A method and device for enhancing the accuracy of electricity consumption collection data

Abstract

The present invention discloses a method and device for enhancing the accuracy of electricity consumption data collection, and relates to the field of data processing technology. The method includes: generating a predicted power characteristic parameter set by analyzing historical power quality records, and calculating a predicted power quality index; performing multi-dimensional power collection through a first-level collector to generate a first power quality index, and judging whether the deviation between the first-level collector and the predicted power quality index is within a threshold. If the deviation exceeds the threshold, activating a second-level collector to perform more detailed collection, and performing accuracy enhancement adjustment to obtain a target power quality index. The present invention solves the technical problem that traditional power quality monitoring in the prior art relies on a single-level data collection method, resulting in insufficient monitoring accuracy and poor real-time performance, and achieves the technical effect of performing multi-dimensional monitoring of power data through multi-level collectors, and performing accuracy enhancement processing on the collected data to improve the accuracy and real-time performance of power quality monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for enhancing the accuracy of electricity consumption collection data. Background Art

[0002] With the rapid development of modern power grids and the increase in electricity demand, power quality monitoring and control has become one of the key factors to ensure the stable operation of power grids. The quality of power directly affects the safe operation of user equipment, the effective use of energy, and the overall efficiency of the power grid. Traditional power quality monitoring usually relies on a single-level data collection method, which cannot fully and accurately reflect the changes in various power parameters in the power grid. Especially in the face of complex power grid environments and dynamic load changes, it is easy to lead to insufficient accuracy of collected data and fail to capture power quality fluctuations in a timely and accurate manner. Summary of the invention

[0003] The present application provides a method and device for enhancing the accuracy of electricity consumption collection data, which is used to solve the technical problem that traditional power quality monitoring in the prior art relies on a single-level data collection method, resulting in insufficient monitoring accuracy and poor real-time performance.

[0004] In a first aspect of the present application, a method for enhancing the accuracy of electricity consumption data collection is provided, and the method for enhancing the accuracy of electricity consumption data collection is applied to a device for enhancing the accuracy of electricity consumption data collection, and the device for enhancing the accuracy of electricity consumption data collection includes a first-level collector and a second-level collector. The method includes: reading a power quality prediction strategy, and analyzing the historical power quality records of the power grid according to the power quality prediction strategy to obtain a predicted power feature parameter set, and normalizing and weighting the predicted power feature parameter set to obtain a predicted power quality index; performing multi-dimensional power collection on the power grid through the first-level collector to obtain a first power feature Parameter set, and normalize and weight the first power characteristic parameter set to obtain a first power quality index; determine whether the first index deviation of the first power quality index and the predicted power quality index is within the deviation threshold; if not, activate the second-level collector to perform multi-dimensional power collection on the power grid to obtain a second power characteristic parameter set, and normalize and weight the second power characteristic parameter set to obtain a second power quality index; perform precision enhancement adjustment on the second power quality index with the second power quality index to obtain a target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid.

[0005] According to a second aspect of the present application, there is provided a device for enhancing the accuracy of electricity consumption data collection, the device comprising a first-level collector and a second-level collector, the device comprising: a power quality prediction module, the power quality prediction module being used to read a power quality prediction strategy, and analyzing the historical power quality records of the power grid according to the power quality prediction strategy to obtain a predicted power characteristic parameter set, and normalizing and weighting the predicted power characteristic parameter set to obtain a predicted power quality index; a first power quality analysis module, the first power quality analysis module being used to perform multi-dimensional power collection on the power grid through the first-level collector to obtain a first power characteristic parameter set, and normalizing and weighting the first power characteristic parameter set to obtain a first power quality index; a power quality deviation judgment module, the power quality deviation judgment module A quantity deviation judgment module is used to judge whether the first index deviation between the first power quality index and the predicted power quality index is within the deviation threshold; a second power quality analysis module, the second power quality analysis module is used to activate the second-level collector to perform multi-dimensional power collection on the power grid to obtain a second power characteristic parameter set, and normalize and weight the second power characteristic parameter set to obtain a second power quality index when the first index deviation between the first power quality index and the predicted power quality index is not within the deviation threshold; a power quality index adjustment module, the power quality index adjustment module is used to perform precision enhancement adjustment on the second power quality index with the second power quality index to obtain a target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides a method and device for enhancing the accuracy of electricity consumption data collection, which relates to the field of data processing technology. By analyzing historical data, the predicted power quality index is calculated, and the first-level collector is used for multi-dimensional power collection, a first power quality index is generated and its deviation from the predicted index is judged. If it exceeds the threshold, the second-level collector is activated for fine collection, a second power quality index is generated and adjusted for accuracy enhancement, and a target power quality index is obtained to quantitatively characterize the power quality of the power grid. The technical problem that the traditional power quality monitoring in the prior art relies on a single-level data collection method, resulting in insufficient monitoring accuracy and poor real-time performance is solved, and the multi-dimensional monitoring of power data through multi-level collectors is realized, and the collected data is processed with enhanced accuracy to improve the accuracy and real-time performance of power quality monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a method for enhancing the accuracy of electricity consumption collection data provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of a process for obtaining a predicted power quality index in a method for enhancing the accuracy of electricity collection data provided in an embodiment of the present application.

