CN112101765A - Abnormal data processing method and system for operation index data of power distribution network - Google Patents
Abnormal data processing method and system for operation index data of power distribution network Download PDFInfo
- Publication number
- CN112101765A CN112101765A CN202010934503.1A CN202010934503A CN112101765A CN 112101765 A CN112101765 A CN 112101765A CN 202010934503 A CN202010934503 A CN 202010934503A CN 112101765 A CN112101765 A CN 112101765A
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- cluster
- operation index
- distribution network
- 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.)
- Pending
Links
Images
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a method and a system for processing abnormal data of operation index data of a power distribution network, wherein the method comprises the following steps: acquiring real-time operation index data of the power distribution network; clustering the real-time operation index data at the current moment, and dividing the cluster into a normal cluster, a suspected cluster and an abnormal cluster according to the cluster density; calculating the abnormality degree of the data at the current moment according to the Manhattan distance; and identifying abnormal data according to the cluster to which the data belongs and the abnormal degree. The method is based on cluster analysis and abnormal degree analysis, realizes comprehensive judgment of abnormal data, and is higher in accuracy.
Description
Technical Field
The invention belongs to the technical field of power distribution network data processing, and particularly relates to a power distribution network operation index data abnormal data processing method and system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the accelerated construction of modern power distribution networks, production management systems, scheduling management systems, power marketing 95598 systems, distribution network automation systems and the like are widely applied, and the informatization and automation levels of the power distribution networks are greatly improved. A large amount of power distribution network operation data are recorded in each system, wherein implicit rules of power distribution network operation are contained, and the system has important significance for guiding the safe operation of the power distribution network. At present, the data of the power distribution network presents the following characteristics: (1) the data volume of the power distribution network is large, and abnormal conditions exist in the data; (2) in metrology data, where large amounts of data are repetitive and similar, noisy data exists. How to manage, clean and handle data becomes the work of studying distribution network data mining and accomplishing first.
The inventor finds that with the construction of data acquisition of a power distribution network, problems such as large data, data missing, data noisy and the like occur, and at present, a relevant solution has been provided for data missing filling and data abnormal value identification, but at present, data abnormal value identification is usually determined only according to the overall time change trend of data, and if adjacent data is also abnormal or missing, the identification accuracy of the abnormal value is affected, and data filling also mainly depends on data of adjacent time, and the accuracy can not be guaranteed.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a method and a system for processing abnormal data of operation index data of a power distribution network, which realize comprehensive judgment of the abnormal data in cluster analysis and abnormal degree analysis and have higher accuracy.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
a method for processing abnormal data of operation index data of a power distribution network comprises the following steps:
acquiring real-time operation index data of the power distribution network;
clustering the real-time operation index data at the current moment, and dividing the cluster into a normal cluster, a suspected cluster and an abnormal cluster according to the cluster density;
calculating the abnormality degree of the data at the current moment according to the Manhattan distance;
and identifying abnormal data according to the cluster to which the data belongs and the abnormal degree.
One or more embodiments provide a power distribution network operation index data exception data processing system, which includes:
the data acquisition module is used for acquiring real-time operation index data of the power distribution network;
the data clustering module is used for clustering the real-time operation index data at the current moment and dividing the clustering clusters into normal clusters, suspected clusters and abnormal clusters according to the clustering cluster density;
the abnormality degree calculation module is used for calculating the abnormality degree of the data at the current time according to the Manhattan distance;
and the abnormal data identification module is used for identifying abnormal data according to the cluster to which the data belongs and the abnormal degree.
One or more embodiments provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the processor implements the method for processing abnormal data of operation index data of a power distribution network.
One or more embodiments provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method for processing abnormal data of operation index data of a power distribution network.
The above one or more technical solutions have the following beneficial effects:
(1) the invention provides an algorithm combining clustering and abnormal degree, which is characterized in that abnormal data clusters are preliminarily judged by carrying out data clustering on distribution network operation index data, and then abnormal degree judgment is carried out, so that the accuracy of abnormal point data identification is increased by double judgment.
