Non-invasive Power Data Acquisition Method, Platform, Device and Medium

Abstract

The present invention discloses a non-invasive power data acquisition method, platform, device and medium, which relates to the field of power grid technology. The method includes: identifying the efficacy characteristics of electrical appliances and classifying the electrical appliances according to the efficacy characteristics; obtaining the electrical signal data and performing time-series feature analysis on the electrical signal data according to the preset stage segmentation relationship; based on the efficacy classification label, performing type clustering on the electrical appliance electrical signal time-series feature list, aligning the features of the clustering result, and identifying the differential data and time-series features; performing similarity evaluation, configuring an electrical signal amplifier, and determining the efficacy identification features; searching for the efficacy identification features, electrical signal identification features and amplified electrical signal features, performing feature aggregation, and generating a data acquisition identity label; and performing non-invasive power data acquisition. It solves the technical problem of insufficient accuracy and reliability existing in the existing non-invasive power data acquisition, and achieves the technical effect of improving the accuracy and reliability of data acquisition.

Description

Technical Field

[0001] The present application relates to the field of power grid technologies, and in particular, to non-intrusive power data acquisition methods, platforms, devices, and media. Background Art

[0002] Power data acquisition is used to monitor each link of the power system in real time, accurately, and efficiently, providing data support for the stable operation and optimized management of the power system. In the field of power data acquisition, there are mainly two technical methods: intrusive and non-intrusive. Intrusive power data acquisition requires installing sensors or measuring devices on electrical equipment or power lines to directly obtain power data. Although the data accuracy is high, the installation and maintenance costs are relatively high, and it will have a certain impact on the normal operation of the power system. Non-intrusive power data acquisition does not require physical modification of electrical equipment or power lines. By monitoring parameters such as the total current and voltage of the power line, the power consumption of each electrical equipment is estimated. However, due to the large variety and quantity of electrical equipment and their different power consumption characteristics, it is difficult to accurately identify the consumption of each electrical equipment in the total power data, and problems such as data confusion and misidentification are likely to occur, affecting the accuracy and reliability of data acquisition.

[0003] In the related technologies at the present stage, there are technical problems of insufficient accuracy and reliability in non-intrusive power data acquisition. Summary of the Invention

[0004] The present application provides a non-intrusive power data acquisition method, platform, device, and medium. By identifying and classifying the power consumption characteristics of electrical appliances in the data acquisition area, obtaining power consumption classification labels, acquiring the electrical signal data of these electrical appliances, and performing time series feature analysis, an electrical appliance electrical signal time series feature list is constructed. Based on the power consumption classification labels, type clustering and feature alignment are performed on the time series feature list to identify differential data and time series features. Further, similarity evaluation is performed according to the differential data and time series features, and an electrical signal amplifier is configured to amplify the electrical signals that meet the confusion conditions. Using the regional electrical appliance label as an index, the power consumption identification features, electrical signal identification features, and amplified electrical signal features are aggregated to generate a data acquisition identity label, providing a target identifier and other technical means for power data acquisition, achieving the technical effect of improving the accuracy and reliability of data acquisition.

[0005] The present application provides a non-intrusive power data acquisition method, including:

[0006] Identify the power efficiency characteristics of electrical appliances in the data collection area, classify the electrical appliances according to the power efficiency characteristics of the electrical appliances, and obtain power classification labels; obtain the electrical signal data of the regional electrical appliances, perform time series feature analysis on the electrical signal data according to the preset stage segmentation relationship, and construct a time series feature list of the electrical appliance electrical signals; based on the power classification labels, perform type clustering on the time series feature list of the electrical appliance electrical signals, and perform feature alignment on the clustering results to identify differential data and time series features; perform similarity evaluation according to the differential data and time series features, configure an electrical signal amplifier according to the similarity evaluation result, and determine the power identification feature, where the electrical signal amplifier is used to amplify electrical signals whose similarity evaluation results meet the confusion condition; search for the power identification feature, the electrical signal identification feature, and the amplified electrical signal feature using the label of the regional electrical appliance as an index, aggregate the power identification feature, the electrical signal identification feature, and the amplified electrical signal feature, and generate a data collection identity label; perform non-intrusive power data collection on the regional electrical appliances based on the data collection identity label.

[0007] In a possible implementation manner, for identifying the power efficiency characteristics of electrical appliances in the data collection area, classifying the electrical appliances according to the power efficiency characteristics of the electrical appliances, and obtaining power classification labels, the following processing is performed:

[0008] Collect the load characteristics of the regional electrical appliances, perform level configuration on the load characteristics to obtain the load level; based on the load level, respectively identify the starting current peak value, steady-state power, power curve, and harmonic characteristics of the electrical appliance signals to obtain the power efficiency characteristics of the electrical appliances, and establish a mapping association between the load level and the power efficiency characteristics of the electrical appliances; configure data labels for the electrical appliance type, the load level, and the power efficiency characteristics of the electrical appliances, integrate the data labels according to the mapping association relationship, and perform power efficiency characteristic identification on the regional electrical appliances to obtain the power classification labels.

[0009] In a possible implementation manner, for performing time series feature analysis on the electrical signal data according to the preset stage segmentation relationship, the following processing is performed:

[0010] Establish a stage template signal according to the preset stage, where the preset stage includes a startup stage, a stable operation stage, and a shutdown stage; use the electrical signal data to perform time series alignment with the stage template signal, and calculate the distance measurement result between the time series signals; based on the distance measurement result, determine the key time series nodes of the stage segmentation interval to obtain the preset stage segmentation relationship; perform time series fluctuation feature analysis on the electrical signal data according to the preset stage segmentation relationship to obtain the time series features of the electrical signals, including the fluctuation amplitude, fluctuation frequency, and periodic fluctuation of current, voltage, or power.

