Data cleaning and alarm analysis method and system of digital energy platform

Abstract

The application discloses a data cleaning and alarm analysis method and system of a digital energy platform, belongs to the technical field of data processing of digital energy, and aims to solve the technical problem of how to reduce the error rate of a data collector, improve resource utilization, and then more normatively and accurately count digital energy data.The technical scheme is as follows:the method specifically includes the following steps: cleaning and deleting analog values, digital values and energy consumption value data that exceed a time limit value; marking data that exceeds a data point limit value, conforms to a convex model and conforms to a concave model; performing alarm analysis on the analog values, digital values and energy consumption value data; and if data that exceeds a data point high limit value or a data point low limit value, conforms to the convex model or conforms to the concave model appears, alarm information is generated.

Description

Technical Field

[0001] This invention relates to the field of data processing technology in digital energy, specifically a data cleaning and alarm analysis method and system for a digital energy platform. Background Technology

[0002] Digital technology: With the deep integration and innovative applications of digital technology in the fields of resources, energy, and environment, its role is receiving increasing attention. Digital technology is a science and technology that has developed alongside computers. It transforms various types of information into binary numbers that computers can recognize, and then performs calculations, processing, storage, transmission, dissemination, and reconstruction. Its essence lies in improving the information efficiency of society as a whole.

[0003] AI technology is an effective measure to solve control and decision-making problems in complex systems. Its in-depth application in the energy industry helps promote clean energy production and reduce carbon emissions, thus achieving a shift from high-carbon to low-carbon, and then from low-carbon to even lower carbon emissions. In the energy sector, reducing energy costs and reducing pollutant emissions are equally important. Therefore, while ensuring the reliability and quality of energy supply, applying AI technology to achieve efficient energy dispatch and utilization has become an important practical measure for carbon reduction in countries around the world.

[0004] Blockchain technology: The future energy trading market is characterized by multiple participants, multiple models, and multiple rules, which presents both demands and challenges for transparency, real-time performance, and data security in energy market transactions. Addressing the service requirements of an "open at both ends" energy trading market—namely, "equal participants, intelligent mutual trust, transparent transactions, and information sharing"—and combining this with the four key technical characteristics of blockchain technology—"decentralization, transparency and security, immutability, and information traceability"—can create a new type of distributed energy trading market, providing a concrete means to achieve my country's goals.

[0005] Digital twin technology: Digital twins are a key technology for mapping real physical environments to digital models in information space. They create virtual entities of physical entities digitally to simulate, verify, predict, and control the entire lifecycle of these physical entities. By fully utilizing sensors deployed throughout the physical system, data analysis and modeling are performed to reflect the entire lifecycle of the physical entity in different real-world scenarios. Based on digital twin technology, two-dimensional or three-dimensional visualized carbon map models can be established, enabling capabilities such as tracking emission drivers, dynamic simulation and extrapolation of emission reduction, and energy consumption alarm detection and analysis. This establishes a clear path for carbon emission monitoring, control, planning, and strategy implementation.

[0006] SCADA (Supervisory Control and Data Acquisition) system is a computer-based DCS and power automation monitoring system. It has a wide range of applications, including data acquisition and monitoring control, and process control in industries such as power, metallurgy, petroleum, chemical, gas, and railway.

[0007] A microgrid is a system composed of loads and distributed power sources. Compared to the external power grid, it appears as a single controlled unit and can simultaneously meet users' requirements for power quality and power supply security.

[0008] The data acquisition process of existing energy-consuming equipment such as wind power, electricity, and coal is complex, and the collected data is diverse and complex. Therefore, how to reduce the error rate of data acquisition equipment, improve resource utilization, and thus achieve more standardized and accurate statistics on digital energy data is a technical problem that urgently needs to be solved. Summary of the Invention

[0009] The technical objective of this invention is to provide a data cleaning and alarm analysis method and system for a digital energy platform to address the issues of how to reduce the error rate of data collectors, improve resource utilization, and thus achieve more standardized and accurate statistics on digital energy data.

[0010] The technical objective of this invention is achieved as follows: a data cleaning and alarm analysis method for a digital energy platform, the specific method of which is as follows:

[0011] Clean and delete analog, digital, and energy consumption data that exceed the time limit;

[0012] Data that exceeds the data point limit, conforms to the convex model (individual values ​​are abnormally higher than surrounding values), or conforms to the concave model (individual values ​​are abnormally lower than surrounding values) is marked.