(2) The method and the device can be used for repairing the abnormal data points based on the similar normal data points instead of the temporally adjacent normal data points, so that the accuracy of the data is improved, the quality and the accuracy of the follow-up analysis decision results are improved, and the accurate mastering of the running condition of the power distribution network is realized.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a flowchart of a method for processing abnormal data of operation index data of a power distribution network in an embodiment of the invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
The embodiment provides a method for processing abnormal data of operation index data of a power distribution network, which comprises the following steps:
step 1: acquiring real-time operation index data of the power distribution network;
n pieces of operation index data are arranged, and each data has m dimensions, S (t)0) Collecting data samples for the current time, different times tkThe collected power distribution network operation index data sample is S (t)k)。
Step 2: clustering the real-time operation index data at the current moment, and dividing the cluster into a normal cluster, a suspected cluster and an abnormal cluster according to the cluster density;
the step 1 specifically comprises:
(1) calculating the correlation coefficient of each data point in the data set D and the rest n-1 data points;
suppose Xi、XjE.g. D, correlation coefficient
And the correlation coefficient can be used for calculating the correlation between any two power distribution network operation index data.
Wherein the content of the first and second substances,
as data XiIs located in the center of the (c),
as data XjOf the center of (c).
(2) Calculating correlation coefficients among the data, arranging the n average correlation coefficients in a descending order, selecting the data with high K correlation coefficients as a K-Means clustering center, and starting clustering;
wherein the average correlation coefficient is
(3) Calculating the density rho of k cluster clusterszSetting rhoz<0.0002 was classified as abnormal data, 0.0002<ρz<0.0005 is a suspected cluster, ρz>0.0005 for normal cluster.
Wherein the density of the aggregated clusters
Wherein Q iszAnd V is the volume of the cluster enclosing ball with the average correlation coefficient of the cluster center of the cluster as the radius.
And step 3: calculating the abnormality degree of the data at the current moment according to the Manhattan distance;
consider the timing sequence of data, assume SC(t-1) Is distribution network operation index data at the time of t-1, gamma (S)C(t-1) Represents a pair SC(t-1) Result of sampling of (1), S+(t0) For the data set to be detected:
γ(SC(t-1))∪S(t0)→S+(t0)
the operation index data of the power distribution network has the following characteristics: 1) outliers are easy to gather, such as zero values or outliers caused by scrambling codes due to communication errors are mostly similar; 2) considering abnormal value distribution, a power distribution network line or communication network fault can generate a large amount of null data in the same period. Based on the above characteristics of the index data, in consideration of the time sequence characteristics of the data, the present embodiment incorporates part of the previous-time data for enhancing the robustness of the sample, thereby increasing the accuracy of detecting the data set.
Assuming S as the set S to be detected+(t0) A point of (1) set as an analysis target region radius RAD(s) a manhattan length from the kth object of d (i, j) ═ Σ | xik-xjk|。
Set S to be detected+(t0) The ith node in the node is si,siThe abnormality degree calculation method of (2) is as follows:
wherein N isk(si) Is represented by siCentered, a minimum-range dataset containing k objects, i.e., a set of these k objects; rAD(si) Radius representing the minimum range, i.e. point siThe minimum value of the manhattan length between the other points in the range; | Nk(si) I represents the set Nk(si) The number of data in.
Point p is set Nk(si) Any point in (1)rdk(p) is from point p to point siIs reached.
Point siThe reachable distance from point p is: rEA(si,p)＝max{RAD(p),d(siP) in which R isAD(p) represents the radius of the minimum range containing k objects centered on p, i.e., the minimum value of the Manhattan length between point p and each of the other points in the range, where the minimum distance is RAD(p)；d(siP) represents a point siAnd the manhattan length between point p.
Nk(p) minimum range dataset containing k objects centered on p, lrdk(si) Is a part Nk(p) the inverse of the average achievable distance density in the set.
