CN113077357B - Power time sequence data anomaly detection method and filling method thereof - Google Patents
Power time sequence data anomaly detection method and filling method thereof Download PDFInfo
- Publication number
- CN113077357B CN113077357B CN202110335947.8A CN202110335947A CN113077357B CN 113077357 B CN113077357 B CN 113077357B CN 202110335947 A CN202110335947 A CN 202110335947A CN 113077357 B CN113077357 B CN 113077357B
- Authority
- CN
- China
- Prior art keywords
- data
- value
- missing
- abnormal
- time sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 59
- 230000005856 abnormality Effects 0.000 claims abstract description 47
- 230000003068 static effect Effects 0.000 claims abstract description 5
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method for detecting abnormality of power time sequence data, which comprises the steps of obtaining power time sequence data to be analyzed and judging missing values; filling missing data and performing abnormality judgment; and finally detecting the power time sequence data abnormality according to the abnormality judgment result. The invention also discloses a filling method comprising the power time sequence data anomaly detection method. The invention judges whether the data needs to be filled according to the missing condition of the power time sequence data, and fills the data by using a moving average method of daytime data; meanwhile, whether filling abnormality is considered for the filled data, and an abnormality detection method of combining a horizontal short-term loop ratio with a dynamic threshold and combining a longitudinal same-ratio amplitude with a static threshold is adopted to detect abnormal points; finally, correcting the data with abnormal detection by using a moving average method of data in the day; therefore, the method can realize the anomaly detection and filling of the power time sequence data, and is stable, reliable, high in accuracy and high in efficiency.
Description
Technical Field
The invention belongs to the field of electrical automation, and particularly relates to a power time sequence data anomaly detection method and a filling method thereof.
Background
Along with the development of economic technology and the improvement of living standard of people, electric energy becomes an indispensable secondary energy source in the production and living of people, and brings endless convenience to the production and living of people. Therefore, the stable and reliable operation of the power system becomes one of the most important tasks of the power system.
In the power system, terminal acquisition equipment acquires power time sequence data such as active power, power consumption and the like according to set time frequency, and saves and uniformly uploads the acquired data. However, due to uncontrollable factors such as equipment failure and transmission channel interference, an abnormal situation of power data loss is unavoidable. Because of the unrepeatability of the power grid data collection, the missing power data needs to be filled and abnormality detected.
However, in the current power system, a complete, reliable and high-efficiency detection method and a corresponding filling method for power time sequence data abnormality do not exist.
Disclosure of Invention
The invention aims to provide a stable, reliable, high-accuracy and high-efficiency power time sequence data anomaly detection method.
The second object of the present invention is to provide a filling method including the method for detecting power time series data anomalies.
The power time sequence data anomaly detection method provided by the invention comprises the following steps:
s1, acquiring power time sequence data to be analyzed;
s2, judging the missing value of the data obtained in the step S1;
s3, filling missing data by adopting a daytime data moving average algorithm according to the missing value determined in the step S2;
s4, carrying out abnormality judgment on the data by adopting a short-term ring ratio abnormality detection algorithm according to the filled data obtained in the step S3;
s5, carrying out abnormality judgment on the filled data obtained in the step S3 by adopting a homonymous amplitude abnormality detection algorithm;
s6, performing final power time sequence data abnormality detection according to the abnormality determination results obtained in the step S4 and the step S5.
The step S2 is to determine the missing value of the data acquired in the step S1, specifically, the missing value determination is performed by adopting the following steps:
if the power time sequence data is complete, the abnormal filling of the missing value is not needed;
if the proportion of the power time sequence data missing is higher than the set threshold value, the group of power time sequence data is directly discarded;
if the ratio of the power time series data missing is within the set threshold value range, the following determination is made again:
if the missing data is NA, judging the missing value according to the region where the transformer substation is located and the actual condition of the collected data;
if the missing data is 0, judging again according to the granularity division of the data acquisition source:
if the data is the data collected on the equipment with the area or finer granularity, the data is considered to be normal, and the missing abnormal condition is not required to be processed;
if the data are collected on substations of various voltage classes or coarser-grained equipment, the data are identified as abnormal, and the abnormal condition of the data is required to be processed.