[0011] In a possible implementation, the electrical signal data is aligned with the phase template signal in time sequence, and the distance metric result between the time sequence signals is calculated, and the following processing is performed:

[0012] Align the electrical signal data with the phase template signal in time sequence to obtain time sequence data pairs; calculate the Euclidean distance of the time sequence data pairs; according to the Euclidean distance, find the minimum distance through a dynamic programming algorithm to obtain an accumulation path, and perform superposition of the Euclidean distances in the path according to the accumulation path to obtain the distance metric result.

[0013] In a possible implementation, based on the distance metric result, key time sequence nodes of the phase segmentation interval are determined, and the following processing is performed:

[0014] According to the change of the cumulative distance value in the accumulation path, identify the first distance change attenuation node of the starting time sequence to obtain the key time sequence node of the starting stage, and the key time sequence node of the starting stage is the inflection point where the distance change rate decreases; take the key time sequence node of the starting stage as the starting observation point, identify that the change rate of the cumulative distance value starts to increase, determine the inflection point where the distance change rate increases, and obtain the key time sequence node of the closing stage; the part between the key time sequence node of the starting stage and the key time sequence node of the closing stage is the time sequence interval of the stable operation stage, and the time sequence interval of the stable operation stage is the area where the distance change is gentle.

[0015] In a possible implementation, electrical signal time sequence features are obtained, and the following processing is performed:

[0016] Calculate the mean value of the electrical signal sequence: , where N is the length of the electrical signal sequence, is the electrical signal data at time t; according to the time sequence relationship of the electrical signal sequence, calculate the time lag amount, and the time lag amount is the alignment amount between the signal itself and the signal after r time units in the subsequent time sequence; calculate the autocorrelation value of the time lag amount: , where is the mean value of the electrical signal sequence, is the autocorrelation value of the time lag amount r; according to the Identify periodic fluctuation characteristics.

[0017] In a possible implementation, the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature are aggregated to generate a data acquisition identity label, and the following processing is performed:

[0018] Represent the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature as feature vectors respectively; perform multi-scale analysis on each of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature to obtain multi-scale features; based on the multi-scale features, calculate the attention weights of each feature through a self-attention mechanism; use the attention weights to calculate the attention scores of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature, and then perform weighted summation to obtain a comprehensive feature; map the comprehensive feature to the data acquisition identity label of the regional electrical appliance.

[0019] This application also provides a non-intrusive power data acquisition platform, including:

[0020] An electrical appliance efficacy classification module, which is used to identify the efficacy characteristics of electrical appliances in the data acquisition area, classify the electrical appliances according to the electrical appliance efficacy characteristics, and obtain efficacy classification labels; an electrical signal time series feature analysis module, which is used to obtain the electrical signal data of regional electrical appliances, perform time series feature analysis on the electrical signal data according to the preset stage segmentation relationship, and construct an electrical appliance electrical signal time series feature list; a differential data recognition module, which is used to perform type clustering on the electrical appliance electrical signal time series feature list based on the efficacy classification labels, and perform feature alignment on the clustering results to identify differential data and time series features; an electrical signal amplification module, which is used to perform similarity evaluation according to the differential data and time series features, configure an electrical signal amplifier according to the similarity evaluation result, and determine the efficacy recognition feature, and the electrical signal amplifier is used to amplify the electrical signals whose similarity evaluation results meet the confusion conditions; a data acquisition identity label generation module, which is used to search for the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature with the label of the regional electrical appliance as the index, aggregate the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature, and generate a data acquisition identity label; a non-intrusive power data acquisition module, which is used to perform non-intrusive power data acquisition of regional electrical appliances based on the data acquisition identity label.

[0021] This application also provides an electronic device, including:

[0022] A memory for storing executable instructions; a processor for implementing the non-intrusive power data acquisition method when executing the executable instructions stored in the memory.

[0023] This application also provides a computer-readable storage medium, including:

[0024] A computer program is stored thereon, and when the program is executed by a processor, a non-invasive power data acquisition method is implemented.

[0025] It is intended to propose a non-invasive power data acquisition method, platform, device and medium through the present application. First, the power consumption characteristics of electrical appliances in the data acquisition area are identified, the electrical appliances are classified according to the power consumption characteristics of the electrical appliances to obtain power consumption classification labels, and then the electrical signal data of the regional electrical appliances are obtained. The electrical signal data is subjected to time series feature analysis according to a preset stage segmentation relationship to construct a list of electrical signal time series features of the electrical appliances. Then, based on the power consumption classification labels, type clustering is performed on the list of electrical signal time series features of the electrical appliances, and the feature alignment is performed on the clustering results to identify differential data and time series features. Furthermore, similarity evaluation is performed according to the differential data and time series features, and an electrical signal amplifier is configured according to the similarity evaluation result to determine the power consumption identification features. The electrical signal amplifier is used to amplify the electrical signals whose similarity evaluation results meet the confusion conditions, and then search for the power consumption identification features, electrical signal identification features and amplified electrical signal features by using the label of the regional electrical appliances as an index. The power consumption identification features, electrical signal identification features and amplified electrical signal features are subjected to feature aggregation to generate a data acquisition identity label. Finally, non-invasive power data acquisition of the regional electrical appliances is performed based on the data acquisition identity label, achieving the technical effect of improving the accuracy and reliability of data acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the platform according to the embodiments of the present application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the needs, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0027] Figure 1 It is a schematic flowchart of the non-invasive power data acquisition method provided by the embodiment of the present application.

[0028] Figure 2 It is a schematic structural diagram of the non-invasive power data acquisition platform provided by the embodiment of the present application.