[0013] Alarm analysis is performed on analog, digital, and energy consumption data:

[0014] An alarm message will be generated if data exceeds the upper or lower limits of the data point, or if the data conforms to the convex model or the concave model.

[0015] As a preferred method, the cleaning and deletion of analog and digital value data are as follows:

[0016] The task of cleaning analog and digital data is defined as a scheduled task, which is implemented through annotations and the cron expression @Scheduled(cron = "0 0* / 8**?").

[0017] Set the execution time limit for the cleaning task, such as executing it once every 8 hours;

[0018] Data exceeding a set time limit will be deleted on a scheduled basis. For example, data older than 365 days needs to be deleted on a scheduled basis. The time limit is configurable.

[0019] The analog and numeric values ​​in the table can be deleted using DateUtil.getExpiredDate(liveInDays) and new LambdaQueryWrapper<>().

[0020] As a preferred method, energy consumption data cleaning involves marking energy consumption data exceeding the highest and lowest limits as bad data based on the highest and lowest values ​​of the data point. When analyzing energy consumption data for the same data point, the trend of energy consumption values ​​is normally flat or cumulative. If a data point shows a value lower than the previous energy consumption value, it will be marked as bad data. If an individual energy consumption value of the same data point is higher than the surrounding energy consumption values, the abnormal data will be marked as bad data.

[0021] More specifically, the energy consumption data cleaning process is as follows:

[0022] Threaded approach: After the service starts, the thread executes once every 180 seconds;

[0023] Find the time range for uncleaned data in the query table;

[0024] The minimum time retrieved is pushed back one hour to determine the start time of this cleaning process.

[0025] Obtain data points related to energy consumption values ​​(OBJECT_TYPE = ENERGY_VALUE);

[0026] Query all energy consumption data within the time range of this cleaning process;

[0027] Determine if the data point exists in the energy consumption data for this cleaning:

[0028] If the data point does not exist, update the value of the is_bad field of the data to true;

[0029] Query the energy consumption table again for the uncleaned data, sorting it by data point ID and data time;

[0030] The uncleaned data is placed into a map according to the data points, in the form of (key, value); where key is the data point ID and value is the set of energy consumption data corresponding to that data point;

[0031] Iterate through the energy consumption values ​​of all data points, and determine whether they exceed the maximum or minimum limits of the data points, as well as whether it is a concave or convex model, as follows:

[0032] Data point maximum and minimum limit determination: Determine whether the actual_value is between the high_limit and low_limit in the tbl_point table;

[0033] Concave model judgment: Based on the previous value, if the subsequent value is less than the previous value, the energy consumption value data corresponding to the subsequent value is_bad needs to be marked as true;

[0034] Convex model judgment: If the previous value is labeled, and the growth of the next value exceeds the specified rate, then the energy consumption value data corresponding to the next value, i_bad, needs to be marked as true.

[0035] Mark the is_bad field as false for all unmarked energy consumption data within this cleaning period.

[0036] As a preferred method, simulated value data alarm analysis generates alarm information based on the highest and lowest values ​​of the data points, as well as data exceeding the high and low limits, and notifies the user, as follows:

[0037] The time range for alarm analysis is queried from the table;

[0038] The minimum time retrieved is pushed back one hour to determine the start time of this cleaning process.

[0039] Obtain the relevant data points (OBJECT_TYPE = ANALOG_VALUE);

[0040] Query all simulated value data within the time range of this alarm analysis;

[0041] Determine if the data point exists in the simulated data for this alarm analysis:

[0042] If no data point has an actual_value exceeding the maximum or minimum limit, then update the is_bad field of the simulated value data to true, obtain the corresponding device information based on the data point, insert the alarm information into the alarm table, and then call the alarm notification interface of the demp-service service to notify the alarm.

[0043] Update the time range of this alarm analysis to false for data that is not marked, i_bad.

[0044] Preferably, the numeric value data alarm analysis generates alarm information and notifies the user based on the highest, lowest, and values ​​exceeding the high and low limits of the data point containing the numeric value; specifically as follows:

[0045] Using the previous numeric value as a standard, if the value of the next numeric value is not equal to the value of the previous numeric value, it is considered a shift. The value of the is_bad field of the numeric value is updated to true, the alarm information is inserted into the alarm table, and the alarm notification interface of the demp-service service is called to notify the alarm.

[0046] As a preferred option, energy consumption data alarm analysis generates alarm information and notifies the user based on the highest, lowest, and energy consumption values ​​exceeding the high and low limits of the data points containing the energy consumption data; specifically as follows:

[0047] When analyzing energy consumption data for the same data point, the trend of energy consumption values ​​is normally flat or cumulative. If data shows a value lower than the previous energy consumption value, an alarm message should be generated and the user should be notified.