The missing value determined in step S2 in step S3 is filled with missing data by adopting a daytime data moving average algorithm, specifically, the missing value is processed by adopting the following steps:
filling missing data by adopting data at the same moment in the historical data:
middle val f Is a filling value; val valve h In the historical data corresponding to the missing data, the data values of the same time in the previous h days are obtained; t (T) h Is the time window size of the historical data.
The step S4 of performing abnormality determination on the data after filling obtained in the step S3 by using a short-term loop ratio abnormality detection algorithm, specifically performing abnormality determination by using the following steps:
setting a time window T, and comparing the filled data with each piece of data in the time window T: if the number of times that the difference between the filled data and the data in the time window T is greater than the set difference threshold exceeds the set number of times threshold, the filled data is determined to be an abnormal point:
wherein H is a first determination value of the abnormal point, h=0 is determined to be normal, and h=1 is determined to be abnormal; count () is an operation for determining the number of times a child holds in brackets; val valve c Is the data after filling; val valve i A data value for the ith data within the time window T; n is the total number of data in the time window T; t is t d A set difference threshold; nums is a set number of times threshold.
The step S5 of performing abnormality determination on the filled data obtained in the step S3 by using a homonymous amplitude abnormality detection algorithm, specifically performing abnormality determination by using the following steps:
and c, detecting the amplitude abnormality in the same ratio between the data at the moment c in the filled data and the data at the moment c in the past days by adopting the following formula:
wherein V is a second determination value of the abnormal point, v=0 is determined to be normal, and v=1 is determined to be abnormal; val valve c (t) is data at time c of day t; val valve c (t-1) is data at time c of t-1 day; n is the past n days; alpha is the amplitude, andt s is a static threshold, and t s =min (MAX-AVG, AVG-MIN), MAX is the maximum value of the day-all data on which the value to be detected is located, AVG is the average value of the day-all data on which the value to be detected is located, and MIN is the minimum value of the day-all data on which the value to be detected is located.
And step S6, performing final power time series data abnormality detection according to the abnormality determination results obtained in the step S4 and the step S5, specifically performing abnormality determination by adopting the following rules:
if the first abnormal point determination value H obtained in the step S4 and the second abnormal point determination value V obtained in the step S5 are both 0, the determined power time sequence data is determined to be normal data;
if any one of the first determination value H of the abnormal point obtained in step S4 and the second determination value V of the abnormal point obtained in step S5 is 1, the determined power time series data is determined to be abnormal data.
The invention also discloses a filling method comprising the power time sequence data anomaly detection method, which further comprises the following steps:
s7, if the abnormal data is judged, calculating the value val according to the following formula m And replacing the abnormal data, thereby completing filling of the abnormal data:
middle val m Is padded data; val valve t Historical data at the moment corresponding to the abnormal data of the previous t days; t (T) t Is the size of the set time window.
The power time sequence data abnormality detection method and the filling method thereof provided by the invention judge whether filling data is needed for the missing condition of the power time sequence data, and fill the data by using a moving average method of daytime data; meanwhile, whether filling abnormality is considered for the filled data, and an abnormality detection method of combining a horizontal short-term loop ratio with a dynamic threshold and combining a longitudinal same-ratio amplitude with a static threshold is adopted to detect abnormal points; finally, correcting the data with abnormal detection by using a moving average method of data in the day; therefore, the method can realize the anomaly detection and filling of the power time sequence data, and is stable, reliable, high in accuracy and high in efficiency.
Drawings
FIG. 1 is a flow chart of the abnormality detection method according to the present invention.
FIG. 2 is a schematic diagram showing abnormality determination according to the method of the present invention.
FIG. 3 is a schematic flow chart of a filling method of the present invention.