[0011] Figure 3 A schematic diagram of the structure of a device for enhancing the accuracy of electricity consumption collection data provided in an embodiment of the present application.

[0012] Explanation of the accompanying drawings: power quality prediction module 11, first power quality analysis module 12, power quality deviation judgment module 13, second power quality analysis module 14, power quality index adjustment module 15. DETAILED DESCRIPTION

[0013] The present application provides a method and device for enhancing the accuracy of electricity consumption collection data, which is used to solve the technical problem that traditional power quality monitoring in the prior art relies on a single-level data collection method, resulting in insufficient monitoring accuracy and poor real-time performance.

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a method for enhancing the accuracy of electricity collection data, the method for enhancing the accuracy of electricity collection data is applied to a device for enhancing the accuracy of electricity collection data, the device for enhancing the accuracy of electricity collection data includes a first-level collector and a second-level collector, and the method for enhancing the accuracy of electricity collection data includes:

[0017] P10: Read the power quality prediction strategy, and analyze the historical power quality records of the power grid according to the power quality prediction strategy to obtain a predicted power characteristic parameter set, and normalize and weight the predicted power characteristic parameter set to obtain a predicted power quality index.

[0018] Further, such as Figure 2 As shown, step P10 of the embodiment of the present application also includes:

[0019] P11: Extract the first historical record at the first historical time in the historical power quality record, wherein the first historical record includes first historical power feature information; P12: Read a predetermined power quality factor, and traverse the predetermined power quality factor in the first historical power feature information to obtain a first historical power feature parameter set; P13: Analyze the first historical power feature parameter set to obtain a first historical power quality index; P14: Generate a historical power quality time series based on a first corresponding relationship between the first historical time and the first historical power quality index; P15: Perform predictive analysis on the historical power quality time series based on the power quality prediction strategy to obtain the predicted power quality index.

[0020] Furthermore, step P12 of the embodiment of the present application also includes:

[0021] P12-1: The predetermined power quality factors include a first factor set and a second factor set, the first factor set collects data through the first-level collector, and the second factor set collects data through the second-level collector; wherein, the first factor set includes voltage, current, frequency, power factor, and three-phase imbalance, and the second factor set includes short-term voltage fluctuations, long-term voltage fluctuations, power system interference, and harmonic content.

[0022] It should be understood that the power quality prediction strategy is read, and the historical power quality records of the power grid are analyzed based on the strategy to obtain a set of predicted power characteristic parameters, and these parameter sets are normalized and weighted to generate a predicted power quality index.

[0023] Specifically, first, a first historical record at a specific time point (i.e., a first historical time) is extracted from the historical power quality record. The historical record contains historical power characteristic information at that moment, such as key power quality indicators such as voltage, current, and frequency, i.e., the first historical power characteristic information.

[0024] Next, the predetermined power quality factors are read. These factors are important parameters for measuring power quality. In order to fully obtain the power characteristics, the predetermined power quality factors are traversed in the first historical power characteristic information, thereby obtaining the first historical power characteristic parameter set. During the traversal process, the predetermined power quality factors are divided into a first factor set and a second factor set. Among them, the data of the first factor set is collected by the first-level collector, specifically including basic power parameters such as voltage, current, frequency, power factor and three-phase imbalance. These parameters reflect the basic power quality conditions in the operation of the power grid. The second factor set is collected by the second-level collector, including more refined power parameters such as short-term voltage fluctuations, long-term voltage fluctuations, power system interference and harmonic content. These factors focus more on reflecting power fluctuations and abnormal phenomena in the power grid.

[0025] After traversing and collecting the required power characteristic parameters, the first historical power characteristic parameter set is analyzed and processed. For example, the data are first preprocessed to filter out abnormal values ​​or missing data to ensure the integrity and accuracy of the data set, and then the extracted historical power characteristic data are normalized to standardize the power characteristic parameters of different magnitudes to the same range (such as 0 to 1). Further, the normalized parameters are weighted according to the weight of the impact of each power characteristic on the power quality. For example, voltage fluctuation has a greater impact on power quality, and its weight may be higher, while other minor parameters have lower weights. Through this weighted method, it is ensured that important power characteristics play a key role in the evaluation of power quality. And the first historical power quality index is calculated based on a certain formula or model (such as linear weighted summation or other machine learning algorithms) using the weighted power characteristic parameter set. The index is a quantitative assessment of the power quality of the power grid during the first historical time period.

[0026] According to the correspondence between the first historical time and the first historical power quality index, a historical power quality time series is generated. The time series takes the historical time as the horizontal axis and the power quality index as the vertical axis, reflecting the changing trend of power quality at different time points. The historical power quality time series can intuitively show the fluctuation of power quality over time, especially the fluctuation of power quality when the load changes, weather factors or equipment status changes.

