Method, device and equipment for identifying power failure of medium and low voltage users and storage medium

Abstract

The invention discloses a method, a device and equipment for identifying power failure of medium and low voltage users and a storage medium, belongs to the technical field of power monitoring, and solves the problems that real power failure and metering equipment faults cannot be distinguished and power failure duration cannot be accurately calculated in the prior art. The invention discloses a method for identifying power failure of medium and low voltage users. The method comprises the following steps: S1, acquiring data of the medium and low voltage users and preprocessing the data; s2, establishing a checking model, inputting the preprocessed data into the checking model, and judging whether an abnormal mode exists or not, if yes, determining that the abnormal mode is a suspected power failure event, and entering the step S3, and if not, determining that the power failure event does not occur; and S3, analyzing and verifying the suspected power failure event, and calculating the power failure duration of the suspected power failure event. According to the method, the power failure event of the transformer area is accurately judged, the power failure duration is accurately calculated, and the response speed and the processing efficiency of an electric power department to the power failure event are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of power monitoring, and particularly relates to a method and device for identifying power outage of medium and low voltage users, equipment and storage medium. BACKGROUND

[0002] Power outage of a transformer area is a common fault phenomenon in a power system, and accurate identification of a power outage event and calculation of a power outage duration are crucial for improving power supply reliability and service quality. Traditional power outage identification methods mainly rely on user repair or manual inspection, and have problems such as slow response speed and low accuracy. With the popularization of smart meters, the power system can obtain a large amount of user power consumption data, but existing power outage identification methods have the following problems: 1) cannot distinguish between real power outage and metering equipment failure; 2) cannot accurately calculate the power outage duration; and 3) lack of systematic abnormal data identification rules. SUMMARY

[0003] The present application aims to provide a method and device for identifying power outage of medium and low voltage users, equipment and storage medium, which solves the problem that existing methods cannot distinguish between real power outage and metering equipment failure and cannot accurately calculate the power outage duration.

[0004] To achieve the above-mentioned purpose, the technical solution of the present application is as follows:

[0005] A method for identifying power outage of medium and low voltage users, comprising the following steps:

[0006] Step S1, obtaining data of medium and low voltage users and pre-processing the data;

[0007] Step S2, establishing a verification model, inputting the pre-processed data into the verification model, and determining whether there is an abnormal pattern, if yes, entering step S3 for a suspected power outage event, if not, no power outage event occurs;

[0008] Step S3, analyzing and verifying the suspected power outage event and calculating its power outage duration.

[0009] In some embodiments, the step S1 comprises:

[0010] Step S11, collecting power data of the medium and low voltage users at an interval of 10-30 minutes;

[0011] Step S12, cleaning, labeling, de-duplicating and correcting the power data.

[0012] In some embodiments, the step S2 of establishing a verification model specifically comprises: establishing the verification model according to a pre-set abnormal identification rule.

[0013] In some embodiments, the pre-set abnormal rule comprises:

[0014] The forward active power in the power data is continuously null: the forward active power is null for 2 or more times in succession;

[0015] The forward active power in the power data is continuously 0: the forward active power is 0 for 2 or more times in succession;

[0016] The forward active power in the power data is continuously a fixed value: the forward active power is a fixed value for 2 or more times in succession, and n-day simultaneous period data before and after the fixed value is n days or less, wherein 5≤n≤15, and n is a positive integer;

[0017] The forward active power in the power data is abnormally fluctuating: compared with the average value of n-day simultaneous period data before and after the forward active power, an increase or decrease of more than 20% is abnormal, wherein 5≤n≤15, and n is a positive integer;

[0018] The forward active power in the power data is abnormally jumping: after 4 or fewer times of forward active power being null, and 4 or more times of forward active power being a fixed value with an increase or decrease of more than 20%, compared with n-day simultaneous period data before and after the fixed value, wherein 5≤n≤15, and n is a positive integer.

[0019] In some embodiments, the preset abnormal rule further comprises:

[0020] Terminal replacement: 4 or more times of forward active power being null in succession, and the last value before the null is greater than 30kW, and the first value after the null is 0-30kW;

[0021] Terminal delay online: calculate the power consumption of 2n days before and after n days, obtain the average value of every 10-30 minutes in 2n days, and collect the forward active power being null, then the difference between the first value after the null and the last value before the null is greater than 4 times the average value, and the difference in power consumption before and after the null is greater than 1 degree.