[0048] If the energy consumption value of an individual data point is higher than the energy consumption value of the surrounding data points, an alarm message should be generated and the user should be notified.

[0049] A data cleaning and alarm analysis system for a digital energy platform, the system comprising:

[0050] The cleaning module is used to clean and delete analog, digital, and energy consumption data that have exceeded the time limit.

[0051] The marking module is used to mark data that exceeds the data point limit, conforms to the convex model (individual values ​​are abnormally higher than surrounding values), and conforms to the concave model (individual values ​​are abnormally lower than surrounding values).

[0052] The alarm analysis module is used to perform alarm analysis on analog, digital and energy consumption data. If data exceeds the upper or lower limits of the data point, or conforms to the convex model or the concave model, an alarm message will be generated.

[0053] An electronic device includes: a memory and at least one processor;

[0054] The memory contains computer programs;

[0055] The at least one processor executes the computer program stored in the memory, causing the at least one processor to perform the data cleaning and alarm analysis method of the digital energy platform as described above.

[0056] A computer-readable storage medium storing a computer program that can be executed by a processor to implement the data cleaning and alarm analysis method for a digital energy platform as described above.

[0057] The data cleaning and alarm analysis method and system for the digital energy platform of the present invention have the following advantages:

[0058] (i) This invention can identify and clean abnormal data in a large amount of energy data by analyzing and summarizing the data. This is beneficial for managers to analyze the energy data of each data point, thereby grasping the equipment status of the data point, predicting the energy consumption and output in the future, and making corresponding work arrangements. This improves the accuracy of data analysis and thus improves efficiency.

[0059] (II) This invention solves the complex problems in the data collection process of existing energy-consuming equipment such as wind power, electricity, and coal. The collected data is complex and diverse, which enables this invention to identify errors and abnormal data, providing accurate basis for energy consumption analysis and resource control, improving resource utilization, and providing a solid data foundation for the energy industry through standardized data management.

[0060] (III) This invention reduces the error rate of data collectors, improves resource utilization, and thus provides more standardized and accurate statistics on digital energy data.

[0061] (iv) This invention addresses abnormal data by removing erroneous or abnormal data and reducing the impact of erroneous data on data analysis.

[0062] (v) This invention designs an alarm analysis function for abnormal data collected by the data collector, which can be immediately reflected to the user end, so as to carry out reasonable energy consumption control and improve resource utilization.

[0063] (vi) This invention is easy to understand and applicable to most energy consumption scenarios, such as energy companies, power plants, water stations and other scenarios;

[0064] (vii) This invention is implemented using a common programming language. It performs a unified and standardized analysis on the data collected by the data acquisition device and the energy router from the system platform. The analysis is performed from three perspectives: analog value, digital value, and energy value. Data that does not conform to the system specifications is cleaned and marked, and abnormal data is given an early warning. Attached Figure Description

[0065] The invention will be further described below with reference to the accompanying drawings.

[0066] Appendix Figure 1 A flowchart illustrating the data cleaning and alarm analysis methods for digital energy platforms;

[0067] Appendix Figure 2 This is a schematic diagram of a convex model (where some values ​​are abnormally higher than the surrounding values);

[0068] Appendix Figure 3This is a schematic diagram of a concave model (where some values ​​are abnormally lower than the surrounding values). Detailed Implementation

[0069] The data cleaning and alarm analysis method and system of the digital energy platform of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0070] Example 1:

[0071] As attached Figure 1 As shown in the figure, this embodiment provides a data cleaning and alarm analysis method for a digital energy platform, as detailed below:

[0072] S1. Clean and delete analog, digital, and energy consumption data that exceed the time limit;

[0073] S2. Mark data that exceed the data point limit, conform to the convex model (individual values ​​are abnormally higher than surrounding values), and conform to the concave model (individual values ​​are abnormally lower than surrounding values), as shown in the attached figure. Figure 2 and 3 As shown;

[0074] S3. Perform alarm analysis on analog, digital, and energy consumption data:

[0075] An alarm message will be generated if data exceeds the upper or lower limits of the data point, or if the data conforms to the convex model or the concave model.

[0076] The specific steps for cleaning and deleting analog and digital value data in step S1 of this embodiment are as follows:

[0077] S1-101. Define the task of cleaning analog and digital data as a scheduled task, and implement it through annotation and cron expression @Scheduled(cron="0 0* / 8**?");

[0078] S1-102. Set the execution time limit for the cleaning task, such as executing it once every 8 hours;

[0079] S1-103. Data exceeding a set time limit is deleted on a scheduled basis. For example, data exceeding 365 days needs to be deleted on a scheduled basis. The time limit is configurable.

[0080] S1-104. Delete analog and numeric values ​​from the table using `DateUtil.getExpiredDate(liveInDays)` and `new LambdaQueryWrapper<>()`. Key code is as follows:

[0081] Date expiredDate=DateUtil.getExpiredDate(liveInDays);

[0082] LambdaQueryWrapper <analogvalue>wrapper=new LambdaQueryWrapper<>();

[0083] wrapper.lt(AnalogValue::getUtcDateTime,expiredDate);

[0084] analogValueService.remove(wrapper).

[0085] In step S1 of this embodiment, energy consumption data cleaning involves marking energy consumption data exceeding the highest and lowest limits as bad data based on the highest and lowest values ​​of the data point. For the same data point, the energy consumption trend is normally flat or cumulative. If data appears that is lower than the previous energy consumption value, it will be marked as bad data. If individual energy consumption values ​​at the same data point are higher than the surrounding energy consumption values, the abnormal data will be marked as bad data.

[0086] The specific steps for cleaning the energy consumption data in step S1 of this embodiment are as follows:

[0087] S1-201, Threaded Mode: After the service starts, the thread executes once every 180 seconds; the key code is: class EnergyValueCleaningThread extends Thread.

[0088] S1-202, Query the time range of uncleaned data in the table; the key code is:

[0089] SELECT MIN(utc_date_time)as minDateTime,MAX(utc_date_time)asmaxDateTime

[0090] FROM tbl_energy_value

[0091] WHERE is_bad IS NULL.

[0092] S1-203. The minimum time retrieved is pushed back one hour, which is taken as the start time of this cleaning.

[0093] S1-204. Obtain data points related to energy consumption values ​​(OBJECT_TYPE = ENERGY_VALUE);

[0094] S1-205, Query all energy consumption data within the time range of this cleaning operation; the key code is:

[0095] SELECT*

[0096] FROM tbl_energy_value

[0097] WHERE utc_date_time<=%s and utc_date_time>=%s and is_bad IS NULL.

[0098] S1-206. Determine if the data point exists in the energy consumption data for this cleaning:

[0099] If the data point does not exist, update the value of the is_bad field of the data to true;

[0100] S1-207. Query the cleaned data in the energy consumption table again, sorting by data point ID and data time; the key code is:

[0101] SELECT*

[0102] FROM tbl_energy_value

[0103] WHERE utc_date_time<=%s and utc_date_time>=%s and is_bad is nottrue

[0104] order by point_id,utc_date_time.

[0105] S1-208. Place the uncleaned data into a map according to the data points, in the form of (key, value); where key is the data point ID and value is the set of energy consumption data corresponding to that data point.

[0106] S1-209. Traverse the energy consumption data of all data points, and determine whether it exceeds the maximum or minimum limit of the data point and whether it is a concave or convex model. The following are the possible outcomes:

[0107] ① Determine the maximum and minimum limits of data points: Determine whether the actual_value is between the high_limit and low_limit in the tbl_point table;

[0108] ② As attached Figure 3 As shown, the concave model determines that: if the previous value is the standard, and the subsequent value is less than the previous value, then the energy consumption value data is_bad corresponding to the subsequent value needs to be marked as true;

[0109] ③ As attached Figure 2 As shown, the convex model determines that if the previous value is labeled and the growth of the next value exceeds a specified rate, then the energy consumption data corresponding to the next value, i_bad, needs to be marked as true.

[0110] S1-210. Mark the is_bad field of all unmarked energy consumption data within this cleaning period as false.

[0111] In this embodiment, step S3 involves analyzing simulated value data to generate alarm information based on the highest and lowest values ​​of the data points, as well as data exceeding high and low limits. This information is then sent to the user, as detailed below:

[0112] S301, query the time range for alarm analysis in the table; key code is as follows:

[0113] SELECT MIN(utc_date_time)as minDateTime,MAX(utc_date_time)asmaxDateTime

[0114] FROM tbl_analog_value

[0115] WHERE is_bad IS NULL.

[0116] S302. The minimum time retrieved is pushed back one hour, which is used as the start time for this cleaning.

