Multi-source heterogeneous data fusion-based power utilization data processing method for power transfer and supply main body

Abstract

The invention discloses a multi-source heterogeneous data fusion-based power utilization data processing method for a transfer power supply main body, relates to the technical field of power utilization data processing, and solves the technical problem that missing power utilization data cannot be accurately completed through a flow of data acquisition-dynamic weighted interpolation-result verification in the prior art. The method specifically comprises the steps of ammeter data missing compensation: performing missing compensation on ammeter data of a rotary power supply main body; electricity utilization data correction: after it is determined that the data of the electricity meter is not missing or completely missing data compensation is carried out, electricity utilization data correction is carried out on the user; and emergency scene data stability analysis: after the power utilization data correction is completed, performing stability analysis on the current power utilization data in the emergency scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric data processing, in particular to a power transfer subject electric data processing method based on multi-source heterogeneous data fusion. BACKGROUND

[0002] The power transfer subject electric data processing method mainly includes data acquisition, data calculation and allocation, data storage and management, and data publicity, etc. In the digital era, data sources are increasingly diverse (such as sensors, databases, texts, images, user behavior logs, etc.), and the data format, structure, and semantic differences are significant - this "multi-source" and "heterogeneous" characteristic results in data often being in an "island" state and unable to directly generate value. The core goal of multi-source heterogeneous data fusion is to break down data barriers through technical means and integrate different sources and types of data into unified and valuable information to support subsequent analysis (such as prediction, decision-making, intelligent scheduling).

[0003] Patent No. CN116680753A discloses a power transfer user electric data processing method and system based on a consortium chain, a data acquisition module acquires the power consumption data of terminal users; in the data encryption transmission layer, the data is stored in a distributed database through a distributed consensus algorithm; in the smart contract layer, the user public power consumption and power transfer subject information stored in the database are read, and the public cost is calculated based on the cost allocation algorithm of cooperative game theory; in the user interaction layer, the power consumption details and public allocation of the user under a certain power transfer subject are displayed.

[0004] However, in the prior art, the traditional "deletion of missing data" processing method will destroy the continuity of electric data, cause period power consumption statistical deviation, and thus affect the fairness of public allocation of electricity charges and sub-metering power consumption allocation, leading to user disputes. The missing electric data cannot be accurately completed through the "data acquisition-dynamic weighted interpolation-result verification" process, and in addition, after determining that the electric meter data has no missing data or complete missing data compensation, the user cannot be corrected for electric data, and in the use scenarios of areas where the power grid has not been transformed and temporary power consumption areas, the difference between the actual operating voltage and the rated voltage of the equipment leads to deviation in the power and electric quantity measured by the electric meter according to the standard voltage.

[0005] In view of the above technical defects, a solution is proposed. SUMMARY

[0006] The purpose of the present application is to solve the above-mentioned problems and to propose a power transfer subject electric data processing method based on multi-source heterogeneous data fusion.

[0007] The purpose of the present application can be achieved by the following technical solutions: A data processing method for electricity consumption of power transfer entities based on multi-source heterogeneous data fusion is as follows: Compensation for missing meter data: Compensation is provided for missing meter data from the main power supplier. Electricity consumption data correction: After confirming that there is no missing or completely missing data in the electricity meter, the user's electricity consumption data is corrected. Stability analysis of emergency scenario data: After correcting the electricity consumption data, a stability analysis of the current electricity consumption data is performed under emergency scenarios.

[0008] As a preferred embodiment of the present invention, the process for compensating for missing electricity meter data is as follows: Voltage, current, and power factor of normally functioning electricity meters under the same power supply entity are collected as interpolation references; historical electricity consumption data for the same time period over the past 30 days are extracted to construct a baseline of electricity consumption behavior, covering different seasons, weekdays, and rest days; users are marked as commercial users or residential users; data statistics are performed on commercial users and residential users, and data missing is marked according to the fluctuation of data at each time point, and the corresponding users are set as users with missing data.

[0009] As a preferred embodiment of the present invention, in the case of data missing, the time proximity of users with missing data is collected, wherein the time proximity is used to measure the time distance between the missing time period and the reference time period. The similarity of electricity consumption patterns, Wm, is obtained by calculating the Pearson correlation coefficient between the historical electricity consumption curves of the reference user and the missing user during the same period; a comprehensive weighting is performed based on the temporal proximity, Wt, and the similarity of electricity consumption patterns, Wm. W = αWt + (1-α)Wm, where α is the adjustment coefficient.