[0027] Finally, according to the power quality prediction strategy, the generated historical power quality time series is predicted and analyzed to obtain the predicted power quality index. This index represents the expected state of power quality of the power grid in a certain period of time in the future and is used to guide the operation and management decisions of the power grid.

[0028] Furthermore, step P15 of the embodiment of the present application also includes:

[0029] P15-1: According to the power quality prediction strategy, the historical power quality scatter plot drawn according to the historical power quality time series is sampled and fitted to obtain the first fitting curve corresponding to the first sample point set; P15-2: Compare the historical power quality scatter plot with the first sample point set to obtain a first non-sample point set, and the first non-sample point set includes multiple non-sample points; P15-3: Extract the first non-sample point from the multiple non-sample points, and determine whether the first distance between the first non-sample point and the first fitting curve meets the distance threshold; P15-4: If it meets, add the first non-sample point to the fitting point list, if not, add the first non-sample point to the abnormal point list; P15-5: When the ratio of the number of samples in the fitting point list to the number of samples in the abnormal point list is greater than one half, use the first fitting curve as the historical power quality index fitting curve; P15-6: Analyze the historical power quality index fitting curve to obtain the predicted power quality index.

[0030] Optionally, a predicted power quality index is generated by sampling and fitting historical power quality time series data. First, according to the power quality prediction strategy, the historical power quality scatter plot drawn according to the historical power quality time series is sampled to obtain a first set of sample points. These sample points represent the key data points in the historical time series and reflect the state changes of the power quality at different time points. Then, the first set of sample points is fitted to generate a corresponding first fitting curve. The first fitting curve is a smooth curve derived from the trend of the sample points, which is used to represent the trend of changes in power quality over time.

[0031] After the first fitting curve is generated, the historical power quality scatter plot is compared with the first sample point set to identify data points not included in the sample point set, which are called the first non-sample point set. These non-sample points may be power quality points that were not selected by the initial sampling due to grid fluctuations or other reasons.

[0032] Further, any non-sample point is randomly selected from the first non-sample point set as the first non-sample point, and a first distance between the non-sample point and the first fitting curve is calculated. The first distance represents the degree to which the non-sample point deviates from the fitting curve, and can be used to evaluate whether the non-sample point meets the normal fluctuation range of power quality. The distance calculation here can adopt common methods such as Euclidean distance and Manhattan distance, and the specific selection depends on the characteristics of the data and the analysis requirements.

[0033] Then, it is determined whether the first distance meets the preset distance threshold, which is the preset distance threshold, i.e., the preset allowable range of deviation from the fitting curve, which can be set by professionals based on empirical data. If the distance between the first non-sample point and the fitting curve meets the threshold requirement, the non-sample point is regarded as a normal fluctuation and added to the fitting point list, and these points can further participate in the fitting process. If the distance exceeds the threshold, the non-sample point is regarded as an abnormal fluctuation and added to the abnormal point list. By setting a reasonable distance threshold, normal fluctuations and abnormal fluctuations in the data can be effectively distinguished.

[0034] The fitting point list and the abnormal point list are continuously updated. When the ratio of the number of sample points in the fitting point list to the number of sample points in the abnormal point list is greater than one-half, it means that most of the data conforms to the normal change trend of power quality. It is considered that the first fitting curve can better represent the overall trend of historical power quality data, so it is used as the historical power quality index fitting curve. This fitting curve represents the overall change trend of historical power quality over time.

[0035] Finally, the historical power quality index fitting curve is analyzed, such as trend analysis, volatility analysis, etc., to generate a predicted power quality index. This index is based on the historical data fitting results, represents the expected state of future power quality, and can provide effective decision support for the operation and management of the power grid.

[0036] P20: Perform multi-dimensional electric energy collection on the power grid through the first-level collector to obtain a first electric energy characteristic parameter set, and normalize and weight the first electric energy characteristic parameter set to obtain a first power quality index.

[0037] Specifically, the first-level collector collects multi-dimensional power data from the power grid to generate accurate power quality assessment. First, the first-level collector is deployed at the key nodes of the power grid, responsible for real-time and comprehensive collection of multi-dimensional power data during the operation of the power grid. These power data include but are not limited to key parameters such as voltage, current, frequency, power factor, etc., which together constitute the first power characteristic parameter set.

[0038] Next, in order to unify the different parameters in the first electric energy characteristic parameter set under the same dimension for comparison and analysis, the collected first electric energy characteristic parameter set is normalized. Normalization is a key step in data processing, and its purpose is to standardize parameters of different units and different magnitudes into a unified range, usually between 0 and 1. This can eliminate the deviation caused by different data magnitudes and make different parameters comparable when weighted.

[0039] After normalization, these parameters are weighted. Weighting is to assign corresponding weights to each parameter according to its importance to power quality. For example, frequency and voltage fluctuations may have a greater impact on power quality, so their weights are usually higher, while other relatively minor parameters have lower weights. After weighting according to the assigned weights, the first power quality index is generated. This index is a comprehensive evaluation based on the multi-dimensional power feature data collected by the first-level collector, and can quantify the power quality status of the current power grid. This index can not only be used to evaluate the current power quality, but also serve as an important basis for subsequent predictive analysis and decision support.

