Self-adaptive heuristic grid clustering method suitable for non-intrusive load monitoring

Abstract

The invention discloses a self-adaptive heuristic grid clustering method suitable for non-intrusive load monitoring, which comprises the following steps of: S1, selecting low-frequency data, preprocessing the low-frequency data, and converting the selected data into a four-dimensional tensor containing total load, hour, week and month; s2, event detection is performed on the total load measurement sequence by using a time window, a four-dimensional matrix containing event amplitude and time reference is generated, events are grouped by using a heuristic grid clustering algorithm, and different clustering results represent different states of equipment in an operation process; s3, constructing a state transition matrix according to the event grouping result and the state change of each device in the operation process; and according to the energy consumption period and the state transition matrix of the equipment, reconstructing an energy consumption sequence of the equipment, completing the estimation of the energy consumption of the equipment, and calculating the use frequency of the equipment. The household data processing method has high precision and efficiency in household data processing, and can effectively separate electric energy loads of various types of electric appliances.

Description

Technical Field

[0001] The present invention relates to the technical fields of smart grid and energy management, and particularly to an adaptive heuristic grid clustering method applicable to non-intrusive load monitoring. Background Art

[0002] Non-intrusive load monitoring (NILM), as an important research direction in the current power field, is committed to accurately inferring the energy consumption of each electrical appliance based on the analysis of the main channel current. The accuracy of this technology has a profound impact on practical applications. In the power industry, accurate energy consumption inference can help users understand the contribution of each device to the total load, thereby optimizing the usage mode of electrical appliances and effectively reducing energy waste.

[0003] In current practical research, various solutions have been proposed for the NILM problem. Researchers mainly use probability models or deterministic models (such as finite state machines) to explain the behavior of electrical appliances, and some also adopt heuristic-based technologies. In modeling energy usage, hidden Markov models (HMMs) have become increasingly common, and combined with supervised and unsupervised procedures and signal processing technologies to achieve the decomposition of electrical appliance features. At the same time, the combination of fuzzy clustering and soft computing methods, and energy decomposition using specific algorithms have also been widely used. In addition, related research also involves the discussion of evaluation indicators and the identification scheme of hybrid devices based on time series characteristics.

[0004] However, these existing methods have certain limitations in practical applications. For example, the task complexity of HMMs increases significantly with the increase in the number of electrical appliances, the number of state combinations, and the number of sequences; some methods have limited adaptability to device types and are difficult to meet the accurate monitoring requirements of different types of devices; moreover, in dealing with complex situations such as measurement errors and concurrent multiple events, the accuracy and stability of inference need to be further improved. Summary of the Invention

[0005] Object of the Invention: The object of the present invention is to provide an adaptive heuristic grid clustering method applicable to non-intrusive load monitoring, aiming to identify and decompose the energy consumption of each electrical appliance by analyzing the total current signal in a household or commercial building, so as to achieve accurate monitoring of the usage of electrical appliances and optimized management of energy consumption.

[0006] Technical Solution: An adaptive heuristic grid clustering method applicable to non-intrusive load monitoring, including the following steps: S1, select the low-frequency data in the RAE and REDD datasets and perform preprocessing, and convert the selected data into a four-dimensional tensor containing the total load, hour, week, and month; S2. Detect events for the total load measurement sequence using a time window, generate a four-dimensional matrix containing event amplitudes and time references, and group the events using a heuristic grid clustering algorithm. Different clustering results represent different states of the device during operation; S3. Construct a state transition matrix based on the event grouping results and the state changes of each device during operation; adjust the power amplitude transfer within the period according to the zero-loop and constraints to make the sum of the transfer amplitudes approach zero; reconstruct the energy consumption sequence of the device based on the energy consumption period and state transition matrix of the device, complete the estimation of the device's energy consumption, and deduce the usage frequency of the device.

[0007] Furthermore, the preprocessing of the selected data is as follows: Extract time attributes from the time series and transform them into a four-dimensional tensor containing the total load F(t), hour H(t), week W(t), and month M(t). Unify the data scale through a sine function and normalization processing. The expression is: , where , , represent the total number of hours in a day, the total number of days in a week, and the total number of months in a year respectively; represents the total load, represents the hourly load, represents the weekly load, represents the monthly load.

