CN112288597A - Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm - Google Patents
Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm Download PDFInfo
- Publication number
- CN112288597A CN112288597A CN202011329439.0A CN202011329439A CN112288597A CN 112288597 A CN112288597 A CN 112288597A CN 202011329439 A CN202011329439 A CN 202011329439A CN 112288597 A CN112288597 A CN 112288597A
- Authority
- CN
- China
- Prior art keywords
- cluster
- data
- energy consumption
- feature
- clusters
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 9
- 238000012163 sequencing technique Methods 0.000 claims abstract description 6
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims abstract description 3
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- 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
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an energy consumption online anomaly detection method based on hierarchical clustering and a histogram algorithm, which comprises the following steps: s1, extracting historical data of the established model, including energy consumption time series data and characteristic data; s2, cleaning data and filtering abnormal data; s3, dividing the feature clusters and distributing samples for each feature data; s4, calculating the cluster sample number and the cluster center of the feature clusters, and sequencing the feature clusters from small to large according to the sample number; s5, judging whether the number of the feature clusters is larger than N or whether the number of samples of one cluster is smaller than M, if so, entering a step S6, otherwise, entering a step S7; s6, clustering the feature clusters by adopting a hierarchical clustering algorithm, calculating the cluster sample number and the cluster center of the new feature clusters, and returning to the step S5; and S7, calculating the upper and lower limit threshold values of each feature cluster by adopting a dynamically adjusted box line graph method. The invention can realize the generation of a rapid detection model of the energy consumption data and the data detection.
Description
Technical Field
The invention relates to the technical field of energy consumption abnormity detection, in particular to an energy consumption online abnormity detection method based on hierarchical clustering and a histogram algorithm.
Background
With the development of industry 4.0 and energy internet, energy consumption data acquisition and energy consumption data monitoring can help enterprises to carry out more intelligent management on the use condition of energy. However, due to the increase of the number of the accessed devices and meters, the validity and accuracy of the data become more important, and meanwhile, the system platform end needs to analyze big data of historical energy consumption data to realize online detection of the energy consumption data uploaded by each communication module and judge the abnormal condition of the energy consumption data. Therefore, a fast and stable power consumption anomaly detection algorithm is needed.
Disclosure of Invention
The invention aims to overcome the defects in the background art, and provides an energy consumption online anomaly detection method based on hierarchical clustering and a histogram algorithm, which can realize the generation of a rapid detection model of energy consumption data and the data detection, can realize the respective processing of acquisition anomalies and energy consumption anomalies, and can perform clustering and clustering on samples and calculate a cluster threshold value by combining the histogram calculation of characteristic data and the hierarchical clustering algorithm of the characteristic clusters to form a whole threshold value model.
In order to achieve the technical effects, the invention adopts the following technical scheme:
an energy consumption online anomaly detection method based on hierarchical clustering and a histogram algorithm comprises the following steps:
s1, extracting historical data of the established model, including energy consumption time series data and characteristic data;
s2, cleaning data and filtering abnormal data;
s3, dividing the feature clusters and distributing samples for each feature data;
s4, calculating the cluster sample number and the cluster center of the feature clusters, and sequencing the feature clusters from small to large according to the sample number;
s5, judging whether the number of the feature clusters is larger than N or whether the number of samples of one cluster is smaller than M, if so, entering a step S6, otherwise, entering a step S7;
s6, clustering the feature clusters by adopting a hierarchical clustering algorithm, calculating the cluster sample number and the cluster center of the new feature clusters, and returning to the step S5;
s7, calculating an upper limit threshold and a lower limit threshold of each feature cluster by adopting a dynamically adjusted box line graph method;
s8, repeating the steps S3 to S7 until all the feature data are subjected to threshold value calculation and a threshold value set of the features is formed.
Further, the characteristic data is used for multi-dimensional and multi-scene identification of the dimension and scene containing time, climate and production.
Further, the step S2 includes obtaining thresholds of the sequence data and the feature data by using a box-plot method, and eliminating data points that are not within the threshold range, and this step is mainly to clean data that are incorrectly reported and missed to be reported due to reasons such as communication abnormality, etc., so as to eliminate the influence caused by data errors as much as possible, and establish a basis for better energy consumption abnormality detection.