[0022] In some embodiments, the step S3 comprises:

[0023] Step S31, according to the power supply relationship between the low-voltage user and the medium-voltage user, the difference between the low-voltage user outage start time and the medium-voltage user voltage disappearance time on the same feeder is less than or equal to 1 minute, confirming the relevance of the low-voltage user and the medium-voltage user;

[0024] Step S32, when the low-voltage user is powered off, the forward active power data of the medium-voltage user on the same feeder is detected, if the forward active power data of the medium-voltage user is 0 or null in the corresponding time period, it is determined that the medium-voltage user is powered off; if the low-voltage user has a suspected power-off event, and the medium-voltage user data on the same feeder is abnormal, it is determined that the medium-voltage user is powered off.

[0025] Step S33, on-site verification or data comparison is performed on the medium voltage user determined to be power failure, to verify whether power failure occurs, if yes, step S34 is entered, if not, step S2 is returned, and data is determined again;

[0026] Step S34, the power failure duration of the low voltage user and the medium voltage user is calculated.

[0027] In some embodiments, the step S34 comprises:

[0028] The power failure start time is the time of the first abnormal data point;

[0029] The power failure end time is the time of the first normal data point after the last abnormal data point;

[0030] The power failure duration is the difference between the power failure end time and the power failure start time.

[0031] Another technical solution of the present application is implemented as follows: a device for identifying power failure of medium and low voltage users, comprising:

[0032] A data processing module: acquiring data of medium and low voltage users and pre-processing the data;

[0033] A power failure determination module: establishing a verification model, inputting the pre-processed data into the verification model to determine whether there is an abnormal pattern, if yes, it is a suspected power failure event, if not, no power failure event occurs;

[0034] A calculation module: analyzing and verifying the suspected power failure event and calculating the power failure duration thereof.

[0035] Another technical solution of the present application is implemented as follows: a device for identifying power failure of medium and low voltage users, comprising a memory, a processor and an identification program for identifying power failure of medium and low voltage users stored in the memory and executable on the processor, the identification program being configured to implement the method for identifying power failure of medium and low voltage users.

[0036] Another technical solution of the present application is implemented as follows: a computer readable storage medium storing a computer program, the computer program being executable by a processor to implement the steps of the method for identifying power failure of medium and low voltage users.

[0037] Compared with the prior art, the present application realizes accurate judgment of power failure events of a transformer area and accurate calculation of power failure duration, effectively improving the response speed and processing efficiency of the power department to power failure events. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 A flowchart of the method for identifying power outage of medium and low voltage users provided by Embodiment 1 of the present application is shown in the figure;

[0039] Figure 2 A structural block diagram of the device for identifying power outage of medium and low voltage users provided by Embodiment 2 of the present application is shown in the figure;

[0040] Figure 3 A structural diagram of the device for identifying power outage of medium and low voltage users related to the hardware running environment of the present application scheme is shown in the figure. DETAILED DESCRIPTION

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer and more comprehensible, the present application will be further described in detail below in combination with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] In the description of the present application, it should be noted that the terms "vertical", "lateral", "longitudinal", "front", "back", "left", "right", "up", "down", "horizontal" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application, and do not mean that the devices or elements referred to must have a particular orientation or position, and therefore cannot be understood as a limitation on the present application. In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connection" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0043] Embodiment 1

[0044] The method for identifying power outage of medium and low voltage users provided by Embodiment 1 of the present application, as shown in the figure, includes the following steps: Figure 1

[0045] Step S1, acquiring data of medium and low voltage users and pre-processing;

[0046] It should be noted that in the specific implementation, the data of medium and low voltage users is collected and pre-processed in real time to ensure that the quality of the data meets the subsequent analysis requirements.

[0047] Step S11, collecting power data of medium and low voltage users at 15-minute intervals;

[0048] ​In a specific implementation, the power data includes fields such as user number, user, data time, forward active, reverse active, etc.; and the data format is unified, including fields such as timestamp, user ID, table code value, etc.

[0049] Step S12, cleaning, labeling, de-duplication processing and error removal processing are performed on the power data.

[0050] In a specific implementation, data cleaning and standardization, and de-duplication processing: based on the timestamp and user ID, repeated data records are deleted to avoid repeated calculation; error data is removed, and according to the data rationality threshold (such as the power value cannot be negative, exceeding the device range, etc.), the obviously erroneous data is marked and removed to prevent abnormal values from misleading power failure judgment; abnormal value processing: all power data is uniformly converted to kilowatt (kW), and the timestamp is uniformly converted to UTC time zone to eliminate the dimension difference; during the cleaning process, data quality logs need to be recorded, including the data amount before and after cleaning, the type and amount of abnormal data, to provide a basis for subsequent optimization;

[0051] Step S2, a verification model is established, the preprocessed data is input into the verification model to determine whether there is an abnormal pattern, if yes, it is a suspected power failure event, and enters step S3, if not, no power failure event occurs.

[0052] The verification model is established according to a preset abnormal identification rule, and the preset abnormal rule includes:

[0053] The forward active in the power data is continuously empty: the forward active is empty for 2 times and more, and is empty for more than one day, excluding the misjudgment caused by long-time no data recording; by traversing the power data sequence of each user, the continuous empty value point is detected, and whether it meets the abnormal identification rule is judged in combination with the time interval;

[0054] The forward active in the power data is continuously 0: the forward active is 0 for 2 times and more, and 0 for more than one day, excluding normal scenes such as night zero power consumption; by scanning the power data sequence with a sliding window, the number of continuous 0 values is counted, and the value is judged in combination with the time;

[0055] The forward active in the power data is continuously constant value abnormal: the forward active is a fixed value for 2 times and more, and compared with the data of the same period of 5 days before and after, there are 5 days and less data of the same period being constant value, and the 0 and empty value before and after are considered as continuous constant value abnormal;

[0056] If there are 5 days or more forward active being constant value in total 10 days of data of 5 days before and after, it is determined as a regular situation.

[0057] Forward active jump change anomaly in the power data: compared with the average value of the same period data of the previous and next 5 days, an increase or decrease of more than 20% is abnormal; compared with the average value of the same period data of the previous and next 5 days, an increase of more than 20% is determined to be a sudden increase anomaly; compared with the average value of the same period data of the previous and next 5 days, a decrease of more than 20% is determined to be a sudden decrease anomaly;

[0058] Forward active anomaly jump in the power data: after 4 or fewer forward active null values appear, and the forward active value increases or decreases by more than 20% for 4 or more times, the forward active value is determined to be a constant value;

[0059] Terminal replacement: 4 or more consecutive forward active null values appear, and the last value before the null value is greater than 30kW, and the first value after the null value is 0-30KW;

[0060] Terminal delay online: calculate the daily average power consumption of the previous and next 5 days, and then divide by 10 to obtain the average value of every 15 minutes in 10 days. If the forward active is null, the difference between the first value after the null value and the last value before the null value is greater than 4 times the average value, and the power consumption difference before and after the null value is greater than 1 degree. The power data sequence is matched by the rule engine, and the detection result is verified by combining the field records and historical data;

[0061] Step S3, analyze and verify the suspected power outage event and calculate the power outage duration;

[0062] Step S31, according to the power supply relationship between the low-voltage user and the medium-voltage user, the difference between the low-voltage user power outage start time and the medium-voltage user voltage disappearance time on the same feeder is less than or equal to 1 minute, confirming the relevance of the low-voltage user and the medium-voltage user (excluding false positives caused by time delay);

[0063] Step S32, when the low-voltage user is powered off, the forward active data of the medium-voltage user on the same feeder is detected. If the forward active data of the medium-voltage user is 0 or null in the corresponding time period, it is determined that the medium-voltage user is powered off. If the low-voltage user has a suspected power outage event, and the medium-voltage user data on the same feeder is abnormal, it is determined that the medium-voltage user is powered off;

[0064] Step S33, the medium-voltage user determined to be powered off is verified on site or by data comparison to verify whether it has been powered off. If yes, go to step S34, if no, return to step S2 and determine the data again;

[0065] Step S34, calculate the power outage duration of the low-voltage user and the medium-voltage user;

[0066] The power outage start time is the time of the first abnormal data point;

[0067] The power outage end time is the time of the first normal data point after the last abnormal data point;

[0068] The power outage duration is the difference between the power outage end time and the power outage start time.

[0069] After the above scheme is adopted, accurate judgment of the power outage event of the transformer area and accurate calculation of the power outage duration are realized, the response speed and processing efficiency of the power department to the power outage event are effectively improved, and the reliability and user satisfaction of the power supply service are significantly improved.

[0070] Embodiment 2

[0071] The recognition device for the power outage of the medium and low voltage user provided in the embodiment 2 of the present application comprises: Figure 2 As shown in the figure, the recognition device for the power outage of the medium and low voltage user comprises:

[0072] The data processing module: acquires the data of the medium and low voltage user and performs preprocessing;

[0073] The determination module for the power outage: establishes a verification model, inputs the preprocessed data into the verification model to determine whether there is an abnormal mode, if yes, it is a suspected power outage event, and if no, no power outage event occurs;

[0074] The calculation module: analyzes and verifies the suspected power outage event and calculates the power outage duration thereof.

[0075] The embodiment 2 acquires the data of the medium and low voltage user and performs preprocessing, establishes a verification model, inputs the preprocessed data into the verification model to determine whether there is an abnormal mode, if yes, it is a suspected power outage event, and if no, no power outage event occurs; analyzes and verifies the suspected power outage event and calculates the power outage duration thereof; accurate judgment of the power outage event of the transformer area and accurate calculation of the power outage duration are realized.

[0076] Embodiment 3

[0077] The recognition device for the power outage of the medium and low voltage user provided in the embodiment 3 of the present application comprises: Figure 3As shown, the identification of low-voltage user power failure device can include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection communication between the components. The user interface 1003 can include a display screen, an input unit such as a keyboard, and an optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM), and can also be a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0078] Those skilled in the art can understand that Figure 3 The structure shown in the figure does not constitute a limitation on the identification of low-voltage user power failure device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0079] As Figure 3 As shown, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and an identification of low-voltage user power failure program.

[0080] In Figure 3 As shown in the identification of low-voltage user power failure device, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the identification of low-voltage user power failure device of the application can be arranged in the identification of low-voltage user power failure device, and the identification of low-voltage user power failure device calls the identification of low-voltage user power failure program stored in the memory 1005 through the processor 1001, and executes the identification of low-voltage user power failure method provided by the embodiment 1 of the application.

[0081] Embodiment 4

[0082] The computer readable storage medium provided by the embodiment 4 of the application stores a computer program, and the storage medium stores an identification of low-voltage user power failure program. When the processor executes the identification of low-voltage user power failure program, the steps of the identification of low-voltage user power failure method described in the embodiment 1 are realized.

[0083] Since the storage medium adopts all the technical solutions of the above embodiments, at least all the beneficial effects brought by the technical solutions of the above embodiments are achieved, and thus will not be repeated here.

[0084] It should be understood that the above is only illustrative, and does not constitute any limitation on the technical solutions of the present application. In specific applications, those skilled in the art can set up according to the needs, and the present application does not limit this.

[0085] It should be noted that the above-described workflow is only illustrative and does not limit the scope of protection of the present application. In actual application, those skilled in the art can select part or all of them to achieve the purpose of the embodiment scheme according to the actual needs, which is not limited here.

[0086] In addition, technical details not described in detail in this embodiment can be referred to the identification method of low-voltage user power failure provided by any embodiment of the present application, which will not be repeated here.

[0087] In addition, it should be noted that in this paper, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or system. Without more limitations, the element defined by the sentence "includes a" does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0088] The above embodiment number of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0089] From the above description of the embodiments, those skilled in the art can clearly understand that the above embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of software product, which is stored in a storage medium (such as read only memory (Read Only Memory, ROM) / RAM, magnetic disk, optical disk), including a plurality of instructions to make a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the method described in each embodiment of the present application.

[0090] The above merely describes preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any changes or replacements within the technical scope disclosed by the present application, which can be easily thought by those skilled in the art, should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for identifying power outages for medium- and low-voltage users, characterized in that, Includes the following steps: Step S1: Obtain data from medium and low voltage users and perform preprocessing; Step S2: Establish a verification model, input the preprocessed data into the verification model, and determine whether there is an abnormal pattern. If so, it is a suspected power outage event and proceeds to step S3. If not, no power outage event has occurred. Step S3: Analyze and verify the suspected power outage event and calculate its outage duration.

2. The method for identifying power outages for medium and low voltage users according to claim 1, characterized in that, Step S1 includes: Step S11: Collect power data of the medium and low voltage users at 10-30 minute intervals; Step S12: Clean, label, deduplicate, and remove errors from the power data.

3. The method for identifying power outages for medium and low voltage users according to claim 1 or 2, characterized in that, The establishment of the verification model in step S2 specifically includes: establishing the verification model according to the preset anomaly identification rules.

4. The method for identifying power outages for medium and low voltage users according to claim 3, characterized in that, The preset exception rules include: The positive active power in the power data is continuously null: positive active power is null for two or more consecutive times; The positive active power in the power data is continuously 0: positive active power is 0 for 2 or more consecutive times; The positive active power in the power data is continuously constant and abnormal: there are two or more consecutive positive active power values ​​that are constant, and compared with the data of the same period n days before and after, there are n days or less of data that are constant, where 5≤n≤15, and n is a positive integer; Abnormal fluctuations in the positive active power data: An increase or decrease exceeding 20% ​​compared to the average of data from the same period n days prior or subsequent is considered abnormal, where 5 ≤ n ≤ 15, and n is a positive integer; The positive active power abnormal jump in the power data is defined as follows: after comparing with the data of the same period n days before and after, the positive active power that appears as null value 4 or less times and then continues to increase or decrease by more than 20% for 4 or more consecutive times is defined as a constant value, where 5≤n≤15 and n is a positive integer.

5. The method for identifying power outages for medium and low voltage users according to claim 4, characterized in that, The preset anomaly rules also include: Terminal replacement: Four or more consecutive positive active power values ​​are empty, and the last value before the empty value is greater than 10kW, and the first value after the empty value is 0-30kW; Terminal delay online: Calculate the electricity consumption for a total of 2n days (n days before and after), and obtain the average value every 10-30 minutes within 2n days. If the collected positive active power is null, then the difference between the first value after the null value and the last value before the null value is greater than 4 times the average value, and the difference in electricity consumption before and after the null value is greater than 1 kWh.

6. The method for identifying power outages for medium and low voltage users according to claim 3, characterized in that, Step S3 includes: Step S31: Based on the power supply relationship between the low-voltage user and the medium-voltage user, if the difference between the start time of the power outage of the low-voltage user and the time when the voltage of the medium-voltage user on the same feeder disappears is ≤1 minute, confirm the correlation between the low-voltage user and the medium-voltage user. Step S32: When a low-voltage user experiences a power outage, the positive active power data of the medium-voltage user on the same feeder is detected. If the positive active power data of the medium-voltage user is 0 or empty within the corresponding time period, the medium-voltage user is determined to be out of power. If a low-voltage user experiences a suspected power outage event, and the data of the medium-voltage user on the same feeder is abnormal, the medium-voltage user is determined to be out of power. Step S33: Conduct on-site verification or data comparison for the medium-voltage users who are determined to have experienced a power outage to verify whether a power outage has occurred. If so, proceed to step S34; otherwise, return to step S2 and re-evaluate the data. Step S34: Calculate the power outage duration for the low-voltage user and the medium-voltage user.

7. The method for identifying power outages for medium and low voltage users according to claim 6, characterized in that, Step S34 includes: The power outage started at the time of the first abnormal data point; The power outage end time is the time it takes for the first normal data point to be restored after the last abnormal data point. The power outage duration is the difference between the power outage end time and the power outage start time.

8. A device for identifying power outages in medium and low voltage users, characterized in that, The device for identifying power outages for medium and low voltage users includes: Data processing module: Acquires data from medium and low voltage users and performs preprocessing; Power outage detection module: Establish a verification model, input the preprocessed data into the verification model to determine whether there is an abnormal pattern. If so, it is a suspected power outage event; if not, no power outage event has occurred. Calculation module: Analyzes and verifies the suspected power outage event and calculates its outage duration.

9. A device for identifying power outages in medium and low voltage users, characterized in that, The device for identifying power outages of medium and low voltage users includes: a memory, a processor, and a program for identifying power outages of medium and low voltage users stored in the memory and executable on the processor, wherein the program for identifying power outages of medium and low voltage users is configured to implement the method for identifying power outages of medium and low voltage users according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it can implement the steps of the method for identifying power outages of medium and low voltage users as described in any one of claims 1-7.

Images