[0008] Furthermore, in step S2, if any of the following conditions are met within the time window, it is determined as an event: The local change in the total load is greater than or equal to the threshold ; or the absolute value of the power difference between the input and output of the time window is greater than or equal to the threshold ; , where represents the average power within the time window, represents the power measurement value at the i-th time point within the time window, and n is the number of measurement points within the time window; represents the n-th time measurement point; When a certain electrical appliance is suddenly turned on, the power will fluctuate greatly. At this time, the value of will increase accordingly. At this time, it is necessary to calculate the local average power as the transitional amplitude: , When , register as an event; The absolute value of the power difference between the input and output of the time window , which reflects the change amplitude of the power within the window. The calculation formula is as follows: , where and are the power values at the start and end moments of the time window respectively; When , is registered as an event.

[0009] Furthermore, in step S2, the implementation process of grouping events using the heuristic grid clustering algorithm is as follows: S21, Initialize a grid structure containing N bins in the k-dimensional space, and fill the detected event data into the grid structure; define the grid space filled with data as a block, then calculate the density and center point of each block, classify the blocks into main blocks and ordinary blocks according to the density, and identify the main blocks. The main blocks have high density and their directly adjacent blocks are not selected as main blocks; S22, Use the middle range as the dissimilarity index to group events with similar characteristics into the same class; the calculation formula for the middle range is: , where Mid-Range represents the middle range, which is used to evaluate the difference degree of event characteristics. By comparing the middle range values of different event blocks, the similarity between events is judged; u represents an event in the block in the grid structure, represents the maximum value of the data contained in event u in the block in the grid structure, represents the minimum value of the data contained in event u in the block in the grid structure; S23, Merge the blocks; If , then merge the ordinary block with the main block, represents the density after the merger of the main block and the ordinary block, represents the initial density of the main block; If , the ordinary block is regarded as a new independent cluster; Repeat the above judgment process for the remaining blocks until there are no blocks that meet the merger conditions.

[0010] Furthermore, in step S3, associate the clustering result with the start and end markers of the device operation stage to construct a state transition matrix; the row and column indices of the state transition matrix represent the device operation stages, and the values in the matrix indicate whether a transition can occur between different stages; For the same device over a period of time, signals with similar power amplitudes and similar change trends are grouped together and determined as a complete consumption cycle; For a cycle containing s power amplitude transitions, according to the zero loop sum constraint, the following conditions are satisfied: , , wherein, is the s-th transition in the initial cycle, is the power amplitude transition value, is the threshold value defining the effective tolerance interval of the cycle.

[0011] Compared with the prior art, the remarkable effects of the present invention are as follows: 1. The present invention adopts a heuristic grid clustering algorithm to achieve optimized event grouping. Compared with traditional clustering methods (such as Kmeans, KNN), this algorithm can process high-dimensional data (including the time dimension) more efficiently, reduce noise interference, and improve the accuracy of event grouping; 2. The load reconstruction based on the state transition matrix of the present invention constructs the steady-state transition probability matrix of the device in combination with the clustering results to identify the complete cycle of the device operation mode (such as switch state, multi-mode switching); for multi-state devices (such as type II devices), by dynamically adjusting the transition matrix and the error correction algorithm, it ensures that the total power change in each cycle approaches zero (zero loop sum constraint, ZLSC), solves the complexity problem of load decomposition of multi-mode devices, and improves the accuracy of energy consumption inference through mathematical constraints; it can help consumers understand the energy consumption of each electrical appliance, optimize the use and reduce energy waste; 3. The present invention breaks through the limitation of traditional NILM that depends on the total load, takes the time attribute decomposition as the core feature and inputs it into the model; and performs multi-dimensional feature fusion, combines the total load data (F(t)) with time features (hour (H(t)), week (D(t)), month (M(t)) to form a four-dimensional input tensor; the introduction of time features enables the model to capture the periodicity of electricity consumption behavior (such as weekday / weekend differences, seasonal changes); compared with the traditional method that it is difficult to distinguish the operation modes of different devices only through power changes (for example, air conditioners and electric water heaters may have similar power fluctuations), multi-dimensional feature fusion helps the model associate the typical usage periods of specific devices (such as air conditioners are frequently used during the day in summer), can solve the problem of device load mode confusion, and increases the adaptability of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is an event-based energy decomposition diagram; Figure 2 is the overall flow chart of the present invention; Figure 3 It is a flow chart for event detection; Figure 4 It is a schematic diagram of the operation modes and state transitions of different devices. Among them, (a) is a schematic diagram of the state transition of a device with two operation modes, (b) is a schematic diagram of the state transition of a device with three operation modes, and (c) is a schematic diagram of the state transition of a device with four operation modes; Figure 5 It is a performance graph based on the correct energy percentage allocation. Among them, (a) is the performance graph of the proposed model on the RAE dataset based on the correct energy percentage allocation, and (b) is the performance graph of the proposed model on the REDD dataset based on the correct energy percentage allocation; Figure 6 It is a comparison graph of the decomposition results and the real data within 24 hours. Among them, (a) is the comparison graph of the decomposition results and the real data within 24 hours of the RAE dataset, and (b) is the comparison graph of the decomposition results and the real data within 24 hours of the REDD dataset. Detailed implementation manners