Detailed Description
FIG. 1 is a flow chart of the abnormality detection method according to the present invention: the power time sequence data anomaly detection method provided by the invention comprises the following steps:
s1, acquiring power time sequence data to be analyzed;
after the data is acquired, the number of variables involved in the data needs to be determined, and the missing data processing operation can be directly carried out on the time sequence data of the single variable; however, for multiple variables, a variable singleness process is required to prevent multiple variables from affecting each other during the missing data fill process operation;
s2, judging the missing value of the data obtained in the step S1; specifically, the missing value determination is carried out by adopting the following steps:
if the power time sequence data is complete, the abnormal filling of the missing value is not needed;
if the proportion of the power time sequence data missing is higher than the set threshold value, the group of power time sequence data is directly discarded;
if the ratio of the power time series data missing is within the set threshold value range, the following determination is made again:
if the missing data is NA, judging the missing value according to the region where the transformer substation is located and the actual condition of the collected data;
if the missing data is 0, judging again according to the granularity division of the data acquisition source:
if the data is the data collected on the equipment with the area or finer granularity, the data is considered to be normal, and the missing abnormal condition is not required to be processed;
if the data are collected on substations of different voltage levels or coarser-granularity equipment, the data are determined to be abnormal, and the abnormal missing condition is required to be processed;
s3, filling missing data by adopting a daytime data moving average algorithm according to the missing value determined in the step S2; the method comprises the following steps:
filling missing data by adopting data at the same moment in the historical data:
middle val f Is a filling value; val valve h In the historical data corresponding to the missing data, the data values of the same time in the previous h days are obtained; t (T) h A time window size for the historical data;
s4, carrying out abnormality judgment on the data by adopting a short-term ring ratio abnormality detection algorithm according to the filled data obtained in the step S3; specifically, the abnormality determination is performed by the following steps:
setting a time window T, and comparing the filled data with each piece of data in the time window T: if the number of times that the difference between the filled data and the data in the time window T is greater than the set difference threshold exceeds the set number of times threshold, the filled data is determined to be an abnormal point:
wherein H is a first determination value of the abnormal point, h=0 is determined to be normal, and h=1 is determined to be abnormal; count () is an operation for determining the number of times a child holds in brackets; val valve c Is the data after filling; val valve i A data value for the ith data within the time window T; n is the total number of data in the time window T; t is t d A set difference threshold; nums is a set number of times threshold;
s5, carrying out abnormality judgment on the filled data obtained in the step S3 by adopting a homonymous amplitude abnormality detection algorithm; specifically, the abnormality determination is performed by the following steps:
and c, detecting the amplitude abnormality in the same ratio between the data at the moment c in the filled data and the data at the moment c in the past days by adopting the following formula:
wherein V is a second determination value of the abnormal point, v=0 is determined to be normal, and v=1 is determined to be abnormal; val valve c (t) is data at time c of day t; val valve c (t-1) is data at time c of t-1 day; n is the past n days; alpha is the amplitude, andt s is a static threshold, and t s =min (MAX-AVG, AVG-MIN), MAX being the maximum value of the day-all data on which the value to be detected is located, AVG being the average value of the day-all data on which the value to be detected is located, MIN being the minimum value of the day-all data on which the value to be detected is located;
the detection ideas of S4 and S5 are shown in FIG. 2;
s6, performing final power time sequence data anomaly detection according to the anomaly determination results obtained in the step S4 and the step S5; specifically, the abnormality determination is performed by adopting the following rules:
if the first abnormal point determination value H obtained in the step S4 and the second abnormal point determination value V obtained in the step S5 are both 0, the determined power time sequence data is determined to be normal data;
if any one of the first determination value H of the abnormal point obtained in the step S4 and the second determination value V of the abnormal point obtained in the step S5 is 1, the determined power time sequence data is determined to be abnormal data;
the expression is adopted, namely: is or operates; yc=0 indicates that the power timing data is normal data, and yc=1 indicates that the power timing data is normal data.
Fig. 3 is a schematic flow chart of a filling method of the method according to the present invention: the filling method comprising the power time sequence data anomaly detection method provided by the invention further comprises the following steps:
s7, if the abnormal data is judged, calculating the value val according to the following formula m And replacing the abnormal data, thereby completing filling of the abnormal data:
middle val m Is padded data; val valve t Historical data at the moment corresponding to the abnormal data of the previous t days; t (T) t Is the size of the set time window.