[0040] P30: Determine whether a first index deviation between the first power quality index and the predicted power quality index is within a deviation threshold.

[0041] It should be understood that by comparing the first power quality index with the predicted power quality index, it is determined whether the deviation between the two is within a preset allowable range. The purpose of this step is to determine whether the power quality of the current power grid meets the predicted standard, so as to promptly discover potential abnormalities.

[0042] Specifically, the difference between the first power quality index and the predicted power quality index, that is, the first index deviation, is first calculated. This deviation value reflects the degree of difference between the actual power quality of the current power grid and the predicted power quality. The method of calculating the deviation usually involves simple mathematical operations, such as subtraction or percentage calculation, depending on the representation of the power quality index and the analysis requirements. The deviation quantifies the gap between the current power quality state and the expected value, and is an important indicator for detecting whether the power grid is operating normally. If the deviation is small, it means that the current operation status of the power grid is consistent with the predicted value and the power quality is within the expected range; if the deviation is large, it may mean that the operation of the power grid is abnormal and further detection or adjustment is required.

[0043] In order to ensure that the system can effectively cope with different degrees of deviation, a deviation threshold is set. The threshold value defines the maximum allowable deviation range, that is, the threshold value determined based on factors such as grid operation experience, power quality standards, and system accuracy requirements, and is used to determine whether the power quality index deviation is within an acceptable range. It is usually set based on the grid operation requirements and the stability requirements of power quality. For example, in a grid with high requirements for power quality, the threshold value may be smaller to ensure the precise stability of the grid; in some environments where large fluctuations are allowed, the threshold value can be appropriately relaxed.

[0044] By comparing the first index deviation with the deviation threshold, we can determine whether the power quality of the current power grid is within the predicted range. If the deviation value is less than or equal to the threshold, it means that the power quality of the power grid meets expectations and the system can continue to operate normally. If the deviation value exceeds the threshold, it may indicate potential problems or anomalies in the power grid. The system will activate further refined detection steps or take corresponding adjustment measures to ensure that the power quality returns to the expected range.

[0045] P40: If not, activate the second-level collector to perform multi-dimensional power collection on the power grid to obtain a second power characteristic parameter set, and normalize and weight the second power characteristic parameter set to obtain a second power quality index.

[0046] In a possible embodiment of the present application, when it is detected that the deviation between the first power quality index and the first index of the predicted power quality index exceeds a preset deviation threshold, the second-level collector is activated to perform more refined power data collection. This process is intended to further analyze the abnormal conditions of the power quality of the power grid through more accurate monitoring means and generate more accurate power quality assessment results.

[0047] First, activate the second-level collector. Compared with the first-level collector, the second-level collector has stronger data collection capabilities. It is deployed on more critical or complex nodes of the power grid and can capture more detailed and abnormal power quality characteristics. At this time, the second-level collector will once again perform multi-dimensional power collection on the power grid to obtain more detailed data related to power quality. Unlike the first-level collection, the second-level collector focuses on detecting deep-level indicators of power quality fluctuations and power grid anomalies, such as short-term voltage fluctuations, long-term voltage fluctuations, power system interference, and harmonic content. These data can better reflect the potential power fluctuations and quality problems in the power grid.

[0048] After the collection is completed, the data is organized into the second power characteristic parameter set. This parameter set is more comprehensive and detailed than the first-level collection results, and can reveal the causes of power quality fluctuations in more depth. Next, the second power characteristic parameter set is normalized to standardize parameters of different units and magnitudes to the same range, ensuring that the subsequent weighted and calculated processes will not be biased due to differences in data magnitude.

[0049] After normalization, these normalized parameters are weighted. The second level of weighting is more complex and detailed because different power characteristics may have significantly different effects on power quality. For example, harmonic content and power system interference may play an important role when the power grid is abnormal, so their weights may be higher, while other minor factors have lower weights. After normalization and weighting, a second power quality index is generated. This index is based on the multi-dimensional power feature data collected by the second-level collector and is a further quantitative assessment of the power quality status of the power grid. Compared with the first power quality index, the second power quality index is more accurate and can provide more detailed and reliable information for the analysis of power quality of the power grid.

[0050] P50: Performing precision enhancement adjustment on the second power quality index using the second power quality index to obtain a target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid.

[0051] Specifically, the second power quality index is adjusted for precision enhancement, and finally a target power quality index is generated, which is used to more accurately quantify and characterize the power quality state of the power grid.

[0052] First, based on the second power quality index generated by the second-level collector, precision enhancement adjustment is performed. Precision enhancement refers to further optimization and correction of the existing power quality assessment results to compensate for errors or data incompleteness that may occur during the collection and processing process. Exemplarily, a variety of technical means can be used to optimize the second power quality index. Including data correction, that is, by comparing historical data with existing power quality characteristics, correcting possible abnormal data points or values ​​with large fluctuations to ensure data stability. Dynamic adjustment is performed, that is, according to the real-time data of the current power grid operation status, the calculation method of the power quality index is dynamically adjusted to ensure that it can adapt to changes and fluctuations in the power grid load. Multi-level analysis is performed, that is, combined with multi-level power feature analysis (such as short-term voltage fluctuations, harmonic content, power system interference, etc.), the calculation of the index is optimized at a deeper level to ensure that the final result can fully reflect the multi-dimensional characteristics of the power quality of the power grid.