[0013] The present invention will be further described in detail below in conjunction with the accompanying drawings of the specification and the detailed implementation manners.

[0014] The present invention proposes a NILM method based on heuristic grid clustering, aiming to infer the energy consumption of each electrical appliance by analyzing the household load power. This method detects the operation mode period of the electrical appliance through the steady-state transition probability matrix and conducts detailed energy consumption inference. It is carried out on the household data with low-frequency sampling, and verifies that this data-driven model can efficiently and accurately estimate the power consumption. This method constructs a unique non-intrusive analysis platform, introduces feature engineering to increase the dimension of the input data on the basis of the typical NILM framework (Non-Intrusive Load Monitoring Framework), and adopts an error correction algorithm to improve the credibility of the decomposition method. In terms of data, the low-frequency data of the publicly available RAE and REDD datasets are selected for experiments. In the data preprocessing stage, the time attributes in the time series are extracted and transformed into a four-dimensional tensor and normalized; in the event detection stage, the total load measurement sequence is processed to generate a four-dimensional matrix; the heuristic grid clustering algorithm is used to group the events; in the load reconstruction link, a device state transition matrix is created, the error is corrected, and the energy consumption is estimated. To solve the problems existing in the prior art and achieve more accurate and efficient non-intrusive load monitoring. The specific steps are as follows: The first step is to perform data processing; Select the RAE and REDD datasets, and divide them into training set, test set and validation set according to the data characteristics and experimental requirements. Extract the time attributes from the time series, transform them into a four-dimensional tensor containing the total load F(t), hour H(t), day of the week D(t) and month M(t), and make the data reach a unified scale through sine function and normalization processing, and segment by day.

[0015] In the second step, perform event detection; Use a time window to process the total load measurement sequence. If the local change of the total load within the window is greater than or equal to the threshold , or the absolute value of the power difference is greater than or equal to the threshold , then it is determined as an event, and a four-dimensional matrix containing the event amplitude and time reference is generated.

[0016] In the third step, initialize a grid structure with 100 bins in the k-dimensional space. After filling with event data, calculate the density and center point of each block, identify the main block and use the middle range as the dissimilarity index, and perform iterative merging of blocks according to the formula to achieve effective grouping of events.

[0017] In the fourth step, carry out load reconstruction; Construct the state transition matrix of the device according to the clustering result, analyze the unclassified events to determine the energy consumption pattern of the device. According to the energy consumption pattern of the device and the corrected state transition matrix, reconstruct the energy consumption sequence of the device, complete the estimation of the device energy consumption and the calculation of the usage frequency, and reserve a tolerance of 5W for matching. Adjust the power amplitude transfer within the period according to the zero loop and constraint (ZLSC) to make the sum of the transfer amplitudes approach zero, and discard the periods that cannot be balanced within the set interval. Finally, according to the energy consumption pattern of the device and the corrected state transition matrix, reconstruct the energy consumption sequence of the device, complete the estimation of the device energy consumption and the calculation of the usage frequency.

[0018] In the fifth step, conduct result evaluation; Adopt evaluation indicators for energy decomposition such as precision, recall rate, decomposition accuracy rate and Fmeasure, combine with error quantification methods, compare and analyze the estimation results with the true values of actual measurements, and comprehensively evaluate the performance of the scheme.