[0117] S303, Obtain the relevant data points (OBJECT_TYPE = ANALOG_VALUE);

[0118] S304. Query all simulated value data within the time range of this alarm analysis; key code is as follows:

[0119] SELECT*

[0120] FROM tbl_energy_value

[0121] WHERE utc_date_time<=%s and utc_date_time>=%s and is_bad is nottrue.

[0122] S305. Determine if the data point exists in the simulated data of this alarm analysis:

[0123] If no data point has an actual_value exceeding the maximum or minimum limit, then update the is_bad field of the simulated value data to true, obtain the corresponding device information based on the data point, insert the alarm information into the alarm table, and then call the alarm notification interface of the demp-service service to notify the alarm.

[0124] S306. Update the data in the time range of this alarm analysis that is not marked to false.

[0125] In this embodiment, step S3, the digital value data alarm analysis, involves generating alarm information and notifying the user based on the highest and lowest values ​​of the data points containing the digital values, as well as data exceeding the high and low limits. Specifically:

[0126] Using the previous numeric value as a standard, if the value of the next numeric value is not equal to the value of the previous numeric value, it is considered a shift. The value of the is_bad field of the numeric value is updated to true, the alarm information is inserted into the alarm table, and the alarm notification interface of the demp-service service is called to notify the alarm.

[0127] In this embodiment, step S3 involves analyzing energy consumption data to generate alarm information based on the highest, lowest, and energy consumption values ​​exceeding the high and low limits of the data points containing the energy consumption data, and then notifying the user. Specifically:

[0128] When analyzing energy consumption data for the same data point, the trend of energy consumption values ​​is normally flat or cumulative. If data shows a value lower than the previous energy consumption value, an alarm message should be generated and the user should be notified.

[0129] If the energy consumption value of an individual data point is higher than the energy consumption value of the surrounding data points, an alarm message should be generated and the user should be notified.

[0130] Example 2:

[0131] This embodiment provides a data cleaning and alarm analysis system for a digital energy platform. The system includes:

[0132] The cleaning module is used to clean and delete analog, digital, and energy consumption data that have exceeded the time limit.

[0133] The marking module is used to mark data that exceeds the data point limit, conforms to the convex model (individual values ​​are abnormally higher than the surrounding values), and conforms to the concave model (individual values ​​are abnormally lower than the surrounding values), as shown in Figures 2 and 3.

[0134] The alarm analysis module is used to perform alarm analysis on analog, digital and energy consumption data. If data exceeds the upper or lower limits of the data point, or conforms to the convex model or the concave model, an alarm message will be generated.

[0135] Example 3:

[0136] This embodiment also provides an electronic device, including: a memory and a processor;

[0137] The memory stores the instructions executed by the computer.

[0138] The processor executes computer execution instructions stored in the memory, causing the processor to perform the data cleaning and alarm analysis method of the digital energy platform in any embodiment of the present invention.

[0139] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can be a microprocessor or any conventional processor.

[0140] Memory is used to store computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, at least one application program required for a function, etc.; the data storage area can store data created based on the use of the terminal, etc. In addition, memory can also include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart memory cards (SMC), secure digital cards (SD cards), flash memory cards, at least one disk storage device, flash memory devices, or other volatile solid-state storage devices.

[0141] Example 4:

[0142] This embodiment also provides a computer-readable storage medium storing multiple instructions, which are loaded by a processor to cause the processor to execute the data cleaning and alarm analysis method of the digital energy platform in any embodiment of the present invention. Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU) of the system or apparatus can read and execute the program code stored in the storage medium.

[0143] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0144] Storage media embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RYM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0145] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0146] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion unit connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion unit execute some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.< / analogvalue>