[0010] In a preferred embodiment of the present invention, for the missing time period, normal user data of the same type and adjacent time are selected, and the average value is calculated by weighting. The obtained data missing compensation value is stored and timestamped, and then sent to the corresponding user terminal. At the same time, data missing analysis is performed on the user terminal. If the frequency of consecutive data loss for a user with missing data increases, and if the frequency increase span shows an upward trend, or if the rate of increase of the number of times exceeding the set span threshold during the frequency increase span phase exceeds the rate threshold, then it is inferred that the current user with missing data needs to have their meter type adjusted and the electricity monitoring scheme modified, i.e., shorten the power supply meter reading cycle or perform data verification during the meter reading process. If the frequency increase span does not show an upward trend, and the rate of increase of the number of times exceeding the set span threshold during the frequency increase span increase phase does not exceed the rate threshold, it is inferred that the user with missing data does not need to adjust the meter type, and electricity data monitoring will continue.

[0011] In a preferred embodiment of the present invention, the electricity data correction process is as follows: Actual voltage monitoring for users involves deploying smart voltage sensors at the user's side to collect the real-time supply voltage Uactual; simultaneously, the rated voltage Urated and rated power Prated are collected; a correction logic is constructed, where power and voltage satisfy a square relationship, i.e., the correction formula is: , where P 修 U is represented as the corrected actual power. 标 Indicates the set rated voltage, U 实 P represents the voltage being monitored in real time. 表 This represents the power displayed on the electricity meter.

[0012] As a preferred embodiment of the present invention, the status matching verification of electrical equipment is performed. For motor-type equipment, the actual speed n is collected by a speed sensor and combined with the rated speed n of the motor to verify the rationality of the power correction. The specific formula is as follows: Where PC is the deviation rate, n 修 This represents the corrected rotational speed. ; Based on the deviation analysis of the user's electrical equipment, if the deviation rate exceeds the set deviation rate threshold, the time when the power is applied will be marked as a risk deviation time; otherwise, if the deviation rate does not exceed the set deviation rate threshold, the time when the power is applied will be marked as a stable deviation time.

[0013] In a preferred embodiment of the present invention, the total number of statistical moments before the identification of the user's electrical equipment risk deviation moment is obtained, and the interval between the user's stable deviation moment and the historical adjacent risk deviation moment is obtained and compared: If the total number of statistical moments for which data collection was completed before the identification of risk deviation moments of a user's electrical equipment exceeds the threshold for the total number of statistical moments, or if the interval between the stable deviation moment of a user's electrical equipment and the historical adjacent risk deviation moment does not exceed the interval threshold, then an electricity data tracing signal will be generated and the user's electricity data tracing detection will be performed to infer the source of the data anomaly and rectify it. After completion, electricity data statistics will be performed. If the total number of statistical moments for which data collection was completed before the identification of the user's electrical equipment risk deviation moment does not exceed the total number of statistical moments threshold, and the interval between the user's stable deviation moment and the historical adjacent risk deviation moment exceeds the interval duration threshold, then an electricity consumption data statistical signal will be generated and the user's electricity consumption data will be corrected before real-time statistics are performed.

[0014] As a preferred embodiment of the present invention, the emergency scenario data stability analysis process is as follows: The system obtains the rising rate of the correction frequency of electricity consumption data in emergency scenarios and the increasing rate of the time when electricity consumption data needs to be corrected. The values ​​are summed to obtain the sum of the rates, which reflects the need for data correction in the current emergency scenario, thereby inferring the stability of the electricity consumption data. After the electricity consumption data is corrected in the emergency scenario, the system obtains the deviation between the preset electricity consumption and the actual electricity consumption of the user terminal in the application of the electricity data, and marks it as the correction deviation value.