[0019] As Figure 1 shown, a typical event-based NILM framework for non-intrusive analysis platform includes event recognition, establishing an operation mode conversion matrix, grouping highly similar conversions, identifying the complete usage cycle of the device, reconstructing the sequence corresponding to the device consumption profile, and then deriving the share of each device. The present invention is in Figure 1On the basis of the framework, additional optimization steps are introduced. The dimensionality of the model input data is increased through feature engineering, important parameters other than the total load are incorporated, and an error correction algorithm is adopted after identifying the device consumption cycle to enhance the credibility of the decomposition method. The overall solution is as Figure 2 shown. The steps are as follows: Step 1: Collect data; The RAE (Rainforest automation energy) dataset was released in 2018 and contains data from two households. The sampling frequency is 1 Hz, and in addition to power data, there are also environmental and sensor data. The REDD (Reference energy disaggregation data set) dataset is a commonly used energy disaggregation dataset that provides high-frequency (15 kHz) and low-frequency (1 Hz) data. In this embodiment, low-frequency data is mainly used because it is more in line with the commonly used power measurement devices in households.

[0020] Step 2: Preprocess the collected data; The data processing part covers data preprocessing and feature engineering. In the data preprocessing stage, considering that household energy consumption is comprehensively affected by various factors (such as season, week, daily time period, geographical location, house size, and the devices used, etc.), the corresponding time attributes are extracted from the time series and transformed into a four-dimensional tensor containing the total load, hour, week, and month. Subsequently, the sine function is used to transform these time data into a periodic sequence and normalized to make it have a unified scale.

[0021] 2.1) Data partitioning; The RAE dataset and the REDD dataset are selected as the sources of experimental data. In actual data processing, although there is no clear similar time node partitioning method, in actual applications, the dataset can be partitioned into a training set, a test set, and a validation set according to the data characteristics and experimental requirements to serve model training and evaluation.

[0022] 2.2) Data preprocessing; Extract time attributes from the time series. Considering that household energy consumption is affected by factors such as season, week, and daily time period, it is transformed into a four-dimensional tensor containing the total load F(t), hour H(t), week D(t), and month M(t). The specific process is to transform the time data into a periodic sequence through the sine function and then normalize it to achieve a unified scale. The expression is: (1) Among them, , , respectively represent the total number of hours in a day, the total number of days in a week, and the total number of months in a year; i represents the i-th time point, represents the total load, represents the hourly load, represents the weekly load, represents the monthly load. The processed data is segmented by day and analyzed based on the time axis.

[0023] Step 3, through the event detection and clustering process, using the intermediate range as the dissimilarity index, iteratively merge the grid blocks according to specific conditions of density and intermediate range, so that events with similar characteristics are grouped into the same category, realizing the effective grouping of events; 3.1) Event detection; As Figure 3 shown, use the time window to process the total load measurement sequence. If any of the following conditions are met within the time window, it is determined as an event: One is the local change of the power load is greater than or equal to the threshold ; The expression of (2) Among them, represents the average power within the time window, represents the power measurement value at the i-th time point within the time window, and n is the number of measurement points within the time window.

[0024] The local change of the total load reflects the power fluctuation within the time window: If the total load (i.e., the total power) fluctuates greatly within the time window, that is the value of

[0025] is large, it may mean that the operating state of an electrical appliance has changed, such as the electrical appliance being turned on or off. When a certain electrical appliance is suddenly turned on, the power will fluctuate greatly. At this time the value of will increase accordingly. At this time, it is necessary to calculate the local average power as the transitional amplitude; calculate the local average power (3) When the value of is greater than or equal to the threshold the local average power of this time window

[0026] Second, it is the absolute value of the power difference between the input and output of the time window is greater than or equal to ; The absolute value of the power difference reflects the change range of the power within the window, and the calculation formula is as follows: (4) Among them, , are the power values at the start and end times of the time window respectively.

[0027] When is greater than or equal to , is registered as an event.

[0028] Figure 3 Figure [figure number] details the event detection process.

[0029] 3.2) Heuristic grid clustering algorithm; Initialize a grid structure containing N bins in the k-dimensional space. In this embodiment, N = 100 is taken, and the detected event data is filled into the grid structure. The grid space filled with data is defined as a block. Then, calculate the density and center point of each block, and classify the blocks into main blocks and ordinary blocks according to the density. Identify the main blocks, that is, the blocks with high density and whose directly adjacent blocks are not selected as main blocks.

[0030] Take the middle range as the dissimilarity index, and the middle range calculation formula is: (5) Among them, Mid-Range represents the middle range, which is used to evaluate the difference degree of event features. By comparing the middle range values of different event blocks, the similarity between events is judged, and then the events with similar features are classified into the same category; u represents an event in the block of the grid structure, represents the maximum value of the data contained in event u in the block in the grid structure, represents the minimum value of the data contained in event u in the block in the grid structure.