[0053] After precision enhancement adjustment, the target power quality index is obtained. This index not only inherits the comprehensiveness and precision of the second power quality index, but also has significantly improved accuracy. It can more accurately quantify and characterize the power quality status of the power grid, providing a more reliable and accurate basis for decision-making for power grid managers. It can serve as an important reference for future power grid dispatching, control and optimization. For example, if the target power quality index shows that the power quality is close to or exceeds the preset safety range, the system can issue a warning signal in time, prompting the operator to take corresponding measures to ensure the safe and stable operation of the power grid.

[0054] Furthermore, the embodiment of the present application further includes step P40a, and step P40a further includes:

[0055] P40a: If in, retrieve the predicted power quality index to perform precision enhancement adjustment on the first power quality index to obtain the target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid.

[0056] Optionally, when it is detected that the deviation between the first power quality index and the predicted power quality index is within a threshold range, it is not necessary to activate the second-level collector for more detailed collection. The predicted power quality index can be directly retrieved and compared with the first power quality index for analysis, thereby enhancing the accuracy of the first power quality index.

[0057] In this process, the potential deviation or deficiency in the first power quality index can be corrected by predicting the trend of the power quality index and the historical data model. This precision enhancement adjustment may include: data comparison and correction, that is, comparing the first power quality index with the predicted power quality index point by point to ensure that each data point of the first power quality index is consistent with the prediction model. If a small deviation is found in the local data, it is corrected according to the predicted index. Dynamic trend adjustment, that is, based on the time trend of the predicted power quality index, analyzing whether the first power quality index can reflect the actual dynamics of the power grid operation. If it is found that the first power quality index fails to fully capture certain trends in the operation of the power grid, the index is further optimized and adjusted according to the dynamic information of the prediction model. Weighted optimization, that is, in the process of precision enhancement, the weighted processing method of the first power quality index is re-optimized, especially when the importance of certain feature data changes. For example, if it is predicted that the frequency fluctuation of the electric energy will be more significant during a certain period of time, the weight of the frequency in the power quality index is increased to ensure that the final evaluation result can better reflect the actual situation.

[0058] Through these adjustments and optimizations, a more accurate target power quality index is generated. This target index not only takes into account the real-time data of the first power quality index, but also incorporates the historical trend and model results of the predicted power quality index, ensuring the accuracy and reliability of the evaluation. The final target power quality index can be used to quantitatively characterize the power quality of the power grid. As a comprehensive evaluation indicator of power quality, it can provide important decision-making support for the operation and maintenance, dispatch optimization and fault warning of the power grid. Through this precision enhancement adjustment, even if the deviation is detected within the allowable range, the accuracy of the evaluation can be maximized to ensure the efficient and stable operation of the power grid.

[0059] Furthermore, the device for enhancing the accuracy of power consumption data collection further includes a power consumption feature collector, so the embodiment of the present application further includes step P60, and step P60 further includes:

[0060] P61: Obtain a predetermined power consumption characteristic factor, wherein the predetermined power consumption characteristic factor refers to a power consumption characteristic factor that affects the power quality; P62: Activate a power consumption characteristic collector, wherein the power consumption characteristic collector dynamically monitors the predetermined power consumption characteristic factor to obtain a power consumption characteristic parameter set; P63: Use the power consumption characteristic parameter set as input information of a power quality impact rate prediction model to obtain a predicted impact rate; P64: Calibrate and adjust the target power quality index based on the predicted impact rate.

[0061] It should be understood that a device for enhancing the accuracy of electricity consumption collection data in the present application also includes an electricity consumption feature collector, which can dynamically monitor electricity consumption characteristic factors related to power quality, thereby further improving the accuracy of power quality assessment.

[0062] Specifically, first obtain a set of predetermined power consumption characteristic factors. These factors refer to power consumption characteristic factors that can affect the power quality, that is, key power consumption characteristics, which usually include the operating characteristics, load changes, power consumption patterns, etc. of electrical equipment in the operation of the power grid. After determining the predetermined power consumption characteristic factors, activate the power consumption characteristic collector. The power consumption characteristic collector can dynamically monitor the power consumption characteristic parameters in the power grid, and collect data in real time according to the predetermined power consumption characteristic factors to form a set of power consumption characteristic parameters, ensuring that when analyzing the power quality, not only the basic power characteristics of the power grid are considered, but also the impact of actual power consumption behavior, thereby improving the comprehensiveness and accuracy of the overall evaluation.