And step 3: according to the cluster to which the data belongs and the abnormal degree, abnormal data identification is carried out;
specifically, the abnormality degree L is setOF(si) And if the threshold value is exceeded, judging the data to be suspected abnormal.
If the data is lower than the abnormality degree LOF(si) If the threshold is the data in the suspected cluster or the abnormal cluster, the data is considered as the abnormal point.
And 4, step 4: and repairing the abnormal data according to the neighboring normal data.
Specifically, the step 4 includes:
(1) calculating Euclidean distances between each abnormal data and all data in the normal data cluster, and selecting k data with the minimum distance to the abnormal data as a nearest neighbor normal data set of the abnormal data;
(2) and repairing the abnormal data according to the nearest neighbor normal data set.
Specifically, weights are assigned to normal data in the nearest neighbor normal data set according to the Euclidean distance from the abnormal data, and the closer the distance, the higher the weight, the farther the distance, the lower the weight. And taking the weighted average value of the nearest neighbor normal data as a repair estimation value of the abnormal data, and replacing the abnormal point with the estimation value.
According to the method and the device, abnormal data of the operation index data of the power distribution network can be effectively identified, the quality and the precision of a follow-up analysis decision result are improved, the accurate grasping of the operation condition of the power distribution network is facilitated, and the operation index data is fully and reasonably utilized to guide the production work of the power distribution network in the follow-up process.
Example two
The purpose of this embodiment is to provide a distribution network operation index data exception data processing system, includes:
the data acquisition module is used for acquiring real-time operation index data of the power distribution network;
the data clustering module is used for clustering the real-time operation index data at the current moment and dividing the clustering clusters into normal clusters, suspected clusters and abnormal clusters according to the clustering cluster density;
the abnormality degree calculation module is used for calculating the abnormality degree of the data at the current time according to the Manhattan distance;
and the abnormal data identification module is used for identifying abnormal data according to the cluster to which the data belongs and the abnormal degree.
Furthermore, the system also comprises an abnormal data repairing module which is used for repairing the abnormal data according to the neighbor normal data.
EXAMPLE III
The embodiment aims at providing an electronic device.
An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program, comprising:
acquiring real-time operation index data of the power distribution network;
clustering the real-time operation index data at the current moment, and dividing the cluster into a normal cluster, a suspected cluster and an abnormal cluster according to the cluster density;
calculating the abnormality degree of the data at the current moment according to the Manhattan distance;
and identifying abnormal data according to the cluster to which the data belongs and the abnormal degree.
Example four
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, performs the steps of:
acquiring real-time operation index data of the power distribution network;
clustering the real-time operation index data at the current moment, and dividing the cluster into a normal cluster, a suspected cluster and an abnormal cluster according to the cluster density;
calculating the abnormality degree of the data at the current moment according to the Manhattan distance;
and identifying abnormal data according to the cluster to which the data belongs and the abnormal degree.
The steps involved in the apparatuses of the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A method for processing abnormal data of operation index data of a power distribution network is characterized by comprising the following steps:
acquiring real-time operation index data of the power distribution network;
clustering the real-time operation index data at the current moment, and dividing the cluster into a normal cluster, a suspected cluster and an abnormal cluster according to the cluster density;
calculating the abnormality degree of the data at the current moment according to the Manhattan distance;
and identifying abnormal data according to the cluster to which the data belongs and the abnormal degree.
2. The method for processing the abnormal data of the operation index data of the power distribution network according to claim 1, wherein clustering the real-time operation index data at the current moment comprises:
for each data, calculating a correlation coefficient of the data with other respective data;
calculating the average correlation coefficient of the data and other data;
and clustering by using the set number data with the highest average correlation coefficient as a clustering center.
3. The method for processing abnormal data of operation index data of a power distribution network according to claim 1, wherein the cluster density is the volume of a cluster surrounding sphere, in which the cluster number is the number of data in the cluster/the cluster surrounding sphere takes an average correlation coefficient as a radius.