[0015] In a preferred embodiment of the present invention, the speed sum and the correction deviation value are compared with the speed sum threshold and the deviation correction threshold, respectively: If the sum of speeds exceeds the speed and threshold, or the correction deviation exceeds the deviation correction threshold, it is inferred that the power consumption data stability analysis of the power supply entity in the emergency scenario is abnormal. A correction and control signal is generated, and the power consumption data of the users currently covered by the power grid is diverted and corrected. The power supply required for the emergency scenario is divided into lines. If the sum of speeds does not exceed the speed and threshold, and the correction deviation does not exceed the deviation correction threshold, it is inferred that the power consumption data stability analysis of the power supply entity in the emergency scenario is normal. A correction and stabilization signal is generated, and the power consumption data is continuously corrected and statistically analyzed.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. In this invention, missing meter data of the main power supply entity is compensated, overcoming the problem that the traditional "deleting missing data" processing method will destroy the continuity of electricity data, cause deviation in electricity consumption statistics during a period, and thus affect the fairness of the shared electricity cost and the allocation of electricity consumption by individual meters, leading to user disputes. For the problem of missing meter data for shops / residential users, the missing electricity data is accurately supplemented through the process of "data collection - dynamic weighted interpolation - result verification", ensuring the fairness of electricity allocation and adapting to complex working conditions such as meter failure and lack of coverage in old communities.

[0017] 2. In this invention, after determining that the electricity meter data is complete or has no missing data, the electricity consumption data of the user is corrected. In the usage scenarios of areas where the power grid transformation is not yet in place or temporary power distribution areas, the actual operating voltage of the equipment differs from the rated voltage, which causes the power and electricity consumption measured by the electricity meter according to the standard voltage to deviate, affecting the fairness of electricity bill settlement. By correcting the electricity consumption data, the accuracy of electricity data transmission is improved and the data processing efficiency is improved.

[0018] 3. In this invention, after the electricity consumption data is corrected, a stability analysis is performed on the current electricity consumption data in an emergency scenario. The stability analysis is used to infer the impact of data correction on sudden increases in electricity consumption data, so as to avoid the mismatch between user data correction and real-time data in emergency scenarios, which would cause electricity consumption data chaos and reduce the efficiency of electricity consumption data correction for the power supply entity, making it impossible to effectively process data. Attached Figure Description