[0063] Subsequently, the power consumption characteristic parameter set is used as input information and input into a power quality impact rate prediction model. This model is built based on advanced algorithms and a large amount of historical data, and can accurately predict the degree of impact of different power consumption characteristics on power quality, that is, the predicted impact rate. The predicted impact rate refers to the degree of impact of power consumption characteristic factors on power quality, reflecting the interference or improvement effect of current power consumption behavior on power quality. For example, when the load increases sharply, the predicted impact rate may rise, indicating that there is a risk of deterioration in power quality.

[0064] Finally, the previously generated target power quality index is calibrated and adjusted based on the predicted impact rate. The purpose of this calibration adjustment is to correct the target power quality index so that it can better reflect the impact of the power consumption characteristic factors in the actual power grid. Specifically, if the predicted impact rate is high, it means that the power consumption characteristics have a greater impact on the power quality, and the target power quality index is reduced accordingly; conversely, if the predicted impact rate is low, it means that the power consumption characteristics have less interference with the power quality, and the evaluation result of the target power quality index is maintained or improved. By dynamically monitoring the power consumption characteristics, predicting their impact rates, and calibrating and adjusting the target power quality index, the power quality status of the power grid can be more accurately reflected, providing a more reliable decision-making basis for power grid managers.

[0065] Furthermore, step P63 of the embodiment of the present application also includes:

[0066] P63-1: The first historical record also includes a first historical electricity consumption characteristic parameter set and a first historical actual power quality index; P63-2: The ratio of the first historical actual power quality index to the first historical power quality index is taken as the first historical impact rate; P63-3: The first data group consisting of the first historical electricity consumption characteristic parameter set and the first historical impact rate is subjected to supervised training to obtain the power quality impact rate prediction model.

[0067] Optionally, the process of constructing a power quality impact rate prediction model through a power consumption characteristic parameter set is further refined. First, a first historical power consumption characteristic parameter set and a first historical actual power quality index are extracted from a first historical record. Among them, the first historical power consumption characteristic parameter set refers to power consumption behavior data related to the historical operating status of the power grid, such as load fluctuations, equipment start-up and stop, power factor changes, etc., which reflect the direct impact of power consumption characteristics on power grid operation. The first historical actual power quality index is a power quality assessment value calculated based on historical data, reflecting the actual state of power quality of the power grid at that time. By combining these historical data, it is possible to further analyze the impact of power consumption characteristics on power quality, laying the foundation for training the prediction model.

[0068] Next, the ratio of the first historical actual power quality index to the first historical power quality index is calculated to obtain the first historical impact rate. By calculating the ratio of the two, the actual impact of power consumption characteristics on power quality is quantified. If the ratio is close to 1, it means that the predicted power quality is basically consistent with the actual power quality; if the ratio deviates from 1, it means that the power consumption characteristics have a significant impact on the power quality. Therefore, the first historical impact rate reflects the degree of difference between the actual power quality of the power grid and the predicted or simplified model power quality under specific power consumption characteristics, and is an important basic data for constructing a power quality impact rate prediction model.

[0069] Next, the first historical power consumption characteristic parameter set and the first historical impact rate are combined into a first data group, and supervised training is performed on the data group. Supervised training means that the model learns the relationship between these data through given historical inputs and target outputs (in this case, power consumption characteristic parameters and impact rates). By continuously adjusting the model parameters, the model can accurately predict the impact of power consumption characteristics on power quality. Finally, a model that can predict the impact of future power quality is generated, namely, a power quality impact rate prediction model. The model can predict the degree of impact of current and future power consumption characteristic data on power quality by analyzing them.

[0070] Ultimately, the prediction model can be applied to real-time grid operation monitoring as an important tool for adjusting power quality assessment. When the system detects changes in power consumption characteristics, the prediction model can be used to calculate the impact of power consumption characteristics on power quality, thereby more accurately adjusting the target power quality index and providing support for the stability and optimization of grid operation.

[0071] In summary, the embodiments of the present application have at least the following technical effects:

[0072] The present application analyzes historical data, calculates and predicts the power quality index, uses the first-level collector to perform multi-dimensional power collection, generates a first power quality index and determines its deviation from the predicted index. If the deviation exceeds the threshold, the second-level collector is activated for fine collection, and the second power quality index is generated and adjusted for accuracy enhancement to obtain the target power quality index to quantitatively characterize the power quality of the power grid.

[0073] The technical effect of multi-dimensional monitoring of electric energy data through multi-level collectors and precision enhancement processing of the collected data has been achieved, thereby improving the accuracy and real-time performance of power quality monitoring.

[0074] Embodiment 2 is based on the same inventive concept as the method for enhancing the accuracy of power consumption data collection in the above embodiment. Figure 3 As shown, the present application provides a device for enhancing the accuracy of electricity consumption data collection, and the device and method embodiments in the present application are based on the same inventive concept. The device includes:

[0075] The power quality prediction module 11 is used to read the power quality prediction strategy, and analyze the historical power quality records of the power grid according to the power quality prediction strategy to obtain a predicted power characteristic parameter set, and normalize and weight the predicted power characteristic parameter set to obtain a predicted power quality index.