[0031] Through the block merging operation, select the eligible blocks, and finally complete the classification of events. When merging, if the density after the merger of the main block and the ordinary block plus the middle range Mid-Range is not greater than the initial density of the main block, that is , then merge the ordinary block with the main block; otherwise, the ordinary block is regarded as a new independent cluster. Repeat the above judgment process for the remaining blocks until there are no blocks that meet the merging conditions.

[0032] Step 4: Identify the state by constructing a state transition matrix, reconstruct the load using the error correction state, complete the full cycle of identifying the operating mode of the device, and estimate the energy consumption of the device in combination with the load time.

[0033] 4.1) Identify the state transition matrix and the complete consumption cycle; In the heuristic grid clustering algorithm, different clustering results represent different states of the device during operation, and one clustering result represents one state of one device. By associating these clustering results with the start and end markers of the device operation phase, the transition situation between different states of each device can be accurately determined, and then the state transition matrix can be constructed. The row and column indices of the state transition matrix represent the operation phases of the device, and the values in the state transition matrix indicate whether a transition can occur between different phases. Figure 4 Graphically and intuitively shows the operating modes and state transition situations of different devices. Among them, Figure (a) presents the state transition situation of a device with two operating modes, Figure (b) shows a finite state machine with 3 operating modes, and Figure (c) illustrates the state transition of a device with 4 operating modes. The state transition situation is the key basis for determining the elements of the state transition matrix.

[0034] After the event assignment is completed for all input axes (i.e., all data input is completed), the cycles are grouped according to similar amplitudes. The signals from the same device are concentrated together to obtain the complete consumption cycle of the device. For example, by analyzing the power change signals of the device over a period of time, the signals with similar power amplitudes and similar change trends are grouped together and determined as a complete consumption cycle. For a device with multiple operating phases, in-depth research is required to determine its energy consumption pattern. The device corresponds to different power levels in different operating phases, and the state transition matrix closely links the state transition of the device with the power change. With the help of this state transition matrix, not only can we know the power magnitude of the device in each state, but also the specific change value of the power during the state transition can be determined. The state transition matrix is an important reference index for the state of electrical equipment, and analyzing the state transition matrix is a key step in identifying the complete consumption cycle of the device. As Figure 2 shown in [0W, 21W, 15W, 41W, 0W], it represents that a certain electrical appliance has different power states in a consumption cycle.

[0035] 4.2) Error correction algorithm; According to the zero-loop sum constraint (ZLSC), the power transfer amplitude within a period is adjusted so that the sum of the power transfer amplitudes approaches zero as much as possible. When the sum of the power transfer amplitudes is zero, it can be considered that the power is stable and unchanged during this period. In actual electrical load measurement, due to various interference factors, the measurement results often have errors, resulting in the sum of the power amplitude transitions deviating from zero. The error correction algorithm aims to adjust the power transfer amplitude so that the sum of the power amplitude transitions approaches zero as much as possible. For a period containing s power transfers, according to the zero-loop sum constraint, the following conditions are satisfied: (6) (7) where is the s-th transfer in the initial period, is the power amplitude transition value, is the threshold defining the effective tolerance interval of the period.

[0036] If some periods cannot be balanced within the set interval, they are discarded. According to the error correction, the load reconstruction is completed, and the accurate device state and state transition matrix are obtained, which can further accurately identify the device consumption period.

[0037] 4.3) Estimate the device energy consumption; Based on the energy consumption period state transition matrix of the device, the energy consumption sequence of the device is reconstructed, the estimation of the device energy consumption is completed, and the usage frequency of the device is calculated accordingly.

[0038] Step Five, result evaluation; Adopt evaluation indicators specifically for energy decomposition, including precision (Precision(P)), recall (Recall(R)), decomposition accuracy (Accuarcy(Acc.)), and F-measure. The expressions are as follows: (8) (9) (10) (11) where TP is the true positive example, TN is the true negative example, FP is the false positive example, and FN is the false negative example.

[0039] At the same time, combined with the error quantization method, the estimation result is compared and analyzed with the actual measured true value to comprehensively evaluate the accuracy of the device calculated by the present invention.