[0019] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0020] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a detailed process diagram of the method of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] Please see Figure 1 - Figure 2 As shown, the power consumption data processing method for power transfer entities based on multi-source heterogeneous data fusion is as follows: Compensation for missing meter data: Compensating for missing meter data in the electricity reseller system is crucial. The traditional method of "deleting missing data" disrupts the continuity of electricity consumption data, causing statistical deviations in electricity consumption over different time periods. This, in turn, affects the fairness of shared electricity costs and the allocation of electricity consumption by individual meters, leading to disputes among users. In the electricity reseller system, aging and incomplete meter coverage can result in missing real-time electricity consumption data for shops and residents, such as meter malfunctions or the absence of smart meters in un-upgraded areas, leading to incomplete electricity consumption statistics. To address the issue of missing electricity meter data for shops and residential users, a process of "data collection - dynamic weighted interpolation - result verification" is used to accurately complete the missing electricity data, ensuring the fairness of electricity allocation and adapting to complex working conditions such as meter malfunctions and lack of coverage in older residential areas. Electricity consumption data correction: After confirming that there is no missing or completely missing data in the electricity meter, the electricity consumption data of users is corrected. In the usage scenarios of areas where the power grid transformation is not yet in place or temporary power distribution areas, the actual operating voltage of the equipment differs from the rated voltage, which causes the power and electricity consumption measured by the electricity meter according to the standard voltage to deviate, affecting the fairness of electricity billing. By correcting the electricity consumption data, the accuracy of electricity data transmission is improved and the data processing efficiency is increased. Stability analysis of emergency scenario data: After completing the power consumption data correction, a stability analysis is performed on the current power consumption data in emergency scenarios. For example, temporary events (such as exhibitions and performances) may briefly connect high-power equipment (lighting, sound, etc., lasting 2-3 hours), causing a sudden increase in total power consumption. By analyzing the stability, the impact of the data correction on the sudden increase in power consumption data can be inferred, avoiding the mismatch between user data correction and real-time data in emergency scenarios, which would cause power consumption data chaos and reduce the efficiency of power consumption data correction for the power supply entity, making it impossible to effectively process the data. The process for compensating for missing electricity meter data is as follows: Real-time electrical parameters such as voltage, current, and power factor of normally functioning electricity meters are collected from users under the same power supply entity, covering both commercial and residential user groups, providing "same-same-period references" for interpolation; historical electricity consumption data for the same time period (e.g., 8-10 am and 18-22 pm daily) is extracted over the past 30 days to construct a baseline for electricity consumption behavior, covering different seasons, weekdays / rest days, and other scenarios; users are labeled as commercial or residential users to distinguish the differences in electricity consumption patterns between the two groups (e.g., high daytime load for commercial users and high evening load for residential users). Relying on the communication modules of smart meters (such as RS485, LoRa, NB-IoT), data is periodically retrieved through power acquisition terminals; for users without smart meters, portable power acquisition devices can be temporarily deployed to supplement the data source; the collected data is stored in databases (such as MySQL, InfluxDB time-series databases), and an index is created by "user ID + timestamp" for convenient and quick retrieval; Data statistics are collected on shop users and residential users, and data missing is marked based on the fluctuation of data at each time point, and the corresponding users are set as users with missing data. In scenarios with missing data, time proximity is collected for users with missing data, where time proximity is used to measure the time distance between the missing period and the reference period; The specific calculation formula is as follows: ,in, For the time difference, The maximum time difference on a single day is represented by Wt. The closer the times are, the closer Wt is to 1, and the higher its weight. The electricity consumption pattern similarity Wm was obtained, and the Pearson correlation coefficient was calculated between the historical electricity consumption curves of the reference user and the missing user for the same period. xi and yi represent the electricity consumption sequences for two types of users. , The value of r is the mean; the closer r is to 1, the more similar the patterns. Wm = r; i represents the corresponding user. A comprehensive weighting calculation is performed based on time proximity Wt and electricity consumption pattern similarity Wm; W = αWt + (1-α)Wm, where α is the adjustment coefficient (0.6 is recommended, prioritizing time proximity), which is used to weight and harmonize the reference value of different dimensions. For missing time periods, select normal user data of the same type and close in time, calculate the mean by weighting, and the formula for the data missing compensation value is: Ei represents the reference user's battery level, and Wi represents the corresponding weight; The obtained data loss compensation values ​​are stored and timestamped, and then sent to the corresponding user terminals; simultaneously, data loss analysis is performed on the user terminals. If the frequency of consecutive data loss for a user with missing data increases, and if the frequency increase span shows an upward trend, or if the rate of increase of the number of times exceeding the set span threshold during the frequency increase span phase exceeds the rate threshold, then it is inferred that the current user with missing data needs to have their meter type adjusted and the electricity monitoring scheme modified, i.e., shorten the power supply meter reading cycle or perform data verification during the meter reading process. If the frequency increase span does not show an upward trend, and the increase rate of the number of times exceeding the set span threshold during the frequency increase span increase phase does not exceed the speed threshold, it is inferred that the user with missing data does not need to adjust the meter type, and electricity data monitoring will continue. The process for correcting electricity consumption data is as follows: Actual voltage monitoring for users involves deploying smart voltage sensors (such as LoRa wireless voltage modules, with a sampling frequency of 1 time / minute) on the user's side to collect the supply voltage (Uactual, unit V) in real time, covering three-phase line voltage and phase voltage; at the same time, the rated voltage (Urated) and rated power (Prated) are also collected. Noise removal and cleaning of voltage and meter data: Remove abnormal values ​​caused by sudden voltage rises and falls (such as lightning interference) and meter communication errors, and fill in missing data using the "sliding window mean method"; The correction logic is constructed such that power and voltage satisfy a square relationship, i.e., the correction formula is: , where P 修U is represented as the corrected actual power. 标 Indicates the set rated voltage, U 实 P represents the voltage being monitored in real time. 表 This is represented by the power displayed on the meter; Perform status matching verification of electrical equipment. For example, for motor-type equipment, collect the actual speed n through speed sensors (such as Hall speed modules, or read from the frequency converter), and verify the rationality of power correction by combining it with the rated speed n of the motor. The specific formula is as follows: Where PC is the deviation rate, n 修 This represents the corrected rotational speed. ; Based on the deviation analysis of the user's electrical equipment, if the deviation rate exceeds the set deviation rate threshold, the time when the power is applied will be marked as a risk deviation time; otherwise, if the deviation rate does not exceed the set deviation rate threshold, the time when the power is applied will be marked as a stable deviation time. The system obtains the total number of statistical moments before data collection was completed before the identification of risk deviation moments for the user's electrical equipment. It also obtains the interval between the user's stable deviation moments and historical adjacent risk deviation moments. The system then compares the total number of statistical moments before data collection was completed before the identification of risk deviation moments for the user's electrical equipment, and the interval between the user's stable deviation moments and historical adjacent risk deviation moments, with the total statistical moment threshold and the interval threshold, respectively. If the total number of statistical moments for which data collection was completed before the identification of the user's electrical equipment risk deviation moment exceeds the threshold of the total number of statistical moments, or if the interval between the user's stable deviation moment and the historical adjacent risk deviation moment does not exceed the interval threshold, it is inferred that there is a risk in the correction of the current user's electricity data. An electricity data tracing signal is generated and the user's electricity data tracing is detected to infer the source of the data anomaly and rectify it. After completion, electricity data statistics are performed. If the total number of statistical moments for which data collection was completed before the identification of the user's power equipment risk deviation moment does not exceed the threshold of the total number of statistical moments, and the interval between the user's stable deviation moment and the historical adjacent risk deviation moment exceeds the interval threshold, then it is inferred that the current user's power consumption data correction is stable, power consumption data statistical signal is generated, and real-time statistics are performed after the user's power consumption data is corrected. The process of stabilizing emergency scenario data is as follows: The rising rate of the correction frequency of electricity consumption data in emergency scenarios and the increasing rate of the electricity consumption time that needs to be corrected for application electricity data are obtained. The sum of the values ​​is obtained, and the sum of the rates reflects the need for data correction in the current emergency scenario, thereby inferring the stability of electricity consumption data. After the electricity consumption data is corrected in an emergency scenario, the deviation between the preset electricity consumption and the actual electricity consumption of the user terminal that applied the electricity data is obtained and marked as the correction deviation value. Compare the sum of speed and the corrected deviation value with the sum of speed threshold and the deviation correction threshold, respectively: If the speed and value exceed the speed and threshold, or the correction deviation value exceeds the deviation correction threshold, it is inferred that the power consumption data stability analysis of the main power supply entity in the emergency scenario is abnormal, a correction control signal is generated, and the power consumption data of the current grid-covered users is diverted and corrected. If necessary, the power supply required for the emergency scenario is divided into lines. If the speed and value do not exceed the speed and threshold, and the correction deviation value does not exceed the deviation correction threshold, it is inferred that the power consumption data of the main power supply entity in the emergency scenario is stable and normal, and a correction stability signal is generated to continuously correct and statistically analyze the power consumption data.

