-term trend in the data, ensuring that when processing the device load data, the high-load fluctuation data can be effectively smoothed, improving the accuracy and reliability of the data.

[0048] In some embodiments, determining the high-load fluctuation data from the high-load data of the target fluctuation data group includes:

[0049] Determine the second difference between the high-load data in the target fluctuation data group and the device load data corresponding to its previous position;

[0050] In response to determining that the second difference is greater than or equal to the first preset difference, determine that the high-load data is high-load fluctuation data.

[0051] In specific implementation, high-load fluctuation data refers to data points in the target fluctuation data group where the load changes significantly and has a large value, usually manifested as obvious spikes or mutations, reflecting the operating conditions of the device under high-load states. The second difference is the difference between the high-load data in the target fluctuation data group and the device load data at the previous position, reflecting the change of the high-load data relative to the data at the previous position. The first preset difference is a preset threshold used to determine whether significant fluctuations have occurred in the data. The first preset difference can be adjusted according to specific application scenarios and data characteristics, usually determined based on experience or statistical analysis. The second difference is compared with the first preset difference to determine whether the high-load data is high-load fluctuation data. If the second difference is greater than or equal to the first preset difference, it is determined that the high-load data is high-load fluctuation data.

[0052] In this embodiment, by calculating the second difference between each high-load data in the target fluctuation data group and the data at the previous position, and comparing the second difference with the first preset difference, it is determined which high-load data in the target fluctuation data group are high-load fluctuation data. This ensures that when processing device load data, high-load fluctuation data can be accurately identified, providing a basis for subsequent smoothing processing and feature extraction.

[0053] In some embodiments, the target fluctuation data group includes low-load data that meets the low-load condition; the removing of noise data includes:

[0054] Determining a third difference between the low-load data in the target fluctuation data group and the device load data corresponding to the previous position, and a fourth difference between the low-load data and the device load data corresponding to the next position;

[0055] In response to determining that the third difference is greater than or equal to the second preset difference and the fourth difference is greater than or equal to the second preset difference, determining that the low-load data is noise data;

[0056] Removing the noise data from the target fluctuation data group.

[0057] In specific implementation, low-load data refers to the device load data with relatively small load and insignificant changes in the target fluctuation data group, which usually reflects the operation of the device under low-load conditions. The low-load data appears as relatively stable values in the target fluctuation data group. The third difference is the difference between the low-load data point in the target fluctuation data group and the device load data corresponding to its previous position, which reflects the change of the low-load data point relative to the data at the previous position. The fourth difference is the difference between the low-load data point in the target fluctuation data group and the device load data corresponding to its next position, which reflects the change of the low-load data point relative to the data at the next position. To ensure that the third difference and the fourth difference are positive values, their absolute values are usually taken. If it is determined that the third difference is greater than or equal to the second preset difference (the second preset difference can be adjusted according to specific application scenarios and data characteristics, and is usually determined based on experience or statistical analysis), and the fourth difference is greater than or equal to the second preset difference, it is determined that the low-load data is noise data; once a certain low-load data point is determined to be noise data, it is removed from the target fluctuation data group.

[0058] In this embodiment, by calculating the third difference between the low-load data point and the data at its previous position, and the fourth difference between the low-load data point and the data at its next position, and comparing the third difference and the fourth difference with the second preset difference respectively, it is determined whether the low-load data point is noise data. Once a certain low-load data point is determined to be noise data, it is removed from the target fluctuation data group and the data group is updated, ensuring that when processing device load data, noise data can be effectively removed, improving the accuracy and reliability of the data, and providing a basis for subsequent feature extraction and analysis.

[0059] In some embodiments, constructing the feature vector of each fluctuation data group includes:

[0060] Determining the average value, standard deviation, peak-to-peak value, and fluctuation density of all device load data in the fluctuation data group, and constructing the feature vector of the fluctuation data group according to the average value, standard deviation, peak-to-peak value, and fluctuation density.