[0076] The first power quality analysis module 12 is used to perform multi-dimensional power collection on the power grid through the first-level collector to obtain a first power characteristic parameter set, and normalize and weight the first power characteristic parameter set to obtain a first power quality index.

[0077] The power quality deviation judging module 13 is used to judge whether a first index deviation between the first power quality index and the predicted power quality index is within a deviation threshold.

[0078] The second power quality analysis module 14 is used for activating the second-level collector to perform multi-dimensional power collection on the power grid to obtain a second power characteristic parameter set when the first index deviation between the first power quality index and the predicted power quality index is not within the deviation threshold, and normalizing and weighting the second power characteristic parameter set to obtain a second power quality index.

[0079] A power quality index adjustment module 15, wherein the power quality index adjustment module 15 is used to perform precision enhancement adjustment on the second power quality index using the second power quality index to obtain a target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid.

[0080] Furthermore, the power quality prediction module 11 is also used to perform the following steps:

[0081] Extract a first historical record at a first historical time in the historical power quality record, wherein the first historical record includes first historical power feature information; read a predetermined power quality factor, and traverse the predetermined power quality factor in the first historical power feature information to obtain a first historical power feature parameter set; analyze the first historical power feature parameter set to obtain a first historical power quality index; generate a historical power quality time series according to a first corresponding relationship between the first historical time and the first historical power quality index; perform predictive analysis on the historical power quality time series according to the power quality prediction strategy to obtain the predicted power quality index.

[0082] Furthermore, the power quality prediction module 11 is also used to perform the following steps:

[0083] The predetermined power quality factors include a first factor set and a second factor set, the first factor set is collected through the first-level collector, and the second factor set is collected through the second-level collector; wherein the first factor set includes voltage, current, frequency, power factor, and three-phase imbalance, and the second factor set includes short-term voltage fluctuations, long-term voltage fluctuations, power device interference, and harmonic content.

[0084] Furthermore, the power quality prediction module 11 is also used to perform the following steps:

[0085] According to the power quality prediction strategy, a historical power quality scatter plot drawn according to the historical power quality time series is sampled and fitted to obtain a first fitting curve corresponding to a first sample point set; the historical power quality scatter plot is compared with the first sample point set to obtain a first non-sample point set, wherein the first non-sample point set includes multiple non-sample points; a first non-sample point among the multiple non-sample points is extracted, and it is determined whether a first distance between the first non-sample point and the first fitting curve meets a distance threshold; if so, the first non-sample point is added to a fitting point list, and if not, the first non-sample point is added to an abnormal point list; when the ratio of the number of sample points in the fitting point list to the number of sample points in the abnormal point list is greater than one-half, the first fitting curve is used as a historical power quality index fitting curve; and the historical power quality index fitting curve is analyzed to obtain the predicted power quality index.

[0086] Furthermore, the second power quality analysis module 14 is further configured to perform the following steps:

[0087] If it is, the predicted power quality index is retrieved to perform precision enhancement adjustment on the first power quality index to obtain the target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid.

[0088] Furthermore, the device also includes:

[0089] A predetermined electricity consumption characteristic factor acquisition module, the predetermined electricity consumption characteristic factor acquisition module is used to obtain predetermined electricity consumption characteristic factors, and the predetermined electricity consumption characteristic factors refer to electricity consumption characteristic factors that affect the power quality; a dynamic monitoring module, the dynamic monitoring module is used to activate the electricity consumption characteristic collector, and the electricity consumption characteristic collector dynamically monitors the predetermined electricity consumption characteristic factors to obtain a set of electricity consumption characteristic parameters; an impact rate prediction module, the impact rate prediction module is used to use the electricity consumption characteristic parameter set as input information of a power quality impact rate prediction model to obtain a predicted impact rate; an index calibration module, the index calibration module is used to calibrate and adjust the target power quality index based on the predicted impact rate.

[0090] Furthermore, the impact rate prediction module is also used to perform the following steps:

[0091] The first historical record also includes a first historical electricity consumption characteristic parameter set and a first historical actual power quality index; the ratio of the first historical actual power quality index to the first historical power quality index is taken as the first historical impact rate; supervised training is performed on a first data group consisting of the first historical electricity consumption characteristic parameter set and the first historical impact rate to obtain the power quality impact rate prediction model.