[0024] When in use, this invention includes: electricity meter data missing compensation: compensation for missing electricity meter data of the main power supplier; electricity consumption data correction: after determining that there is no missing or completely missing electricity meter data, electricity consumption data is corrected for the user; emergency scenario data stability analysis: after completing the electricity consumption data correction, stability analysis of the current electricity consumption data is performed in emergency scenarios.

[0025] Thresholds, preset values, preset ranges, etc. are set for result comparison and analysis to determine whether they are good or bad. The value of these thresholds is determined by a combination of large-scale model analysis of sample data and human experience. They can also be adjusted appropriately based on seasonal or common-sense influences. Furthermore, the settings for weighting ratios, influence factors, etc., are based on the magnitude of each parameter's influence on the results. The specific values ​​are allocated to ultimately reflect the impact on the results. The settings for input and storage are also determined by a combination of large-scale model analysis of sample data and human experience. Appropriate adjustments can also be made based on seasonal or rational influence conditions.

[0026] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion, characterized in that, The data processing method is as follows: Compensation for missing electricity meter data: Compensation is provided for missing meter data from the main power supplier. Electricity consumption data correction: After confirming that there is no missing or completely missing data in the electricity meter, the user's electricity consumption data is corrected. Stability analysis of emergency scenario data: After correcting the electricity consumption data, a stability analysis of the current electricity consumption data is performed under emergency scenarios.

2. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The process for compensating for missing electricity meter data is as follows: Voltage, current, and power factor of normally functioning electricity meters under the same power supply entity are collected as interpolation references; historical electricity consumption data for the same time period over the past 30 days are extracted to construct a baseline of electricity consumption behavior, covering different seasons, weekdays, and rest days; users are marked as commercial users or residential users; data statistics are performed on commercial users and residential users, and data missing is marked according to the fluctuation of data at each time point, and the corresponding users are set as users with missing data.

3. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 2, characterized in that, In scenarios with missing data, time proximity is collected for users with missing data, where time proximity is used to measure the time distance between the missing period and the reference period; Obtain the electricity consumption pattern similarity Wm by calculating the Pearson correlation coefficient between the historical electricity consumption curves of the reference user and the missing user during the same period; The combined weights are calculated based on the temporal proximity Wt and the electricity consumption pattern similarity Wm.

4. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 3, characterized in that, For the missing time period, select normal user data of the same type and close in time, calculate the mean by weighting, store the obtained data missing compensation value with a timestamp, and send it to the corresponding user terminal; at the same time, perform data missing analysis on the user terminal: If the frequency of consecutive data loss for a user with missing data increases, and if the frequency increase span shows an upward trend, or if the rate of increase of the number of times exceeding the set span threshold during the frequency increase span phase exceeds the rate threshold, then it is inferred that the current user with missing data needs to have their meter type adjusted and the electricity monitoring scheme modified, i.e., shorten the power supply meter reading cycle or perform data verification during the meter reading process. If the frequency increase span does not show an upward trend, and the rate of increase of the number of times exceeding the set span threshold during the frequency increase span increase phase does not exceed the rate threshold, it is inferred that the user with missing data does not need to adjust the meter type, and electricity data monitoring will continue.

5. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The process for correcting electricity consumption data is as follows: Actual voltage monitoring for users involves deploying smart voltage sensors at the user's side to collect the real-time supply voltage Uactual; simultaneously, the rated voltage Urated and rated power Prated are collected; a correction logic is constructed, where power and voltage satisfy a square relationship, i.e., the correction formula is: , where P 修 U is represented as the corrected actual power. 标 Indicates the set rated voltage, U 实 P represents the voltage being monitored in real time. 表 This represents the power displayed on the meter.

6. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 5, characterized in that, Perform status matching verification of electrical equipment. For motor-type equipment, collect the actual speed n through the speed sensor and combine it with the rated speed n of the motor to verify the rationality of the power correction. The specific formula is as follows: Where PC is the deviation rate, n 修 This represents the corrected rotational speed. ; Based on the deviation analysis of the user's electrical equipment, if the deviation rate exceeds the set deviation rate threshold, the time when the power is applied will be marked as a risk deviation time; otherwise, if the deviation rate does not exceed the set deviation rate threshold, the time when the power is applied will be marked as a stable deviation time.

7. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 6, characterized in that, The system obtains the total number of statistical moments before data collection was completed before the identification of risk deviation moments for the user's electrical equipment. It also obtains and compares the interval between the user's stable deviation moments and historical adjacent risk deviation moments. If the total number of statistical moments for which data collection was completed before the identification of risk deviation moments of a user's electrical equipment exceeds the threshold for the total number of statistical moments, or if the interval between the stable deviation moment of a user's electrical equipment and the historical adjacent risk deviation moment does not exceed the interval threshold, then an electricity data tracing signal will be generated and the user's electricity data tracing detection will be performed to infer the source of the data anomaly and rectify it. After completion, electricity data statistics will be performed. If the total number of statistical moments for which data collection was completed before the identification of the user's electrical equipment risk deviation moment does not exceed the total number of statistical moments threshold, and the interval between the user's stable deviation moment and the historical adjacent risk deviation moment exceeds the interval duration threshold, then an electricity consumption data statistical signal will be generated and the user's electricity consumption data will be corrected before real-time statistics are performed.

8. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The process of stabilizing emergency scenario data is as follows: The rising rate of the correction frequency of electricity consumption data in emergency scenarios and the increasing rate of the electricity consumption time that needs to be corrected for application electricity data are obtained. The sum of the values ​​is then obtained, and the sum of the rates reflects the need for data correction in the current emergency scenario, thereby inferring the stability of the electricity consumption data. After the electricity consumption data is corrected in an emergency scenario, the deviation between the preset electricity consumption and the actual electricity consumption of the user terminal that applied the electricity data is obtained and marked as the correction deviation value.

9. The method for processing electricity consumption data of a power transfer entity based on multi-source heterogeneous data fusion according to claim 8, characterized in that, Compare the sum of speed and the corrected deviation value with the sum of speed threshold and the deviation correction threshold, respectively: If the speed and value exceed the speed and threshold, or the correction deviation value exceeds the deviation correction threshold, it is inferred that the power consumption data stability analysis of the main power supply entity in the emergency scenario is abnormal, a correction control signal is generated, and the power consumption data of the current grid-covered users is diverted and corrected, and the power supply required in the emergency scenario is divided into lines. If the speed and value do not exceed the speed and threshold, and the correction deviation value does not exceed the deviation correction threshold, it is inferred that the power consumption data of the main power supply entity in the emergency scenario is stable and normal, and a correction stability signal is generated to continuously correct and statistically analyze the power consumption data.

Images