[0029] Figure 3 It is a schematic structural diagram of an electronic device provided by the embodiment of the present application.

[0030] Description of the drawing reference numerals: electrical efficacy classification module 10, electrical signal timing feature analysis module 20, differential data identification module 30, electrical signal amplification module 40, data acquisition identity tag generation module 50, non-intrusive power data acquisition module 60, input device 301, processor 302, memory 303, output device 304. Detailed implementation manners

[0031] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0032] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0033] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, platform, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0034] The embodiments of the present application provide a non-intrusive power data acquisition method, as Figure 1 shown, the method includes:

[0035] Step S100: Identify the efficacy characteristics of the electrical appliances in the data collection area, classify the electrical appliances according to their efficacy characteristics, and obtain efficacy classification labels. Specifically, collect the load characteristics of all electrical appliances in the area, including the rated power, working current, etc. of the electrical appliances. According to the load characteristics of the electrical appliances, identify the start current peak, steady-state power, power curve, harmonic characteristics, etc. of the electrical appliance signals. These characteristics together constitute the efficacy characteristics of the electrical appliances. Configure a type label for each electrical appliance according to the efficacy characteristics of the electrical appliances to obtain the efficacy classification labels.

[0036] In a possible implementation, the electrical appliances in the data collection area are identified for their efficacy characteristics, classified according to the electrical appliance efficacy characteristics, and efficacy classification labels are obtained. Step S100 further includes step S110, which is to collect the load characteristics of the electrical appliances in the collection area and configure levels for the load characteristics to obtain load levels. Specifically, through devices such as sensors or electricity meters, the load characteristic data of each electrical appliance in the area is collected, including parameters such as current, voltage, and power, which reflect the energy consumption of the electrical appliance under different working conditions. The collected load characteristic data is analyzed to identify different working modes or load states of the electrical appliance. For example, an air conditioner has multiple modes such as cooling, heating, and dehumidifying, and the load characteristics are different for each mode. According to the analysis results, based on factors such as power range and energy consumption mode, the load characteristics of the electrical appliances are divided into different levels. Step S120, based on the load levels, respectively identify the starting current peak, steady-state power, power curve, and harmonic characteristics of the electrical appliance signals to obtain the electrical appliance efficacy characteristics, and establish a mapping association between the load levels and the electrical appliance efficacy characteristics. Specifically, for each load level, a series of characteristic identification operations are performed, including the starting current peak (the maximum current value at the moment when the electrical appliance starts, which reflects the starting characteristics of the electrical appliance and the impact on the power grid), the steady-state power (the power value of the electrical appliance in the stable working state, which reflects the energy consumption level and working efficiency of the electrical appliance), the power curve (the change of power with time during the working process of the electrical appliance, which reflects the working mode and energy consumption characteristics of the electrical appliance), and the harmonic characteristics (the harmonic components in the current or voltage waveform generated by the electrical appliance, which reflects the electromagnetic compatibility of the electrical appliance and its impact on the power grid). Through characteristic identification, the efficacy characteristics of the electrical appliance are extracted, and these characteristics comprehensively reflect the energy consumption characteristics and working state of the electrical appliance. Map each load level to its corresponding efficacy characteristics for quick access to the corresponding characteristic information when classifying and identifying electrical appliances. Step S130, configure data labels for the electrical appliance type, the load level, and the electrical appliance efficacy characteristics, integrate the data labels according to the mapping association relationship, and identify the efficacy characteristics of the area electrical appliances to obtain the efficacy classification labels. Specifically, according to information such as the type, load level, and efficacy characteristics of the electrical appliance, corresponding data labels are configured for each electrical appliance. These labels are used to uniquely identify each electrical appliance and contain important energy consumption characteristics and working state information. Integrate the data labels of all electrical appliances to form a complete database or data table. This database or data table is used for querying and retrieval. According to the integrated data labels, identify the efficacy characteristics of each electrical appliance, that is, configure a unique identifier for it according to the energy consumption characteristics and working state information of the electrical appliance.This implementation method classifies electrical appliances in a refined manner by performing hierarchical configuration and feature recognition on the load characteristics of electrical appliances. Whether it is electrical appliances with large power variations such as air conditioners and refrigerators, or electrical appliances with small power variations such as light bulbs, accurate identification can be achieved, improving the accuracy and reliability of non-intrusive power data collection.

[0037] Step S200: Obtain the electrical signal data of the regional electrical appliances, perform time-series feature analysis on the electrical signal data according to the preset stage segmentation relationship, and construct an electrical appliance electrical signal time-series feature list. Specifically, obtain the electrical signal data of the electrical appliances in the region through devices such as sensors. Establish a stage template signal according to the typical working stages of the electrical appliances (such as startup, stable operation, shutdown), align the electrical signal data with the stage template signal in time series, and calculate the distance metric result between the two. According to the distance metric result, determine the key time-series nodes of the stage segmentation interval, such as the key time-series nodes of the startup stage and the shutdown stage. Perform time-series fluctuation feature analysis on the electrical signal data according to the preset stage segmentation relationship to obtain time-series features such as the fluctuation amplitude, fluctuation frequency, and periodic fluctuation of current, voltage, or power.