Claims (1)
1. A power time sequence data abnormality detection method comprises the following steps:
s1, acquiring power time sequence data to be analyzed;
s2, judging the missing value of the data obtained in the step S1; specifically, the missing value determination is carried out by adopting the following steps:
if the power time sequence data is complete, the abnormal filling of the missing value is not needed;
if the proportion of the power time sequence data missing is higher than a set threshold value, the group of power time sequence data is directly discarded;
if the ratio of the power time series data missing is within the set threshold value range, the following determination is made again:
if the missing data is NA, judging the missing value according to the region where the transformer substation is located and the actual condition of the collected data;
if the missing data is 0, judging again according to the granularity division of the data acquisition source:
if the data is the data collected on the equipment with the area or finer granularity, the data is considered to be normal, and the missing abnormal condition is not required to be processed;
if the data are collected on substations of different voltage levels or coarser-granularity equipment, the data are determined to be abnormal, and the abnormal missing condition is required to be processed;
s3, filling missing data by adopting a daytime data moving average algorithm according to the missing value determined in the step S2; the method comprises the following steps:
filling missing data by adopting data at the same moment in the historical data:
middle val f Is a filling value; val valve h In the historical data corresponding to the missing data, the data values of the same time in the previous h days are obtained; t (T) h A time window size for the historical data;
s4, carrying out abnormality judgment on the data by adopting a short-term ring ratio abnormality detection algorithm according to the filled data obtained in the step S3; specifically, the abnormality determination is performed by the following steps:
setting a time window T, and comparing the filled data with each piece of data in the time window T: if the number of times that the difference between the filled data and the data in the time window T is greater than the set difference threshold exceeds the set number of times threshold, the filled data is determined to be an abnormal point:
wherein H is a first determination value of the abnormal point, h=0 is determined to be normal, and h=1 is determined to be abnormal; count () is an operation for determining the number of times a child holds in brackets; val valve c Is the data after filling; val valve i Is a time windowA data value of the ith data in port T; n is the total number of data in the time window T; t is t d A set difference threshold; nums is a set number of times threshold;
s5, carrying out abnormality judgment on the filled data obtained in the step S3 by adopting a homonymous amplitude abnormality detection algorithm; specifically, the abnormality determination is performed by the following steps:
and c, detecting the amplitude abnormality in the same ratio between the data at the moment c in the filled data and the data at the moment c in the past days by adopting the following formula:
wherein V is a second determination value of the abnormal point, v=0 is determined to be normal, and v=1 is determined to be abnormal; val valve c (t) is data at time c of day t; val valve c (t-1) is data at time c of t-1 day; n is the past n days; alpha is the amplitude, andt s is a static threshold, and t s =min (MAX-AVG, AVG-MIN), MAX being the maximum value of the day-all data on which the value to be detected is located, AVG being the average value of the day-all data on which the value to be detected is located, MIN being the minimum value of the day-all data on which the value to be detected is located;
s6, performing final power time sequence data anomaly detection according to the anomaly determination results obtained in the step S4 and the step S5; specifically, the abnormality determination is performed by adopting the following rules:
if the first abnormal point determination value H obtained in the step S4 and the second abnormal point determination value V obtained in the step S5 are both 0, the determined power time sequence data is determined to be normal data;
if any one of the first determination value H of the abnormal point obtained in the step S4 and the second determination value V of the abnormal point obtained in the step S5 is 1, the determined power time sequence data is determined to be abnormal data;