4. The method for processing abnormal data of operation index data of a power distribution network according to claim 1, wherein calculating the degree of abnormality of the data at the current time based on the manhattan distance comprises:
sampling the operation index data of the power distribution network at the previous moment, and taking the union of the sampled data and the data at the current moment as a data set to be detected;
and calculating the abnormality degree of each data in the data set to be detected.
5. The method for processing the abnormal data of the operation index data of the power distribution network according to claim 1, wherein the identification of the abnormal data according to the cluster to which the data belongs and the abnormal degree comprises the following steps: and if the data abnormality degree exceeds a set threshold and belongs to the suspected cluster or the abnormal cluster, the abnormal data is determined.
6. The method for processing abnormal data of operation index data of power distribution network according to claim 1, wherein the method further comprises: and repairing the abnormal data according to the neighboring normal data.
7. The method for processing the abnormal data of the operation index data of the power distribution network according to claim 6, wherein the repairing the abnormal data comprises the following steps:
calculating Euclidean distances between each abnormal data and all data in the normal data cluster, and selecting k data with the minimum distance to the abnormal data as a nearest neighbor normal data set of the abnormal data;
according to the Euclidean distance from the abnormal data, distributing weight to normal data in the nearest neighbor normal data set, wherein the weight is larger when the distance is closer;
and taking the weighted average value of the nearest neighbor normal data as the repair estimation value of the abnormal data.
8. The utility model provides a distribution network operation index data exception data processing system which characterized in that includes:
the data acquisition module is used for acquiring real-time operation index data of the power distribution network;
the data clustering module is used for clustering the real-time operation index data at the current moment and dividing the clustering clusters into normal clusters, suspected clusters and abnormal clusters according to the clustering cluster density;
the abnormality degree calculation module is used for calculating the abnormality degree of the data at the current time according to the Manhattan distance;
and the abnormal data identification module is used for identifying abnormal data according to the cluster to which the data belongs and the abnormal degree.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for processing abnormal data of operation index data of power distribution network according to any one of claims 1 to 7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method for processing abnormal data of operation index data of a power distribution network according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010934503.1A CN112101765A (en) | 2020-09-08 | 2020-09-08 | Abnormal data processing method and system for operation index data of power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010934503.1A CN112101765A (en) | 2020-09-08 | 2020-09-08 | Abnormal data processing method and system for operation index data of power distribution network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112101765A true CN112101765A (en) | 2020-12-18 |
Family
ID=73752168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010934503.1A Pending CN112101765A (en) | 2020-09-08 | 2020-09-08 | Abnormal data processing method and system for operation index data of power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101765A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662464A (en) * | 2022-12-29 | 2023-01-31 | 广州市云景信息科技有限公司 | Method and system for intelligently identifying environmental noise |
| CN116111727A (en) * | 2023-04-13 | 2023-05-12 | 盛锋电力科技有限公司 | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold |
| CN116304763A (en) * | 2023-05-18 | 2023-06-23 | 国网山东省电力公司日照供电公司 | Power data pre-analysis method, system, equipment and medium |
| CN116502169A (en) * | 2023-06-28 | 2023-07-28 | 深圳特力自动化工程有限公司 | Centrifugal dehydrator working state detection method based on data detection |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160104945A (en) * | 2015-02-27 | 2016-09-06 | 충북대학교 산학협력단 | Apparatus and Method for Evaluating Outlierness based on Data Association |