[0038] In a possible implementation, the timing feature analysis of the electrical signal data is performed according to a preset stage segmentation relationship. Step S200 further includes step S210 of establishing a stage template signal according to a preset stage. The preset stage includes a startup stage, a stable operation stage, and a shutdown stage. Specifically, the template signal represents a signal sequence of typical electrical signal characteristics in a certain stage and is used to compare with the actual signal. Specifically, by collecting the electrical signal data when the device starts up multiple times, preprocessing these data, such as denoising and filtering, calculating the average value or typical pattern of these data (the representative signal pattern that appears in multiple observations), a timing template signal for the startup stage is generated. By collecting the electrical signal data of the device in a stable state, extracting the typical steady-state characteristic curve of this stage (the characteristic curve of the electrical signal when the device is running stably, manifested as a relatively smooth waveform), a timing template signal for the stable operation stage is generated. Monitoring the electrical signal data when the device shuts down, extracting the attenuation characteristics of the electrical signal during the shutdown process, including fitting the attenuation curve or calculating the attenuation rate, a timing template signal for the shutdown stage is generated. Step S220, perform timing alignment between the electrical signal data and the stage template signal, and calculate the distance metric result between the timing signals. Specifically, use the dynamic time warping (DTW) algorithm to align the actual electrical signal data with each stage template signal and calculate the time distance between them. Step S230, based on the distance metric result, determine the key timing nodes of the stage segmentation interval and obtain the preset stage segmentation relationship. Specifically, according to the distance metric result calculated by the DTW algorithm, find the time points with the highest matching degree between the actual signal and the template signal, and use these time points as the key timing nodes of the stage segmentation interval. Step S240, perform timing fluctuation feature analysis on the electrical signal data according to the preset stage segmentation relationship to obtain electrical signal timing features, including the fluctuation amplitude, fluctuation frequency, and periodic fluctuation of current, voltage, or power. Specifically, within each stage, use statistical methods or signal processing techniques to calculate features such as the fluctuation amplitude, fluctuation frequency, and periodic fluctuation of current, voltage, or power. This implementation improves the accuracy of identifying each stage of device operation by constructing a template signal and comparing it with the actual signal, thereby improving the accuracy of extracting timing fluctuation features. By dynamically adjusting the segmentation result through the DTW algorithm to adapt to signal fluctuations and stage changes, the robustness of the system is enhanced.

[0039] In a possible implementation, the timing alignment is performed between the electrical signal data and the phase template signal, and the distance metric result between the timing signals is calculated. Step S220 further includes step S221 of performing the timing alignment between the electrical signal data and the phase template signal to obtain a pair of timing data. Specifically, the electrical signal data sequence and the phase template signal sequence are read, and in the preliminary step of using the dynamic time warping (DTW) algorithm, the electrical signal data sequence and the phase template signal sequence are aligned on the time axis. During the alignment process, a series of pairs of timing data are generated, and each pair of data includes the signal values of the electrical signal data sequence and the phase template signal sequence at a certain time point. Step S222 is to calculate the Euclidean distance of the pair of timing data. Specifically, for each pair of timing data, its Euclidean distance is calculated, that is, the square root of the sum of the squares of the differences between the signal values of the electrical signal data sequence and the phase template signal sequence at a certain time point. The Euclidean distances of all pairs of timing data are stored in a matrix, where the rows and columns of the matrix correspond to the time points of the electrical signal data sequence and the phase template signal sequence respectively. Step S223 is to find the minimum distance through the dynamic programming algorithm according to the Euclidean distance, obtain the cumulative path, and superimpose the Euclidean distances in the path according to the cumulative path to obtain the distance metric result. Specifically, using the dynamic programming algorithm, starting from the upper left corner of the matrix, gradually move to the lower right corner to find the minimum path sum from the starting point to the ending point (i.e., the minimum distance sum). In each step, select the minimum distance among the positions on the right, below, or lower right of the current position, and accumulate it to the distance at the current position. Repeat the above steps until reaching the lower right corner of the matrix. At this time, the obtained sum is the distance metric result. According to the cumulative path, trace back to obtain the best matching path between the electrical signal data sequence and the phase template signal sequence. This implementation method ensures that the electrical signal data sequence and the phase template signal sequence are compared on the same time scale through timing alignment, quantifies the difference between the electrical signal data sequence and the phase template signal sequence by calculating the Euclidean distance of the pair of timing data, and avoids the complexity of directly calculating all possible paths through the dynamic programming algorithm, improves the calculation efficiency of the minimum distance sum between the electrical signal data sequence and the phase template signal sequence, and realizes the accurate measurement of the matching degree between the electrical signal data and the phase template signal.

[0040] In a possible implementation, based on the distance metric result, the key timing nodes of the phase segmentation interval are determined. Step S230 further includes step S231. According to the change of the cumulative distance value in the cumulative path, the first distance change attenuation node of the starting timing is identified, and the key timing node of the startup phase is obtained. The key timing node of the startup phase is the inflection point where the distance change rate decreases. Specifically, starting from the starting point of the cumulative path, the change of the cumulative distance value is analyzed step by step along the path, and the difference between adjacent cumulative distance values is calculated to obtain the distance change amount. Identify the position where the distance change amount first significantly decreases, that is, the inflection point where the distance change rate decreases. This point marks the critical moment when the electrical signal changes from the initial unstable state (such as at the initial stage of device startup) to the relatively stable state. Take this inflection point as the key timing node of the startup phase, which represents the end of the device startup phase.