[0061] In specific implementation, the feature vector is used to represent the characteristics of the fluctuation data group, providing a basis for subsequent clustering and classification. The fluctuation data group refers to a set that includes the fluctuation data and a certain number of adjacent device load data, ensuring that the complete change process before and after the fluctuation is captured. The average value is the average value of all device load data in the fluctuation data group, reflecting the central tendency of the data. The standard deviation is the degree of dispersion of all device load data in the fluctuation data group, reflecting the fluctuation of the data. The peak-to-peak value is the difference between the maximum value and the minimum value in the fluctuation data group, reflecting the fluctuation amplitude of the data. The fluctuation density is the fluctuation frequency of the device load data in the fluctuation data group, reflecting the fluctuation intensity of the data, and the fluctuation density can be determined by calculating the number of changes in the device load data or other statistical methods. The calculated average value, standard deviation, peak-to-peak value, and fluctuation density are synthesized into a feature vector to represent the characteristics of the fluctuation data group.

[0062] In this embodiment, by determining the average value, standard deviation, peak-to-peak value, and fluctuation density of all device load data in the fluctuation data group, and combining the above characteristic values into a feature vector to represent the characteristics of the fluctuation data group. It ensures that when processing device load data, the key features of the data can be effectively extracted, providing a basis for subsequent clustering and classification analysis.

[0063] In some embodiments, after obtaining the device load data in the power grid, it further includes:

[0064] Performing nearest neighbor interpolation on the device load data;

[0065] Performing median filtering on the device load data after nearest neighbor interpolation processing;

[0066] Performing normalization processing on the device load data after median filtering processing.

[0067] In specific implementation, nearest neighbor interpolation is used to fill in missing data or correct abnormal data. By nearest neighbor interpolation, the continuity and integrity of the device load data can be ensured, facilitating subsequent analysis and processing. Median filtering is used to remove spike noise and outliers in the data. By median filtering, the device load data can be smoothed, reducing the random fluctuations and noise in the data. Normalization processing is used to scale the data to a specific range (such as 0 to 1 or -1 to 1). By normalization processing, the dimensional difference in the data can be eliminated, improving the comparability between different features.

[0068] In this embodiment, by performing nearest neighbor interpolation on the device load data to fill in missing data or correct abnormal data, the continuity and integrity of the data are ensured. Median filtering is performed on the device load data after nearest neighbor interpolation processing to remove spike noise and outliers and smooth the data. Normalization processing is performed on the device load data after median filtering processing to scale the data to a specified range and eliminate the dimension difference. This ensures that when processing device load data, the data quality and analysis accuracy can be effectively improved, providing a basis for subsequent feature extraction and analysis.

[0069] It should be noted that the method of the embodiment of the present application can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario, and multiple devices cooperate with each other to complete it. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiment of the present application, and these multiple devices will interact with each other to complete the described method.

[0070] It should be noted that some embodiments of the present application have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order than in the above embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application also provides a device load data processing apparatus.

[0072] Refer to Figure 2 , the device load data processing apparatus includes:

[0073] An acquisition module 701, which is configured to acquire device load data in the power grid, arrange the device load data in a data queue in chronological order, and determine multiple fluctuating data groups in the data queue;

[0074] A clustering module 702, which is configured to construct a feature vector for each fluctuating data group, cluster all the obtained feature vectors, determine a target feature vector cluster in the clustering result, and determine the fluctuating data group corresponding to each feature vector in the target feature vector cluster as a target fluctuating data group, where the target fluctuating data group includes high-load data that meets the high-load condition;

[0075] A calculation module 703, which is configured to smooth the high-load data in each target fluctuating data group and remove noise data to obtain multiple low-load data groups.

[0076] Further, the obtaining module 701 is specifically configured to:

[0077] Determine a data fluctuation threshold according to the device load data within the sliding window of the data queue, and determine whether the target data is fluctuating data based on the data fluctuation threshold, where the target data is the device load data corresponding to the next position of the sliding window of the data queue;

[0078] In response to determining that the target data is fluctuating data, determine the fluctuating data and a preset number of device load data adjacent to the fluctuating data as a fluctuating data group.