Further, the steps S3 and S4 include:
setting a maximum clustering number N and a minimum sample number M in the clusters;
for continuous characteristic data, averagely cutting the continuous characteristic data into a.N histograms in a continuous characteristic value range, wherein each histogram represents a value interval, namely a cluster of one characteristic, and a is the cutting precision;
for the discrete type features, taking each discrete variable different from each other as a cluster of the features;
let the cluster set of features be denoted as C ═ C1,c2,…,ciAnd allocating the energy consumption time series data to a set corresponding to the cluster, and calculating the number of samples of the cluster and the cluster center, wherein the cluster center is the average value of all the samples of the cluster.
Further, the step S6 includes:
and (4) clustering the feature clusters by adopting a hierarchical clustering algorithm, sequencing the feature clusters from small to large according to the number of samples, combining the clusters with the closest centers of the two clusters, calculating the cluster centers and the cluster sample numbers of the new feature clusters, and returning to the step S5 after reordering the new feature clusters.
Further, the step S7 includes:
calculating the upper and lower limit threshold values of each feature cluster by adopting a dynamically adjusted box curve method:
th=q3+k×(q3-q1),tl=q1-k×(q3-q1);
where th denotes an upper threshold, tl denotes a lower threshold, q1And q is3Sample data representing 1/4 and 3/4 quantiles of feature clusters, respectively; the value of k is according to the following formula:
wherein n issampleIs the total number of samples of the energy consumption time series data, nciIs a cluster ciThe number of samples of (a); it can be seen that a tight threshold is used when the number of samples in a cluster is large, whereas a wide threshold is used when there are few samples.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to an energy consumption online anomaly detection method based on hierarchical clustering and a histogram algorithm, which can detect energy consumption data of enterprises and energy consumption comprehensive bodies from different angles, aims to find energy consumption scenes for detection under different energy consumption characteristic data, and then performs anomaly analysis, such as scenes of off-season, high-energy season, summer, winter and the like of industrial production, and needs to start with dimensions of production data or weather data and the like due to different energy consumption modes.
Drawings
FIG. 1 is a schematic flow chart of the method for detecting online abnormal energy consumption based on hierarchical clustering and histogram algorithm.
FIG. 2 is a schematic diagram of an energy consumption online anomaly detection system of the present invention.
Detailed Description
The invention will be further elucidated and described with reference to the embodiments of the invention described hereinafter.
Example (b):
the first embodiment is as follows:
as shown in fig. 1, an energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm includes the following steps:
step 1, extracting historical data needing to be modeled, including recent energy consumption time series data S and other same characteristic data P ═ P1,P1,...PmAnd (4) feature data used for multi-dimensional and multi-scene identification including time, climate, production and the like.
And 2, cleaning data.
For the energy consumption time series data S, firstly discarding the missing report data, and then calculating the threshold of the energy consumption time series data by using a Boxplot (Boxplot) method, which specifically comprises the following steps: 1/4 quantiles and 3/4 quantiles for calculating the energy consumption time series data S are respectively marked as q1And q is3And if the upper and lower thresholds are th and tl respectively, the specific calculation formula is as follows: th is q3+k×(q3-q1),tl=q1-k×(q3-q1). Typically k is taken as [1.5, 3 ]]In this embodiment, k is 3.
Then, data points in the energy consumption time-series data S that are not within the threshold range are corrected to boundary values, and when there is a sufficient number of data, data values that exceed the boundary may be removed.
The method mainly aims to clean the data which are mistakenly reported and missed reported due to the reasons of communication abnormity and the like, and aims to eliminate the influence caused by data errors as much as possible and establish a basis for better energy consumption abnormity detection.
Step 3, aiming at each time series characteristic data PiCarrying out scene clustering on the energy consumption time sequence data S, and specifically comprising the following steps: setting maximum convergenceThe number of classes N and the minimum number of samples M in the classes, for the continuous type features, in the value range of the continuous features, the continuous type features are averagely cut into a.N histograms, each histogram represents a value interval and represents a cluster (namely a scene) of the features, wherein a is the cutting precision; for discrete features, each discrete variable different from each other is taken as a cluster of features.
Let the cluster set of features be denoted as C ═ C1,c2,…,ciAnd allocating the energy consumption time series data S to a set corresponding to the cluster, and calculating the number of samples of the cluster and the cluster center, wherein the cluster center is the average value of all the samples in the cluster.