s7, if the abnormal data is judged, calculating by adopting the following formulaThe value val obtained m And replacing the abnormal data, thereby completing filling of the abnormal data:
middle val m Is padded data; val valve t Historical data at the moment corresponding to the abnormal data of the previous t days; t (T) t Is the size of the set time window.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110335947.8A CN113077357B (en) | 2021-03-29 | 2021-03-29 | Power time sequence data anomaly detection method and filling method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110335947.8A CN113077357B (en) | 2021-03-29 | 2021-03-29 | Power time sequence data anomaly detection method and filling method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113077357A CN113077357A (en) | 2021-07-06 |
CN113077357B true CN113077357B (en) | 2023-11-28 |
Family
ID=76611538
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110335947.8A Active CN113077357B (en) | 2021-03-29 | 2021-03-29 | Power time sequence data anomaly detection method and filling method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113077357B (en) |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012089057A (en) * | 2010-10-22 | 2012-05-10 | Hitachi Engineering & Services Co Ltd | Facility state monitoring method, apparatus therefor and facility state monitoring program |
WO2016012972A1 (en) * | 2014-07-25 | 2016-01-28 | Suez Environnement | Method for detecting anomalies in a distribution network, in particular for drinking water |
CN107463633A (en) * | 2017-07-17 | 2017-12-12 | 中国航天系统科学与工程研究院 | A kind of real time data rejecting outliers method based on EEMD neutral nets |
CN107563539A (en) * | 2017-07-24 | 2018-01-09 | 佛山市顺德区中山大学研究院 | Short-term and long-medium term power load forecasting method based on machine learning model |
CN109299170A (en) * | 2018-10-25 | 2019-02-01 | 南京大学 | A kind of complementing method for tape label time series data |
CN109947812A (en) * | 2018-07-09 | 2019-06-28 | 平安科技(深圳)有限公司 | Consecutive miss value fill method, data analysis set-up, terminal and storage medium |
CN110865929A (en) * | 2019-11-26 | 2020-03-06 | 携程旅游信息技术(上海)有限公司 | Abnormity detection early warning method and system |
CN111340288A (en) * | 2020-02-25 | 2020-06-26 | 武汉墨锦创意科技有限公司 | Urban air quality time sequence prediction method considering space-time correlation |
CN111507412A (en) * | 2020-04-20 | 2020-08-07 | 南京工程学院 | Voltage missing value filling method based on historical data auxiliary scene analysis |
CN111695620A (en) * | 2020-06-08 | 2020-09-22 | 中国电力科学研究院有限公司 | Method and system for detecting and correcting abnormal data of time sequence of power system |
CN111967509A (en) * | 2020-07-31 | 2020-11-20 | 北京赛博星通科技有限公司 | Method and device for processing and detecting data acquired by industrial equipment |
CN111984514A (en) * | 2020-09-02 | 2020-11-24 | 大连大学 | Prophet-bLSTM-DTW-based log anomaly detection method |
CN112101482A (en) * | 2020-10-26 | 2020-12-18 | 西安交通大学 | Method for detecting abnormal parameter mode of missing satellite data |
CN112365070A (en) * | 2020-11-18 | 2021-02-12 | 深圳供电局有限公司 | Power load prediction method, device, equipment and readable storage medium |
CN112527788A (en) * | 2020-12-17 | 2021-03-19 | 北京中恒博瑞数字电力科技有限公司 | Method and device for detecting and cleaning abnormal value of transformer monitoring data |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11204602B2 (en) * | 2018-06-25 | 2021-12-21 | Nec Corporation | Early anomaly prediction on multi-variate time series data |
-
2021
- 2021-03-29 CN CN202110335947.8A patent/CN113077357B/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012089057A (en) * | 2010-10-22 | 2012-05-10 | Hitachi Engineering & Services Co Ltd | Facility state monitoring method, apparatus therefor and facility state monitoring program |
WO2016012972A1 (en) * | 2014-07-25 | 2016-01-28 | Suez Environnement | Method for detecting anomalies in a distribution network, in particular for drinking water |
CN107463633A (en) * | 2017-07-17 | 2017-12-12 | 中国航天系统科学与工程研究院 | A kind of real time data rejecting outliers method based on EEMD neutral nets |
CN107563539A (en) * | 2017-07-24 | 2018-01-09 | 佛山市顺德区中山大学研究院 | Short-term and long-medium term power load forecasting method based on machine learning model |
CN109947812A (en) * | 2018-07-09 | 2019-06-28 | 平安科技(深圳)有限公司 | Consecutive miss value fill method, data analysis set-up, terminal and storage medium |
CN109299170A (en) * | 2018-10-25 | 2019-02-01 | 南京大学 | A kind of complementing method for tape label time series data |
CN110865929A (en) * | 2019-11-26 | 2020-03-06 | 携程旅游信息技术(上海)有限公司 | Abnormity detection early warning method and system |