[0079] Further, the obtaining module 701 is specifically further configured to:

[0080] Determine the mean value of all device load data within the sliding window, and determine the standard deviation of all device load data according to the mean value;

[0081] Determine the product of the standard deviation and a preset fluctuation coefficient as the data fluctuation threshold.

[0082] Further, the obtaining module 701 is specifically further configured to:

[0083] Determine a first difference between the target data in the data queue and the device load data corresponding to its previous position;

[0084] In response to determining that the first difference is greater than or equal to the data fluctuation threshold, determine that the target data is fluctuating data.

[0085] Further, the calculating module 703 is specifically configured to:

[0086] Determine high-load fluctuating data from the high-load data of the target fluctuating data group, perform linear interpolation correction on the high-load fluctuating data to obtain the fluctuating data to be processed;

[0087] Perform baseline correction on the fluctuating data to be processed.

[0088] Further, the calculating module 703 is specifically further configured to:

[0089] Determine a second difference between the high-load data in the target fluctuating data group and the device load data corresponding to its previous position;

[0090] In response to determining that the second difference is greater than or equal to the first preset difference, determine that the high-load data is high-load fluctuating data.

[0091] Further, the calculating module 703 is specifically further configured to:

[0092] Determine the third difference between the low-load data in the target fluctuation data group and the device load data corresponding to its previous position, and the fourth difference between the device load data corresponding to its next position.

[0093] In response to determining that the third difference is greater than or equal to the second preset difference and the fourth difference is greater than or equal to the second preset difference, determine that the low-load data is noise data.

[0094] Remove the noise data from the target fluctuation data group.

[0095] Further, the clustering module 702 is specifically configured to:

[0096] Determine the average value, standard deviation, peak-to-peak value, and fluctuation density of all device load data in the fluctuation data group, and construct a feature vector of the fluctuation data group according to the average value, standard deviation, peak-to-peak value, and fluctuation density.

[0097] Further, the obtaining module 701 is specifically further configured to:

[0098] Perform nearest neighbor interpolation on the device load data.

[0099] Perform median filtering on the device load data after nearest neighbor interpolation processing.

[0100] Perform normalization processing on the device load data after median filtering processing.

[0101] For the convenience of description, when describing the above device, it is described by function as various modules respectively. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0102] The device in the above embodiment is used to implement the corresponding device load data processing method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated herein.

[0103] Based on the same inventive concept, corresponding to the method in any of the above embodiments, the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements the device load data processing method described in any of the above embodiments.

[0104] Figure 3FIG. 0 shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0105] The processor 1010 may be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0106] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0107] The input / output interface 1030 is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0108] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module may implement communication in a wired manner (such as USB, network cable, etc.) or in a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0109] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0110] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0111] The electronic device in the above embodiment is used to implement the corresponding device load data processing method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0112] Based on the same inventive concept, corresponding to the method in any of the above embodiments, the present application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the device load data processing method as described in any of the foregoing embodiments.

[0113] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0114] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the device load data processing method as described in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0115] Based on the same concept, corresponding to the method in any of the above embodiments, the present application also provides a computer program product including computer program instructions, which when running on a computer, cause the computer to execute the method as described in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0116] It is understandable that before using the technical solutions of the various embodiments in the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the authorization of the user will be obtained.

[0117] For example, when responding to an active request from the user, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application program, server, or storage medium that performs the operations of the technical solutions of the present disclosure according to the prompt message.

[0118] As an optional but non-limiting implementation manner, the manner of sending a prompt message to the user in response to receiving an active request from the user can be, for example, in the form of a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0119] It is understandable that the above process of notifying and obtaining the user's authorization is only illustrative and does not limit the implementation manner of the present disclosure. Other manners that comply with relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0120] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present application is limited to these examples; under the concept of the present application, the technical features between the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present application as described above, and they are not provided in detail for the sake of brevity.

[0121] In addition, for the sake of simplicity of description and discussion, and in order not to make the embodiments of the present application difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation manner of these block diagram devices highly depend on the platform on which the embodiments of the present application will be implemented (that is, these details should be completely within the understanding scope of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe the exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0122] Although the present application has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0123] Embodiments of the present application are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the claims of the present application. Accordingly, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application shall be included within the protection scope of the present application.

Claims

1. A method for processing device load data, characterized in that, Including: Obtain the device load data in the power grid, arrange the device load data in chronological order into a data queue, and determine multiple fluctuation data groups in the data queue; Construct the feature vectors of each fluctuation data group, cluster all the obtained feature vectors, determine the target feature vector cluster in the clustering result, and determine the fluctuation data group corresponding to each feature vector in the target feature vector cluster as the target fluctuation data group, where the target fluctuation data group includes high-load data that meets the high-load condition; Smooth the high-load data in each target fluctuation data group and remove the noise data to obtain multiple low-load data groups.

2. The method for processing device load data according to claim 1, characterized in that The determination of multiple fluctuation data groups in the data queue includes: Determine the data fluctuation threshold according to the device load data within the sliding window of the data queue, and determine whether the target data is fluctuation data based on the data fluctuation threshold, where the target data is the device load data corresponding to the next position of the sliding window of the data queue; In response to determining that the target data is fluctuation data, determine the fluctuation data and a preset number of device load data adjacent to the fluctuation data as a fluctuation data group.

3. The method for processing device load data according to claim 2, wherein The determination of the data fluctuation threshold according to the device load data within the sliding window of the data queue includes: Determine the mean value of all device load data within the sliding window, and determine the standard deviation of all device load data according to the mean value; Determine the product of the standard deviation and the preset fluctuation coefficient as the data fluctuation threshold.

4. The method for processing device load data according to claim 2, wherein The determination of whether the target data is fluctuation data based on the data fluctuation threshold includes: Determine the first difference between the target data in the data queue and the device load data corresponding to its previous position; In response to determining that the first difference is greater than or equal to the data fluctuation threshold, determine that the target data is fluctuation data.

5. The method for processing device load data according to claim 1, wherein The smoothing process of the high-load data in each target fluctuation data group includes: Determine the high-load fluctuation data from the high-load data of the target fluctuation data group, perform linear interpolation correction on the high-load fluctuation data to obtain the to-be-processed fluctuation data; Perform baseline correction on the to-be-processed fluctuation data.

6. The method for processing device load data according to claim 5, wherein, The determination of the high-load fluctuation data from the high-load data of the target fluctuation data group includes: Determine the second difference between the high-load data in the target fluctuation data group and the device load data corresponding to its previous position; In response to determining that the second difference is greater than or equal to the first preset difference, determine that the high-load data is high-load fluctuation data.

7. The method for processing device load data according to claim 1, wherein The target fluctuation data group includes low-load data that meets the low-load condition; The removal of the noise data includes: Determine the third difference between the low-load data in the target fluctuation data group and the device load data corresponding to its previous position, and the fourth difference between the low-load data and the device load data corresponding to its next position; In response to determining that the third difference is greater than or equal to the second preset difference and the fourth difference is greater than or equal to the second preset difference, determine that the low-load data is noise data; Remove the noise data from the target fluctuation data group.

8. The method for processing device load data according to claim 1, wherein The construction of the feature vector of each fluctuation data group includes: Determine the average value, standard deviation, peak-to-peak value, and fluctuation density of all device load data in the fluctuation data group, and construct a feature vector of the fluctuation data group based on the average value, standard deviation, peak-to-peak value, and fluctuation density.

9. The method for processing device load data according to claim 1, wherein After obtaining the device load data in the power grid, it further includes: Perform nearest neighbor interpolation on the device load data; Perform median filtering on the device load data after nearest neighbor interpolation processing; Perform normalization processing on the device load data after median filtering processing.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the program, it implements the method according to any one of claims 1 to 9.

Images