And 4, judging whether the number of the feature clusters is greater than N or whether the number of samples of one of the feature clusters is less than M or not for each feature cluster, if so, entering the step 5, and otherwise, entering the step 6.
And 5, clustering the feature clusters by adopting a hierarchical clustering algorithm, firstly, sequencing the feature clusters from small to large according to the number of samples, combining the feature clusters with the two closest cluster centers because the number of the feature clusters is more than N or the number of the samples of the clusters is less than M, recalculating the cluster centers and the cluster sample numbers of the new clusters, and returning to the step 4 to judge again.
Step 6, calculating the upper and lower limit threshold values of each feature cluster by adopting a dynamically adjusted box curve method: th is q3+k×(q3-q1),tl=q1-k×(q3-q1);
Where th denotes an upper threshold, tl denotes a lower threshold, q1And q is3Sample data representing 1/4 and 3/4 quantiles of feature clusters, respectively; the value of k is according to the following formula:
wherein n issampleIs the total number of samples of the energy consumption time series data, nciIs a cluster ciThe number of samples.
And 7, repeating the steps 3 to 6 until all the characteristics are calculated to form a threshold value set of the characteristics.
Example two
As shown in fig. 2, a detection target of the online energy consumption anomaly detection system is mainly divided into data acquisition anomaly and energy consumption anomaly, the data acquisition anomaly refers to an anomaly obtained by incorrectly acquiring reasons such as sensor failure, and the energy consumption anomaly refers to an anomaly occurring in the use process of energy consumption data.
Specifically, the online energy consumption anomaly detection system of this embodiment specifically includes: the system comprises a model generation sub-module, an online detection sub-module, an abnormality detection scheduler and a database. The anomaly detection scheduler is used for managing the model generation submodule and the online detection submodule and comprises a model updating interval, an automatic detection interval and communication data transmitted between the model generation submodule and the online detection submodule, the model generation submodule extracts data from the database, generates a model and stores the model in the database, and the online detection submodule is used for extracting the model stored in the database to detect the data monitored online to obtain an anomaly tag and storing the anomaly tag in the database.
Specifically, when the model generation submodule works, the method includes:
setting the size and frequency of an acquired time window, wherein the size of the time window mainly controls the calculation speed and the long-term dependence degree, the frequency is specifically the acquired time sequence frequency such as minutes, hours, days and the like, and then acquiring energy consumption time sequence data and characteristic data by referring to the set parameters; finally, for each acquisition, a model is established in the first embodiment for calculation, and finally, acquisition abnormal threshold values including a lower threshold value tl and an upper threshold value th are obtained, and a characteristic threshold value set is obtained.
When the online detection submodule works, a stored model is called for new data collected by each collection point, and abnormality detection is carried out, and the online detection submodule specifically comprises the following steps: detecting acquired data by calling abnormal thresholds tl and th, if the acquired data is out of a threshold range, marking the data as acquisition abnormality and returning, in the embodiment, marking the abnormal data as 1, otherwise, marking the data as 0, then, collecting corresponding feature data at the same moment, detecting a feature cluster where each feature is located according to each feature, obtaining a threshold of the feature cluster, if the value of the feature data is not in the threshold range, marking the feature cluster as energy consumption abnormality (specifically marking as 1 in the embodiment), and if the feature data does not exist, skipping; and finally, after all the characteristic anomaly detection labels are obtained, the results can be weighted and averaged according to the characteristic weight set by experience, and then rounded to obtain the final anomaly label, and then the results are returned to the database.
It can be known that the energy consumption online anomaly detection system of the embodiment can simultaneously realize the marking of the collected anomaly data and the marking of the energy consumption anomaly data.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (6)
1. An energy consumption online anomaly detection method based on hierarchical clustering and a histogram algorithm is characterized by comprising the following steps:
s1, extracting historical data of the established model, including energy consumption time series data and characteristic data;
s2, cleaning data and filtering abnormal data;
s3, dividing the feature clusters and distributing samples for each feature data;
s4, calculating the cluster sample number and the cluster center of the feature clusters, and sequencing the feature clusters from small to large according to the sample number;
s5, judging whether the number of the feature clusters is larger than N or whether the number of samples of one cluster is smaller than M, if so, entering a step S6, otherwise, entering a step S7;
s6, clustering the feature clusters by adopting a hierarchical clustering algorithm, calculating the cluster sample number and the cluster center of the new feature clusters, and returning to the step S5;
s7, calculating an upper limit threshold and a lower limit threshold of each feature cluster by adopting a dynamically adjusted box line graph method;
s8, repeating the steps S3 to S7 until all the feature data are subjected to threshold value calculation and a threshold value set of the features is formed.
2. The method for detecting the online abnormal energy consumption based on the hierarchical clustering and the histogram algorithm as claimed in claim 1, wherein the characteristic data is characteristic data for identifying multiple dimensions and multiple scenes including time, climate, production dimension and scene.
3. The method for detecting the online abnormality of energy consumption based on the hierarchical clustering and histogram algorithm as claimed in claim 1, wherein the step S2 includes using a box-line graph method to find thresholds of the sequence data and the characteristic data, and eliminating or correcting data points not within the threshold range to boundary values.
4. The method for detecting the online abnormality of energy consumption based on the hierarchical clustering and histogram algorithm as claimed in claim 1, wherein the steps S3 and S4 include:
setting a maximum clustering number N and a minimum sample number M in the clusters;
for continuous characteristic data, averagely cutting the continuous characteristic data into a.N histograms in a continuous characteristic value range, wherein each histogram represents a value interval, namely a cluster of one characteristic, and a is the cutting precision;
for the discrete type features, taking each discrete variable different from each other as a cluster of the features;
let the cluster set of features be denoted as C ═ C1,c2,…,ciAnd allocating the energy consumption time series data to a set corresponding to the cluster, and calculating the number of samples of the cluster and the cluster center, wherein the cluster center is the average value of all the samples of the cluster.
5. The method for detecting the online abnormality of energy consumption based on the hierarchical clustering and histogram algorithm as claimed in claim 4, wherein the step S6 includes:
and (4) clustering the feature clusters by adopting a hierarchical clustering algorithm, sequencing the feature clusters from small to large according to the number of samples, combining the clusters with the closest centers of the two clusters, calculating the cluster centers and the cluster sample numbers of the new feature clusters, and returning to the step S5 after reordering the new feature clusters.
6. The method for detecting the online abnormality of energy consumption based on the hierarchical clustering and histogram algorithm as claimed in claim 4, wherein the step S7 includes:
calculating the upper and lower limit threshold values of each feature cluster by adopting a dynamically adjusted box curve method:
th=q3+k×(q3-q1),tl=q1-k×(q3-q1);
where th denotes an upper threshold, tl denotes a lower threshold, q1And q is3Sample data representing 1/4 and 3/4 quantiles of feature clusters, respectively; the value of k is according to the following formula:
wherein n issampleIs the total number of samples of the energy consumption time series data, nciIs a cluster ciThe number of samples.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011329439.0A CN112288597A (en) | 2020-11-24 | 2020-11-24 | Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011329439.0A CN112288597A (en) | 2020-11-24 | 2020-11-24 | Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112288597A true CN112288597A (en) | 2021-01-29 |
Family
ID=74425474
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011329439.0A Pending CN112288597A (en) | 2020-11-24 | 2020-11-24 | Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112288597A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113239963A (en) * | 2021-04-13 | 2021-08-10 | 联合汽车电子有限公司 | Vehicle data processing method, device, equipment, vehicle and storage medium |
CN113468157A (en) * | 2021-07-12 | 2021-10-01 | 博锐尚格科技股份有限公司 | Similar building selection method and device based on energy consumption analysis |
CN114280352A (en) * | 2021-12-27 | 2022-04-05 | 杭州电子科技大学 | Current-based large instrument man-hour calculation method |
CN115310879A (en) * | 2022-10-11 | 2022-11-08 | 浙江浙石油综合能源销售有限公司 | Multi-fueling-station power consumption control method based on semi-supervised clustering algorithm |
CN117421618A (en) * | 2023-11-24 | 2024-01-19 | 上海东方低碳科技产业股份有限公司 | Building energy consumption monitoring method and system |
CN117633573A (en) * | 2024-01-26 | 2024-03-01 | 南京群顶科技股份有限公司 | Electric quantity data anomaly detection method and system based on air conditioner operation working condition |
-
2020
- 2020-11-24 CN CN202011329439.0A patent/CN112288597A/en active Pending