[0040] Through Step 1 to Step 4, the present invention can achieve non-intrusive load monitoring based on adaptive heuristic grid clustering and accurately infer the energy consumption of each electrical appliance.

[0041] In this embodiment, low-frequency data from the RAE and REDD public datasets are selected. First, the data is divided, preprocessed, and subjected to feature engineering. The time attribute is transformed into a four-dimensional tensor and normalized. Subsequently, in the event detection stage, the existing method is improved, and time windows are used to identify events and generate a four-dimensional matrix. Then, a heuristic grid clustering algorithm is used to group the events. In the load reconstruction stage, a device state transition matrix is constructed, the error is corrected, and the energy consumption is estimated. Finally, using specialized evaluation metrics such as precision, recall, and combining with an error quantification method, the estimated energy consumption is compared and analyzed with the actual measured value.

[0042] In the process of data processing and analysis of the present invention, metrics such as precision, recall, disaggregation accuracy, and F-measure are used to evaluate the present invention. From the experimental data (as shown in Table 1), in the monitoring of various electrical appliances for different datasets (RAE and REDD), relatively ideal results are obtained. For example, for the Lights & Plugs device in the RAE dataset, the precision reaches 0.990, the recall is 0.865, the F1Measure is 0.923, and the disaggregation accuracy is 0.987; for the Oven device in the REDD dataset, the precision is 0.994. Although the recall is relatively low (0.554), the overall F1 Measure can still reach 0.711, and the disaggregation accuracy is 0.975. This shows that in the energy consumption monitoring of most devices, the present invention can accurately identify the device state and reasonably allocate energy consumption, with high reliability.

[0043] Table 1 Evaluation of the proposed solution based on common disaggregation metrics for 5 days of usage data

[0044] Compared with traditional methods (as shown in Table 2), the adaptive heuristic grid clustering method proposed by the present invention has obvious improvements in various metrics. Taking Precision as an example, in traditional methods, K Means is 0.9241, K NN is 0.8954, etc., while the method of the present invention reaches 0.9565, with a significant improvement. This fully proves that the present invention has better performance in solving the problem of non-intrusive load monitoring compared with traditional methods.

[0045] Table 2 Comparison of the results of the present invention with the technical performance of traditional methods

[0046] The accuracy of the present invention is evaluated by comparing the consistency between the predicted energy consumption and the actual energy consumption. From Figure 5(Performance graph based on correct energy percentage allocation) It can be intuitively seen that on different devices in the REDD and RAE datasets, the present invention can correctly allocate most of the energy consumption to the corresponding devices. For example, for the dryer in the REDD dataset, the correct energy percentage allocation reaches a relatively high level, which means that the prediction of the energy consumption of this device by the present invention is highly consistent with the actual situation, effectively reducing the error of energy consumption allocation.

[0047] As Figure 5 shown, it intuitively demonstrates the performance of the present invention in terms of the accuracy of energy consumption allocation. The abscissa represents different electrical appliances, and the ordinate represents the percentage of correctly allocated energy. Figure 5 In (a) and (b), the devices in different datasets (such as REDD and RAE) are distinguished by bar charts (or other graphical elements) of different colors or shapes. It can be clearly seen the accuracy of the energy consumption allocation of the present invention for each device under different datasets, intuitively demonstrating the performance of the present invention in terms of the accuracy of energy consumption allocation.

[0048] As Figure 6 shown is the comparison graph of the decomposition result and the real data within 24 hours. In the graph, the solid line and the dashed line represent the predicted result and the real result respectively, further showing the degree of fitting between the predicted curve of the device energy consumption and the actual energy consumption curve by the present invention within a 24-hour period. For example, for lamps and plugs, the predicted curve and the real curve are relatively close in trend and value, with only a certain deviation in a few time periods, which indicates that the present invention can accurately track the energy consumption change of the device in practical applications and has good real-time performance. The experimental results show that the present invention has high precision and efficiency in processing household data, can effectively separate the electrical energy loads of various types of appliances, and has good generalization ability on different datasets.

[0049] As Figure 6 in (a) and (b), the abscissa is time (24 hours), and the ordinate is power (or energy consumption). Figure 6 In it, the solid line and the dashed line represent the predicted result (such as Predicted) and the real result (such as Actual) respectively. For different devices (such as lamps and plugs, dishwashers, etc.), the curves of the predicted and real results are plotted respectively to show the comparison of the device energy consumption prediction and the actual energy consumption by the present invention within 24 hours, helping readers intuitively understand the accuracy and stability of the present invention in real-time monitoring of device energy consumption.