[0041] Step S232, taking the key timing node of the startup phase as the starting observation point, identify that the change rate of the cumulative distance value starts to increase, determine the inflection point where the distance change rate increases, and obtain the key timing node of the shutdown phase. Specifically, starting from the key timing node of the startup phase, continue to analyze the change of the cumulative distance value along the cumulative path. Calculate the difference between adjacent cumulative distance values to obtain the new distance change amount, and identify the position where the distance change amount starts to significantly increase, that is, the inflection point where the distance change rate increases. This point marks the critical moment when the electrical signal changes from the stable operating state to the unstable state (such as device shutdown). Take this inflection point as the key timing node of the shutdown phase, which represents the end of the device stable operation phase and the start of the shutdown phase. Step S233, the part between the key timing node of the startup phase and the key timing node of the shutdown phase is the timing interval of the stable operation phase, and the timing interval of the stable operation phase is the area where the distance change is gentle. Specifically, according to the key timing nodes of the startup phase and the shutdown phase, determine the time range between them. The electrical signal data within this time range corresponds to the stable operation phase of the device, that is, the time period when the device operates in the normal working state. Within this time period, the change of the cumulative distance value is relatively gentle, without obvious fluctuations or mutations. This implementation method accurately divides different phases of the device by identifying the key timing nodes of the startup phase and the shutdown phase, and determining that the area between the key timing nodes of the startup phase and the shutdown phase is the stable operation phase, providing a clear time range for the operation of the device in the normal working state and improving the accuracy of determining the preset phase segmentation relationship.

[0042] In a possible implementation, to obtain the electrical signal timing characteristics, step S240 further includes step S241, calculating the mean value of the electrical signal sequence: , where N is the length of the electrical signal sequence, The electrical signal data at time t. Specifically, an electrical signal sequence is obtained, which contains continuous electrical signal data from the start time to the current time. Calculate the mean of the electrical signal sequence, that is, the sum of all electrical signal data divided by the length N of the electrical signal sequence. The mean reflects the overall average level of the electrical signal sequence. Step S242, according to the timing relationship of the electrical signal sequence, calculate the time lag amount, where the time lag amount is the alignment amount between the signal itself and the signal r time units after the post-timing. Specifically, the time lag amount r represents the number of time units for the signal itself to align with the post-timing. For each time point t in the electrical signal sequence, find the signal data at the time point t + r. Calculate the alignment amount between the signal itself and the signal data r time units after the post-timing, that is, the time lag amount. This alignment amount can be the difference, ratio, or other relevant metrics of the signal, and is used to analyze the change trend of the signal over time. Step S243, calculate the autocorrelation value of the time lag amount: , where is the mean of the electrical signal sequence,[[]] is the autocorrelation value of the time lag amount r. Specifically, use the mean of the electrical signal sequence calculated in step S241 to centralize the time lag amount calculated in step S242 (i.e., subtract the mean). For each time lag amount r, calculate its autocorrelation value. The autocorrelation value is a measure of the similarity degree of the time lag amount with itself at different time points, and is used to analyze the periodic characteristics of the signal. Step S244, according to the Identify periodic fluctuation characteristics. Specifically, analyze the autocorrelation values calculated in step S243, especially the changes in the autocorrelation values when r takes different values. Find the r value when the autocorrelation value reaches the maximum or is close to the maximum. This r value corresponds to the period length of the signal. According to the periodic changes of the autocorrelation values, determine the periodic fluctuation characteristics of the signal, including the period length, fluctuation amplitude, etc. This implementation method reveals the hidden periodic information in the signal by calculating the mean, time lag amount, and autocorrelation value of the electrical signal sequence, and accurately identifies the periodic fluctuation characteristics of the signal according to the changes in the autocorrelation values.

[0043] Step S300, based on the efficacy classification label, perform type clustering on the list of electrical appliance electrical signal timing characteristics, and perform feature alignment on the clustering results to identify differential data and timing characteristics. Specifically, according to the efficacy classification label, perform type clustering on the list of electrical appliance electrical signal timing characteristics, and classify electrical appliances with similar characteristics into one category. Perform feature alignment on the clustering results to ensure the consistency and comparability of the characteristics of electrical appliances within the same category. During the clustering process, identify the data with large differences from the characteristics of other electrical appliances within the same category. These differential data represent different electrical appliances. Perform further timing feature identification on the differential data to extract their unique timing characteristics.

[0044] Step S400: Conduct a similarity evaluation based on the differential data and temporal characteristics, configure an electrical signal amplifier according to the similarity evaluation result, and determine the efficacy recognition characteristics. The electrical signal amplifier is used to amplify electrical signals whose similarity evaluation results meet the confusion condition. Specifically, conduct a similarity evaluation on the differential data and its temporal characteristics to evaluate the similarity degree between the data. According to the similarity evaluation result, configure an electrical signal amplifier (a device for amplifying electrical signals) to amplify electrical signals whose similarity evaluation results meet the confusion condition (high similarity of electrical appliance characteristics) to improve the signal strength and recognition accuracy. Combine the amplified electrical signal and the original data to determine the efficacy recognition characteristics of the electrical appliance.

[0045] Step S500: Search for the efficacy recognition characteristics, electrical signal recognition characteristics, and amplified electrical signal characteristics using the label of the regional electrical appliance as an index, aggregate the efficacy recognition characteristics, the electrical signal recognition characteristics, and the amplified electrical signal characteristics to generate a data acquisition identity label. Specifically, use the label of the regional electrical appliance as an index to search for its corresponding efficacy recognition characteristics, electrical signal recognition characteristics, and amplified electrical signal characteristics. Aggregate the searched characteristics to form a comprehensive feature set. Map the comprehensive feature set to the data acquisition identity label of the regional electrical appliance (a unique label for identifying and recognizing the regional electrical appliance) for data acquisition and recognition.

[0046] In a possible implementation, for the feature aggregation of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature to generate a data acquisition identity tag, step S500 further includes step S510 of respectively representing the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature as feature vectors. Specifically, the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature are converted into feature vectors, which are used to describe multiple features of an object. These feature vectors can be numerical, or can be obtained through a certain transformation (such as one-hot encoding, embedding, etc.). Step S520, perform multi-scale analysis on each of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature to obtain multi-scale features. Specifically, perform multi-scale analysis on each feature vector, that is, use filters (such as wavelet transform) to extract features at different time scales or spatial scales. Capture features and information at different levels. Step S530, based on the multi-scale features, calculate the attention weights of each feature through a self-attention mechanism. Specifically, based on the multi-scale features, the self-attention mechanism assigns attention weights to each feature by calculating the correlation between features, and the attention weights represent the relative importance between features. Step S540, use the attention weights to calculate the attention scores of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature, and then perform weighted summation to obtain a comprehensive feature. Specifically, calculate the dot product between features, apply the softmax function to normalize the weights, and obtain the attention score of each feature. Perform weighted summation on the attention scores of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature to obtain a comprehensive feature. Step S550, map the comprehensive feature to the data acquisition identity tag of the regional electrical appliance. Specifically, use a classifier (such as a support vector machine) to map the comprehensive feature to the data acquisition identity tag of the regional electrical appliance for uniquely identifying the regional electrical appliance. This implementation uses a self-attention mechanism to integrate features from different sources (efficacy recognition feature, electrical signal recognition feature, and amplified electrical signal feature). The self-attention mechanism can dynamically assign weights according to the correlation between features, thereby more effectively integrating information, avoiding the problem of unreasonable weight assignment that may occur in traditional weighted average or simple feature splicing methods, and improving the accuracy and robustness of identity tag generation

[0047] Step S600: Based on the data collection identity tag, perform non-invasive power data collection on regional electrical appliances. Specifically, based on the generated data collection identity tag, perform non-invasive power data collection on regional electrical appliances, including collecting information such as real-time energy consumption data and working status of the electrical appliances, and using this data for applications such as energy consumption analysis and energy management. In the embodiment of the present application, by identifying and classifying the efficacy characteristics of the electrical appliances in the data collection area, obtaining efficacy classification tags, obtaining the electrical signal data of these electrical appliances, and performing time series feature analysis, an electrical signal time series feature list of the electrical appliances is constructed. Based on the efficacy classification tags, type clustering and feature alignment are performed on the time series feature list to identify differential data and time series features. Further, similarity evaluation is performed according to the differential data and time series features, and an electrical signal amplifier is configured to amplify the electrical signals that meet the confusion conditions. Indexed by the regional electrical appliance tag, the efficacy recognition features, electrical signal recognition features, and amplified electrical signal features are aggregated to generate a data collection identity tag, providing a target identifier for power data collection and other technical means, achieving the technical effect of improving the accuracy and reliability of data collection.

[0048] In the foregoing, reference is made to Figure 1 describe in detail the non-invasive power data collection method according to the embodiment of the present invention. Next, reference will be made to Figure 2 describe the non-invasive power data collection platform according to the embodiment of the present invention.

[0049] The non-invasive power data collection platform according to the embodiment of the present invention is used to solve the technical problem of insufficient accuracy and reliability existing in the existing non-invasive power data collection, and achieve the technical effect of improving the accuracy and reliability of data collection. The non-invasive power data collection platform includes: an electrical appliance efficacy classification module 10, an electrical signal time series feature analysis module 20, a differential data identification module 30, an electrical signal amplification module 40, a data collection identity tag generation module 50, and a non-invasive power data collection module 60.

[0050] The electrical appliance efficacy classification module 10 is used to identify the efficacy characteristics of electrical appliances in the data collection area, classify the electrical appliances according to the electrical appliance efficacy characteristics, and obtain the efficacy classification labels; the electrical signal time series feature analysis module 20 is used to acquire the electrical signal data of the regional electrical appliances, perform time series feature analysis on the electrical signal data according to the preset stage segmentation relationship, and construct an electrical appliance electrical signal time series feature list; the differential data identification module 30 is used to perform type clustering on the electrical appliance electrical signal time series feature list based on the efficacy classification labels, and perform feature alignment on the clustering results to identify differential data and time series features; the electrical signal amplification module 40 is used to perform similarity evaluation according to the differential data and time series features, configure an electrical signal amplifier according to the similarity evaluation result, and determine the efficacy identification features, and the electrical signal amplifier is used to amplify the electrical signals whose similarity evaluation results meet the confusion conditions; the data collection identity label generation module 50 is used to search for the efficacy identification features, electrical signal identification features, and amplified electrical signal features by taking the label of the regional electrical appliances as an index, aggregate the efficacy identification features, the electrical signal identification features, and the amplified electrical signal features, and generate a data collection identity label; the non-intrusive power data collection module 60 is used to perform non-intrusive power data collection of the regional electrical appliances based on the data collection identity label.

[0051] Next, the specific configuration of the electrical appliance efficacy classification module 10 will be described in detail. As described above, to identify the efficacy characteristics of electrical appliances in the data collection area, classify the electrical appliances according to the electrical appliance efficacy characteristics, and obtain the efficacy classification labels, the electrical appliance efficacy classification module 10 may further include: a load level configuration unit for collecting the load characteristics of the regional electrical appliances, performing level configuration on the load characteristics, and obtaining the load level; an electrical appliance efficacy characteristic identification unit for respectively identifying the starting current peak value, steady-state power, power curve, and harmonic characteristics of the electrical appliance signals based on the load level, obtaining the electrical appliance efficacy characteristics, and establishing a mapping association between the load level and the electrical appliance efficacy characteristics; a data label integration unit for configuring data labels for the electrical appliance type, the load level, and the electrical appliance efficacy characteristics, integrating the data labels according to the mapping association relationship, and performing efficacy characteristic identification on the regional electrical appliances to obtain the efficacy classification labels.

[0052] Next, the specific configuration of the electrical signal timing feature analysis module 20 will be described in detail. As described above, for the electrical signal data, timing feature analysis is performed according to the preset stage segmentation relationship. The electrical signal timing feature analysis module 20 may further include: a stage template signal establishment unit for establishing a stage template signal according to the preset stage, where the preset stage includes a start stage, a stable operation stage, and a shutdown stage; a timing alignment unit for performing timing alignment between the electrical signal data and the stage template signal and calculating a distance metric result between the timing signals; a key timing node determination unit for determining the key timing nodes of the stage segmentation interval based on the distance metric result to obtain the preset stage segmentation relationship; and a timing fluctuation feature analysis unit for performing timing fluctuation feature analysis on the electrical signal data according to the preset stage segmentation relationship to obtain electrical signal timing features, including the fluctuation amplitude, fluctuation frequency, and periodic fluctuation of current, voltage, or power.

[0053] Among them, for performing timing alignment between the electrical signal data and the stage template signal and calculating a distance metric result between the timing signals, the timing alignment unit may further include: a timing data pair acquisition subunit for performing timing alignment between the electrical signal data and the stage template signal to obtain a timing data pair; a Euclidean distance calculation subunit for calculating the Euclidean distance of the timing data pair; and a Euclidean distance superposition subunit for finding the minimum distance through a dynamic programming algorithm according to the Euclidean distance to obtain an accumulation path, and superposing the Euclidean distances in the path according to the accumulation path to obtain the distance metric result.

[0054] Among them, for determining the key timing nodes of the stage segmentation interval based on the distance metric result, the key timing node determination unit may further include: a start stage key timing node acquisition subunit for identifying a first distance change attenuation node of the starting timing according to the change of the cumulative distance value in the accumulation path to obtain the key timing nodes of the start stage, where the key timing nodes of the start stage are the inflection points where the distance change rate decreases; a shutdown stage key timing node acquisition subunit for using the key timing nodes of the start stage as the starting observation point, identifying that the change rate of the cumulative distance value starts to increase, and determining the inflection point where the distance change rate increases to obtain the key timing nodes of the shutdown stage; and a stable operation stage timing interval determination subunit for determining that the part between the key timing nodes of the start stage and the key timing nodes of the shutdown stage is the timing interval of the stable operation stage, where the timing interval of the stable operation stage is the area where the distance change is gentle.

[0055] Among them, for obtaining the electrical signal timing features, the timing fluctuation feature analysis unit may further include: an electrical signal sequence mean calculation subunit for calculating the mean of the electrical signal sequence: , where N is the length of the electrical signal sequence. The electrical signal data at time t; the time lag calculation subunit is used to calculate the time lag according to the timing relationship of the electrical signal sequence, and the time lag is the alignment amount between the signal itself and the signal after r time units in the subsequent timing; the autocorrelation value calculation subunit is used to calculate the autocorrelation value of the time lag: , where is the mean value of the electrical signal sequence, is the autocorrelation value of the time lag r; the periodic fluctuation feature recognition subunit is used to identify the periodic fluctuation feature according to the

[0056] Next, the specific configuration of the data acquisition identity tag generation module 50 will be described in detail. As described above, the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature are aggregated to generate a data acquisition identity tag. The data acquisition identity tag generation module 50 may further include: a feature vector generation unit for respectively representing the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature as feature vectors; a multi-scale analysis unit for performing multi-scale analysis on each of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature to obtain multi-scale features; an attention weight calculation unit for calculating the attention weight of each feature through a self-attention mechanism based on the multi-scale features; a comprehensive feature calculation unit for calculating the attention scores of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature using the attention weights, and then performing weighted summation to obtain a comprehensive feature; a data acquisition identity tag mapping unit for mapping the comprehensive feature to the data acquisition identity tag of the regional electrical appliance.

[0057] The non-intrusive power data acquisition platform provided by the embodiments of the present invention can execute the non-intrusive power data acquisition method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0058] Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0059] ​Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device and a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of the electronic device, the method described in any of the previous embodiments can be implemented.

[0060] Figure 3 FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present invention. The electronic device is presented in the form of a general-purpose computing device, and its components may include, but are not limited to, an input device 301, a processor 302, a memory 303, and an output device 304. Among them, the processor 302 may be one or more; the memory 303 may include a computer-readable medium and at least one program product, and the program product has a set (at least one) of program modules, and these program modules are configured to execute the functions of the embodiments of the present application.

[0061] The memory 303 shown in the embodiments of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, infrared rays, semiconductor systems, devices or components, or any combination of the above, for storing software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the non-intrusive power data acquisition method in the embodiments of the present invention. The processor 302 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 303, that is, the above non-intrusive power data acquisition method is implemented.