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| CN109753991A (en) * | 2018-12-06 | 2019-05-14 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| CN110287256A (en) * | 2019-06-14 | 2019-09-27 | 南京邮电大学 | A kind of electric network data parallel processing system (PPS) and its processing method based on cloud computing |
-
2020
- 2020-09-08 CN CN202010934503.1A patent/CN112101765A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160104945A (en) * | 2015-02-27 | 2016-09-06 | 충북대학교 산학협력단 | Apparatus and Method for Evaluating Outlierness based on Data Association |
| CN109753991A (en) * | 2018-12-06 | 2019-05-14 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| CN110287256A (en) * | 2019-06-14 | 2019-09-27 | 南京邮电大学 | A kind of electric network data parallel processing system (PPS) and its processing method based on cloud computing |
Non-Patent Citations (4)
| Title |
|---|
| ZENGYOU HE ET AL.: "Discovering cluster-based local outliers", PATTERN RECOGNITION LETTERS, no. 24, pages 1641 - 1650 * |
| 刘方方: "高耗能设备能耗异常的在线预警模型研究", 中国优秀硕士学位论文全文数据库 信息科技辑, pages 140 - 1120 * |
| 尹娜 等: "基于混合式聚类算法的离群点挖掘在异常检测中的应用研究", 计算机科学, vol. 44, no. 5, pages 116 - 119 * |
| 郝胜轩: "基于近邻噪声处理的KNN缺失数据填补算法", 计算机仿真, vol. 31, no. 7, pages 264 - 268 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662464A (en) * | 2022-12-29 | 2023-01-31 | 广州市云景信息科技有限公司 | Method and system for intelligently identifying environmental noise |
| CN116111727A (en) * | 2023-04-13 | 2023-05-12 | 盛锋电力科技有限公司 | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold |
| CN116304763A (en) * | 2023-05-18 | 2023-06-23 | 国网山东省电力公司日照供电公司 | Power data pre-analysis method, system, equipment and medium |
| CN116304763B (en) * | 2023-05-18 | 2023-10-24 | 国网山东省电力公司日照供电公司 | Power data pre-analysis method, system, equipment and medium |
| CN116502169A (en) * | 2023-06-28 | 2023-07-28 | 深圳特力自动化工程有限公司 | Centrifugal dehydrator working state detection method based on data detection |
| CN116502169B (en) * | 2023-06-28 | 2023-08-22 | 深圳特力自动化工程有限公司 | Centrifugal dehydrator working state detection method based on data detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112101765A (en) | Abnormal data processing method and system for operation index data of power distribution network | |
| US11915104B2 (en) | Normalizing text attributes for machine learning models | |
| CN109587008B (en) | Method, device and storage medium for detecting abnormal flow data | |
| CN112148955A (en) | Method and system for detecting abnormal time sequence data of Internet of things | |
| US20240020514A1 (en) | Improper neural network input detection and handling | |
| CN107679734A (en) | It is a kind of to be used for the method and system without label data classification prediction | |
| CN109033513B (en) | Power transformer fault diagnosis method and power transformer fault diagnosis device | |
| JP2020123951A (en) | Method, apparatus, and device, for predicting failure of optical module | |
| CN109257383B (en) | BGP anomaly detection method and system | |
| CN111428201B (en) | Prediction method for time series data based on empirical mode decomposition and feedforward neural network | |
| CN111738520A (en) | System load prediction method fusing isolated forest and long-short term memory network | |
| CN114861788A (en) | Load abnormity detection method and system based on DBSCAN clustering | |
| CN114912720A (en) | Memory network-based power load prediction method, device, terminal and storage medium | |
| CN114564345A (en) | Server abnormity detection method, device, equipment and storage medium | |
| CN117131022B (en) | Heterogeneous data migration method of electric power information system | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN116760728A (en) | High-speed data stream-oriented general stream level filtering method | |
| CN115511012B (en) | Class soft label identification training method with maximum entropy constraint | |
| CN116383645A (en) | Intelligent system health degree monitoring and evaluating method based on anomaly detection | |
| CN113255775B (en) | Method and device for identifying abnormal data of power system and intelligent chip | |
| CN115562940A (en) | Load energy consumption monitoring method and device, medium and electronic equipment | |
| CN112083707A (en) | Industrial control physical signal processing method, controller and processing system | |
| CN113128574A (en) | Scene reduction method and device and terminal equipment | |
| CN113919610A (en) | ARIMA model construction method and evaluation method for low-voltage transformer area line loss prediction | |
| Kosela et al. | Tracking of Spermatozoa by YOLOv5 Detection and StrongSORT with OSNet Tracker |
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 |