Claims

1. A data cleaning and alarm analysis method for a digital energy platform, characterized in that, The method is as follows: Clean and delete analog, digital, and energy consumption data that exceed the time limit; Data that exceeds the data point limit, conforms to the convex model, or conforms to the concave model is marked. Alarm analysis is performed on analog, digital, and energy consumption data: If data exceeds the upper or lower limits of the data point, or conforms to the convex model or the concave model, an alarm message will be generated. The energy consumption data cleaning process involves marking data exceeding the highest and lowest limits as "bad" data based on the highest and lowest values ​​of the data points. For the same data point, the energy consumption trend is either flat or cumulative; if a value falls below previous values, it will be marked as "bad." Furthermore, if individual energy consumption values ​​at the same data point are higher than surrounding values, these are considered abnormal and will be marked as "bad." The specific steps for cleaning energy consumption data are as follows: Threaded approach: After the service starts, the thread executes once every 180 seconds; Find the time range for uncleaned data in the query table; The minimum time retrieved is pushed back one hour to determine the start time of this cleaning process. Obtain data points related to energy consumption; Query all energy consumption data within the time range of this cleaning process; Determine if the data point exists in the energy consumption data for this cleaning: If the data point does not exist, update the value of the is_bad field of that data to true; Query the energy consumption table again for the uncleaned data, sorting it by data point ID and data time; The uncleaned data is placed into a map according to the data points, in the form of (key, value); where the key is the data point ID and the value is the set of energy consumption data corresponding to that data point; Iterate through the energy consumption values ​​of all data points, and determine whether they exceed the maximum or minimum limits of the data points, as well as whether it is a concave or convex model, as follows: Data point maximum and minimum limit determination: Determine whether actual_value is between high_limit and low_limit in the tbl_point table; Concave model judgment: Based on the previous value, if the subsequent value is less than the previous value, the energy consumption value data corresponding to the subsequent value is_bad needs to be marked as true; Convex model judgment: If the previous value is the standard, and the growth of the next value exceeds the specified rate, then the energy consumption value data corresponding to the next value, i_bad, needs to be marked as true. Mark the is_bad field as false for all unmarked energy consumption data within this cleaning period.

2. The data cleaning and alarm analysis method for a digital energy platform according to claim 1, characterized in that, The specific steps for cleaning and deleting analog and digital data are as follows: Define the task of cleaning analog and digital data as a scheduled task; Set the execution time limit for the cleaning task; Data exceeding a set time limit is deleted periodically; the time limit is configurable. Delete analog and numeric data from the table.

3. The data cleaning and alarm analysis method for a digital energy platform according to claim 1, characterized in that, Simulated value data alarm analysis generates alarm information and notifies the user based on the highest, lowest, and values ​​exceeding the upper and lower limits of the data points. The specific details are as follows: The time range for alarm analysis is queried from the table; The minimum time retrieved is pushed back one hour to determine the start time of this cleaning process. Obtain the relevant data points; Query all simulated value data within the time range of this alarm analysis; Determine if the data point exists in the simulated data for this alarm analysis: If the actual_value of a data point does not exceed the maximum or minimum limit of the data point, then update the value of the is_bad field of the simulated value data to true, obtain the corresponding device information based on the data point, insert the alarm information into the alarm table, and then call the alarm notification interface to notify the alarm. Update the time range of this alarm analysis to false for data that is not marked, i_bad.

4. The data cleaning and alarm analysis method for a digital energy platform according to claim 1, characterized in that, Numerical value data alarm analysis generates alarm information and notifies the user based on the highest, lowest, and values ​​exceeding the upper and lower limits of the data points containing the numerical values; specifically as follows: Using the previous numeric value as a standard, if the value of the next numeric value is not equal to the value of the previous numeric value, it is considered a shift. The value of the is_bad field of the numeric value is updated to true, the alarm information is inserted into the alarm table, and the alarm notification interface is called to send an alarm notification.

5. The data cleaning and alarm analysis method for a digital energy platform according to claim 1, characterized in that, Energy consumption data alarm analysis generates alarm information and notifies the user based on the highest, lowest, and energy consumption values ​​exceeding the limits for the data points containing the energy consumption data; specifically as follows: When analyzing energy consumption data for the same data point, if the trend of energy consumption is flat or accumulating, and if data shows a value lower than the previous energy consumption value, an alarm message needs to be generated and the user notified. If the energy consumption value of an individual data point is higher than the energy consumption value of the surrounding data points, an alarm message should be generated and the user should be notified.

6. A data cleaning and alarm analysis system for a digital energy platform, characterized in that, This system is used to implement the data cleaning and alarm analysis method for the digital energy platform as described in any one of claims 1 to 5; the system includes, The cleaning module is used to clean and delete analog, digital, and energy consumption data that exceed the time limit. The marking module is used to mark data that exceeds the data point limit, conforms to the convex model, or conforms to the concave model; The alarm analysis module is used to perform alarm analysis on analog, digital and energy consumption data. If data exceeds the upper or lower limits of the data point, or conforms to the convex model or the concave model, an alarm message will be generated.

7. An electronic device, characterized in that, include: Memory and at least one processor; The memory contains computer programs; The at least one processor executes the computer program stored in the memory, causing the at least one processor to perform the data cleaning and alarm analysis method of the digital energy platform as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by a processor to implement the data cleaning and alarm analysis method for the digital energy platform as described in any one of claims 1 to 5.

Images