[0062] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps described in the present application may be executed in a different order from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A non-invasive power data acquisition method, characterized in that, The non-invasive power data acquisition method includes: Identifying the efficacy characteristics of electrical appliances in the data acquisition area, classifying the electrical appliances according to the efficacy characteristics of the electrical appliances, and obtaining efficacy classification labels; Obtaining the electrical signal data of the regional electrical appliances, performing time series feature analysis on the electrical signal data according to the preset stage segmentation relationship, and constructing an electrical signal time series feature list of the electrical appliances; Based on the efficacy classification labels, performing type clustering on the electrical signal time series feature list of the electrical appliances, and performing feature alignment on the clustering results to identify differential data and time series features; Performing similarity evaluation according to the differential data and time series features, configuring an electrical signal amplifier according to the similarity evaluation result, and determining the efficacy recognition feature, where the electrical signal amplifier is used to amplify the electrical signals whose similarity evaluation results meet the confusion condition; Searching for the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature by using the label of the regional electrical appliances as an index, aggregating the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature, and generating a data acquisition identity label; Performing non-invasive power data acquisition of the regional electrical appliances based on the data acquisition identity label; Among them, identifying the efficacy characteristics of the electrical appliances in the data acquisition area, classifying the electrical appliances according to the efficacy characteristics of the electrical appliances, and obtaining the efficacy classification labels includes: Collecting the load characteristics of the regional electrical appliances, configuring the load characteristics to obtain a load level; Based on the load level, respectively identifying the starting current peak value, steady-state power, power curve, and harmonic characteristics of the electrical appliance signal to obtain the efficacy characteristics of the electrical appliance, and establishing a mapping association between the load level and the efficacy characteristics of the electrical appliance; Configuring the data labels of the electrical appliance type, the load level, and the efficacy characteristics of the electrical appliance, integrating the data labels according to the mapping association relationship, and performing efficacy characteristic identification on the regional electrical appliances to obtain the efficacy classification labels; Among them, performing time series feature analysis on the electrical signal data according to the preset stage segmentation relationship includes: Establishing a stage template signal according to a preset stage, where the preset stage includes a starting stage, a stable operation stage, and a shutdown stage; Performing time series alignment on the electrical signal data and the stage template signal, and calculating the distance metric result between the time series signals; Based on the distance metric result, determining the key time series nodes of the stage segmentation interval to obtain the preset stage segmentation relationship; Performing time series fluctuation feature analysis on the electrical signal data according to the preset stage segmentation relationship to obtain electrical signal time series features, including the fluctuation amplitude, fluctuation frequency, and periodic fluctuation of current, voltage, or power; Among them, performing time series alignment on the electrical signal data and the stage template signal, and calculating the distance metric result between the time series signals includes: Performing time series alignment on the electrical signal data and the stage template signal to obtain a time series data pair; Calculating the Euclidean distance of the time series data pair; According to the Euclidean distance, finding the minimum distance through a dynamic programming algorithm to obtain an accumulated path, and superimposing the Euclidean distances in the path according to the accumulated path to obtain the distance metric result.

2. The non-intrusive power data acquisition method according to claim 1, wherein Based on the distance metric results, determine the key timing nodes of the phase segmentation interval, including: According to the change of the cumulative distance value in the cumulative path, identify the first distance change attenuation node of the starting timing, and obtain the key timing node of the starting phase. The key timing node of the starting phase is the inflection point where the distance change rate decreases; Use the key timing node of the starting phase as the starting observation point, identify that the change rate of the cumulative distance value starts to increase, determine the inflection point where the distance change rate increases, and obtain the key timing node of the closing phase; The part between the key timing node of the starting phase and the key timing node of the closing phase is the timing interval of the stable operation phase, and the timing interval of the stable operation phase is the area where the distance change is gentle.

3. The non-invasive power data acquisition method according to claim 1, wherein Obtain the timing characteristics of the electrical signal, including: Calculate the mean value of the electrical signal sequence: , where N is the length of the electrical signal sequence, is the electrical signal data at time t; According to the timing relationship of the electrical signal sequence, calculate the time lag amount, and the time lag amount is the alignment amount between the signal itself and the signal after r time units in the post-timing; Calculate the autocorrelation value of the time lag: , where is the mean of the electrical signal sequence, is the autocorrelation value of the time lag r; According to the above-mentioned Identify the periodic fluctuation characteristics.

4. The non-invasive power data acquisition method according to claim 1, wherein The feature aggregation of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature to generate a data acquisition identity label for the area electrical appliance includes: Represent the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature as feature vectors respectively; Perform multi-scale analysis on each of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature to obtain multi-scale features; Based on the multi-scale features, calculate the attention weight of each feature through the self-attention mechanism; Use the attention weight to calculate the attention scores of the efficacy recognition feature, the electrical signal recognition feature, and the amplified electrical signal feature, and then perform weighted summation to obtain the comprehensive feature; Map the comprehensive feature to the data acquisition identity label of the area electrical appliance.

5. Non-invasive power data acquisition platform, characterized in that The platform is used to implement the non-intrusive power data acquisition method according to any one of claims 1-4. The platform includes: An electrical appliance efficacy classification module, which is used to identify the efficacy characteristics of the electrical appliances in the data acquisition area, classify the electrical appliances according to the electrical appliance efficacy characteristics, and obtain the efficacy classification label; An electrical signal timing feature analysis module, which is used to obtain the electrical signal data of the area electrical appliance, perform timing feature analysis on the electrical signal data according to the preset phase segmentation relationship, and construct a list of electrical signal timing characteristics of the electrical appliance; A differential data identification module, which is used to perform type clustering on the list of electrical signal timing characteristics of the electrical appliance based on the efficacy classification label, perform feature alignment on the clustering result, and identify differential data and timing characteristics; An electrical signal amplification module, which is used to perform similarity evaluation according to the differential data and timing characteristics, configure an electrical signal amplifier according to the similarity evaluation result, determine the efficacy recognition feature, and the electrical signal amplifier is used to amplify the electrical signal whose similarity evaluation result meets the confusion condition; A data acquisition identity tag generation module, which is used to search for efficacy recognition features, electrical signal recognition features, and amplified electrical signal features by using the tag of the regional electrical appliance as an index, aggregate the efficacy recognition features, the electrical signal recognition features, and the amplified electrical signal features, and generate a data acquisition identity tag; A non-intrusive power data acquisition module, which is used to perform non-intrusive power data acquisition of regional electrical appliances based on the data acquisition identity tag.

6. An electronic device, characterized in that, The electronic device includes: A memory for storing executable instructions; A processor, which is used to implement the non-intrusive power data acquisition method according to any one of claims 1 to 4 when executing the executable instructions stored in the memory.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the non-intrusive power data acquisition method according to any one of claims 1-4.

Images