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113239963A (en) * | 2021-04-13 | 2021-08-10 | 联合汽车电子有限公司 | Vehicle data processing method, device, equipment, vehicle and storage medium |
CN113239963B (en) * | 2021-04-13 | 2024-03-01 | 联合汽车电子有限公司 | Method, device, equipment, vehicle and storage medium for processing vehicle data |
CN113468157A (en) * | 2021-07-12 | 2021-10-01 | 博锐尚格科技股份有限公司 | Similar building selection method and device based on energy consumption analysis |
CN113468157B (en) * | 2021-07-12 | 2024-04-26 | 博锐尚格科技股份有限公司 | Similar building selection method and device based on energy consumption analysis |
CN114280352A (en) * | 2021-12-27 | 2022-04-05 | 杭州电子科技大学 | Current-based large instrument man-hour calculation method |
CN114280352B (en) * | 2021-12-27 | 2024-02-13 | 杭州电子科技大学 | Current-based large instrument working hour calculation method |
CN115310879A (en) * | 2022-10-11 | 2022-11-08 | 浙江浙石油综合能源销售有限公司 | Multi-fueling-station power consumption control method based on semi-supervised clustering algorithm |
CN115310879B (en) * | 2022-10-11 | 2022-12-16 | 浙江浙石油综合能源销售有限公司 | Multi-fueling-station power consumption control method based on semi-supervised clustering algorithm |
CN117421618A (en) * | 2023-11-24 | 2024-01-19 | 上海东方低碳科技产业股份有限公司 | Building energy consumption monitoring method and system |
CN117421618B (en) * | 2023-11-24 | 2024-04-05 | 上海东方低碳科技产业股份有限公司 | Building energy consumption monitoring method and system |
CN117633573A (en) * | 2024-01-26 | 2024-03-01 | 南京群顶科技股份有限公司 | Electric quantity data anomaly detection method and system based on air conditioner operation working condition |
CN117633573B (en) * | 2024-01-26 | 2024-04-16 | 南京群顶科技股份有限公司 | Electric quantity data anomaly detection method and system based on air conditioner operation working condition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112288597A (en) | Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm | |
CN111539550B (en) | Method, device, equipment and storage medium for determining working state of photovoltaic array | |
CN109740648B (en) | Method and device for identifying abnormal data of power load and computer equipment | |
CN108446864B (en) | Big data analysis-based fault early warning system and method for rail transit equipment | |
CN110648480B (en) | Single variable alarm system and method based on change rate | |
CN115876258B (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
CN111414571A (en) | Atmospheric pollutant monitoring method | |
CN112598539B (en) | Wind power curve optimization calculation and outlier detection method for wind generating set | |
CN116804668B (en) | Salt iodine content detection data identification method and system | |
CN103902798B (en) | Data preprocessing method | |
CN117251798A (en) | Meteorological equipment anomaly detection method based on two-layer progressive process | |
CN115576981A (en) | Anomaly detection method based on combination of supervised algorithm and unsupervised algorithm | |
CN109211564B (en) | Self-adaptive threshold detection method for health assessment of ball screw pair | |
CN116878590B (en) | Intelligent service collaborative operation management system | |
CN117093947B (en) | Power generation diesel engine operation abnormity monitoring method and system | |
CN107808209B (en) | Wind power plant abnormal data identification method based on weighted kNN distance | |
CN117092980B (en) | Electrical fault detection control system based on big data | |
CN113127464A (en) | Agricultural big data environment feature processing method and device and electronic equipment | |
CN116168019B (en) | Power grid fault detection method and system based on machine vision technology | |
CN115994692B (en) | Intelligent river and lake management platform based on 5G and big data | |
CN115690590B (en) | Crop growth abnormity monitoring method, device, equipment and storage medium | |
CN113554079B (en) | Power load abnormal data detection method and system based on secondary detection method | |
CN110083804B (en) | Wind power plant SCADA data missing intelligent repairing method based on condition distribution regression | |
CN105223945B (en) | Aquaculture Internet of Things equips the fault diagnosis method and system of cluster | |
CN117251749B (en) | Data processing method of Internet of things based on incremental analysis |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |
|
RJ01 | Rejection of invention patent application after publication |