Claims

1. An adaptive heuristic grid clustering method for non-intrusive load monitoring, characterized in that: The steps include: S1, selects low-frequency data from the RAE and REDD datasets and preprocesses them, converting the selected data into a four-dimensional tensor containing total load, hour, week, and month; S2, uses the time window to detect events in the total load measurement sequence, generates a four-dimensional matrix containing event amplitudes and time references, and uses a heuristic grid clustering algorithm to group the events. Different clustering results represent different states of the equipment during operation; S3, constructing a state transition matrix based on the event grouping results and the state changes of each device during operation; According to the zero loop and constraint, the power amplitude transfer within the cycle is adjusted so that the sum of the transfer amplitudes approaches zero; according to the energy consumption cycle and state transfer matrix of the equipment, the energy consumption sequence of the equipment is reconstructed to estimate the energy consumption of the equipment and calculate the usage frequency of the equipment.

2. The adaptive heuristic grid clustering method for non-intrusive load monitoring according to claim 1, characterized in that: The preprocessing of the selected data is as follows: extract the time attribute from the time series and transform it into a four-dimensional tensor containing the total load F(t), hour H(t), week W(t) and month M(t). The data scale is unified through sine function and normalization. The expression is: ， in, , , Represents the total number of hours in a day, the total number of days in a week, and the total number of months in a year; Indicates the total load, Indicates hourly load, Indicates weekly load, Indicates monthly load.

3. The adaptive heuristic grid clustering method for non-intrusive load monitoring according to claim 1, characterized in that: In step S2, if any of the following conditions is met within the time window, it is determined to be an event: local change of total load Greater than or equal to threshold ; or the absolute value of the power difference between the input and output of the time window Greater than or equal to threshold ; ， in, represents the average value of the power in the time window, represents the power measurement value at the i-th time point in the time window, and n is the number of measurement points in the time window; Indicates the nth time measurement point; When an appliance is suddenly turned on, the power will fluctuate greatly. The value of will increase accordingly, and the local average power needs to be calculated at this time As the amplitude of the transition: ， when When Register as an event; The absolute value of the power difference between the input and output of the time window , reflects the change range of power within the window, and the calculation formula is as follows: ， in, , are the power values ​​at the start and end of the time window respectively; when When Register as an event.

4. The adaptive heuristic grid clustering method for non-intrusive load monitoring according to claim 1, characterized in that: In step S2, the implementation process of grouping events using the heuristic grid clustering algorithm is as follows: S21, initialize a grid structure containing N boxes in a k-dimensional space, fill the detected event data into the grid structure; define the grid space filled with data as a block, then calculate the density and center point of each block, divide the blocks into main blocks and common blocks according to the density, and identify the main block, which has a high density and whose directly adjacent blocks are not selected as the main block; S22, using the middle range as the dissimilarity index, classifies events with similar characteristics into the same category; the calculation formula for the middle range is: ， Among them, Mid-Range represents the middle range, which is used to evaluate the difference degree of event characteristics. By comparing the middle range values ​​of different event blocks, the similarity between events can be judged; u represents the block in the grid structure An event, Represents blocks in a grid structure The maximum value of the data contained in event u, Represents blocks in a grid structure The minimum value of the data contained in event u; S23, merging the blocks; like , then merge the common block with the main block, Indicates the density after the main block and the ordinary block are merged, represents the initial density of the main block; like , common blocks are treated as new independent clusters; Repeat the above judgment process for the remaining blocks until there are no blocks that meet the merging conditions.

5. The adaptive heuristic grid clustering method for non-intrusive load monitoring according to claim 1, characterized in that: In step S3, the clustering results are associated with the start and end marks of the device operation phase to construct a state transition matrix; the row and column indexes of the state transition matrix represent the operation phase of the device, and the values ​​in the matrix indicate whether a transition can occur between different phases; For the same device within a period of time, signals with similar power amplitudes and similar change trends are grouped together to determine a complete consumption cycle; For a cycle containing s power amplitude transfers, according to the zero cycle and constraint, the following conditions are satisfied: ， ， in, is the sth transfer in the initial cycle, is the power amplitude transition value, is the threshold that defines the effective tolerance interval of the cycle.

Images