CN111340288A (en) * | 2020-02-25 | 2020-06-26 | 武汉墨锦创意科技有限公司 | Urban air quality time sequence prediction method considering space-time correlation |
CN111507412A (en) * | 2020-04-20 | 2020-08-07 | 南京工程学院 | Voltage missing value filling method based on historical data auxiliary scene analysis |
CN111695620A (en) * | 2020-06-08 | 2020-09-22 | 中国电力科学研究院有限公司 | Method and system for detecting and correcting abnormal data of time sequence of power system |
CN111967509A (en) * | 2020-07-31 | 2020-11-20 | 北京赛博星通科技有限公司 | Method and device for processing and detecting data acquired by industrial equipment |
CN111984514A (en) * | 2020-09-02 | 2020-11-24 | 大连大学 | Prophet-bLSTM-DTW-based log anomaly detection method |
CN112101482A (en) * | 2020-10-26 | 2020-12-18 | 西安交通大学 | Method for detecting abnormal parameter mode of missing satellite data |
CN112365070A (en) * | 2020-11-18 | 2021-02-12 | 深圳供电局有限公司 | Power load prediction method, device, equipment and readable storage medium |
CN112527788A (en) * | 2020-12-17 | 2021-03-19 | 北京中恒博瑞数字电力科技有限公司 | Method and device for detecting and cleaning abnormal value of transformer monitoring data |
Non-Patent Citations (6)
Title |
---|
Power Consumption Predicting and Anomaly Detection Based on Long Short-Term Memory Neural Network;Xiaohui Wang等;《2019 IEEE 4th International Conference on Cloud Computing and Big Data Analysis》;487-491 * |
Power Equipment Anomaly Detection Based on Spatiotemporal Clustering;Yucheng Chen等;《2016 International Conference on Condition Monitoring and Diagnosis(CMD)》;392-395 * |
一种基于滑动窗口的时间序列异常检测算法;裴丽鹊;《巢湖学院学报》;第13卷(第3期);28-31 * |
基于最小二乘支持向量机算法的测量数据时序异常检测方法;倪景峰;《华北电力大学学报(自然科学版)》;第132卷(第3期);62-66 * |
时序遥测数据异常检测方法研究;康旭;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》(第2期);C031-726 * |
电力感知数据的异常模式检测;余斌;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;C042-1682 * |
Also Published As
Publication number | Publication date |
---|---|
CN113077357A (en) | 2021-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116702081B (en) | Intelligent inspection method for power distribution equipment based on artificial intelligence | |
CN117411189B (en) | Monitoring data enhancement method of micro-grid coordination controller | |
CN110716155B (en) | Low-voltage power supply loop abnormal working condition perception algorithm and device | |
CN116990626B (en) | Alternating current power grid voltage transmission state monitoring method and system | |
CN107654342A (en) | A kind of abnormal detection method of Wind turbines power for considering turbulent flow | |
CN109491238A (en) | Subway platform accelerator control system controller redundancy approach | |
CN110187242A (en) | A kind of power distribution network abnormality detection and localization method based on spatio-temporal correlation analysis | |
CN105137213A (en) | Data communication real-time diagnosis system and method | |
CN113077357B (en) | Power time sequence data anomaly detection method and filling method thereof | |
CN115047288A (en) | Transformer area fault positioning method and device based on power acquisition terminal | |
CN108832630B (en) | Power grid CPS prevention control method based on expected accident scene | |
CN116908524B (en) | Abnormal sensing monitoring system of building electrical system based on artificial intelligence | |
CN107991583B (en) | Alternating current outlet fault judgment method and system for converter station of flexible direct current transmission system | |
CN107437816A (en) | A kind of system and method for family energy-storage system dynamic regulation partial electric grid quality | |
CN116260250B (en) | Intelligent monitoring system for high-frequency switch direct-current power supply | |
CN112595906A (en) | Method for judging abnormal operation of transformer area | |
CN112924813A (en) | Power distribution network short-circuit fault monitoring method and device based on electrical data | |
Nakmali et al. | A new hybrid approach to thevenin equivalent estimation for voltage stability monitoring | |
CN117882261A (en) | Predicting grid frequency | |
CN113418632A (en) | Conceptual drift detection method for oil temperature prediction of oil-immersed transformer | |
CN113311352A (en) | Power inverter fault detection method based on output signal analysis | |
CN114047372B (en) | Voltage characteristic-based platform region topology identification system | |
CN117633695B (en) | Transformer operation monitoring method based on electrical parameter time sequence analysis | |
CN116916166B (en) | Telemetry terminal based on AI image analysis | |
CN117937766B (en) | Intelligent management system for energy storage cabinet |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |