Device load data processing method and electronic device
By performing feature vector clustering and smoothing on the load data of power grid equipment, the problem of high load data masking low load data is solved, enabling accurate monitoring and analysis of the status of low load equipment and improving the monitoring effect of the power grid.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 江西冠英智能科技股份有限公司
- Filing Date
- 2025-03-21
- Publication Date
- 2026-06-16
Smart Images
Figure CN120408131B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing technology, and in particular to a method for processing device load data and an electronic device. Background Technology
[0002] To ensure the reliable operation of the power grid, accurate identification and monitoring of the status of load devices are crucial. However, low-load devices such as small household appliances cause relatively weak fluctuations in power grid parameters, while high-load devices such as high-power motors cause significant fluctuations in power grid parameters during operation. These fluctuations often mask the characteristic data of low-load devices, leading to widespread missed and false detections of low-load device status data. Summary of the Invention
[0003] In view of this, the purpose of this 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] To achieve the above objectives, this application provides a method for processing device load data, comprising:
[0005] Acquire equipment load data in the power grid, arrange the equipment load data into a data queue in chronological order, and identify multiple fluctuating data groups in the data queue;
[0006] Construct feature vectors for each fluctuating data group, and cluster all the obtained feature vectors. Determine the target feature vector cluster from the clustering results, and determine the fluctuating data group corresponding to each feature vector in the target feature vector cluster as the target fluctuating data group. The target fluctuating 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 noise data is removed to obtain multiple low-load data groups.
[0008] Based on the same inventive concept, this application also provides an electronic device, including 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 equipment load data processing method and electronic device provided in this application include: acquiring equipment load data in the power grid, arranging the equipment load data in chronological order into a data queue, and determining multiple fluctuation data groups in the data queue. The fluctuation data groups contain complete fluctuation features, providing a data foundation for subsequent feature extraction and cluster analysis; constructing feature vectors for each fluctuation data group, and clustering all obtained feature vectors, determining target feature vector clusters in the clustering results, 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 both low-load data features and high-load data features. Therefore, the high-load data in the target fluctuation data group contains data that includes the changing state of low-load data. After smoothing and removing noise data from the high-load data in each target fluctuation data group, a low-load data group that has removed the influence of high-load data can be obtained. The low-load data group can be used for monitoring and analyzing the status of low-load equipment, and can more accurately display the operating problems of low-load equipment, avoiding the problem of high-load equipment load data masking low-load equipment load data and causing difficulty in identifying low-load equipment load data. Attached Figure Description
[0010] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 This is a flowchart of a device load data processing method according to an embodiment of this application;
[0012] Figure 2 This is a schematic diagram of the device load data processing apparatus according to an embodiment of this application;
[0013] Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0014] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.
[0015] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0016] In related technologies, power grid systems contain various load devices, including high-power industrial motors and small household appliances. During startup, shutdown, and operation, these load devices cause fluctuations in power grid parameters, affecting the stability and performance of the grid. To ensure reliable grid operation, accurate identification and monitoring of the status of these load devices is crucial. However, existing technologies have many shortcomings and deficiencies in this regard. The power grid environment is complex, and the operating status signals of load devices are easily interfered with by various background noises. Existing technologies often struggle to effectively distinguish noise from device status signals when processing this noise, resulting in low recognition rates. Extraction and identification of device status signals are particularly difficult in high-noise environments. For low-load devices such as small household appliances, the fluctuations in power grid parameters they cause are relatively weak. However, high-load devices such as high-power motors cause significant fluctuations in power grid parameters during operation. These fluctuations often mask the characteristic signals of low-load devices, creating blind spots in identification. This leads to widespread missed and false detections of low-load device status signals, affecting not only the monitoring effect of the power grid but also potentially causing operational anomalies in low-load devices to go undetected in a timely manner.
[0017] Based on the above issues, the applicant discovered the following: Obtain equipment load data from the power grid, arrange the equipment load data in chronological order into a data queue, and identify multiple fluctuating data groups within the data queue; construct feature vectors for each fluctuating data group, and cluster all obtained feature vectors to determine target feature vector clusters. The fluctuating data group corresponding to each feature vector in the target feature vector cluster is then identified as the target fluctuating data group, which includes high-load data that meets the high-load conditions; smooth the high-load data in each target fluctuating data group and remove noise data to obtain multiple low-load data groups. These low-load data groups can be used for monitoring and analyzing the status of low-load equipment, more accurately displaying operational problems of low-load equipment, and preventing load data from high-load equipment from masking the load data of low-load equipment, thus avoiding identification blind spots.
[0018] The embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0019] In some embodiments, such as Figure 1 As shown, a device load data processing method is implemented by a data processor. Subsequent embodiments will use a data processor as an example for illustration. The method includes:
[0020] S101. Obtain equipment load data in the power grid, arrange the equipment load data into a data queue in chronological order, and determine multiple fluctuating data groups in the data queue.
[0021] In practice, sensors and data acquisition devices can be used to collect equipment load data from the power grid in real time. Load data typically includes parameters such as three-phase voltage, three-phase current, active power, reactive power, and power factor. This data can be collected through devices such as smart meters, data acquisition units, and monitoring systems to ensure real-time performance and accuracy. Each data point contains a timestamp and a corresponding load parameter value. The collected equipment load data is sorted according to timestamps to form an ordered data queue. This chronological order ensures data continuity and traceability, facilitating subsequent analysis and processing. Within the chronologically ordered data queue, a sliding window technique is used to examine each data point, identifying fluctuating data and determining fluctuating data groups. These fluctuating data groups serve as the basis for subsequent feature extraction and cluster analysis, supporting accurate identification of equipment status.
[0022] S102. Construct feature vectors for each fluctuating data group, and cluster all the obtained feature vectors. Determine the target feature vector cluster in the clustering results, and determine the fluctuating data group corresponding to each feature vector in the target feature vector cluster as the target fluctuating data group. The target fluctuating data group includes high-load data that meets the high-load condition.
[0023] In practice, for each fluctuating data set, its feature values are extracted to form a feature vector. Commonly used features include mean, standard deviation, peak-to-peak value, and fluctuation density, which can effectively describe the dynamic changes and characteristics of the fluctuating data set. The extracted feature values are combined into a feature vector. Each fluctuating data set has a corresponding feature vector. An appropriate clustering algorithm is used to perform cluster analysis on all feature vectors. Commonly used clustering algorithms include K-means and DBSCAN. In this embodiment, the DBSCAN algorithm can be selected. This algorithm can effectively handle noisy data and can identify clusters of arbitrary shapes. Density clustering is performed by setting a distance threshold ε and a minimum number of samples min_samples. All data points are marked as unvisited. An unvisited data point is randomly selected and marked as visited. Using this data point as the center, all data points within its ε-neighborhood are calculated. If the number of data points within the ε-neighborhood is greater than or equal to min_samples, a cluster is formed with this data point as the core, and all data points within the ε-neighborhood are marked as visited. The above process is repeated for newly added data points until the cluster no longer expands. Repeat the above process for all data points until all data points have been accessed. After clustering, each feature vector is assigned a cluster label. The cluster label indicates the cluster to which the feature vector belongs. Based on the clustering results, determine the target feature vector cluster. The cluster label of the target feature vector cluster is a mixed load level (cluster labels in the clustering results are usually set to low load level, high load level, and mixed load level, where the mixed load level indicates that the fluctuating data group includes both high-load and low-load data). The fluctuating data group corresponding to each feature vector in the target feature vector cluster is determined as the target fluctuating data group. The target fluctuating data group contains high-load data that meets the high-load condition. High-load data refers to the operating data of the equipment under high load conditions, usually manifested as a high load value. The high-load condition can be determined by setting a load threshold. When the equipment load data exceeds this load threshold, the equipment load data is considered high-load data. Smooth the high-load data in the target fluctuating data group. After smoothing, remove noise from the data to ensure the reliability and accuracy of the remaining data, resulting in multiple low-load data groups. The low-load data groups mainly contain the operating status data of low-load equipment.
[0024] S103. Smooth the high-load data in each target fluctuation data group and remove noise data to obtain multiple low-load data groups.
[0025] In practice, high-load data in the target fluctuation data set typically exhibits significant fluctuations and large numerical variations. The main purpose of smoothing is to reduce random fluctuations and noise in the high-load data, making it more stable and facilitating subsequent analysis and processing. After smoothing the high-load data in each target fluctuation data set, noise data needs to be removed. Noise data typically manifests as outliers that are significantly different from surrounding data points. After smoothing the high-load data and removing noise data in each target fluctuation data set, multiple low-load data sets are obtained. The low-load data sets mainly contain data on the operating status of low-load equipment. The fluctuations in the low-load data sets are smaller, and the numerical changes are relatively stable, reflecting the operating status of low-load equipment in the power grid.
[0026] In this embodiment, feature vectors are constructed for each fluctuating data group, and all the obtained feature vectors are clustered. The fluctuating data group corresponding to each feature vector in the obtained target feature vector cluster is determined as the target fluctuating data group. Then, the high-load data in each target fluctuating data group is smoothed and noise data is removed to obtain multiple low-load data groups. The low-load data groups can be used for monitoring and analyzing the status of low-load devices, which can more accurately show the operating problems of low-load devices and avoid the load data of high-load devices from masking the load data of low-load devices, thus avoiding blind spots in identification.
[0027] In some embodiments, determining multiple fluctuating data groups in the data queue includes:
[0028] The data fluctuation threshold is determined based on the device load data within the sliding window of the data queue, and the target data is determined to be fluctuating data based on the data fluctuation threshold. The target data is the device load data corresponding to the next position of the sliding window of the data queue.
[0029] In practice, a sliding window is used to progressively move the window across the time series data, performing calculations and analysis at each position. The size of the sliding window (i.e., the number of data points contained within the window) is typically set based on the specific application scenario. For example, the window size could be set to 5 data points. At each sliding window position, a data fluctuation threshold is determined based on the device load data within the sliding window. Based on this threshold, it is determined whether the target data is fluctuating data; the target data refers to the device load data corresponding to the next position of the sliding window in the data queue. Once the target data is identified as fluctuating data, the fluctuating data and its adjacent preset number of device load data points need to be grouped into a fluctuating data group to ensure that the fluctuating 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 practice, once the target data is identified as fluctuating data, the fluctuating data and its adjacent preset number of device load data need to be identified as a fluctuating data group (for example, 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 the target data as fluctuating data, the fluctuating data and the equipment load data adjacent to the fluctuating data are identified as fluctuating data groups. This can effectively capture the complete fluctuation characteristics of the equipment load data. Effectively identifying and extracting fluctuating data groups can provide a data foundation for subsequent feature extraction and cluster analysis, ensuring the accuracy and reliability of equipment status identification.
[0033] In some embodiments, determining the data fluctuation threshold based on device load data within a sliding window of the data queue includes:
[0034] Determine the mean of all device load data within the sliding window, and determine the standard deviation of all device load data based on the mean;
[0035] The product of the standard deviation and the preset volatility coefficient is determined as the data volatility threshold.
[0036] In practice, at each sliding window position, the mean of all device load data within the window is calculated, and the standard deviation of all device load data is determined based on the mean. The mean is the average value of all device load data within the sliding window, reflecting the central trend of the data. The standard deviation is the dispersion of all device load data within the sliding window, reflecting the data fluctuation. 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 within each sliding window position, the product of the standard deviation and the preset fluctuation coefficient is determined as the data fluctuation threshold. This effectively reflects the data fluctuation situation and ensures that the data fluctuation situation can be accurately identified when processing device load data, providing a foundation for subsequent fluctuation data identification and feature extraction.
[0038] In some embodiments, determining whether the target data is fluctuating data based on a 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, the target data is determined to be fluctuating data.
[0041] In practice, the first difference is the difference between the target data and the equipment load data corresponding to its previous position, reflecting the change in the target data relative to the previous position. To ensure the first difference is positive, its absolute value can be taken. The data fluctuation threshold is used to determine whether significant fluctuations have occurred in the data. The first difference is compared with the data fluctuation threshold to determine whether the target data is fluctuating. If the first difference is greater than or equal to the data fluctuation threshold, it indicates that the target data has experienced significant fluctuations, and the target data is determined to be fluctuating data.
[0042] In this embodiment, a first difference between the target data and the data at its previous position is calculated. This first difference is then compared with a data fluctuation threshold to determine whether the target data is fluctuating data. This ensures that data fluctuations can be accurately identified when processing device load data, providing a foundation for subsequent fluctuation data identification and feature extraction.
[0043] In some embodiments, smoothing the high-load data in each target fluctuating data group includes:
[0044] High-load fluctuation data is identified from the high-load data of the target fluctuation data group, and linear interpolation correction is performed on the high-load fluctuation data to obtain the fluctuation data to be processed.
[0045] Baseline correction is performed on the fluctuation data to be processed.
[0046] In practical implementation, high-load fluctuation data refers to equipment load data with significant load changes and large loads within the target fluctuation data set. This typically manifests as obvious peaks or abrupt changes, reflecting the equipment's operation under high load conditions. Linear interpolation is a commonly used smoothing method. It corrects high-load fluctuation data by leveraging the linear relationship between adjacent data points, eliminating outliers and abrupt changes. Linear interpolation smooths the data, making its changes more continuous and stable. The high-load fluctuation data corrected by linear interpolation yields the fluctuation data to be processed. Baseline correction is used to eliminate long-term trends and baseline drift in the data, making the baseline more stable. Common baseline correction methods include local polynomial fitting and smoothing filtering. Local polynomial fitting smooths the data by fitting a polynomial curve within a local range. The local polynomial fitting formula for the fluctuation data to be processed is: [y_t=a_0+a_1t+a_2t^2] where (y_t) is the fitted data point, (t) is the time point, and (a_0,a_1,a_2) are the fitting parameters. The least squares method is used to calculate the fitting parameters (a_0, a_1, a_2) to minimize the deviation of the data points in the fitted curve. Baseline correction is performed on the fluctuating data to eliminate long-term trends. Smoothing is achieved for high-load data.
[0047] In this embodiment, high-load fluctuation data points are identified in the target fluctuation data group, and linear interpolation correction is performed on these high-load fluctuation data points to generate fluctuation data to be processed. Baseline correction is then performed on the fluctuation data to be processed to eliminate long-term trends in the data, ensuring that high-load fluctuation data can be effectively smoothed when processing equipment load data, thereby improving the accuracy and reliability of the data.
[0048] In some embodiments, determining high-load volatility data from high-load data in a target volatility data set includes:
[0049] Determine the second difference between the high load data in the target fluctuation data group and the equipment 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, the high load data is determined to be high load fluctuation data.
[0051] In practical implementation, high load fluctuation data refers to data points in the target fluctuation data set where the load change is significant and the value is large. This typically manifests as a noticeable peak or abrupt change, reflecting the equipment's operation under high load conditions. The second difference is the difference between the high load data in the target fluctuation data set and the load data of the equipment at the previous position, reflecting the change in the high load data relative to 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, the high load data is determined to be high load fluctuation data.
[0052] In this embodiment, by calculating the second difference between each high-load data point in the target fluctuation data group and the data point preceding it, and comparing the second difference with a first preset difference, it is determined which high-load data points in the target fluctuation data group are high-load fluctuation data. This ensures that high-load fluctuation data can be accurately identified when processing equipment load data, providing a foundation for subsequent smoothing processing and feature extraction.
[0053] In some embodiments, the target fluctuation data set includes low-load data that meets low-load conditions; the noise-removed data includes:
[0054] Determine the third difference between the low load data in the target fluctuation data group and the equipment load data corresponding to the previous position, and the fourth difference between the low load data and the equipment 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, the low load data is determined to be noise data;
[0056] The noise data is removed from the target fluctuation data group.
[0057] In practice, low-load data refers to the equipment load data in the target fluctuation data group that has a small load and does not change significantly. It usually reflects the operation of the equipment under low load conditions, and low-load data is a relatively stable value 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 equipment load data corresponding to its previous position, reflecting the change of the low-load data point relative to the previous position. The fourth difference is the difference between the low-load data point in the target fluctuation data group and the equipment load data corresponding to its next position, reflecting the change of the low-load data point relative to the next position. To ensure that the third and fourth differences are positive, their absolute values are usually taken. If the third difference is greater than or equal to the second preset difference (the second preset difference can be adjusted according to the specific application scenario and data characteristics, usually determined based on experience or statistical analysis), and the fourth difference is greater than or equal to the second preset difference, the low-load data is determined to be noise data; once a 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 a low-load data point and its preceding data point, and the fourth difference between it and its following data point, the third and fourth differences are compared with a second preset difference to determine whether the low-load data point is noise data. Once a 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. This ensures that noise data can be effectively removed when processing equipment load data, improving the accuracy and reliability of the data, and providing a foundation for subsequent feature extraction and analysis.
[0059] In some embodiments, constructing the feature vector for each fluctuation data group includes:
[0060] 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 the feature vector of the fluctuation data group based on the average value, standard deviation, peak-to-peak value, and fluctuation density.
[0061] In practice, the feature vector is used to represent the characteristics of the fluctuating data set, providing a foundation for subsequent clustering and classification. A fluctuating data set refers to a collection containing fluctuating data and the load data of several adjacent devices, ensuring the capture of the complete change process before and after the fluctuation. The mean is the average of all device load data in the fluctuating data set, reflecting the central trend of the data. The standard deviation is the dispersion of all device load data in the fluctuating data set, reflecting the data's fluctuation. The peak-to-peak value is the difference between the maximum and minimum values in the fluctuating data set, reflecting the amplitude of the fluctuation. Fluctuation density is the frequency of fluctuations in the device load data in the fluctuating data set, reflecting the intensity of the fluctuation; fluctuation density can be determined by calculating the number of changes in device load data or other statistical methods. The calculated mean, standard deviation, peak-to-peak value, and fluctuation density are combined into a feature vector to represent the characteristics of the fluctuating data set.
[0062] In this embodiment, the average value, standard deviation, peak-to-peak value, and fluctuation density of all device load data in the fluctuation data group are determined, and these feature values are combined into a feature vector to represent the characteristics of the fluctuation data group. This ensures that key features of the data can be effectively extracted when processing device load data, providing a foundation for subsequent clustering and classification analysis.
[0063] In some embodiments, after acquiring the device load data in the power grid, the method further includes:
[0064] Perform nearest neighbor interpolation on the device load data;
[0065] Median filtering is applied to the device load data after nearest neighbor interpolation.
[0066] The equipment load data after median filtering is normalized.
[0067] In practice, nearest neighbor interpolation is used to fill in missing data or correct outliers. Nearest neighbor interpolation ensures the continuity and integrity of equipment load data, facilitating subsequent analysis and processing. Median filtering removes spikes and outliers from the data. Median filtering smooths equipment load data, reducing random fluctuations and noise. Normalization scales the data to a specific range (e.g., 0 to 1 or -1 to 1). Normalization eliminates dimensional differences in the data, improving the comparability between different features.
[0068] In this embodiment, nearest neighbor interpolation is performed on the equipment load data to fill in missing data or correct outliers, ensuring data continuity and integrity. Median filtering is then applied to the interpolated equipment load data to remove spikes and outliers, smoothing the data. Finally, the median-filtered equipment load data is normalized to scale the data to a specified range, eliminating dimensional differences. This ensures that data quality and analytical accuracy are effectively improved when processing equipment load data, providing a foundation for subsequent feature extraction and analysis.
[0069] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.
[0070] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0071] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a device load data processing apparatus.
[0072] refer to Figure 2 The device load data processing apparatus includes:
[0073] The acquisition module 701 is configured to acquire equipment load data in the power grid, arrange the equipment load data in chronological order into a data queue, and identify multiple fluctuating data groups in the data queue.
[0074] Clustering module 702 is configured to construct feature vectors for each fluctuating data group, cluster all obtained feature vectors, determine target feature vector clusters in the clustering results, and determine the fluctuating data group corresponding to each feature vector in the target feature vector cluster as the target fluctuating data group, wherein the target fluctuating data group includes high-load data that meets the high-load conditions.
[0075] The calculation module 703 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] Furthermore, the acquisition module 701 is specifically used for:
[0077] The data fluctuation threshold is determined based on the device load data within the sliding window of the data queue, and the target data is determined to be fluctuating data based on the data fluctuation threshold. 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, the fluctuating data and a preset number of device load data adjacent to the fluctuating data are determined as a fluctuating data group.
[0079] Furthermore, the acquisition module 701 is specifically used for:
[0080] Determine the mean of all device load data within the sliding window, and determine the standard deviation of all device load data based on the mean;
[0081] The product of the standard deviation and the preset volatility coefficient is determined as the data volatility threshold.
[0082] Furthermore, the acquisition module 701 is specifically used for:
[0083] Determine the 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, the target data is determined to be fluctuating data.
[0085] Furthermore, the computing module 703 is specifically used for:
[0086] High-load fluctuation data is identified from the high-load data of the target fluctuation data group, and linear interpolation correction is performed on the high-load fluctuation data to obtain the fluctuation data to be processed.
[0087] Baseline correction is performed on the fluctuation data to be processed.
[0088] Furthermore, the computing module 703 is specifically used for:
[0089] Determine the second difference between the high load data in the target fluctuation data group and the equipment 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, the high load data is determined to be high load fluctuation data.
[0091] Furthermore, the computing module 703 is specifically used for:
[0092] Determine the third difference between the low load data in the target fluctuation data group and the equipment load data corresponding to the previous position, and the fourth difference between the low load data and the equipment load data corresponding to the 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, the low load data is determined to be noise data;
[0094] The noise data is removed from the target fluctuation data group.
[0095] Furthermore, the clustering module 702 is specifically used for:
[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 the feature vector of the fluctuation data group based on the average value, standard deviation, peak-to-peak value, and fluctuation density.
[0097] Furthermore, the acquisition module 701 is specifically used for:
[0098] Perform nearest neighbor interpolation on the device load data;
[0099] Median filtering is applied to the device load data after nearest neighbor interpolation.
[0100] The equipment load data after median filtering is normalized.
[0101] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.
[0102] The apparatus of the above embodiments 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 repeated here.
[0103] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the device load data processing method described in any of the above embodiments.
[0104] Figure 3This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.
[0105] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.
[0106] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.
[0107] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.
[0108] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0109] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.
[0110] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.
[0111] The electronic devices described above are used to implement the corresponding device load data processing methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0112] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this 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 above 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. 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, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer 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 embodiments are used to cause the computer to execute the device load data processing method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0115] Based on the same concept, corresponding to any of the above embodiments, this application also provides a computer program product, including computer program instructions, which, when run on a computer, cause the computer to perform the method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0116] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.
[0117] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations of this disclosed technical solution.
[0118] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.
[0119] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.
[0120] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application is limited to these examples; under the concept of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in detail for the sake of brevity.
[0121] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0122] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.
[0123] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the claims of this application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.
Claims
1. A method for processing equipment load data, characterized in that, include: Acquire equipment load data in the power grid, arrange the equipment load data into a data queue in chronological order, and identify multiple fluctuating data groups in the data queue; Construct feature vectors for each fluctuating data group, and cluster all the obtained feature vectors. Determine the target feature vector cluster from the clustering results, and determine the fluctuating data group corresponding to each feature vector in the target feature vector cluster as the target fluctuating data group. The target fluctuating data group includes high-load data that meets the high-load condition. For each target fluctuating data set, the high-load data is smoothed and noise is removed to obtain multiple low-load data sets. The smoothing process for high-load data in each target fluctuating data group includes: High-load fluctuation data is identified from the high-load data of the target fluctuation data group, and linear interpolation correction is performed on the high-load fluctuation data to obtain the fluctuation data to be processed. Baseline correction is performed on the fluctuation data to be processed; The step of determining 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 equipment 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, the high load data is determined to be high load fluctuation data; The target fluctuation data set includes low-load data that meets the low-load condition; the noise-removed data includes: Determine the third difference between the low load data in the target fluctuation data group and the equipment load data corresponding to the previous position, and the fourth difference between the low load data and the equipment load data corresponding to the 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, the low load data is determined to be noise data; The noise data is removed from the target fluctuation data group.
2. The equipment load data processing method according to claim 1, characterized in that, The determination of multiple fluctuating data groups in the data queue includes: The data fluctuation threshold is determined based on the device load data within the sliding window of the data queue, and the target data is determined to be fluctuating data based on the data fluctuation threshold. 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 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.
3. The equipment load data processing method according to claim 2, characterized in that, The step of determining the data fluctuation threshold based on device load data within a sliding window of the data queue includes: Determine the mean of all device load data within the sliding window, and determine the standard deviation of all device load data based on the mean; The product of the standard deviation and the preset volatility coefficient is determined as the data volatility threshold.
4. The equipment load data processing method according to claim 2, characterized in that, The step of determining whether target data is fluctuating data based on 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, the target data is determined to be fluctuating data.
5. The equipment load data processing method according to claim 1, characterized in that, The construction of the feature vector for 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 the feature vector of the fluctuation data group based on the average value, standard deviation, peak-to-peak value, and fluctuation density.
6. The equipment load data processing method according to claim 1, characterized in that, After acquiring the equipment load data in the power grid, the process also includes: Perform nearest neighbor interpolation on the device load data; Median filtering is applied to the device load data after nearest neighbor interpolation. The equipment load data after median filtering is normalized.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 6.