[0092] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0094] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for enhancing the accuracy of electricity consumption data collection, characterized in that: The method for enhancing the accuracy of electricity consumption data collection is applied to a device for enhancing the accuracy of electricity consumption data collection, the device for enhancing the accuracy of electricity consumption data collection includes a first-level collector and a second-level collector, and the method for enhancing the accuracy of electricity consumption data collection includes: Reading a power quality prediction strategy, and analyzing the historical power quality records of the power grid according to the power quality prediction strategy to obtain a predicted power characteristic parameter set, and normalizing and weighting the predicted power characteristic parameter set to obtain a predicted power quality index; Performing multi-dimensional electric energy collection on the power grid by the first-level collector to obtain a first electric energy characteristic parameter set, and normalizing and weighting the first electric energy characteristic parameter set to obtain a first power quality index; Determining whether a first index deviation between the first power quality index and the predicted power quality index is within a deviation threshold; If not, activating the second-level collector to perform multi-dimensional power collection on the power grid to obtain a second power characteristic parameter set, and normalizing and weighting the second power characteristic parameter set to obtain a second power quality index; Performing precision enhancement adjustment on the second power quality index using the second power quality index to obtain a target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid; Among them, include: Extracting a first historical record at a first historical time from the historical power quality record, wherein the first historical record includes first historical power characteristic information; Reading a predetermined power quality factor, and traversing the predetermined power quality factor in the first historical power feature information to obtain a first historical power feature parameter set; Analyzing the first historical power characteristic parameter set to obtain a first historical power quality index; Generate a historical power quality time series according to a first corresponding relationship between the first historical time and the first historical power quality index; Performing forecast analysis on the historical power quality time series according to the power quality forecast strategy to obtain the forecast power quality index; Wherein, the predetermined power quality factors include a first factor set and a second factor set, the first factor set is collected by the first level collector, and the second factor set is collected by the second level collector; The first factor set includes voltage, current, frequency, power factor, and three-phase imbalance, and the second factor set includes short-term voltage variation, long-term voltage variation, power device interference, and harmonic content; Among them, include: According to the power quality prediction strategy, sampling and fitting are performed on a historical power quality scatter plot drawn according to the historical power quality time series to obtain a first fitting curve corresponding to a first sample point set; Comparing the historical power quality scatter plot with the first sample point set to obtain a first non-sample point set, wherein the first non-sample point set includes a plurality of non-sample points; Extracting a first non-sample point from the plurality of non-sample points, and determining whether a first distance between the first non-sample point and the first fitting curve satisfies a distance threshold; If the condition is satisfied, the first non-sample point is added to the fitting point list; if the condition is not satisfied, the first non-sample point is added to the abnormal point list; When the ratio of the number of sample points in the fitting point list to the number of sample points in the abnormal point list is greater than one half, using the first fitting curve as a historical power quality index fitting curve; The historical power quality index fitting curve is analyzed to obtain the predicted power quality index.

2. According to claim 1, a method for enhancing the accuracy of electricity consumption data collection is characterized in that: Determine whether a first index deviation between the first power quality index and the predicted power quality index is within a deviation threshold; if so, retrieve the predicted power quality index to perform precision enhancement adjustment on the first power quality index to obtain the target power quality index.

3. According to claim 1, a method for enhancing the accuracy of electricity consumption data collection is characterized in that: The device for enhancing the accuracy of power consumption data collection also includes a power consumption feature collector, and further includes: Obtaining a predetermined power consumption characteristic factor, wherein the predetermined power consumption characteristic factor refers to a power consumption characteristic factor that affects power quality; activating a power consumption feature collector, wherein the power consumption feature collector dynamically monitors and obtains a power consumption feature parameter set according to the predetermined power consumption feature factor; Using the power consumption characteristic parameter set as input information of a power quality impact rate prediction model to obtain a predicted impact rate; The target power quality index is calibrated and adjusted based on the predicted impact rate.

4. According to claim 3, a method for enhancing the accuracy of electricity consumption data collection is characterized in that: include: The first historical record also includes a first historical power consumption characteristic parameter set and a first historical actual power quality index; Taking the ratio of the first historical actual power quality index to the first historical power quality index as a first historical impact rate; A supervised training is performed on a first data group consisting of the first historical power consumption characteristic parameter set and the first historical impact rate to obtain the power quality impact rate prediction model.

5. A device for enhancing the accuracy of electricity consumption data collection, characterized in that: The device for enhancing the accuracy of electricity consumption data collection comprises a first-level collector and a second-level collector, and the device is used to perform the steps of the method according to any one of claims 1 to 4, and the device comprises: A power quality prediction module, the power quality prediction module is used to read the power quality prediction strategy, and analyze the historical power quality records of the power grid according to the power quality prediction strategy to obtain a predicted power characteristic parameter set, and normalize and weight the predicted power characteristic parameter set to obtain a predicted power quality index; A first power quality analysis module, the first power quality analysis module is used to obtain a first power characteristic parameter set by performing multi-dimensional power collection on the power grid through the first hierarchical collector, and normalize and weight the first power characteristic parameter set to obtain a first power quality index; A power quality deviation judgment module, the power quality deviation judgment module is used to judge whether the first index deviation between the first power quality index and the predicted power quality index is within a deviation threshold; A second power quality analysis module, wherein the second power quality analysis module is used to activate the second-level collector to perform multi-dimensional power collection on the power grid to obtain a second power characteristic parameter set when the first power quality index and the first index deviation of the predicted power quality index are not within the deviation threshold, and normalize and weight the second power characteristic parameter set to obtain a second power quality index; A power quality index adjustment module, wherein the power quality index adjustment module is used to perform precision enhancement adjustment on the second power quality index using the second power quality index to obtain a target power quality index, wherein the target power quality index is used to quantitatively characterize the power quality of the power grid.

Images