CN116523077B - Early warning method, device, equipment and storage medium based on container technology - Google Patents
Early warning method, device, equipment and storage medium based on container technology Download PDFInfo
- Publication number
- CN116523077B CN116523077B CN202310765060.1A CN202310765060A CN116523077B CN 116523077 B CN116523077 B CN 116523077B CN 202310765060 A CN202310765060 A CN 202310765060A CN 116523077 B CN116523077 B CN 116523077B
- Authority
- CN
- China
- Prior art keywords
- container
- monitoring
- target
- power equipment
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005516 engineering process Methods 0.000 title claims abstract description 58
- 238000012544 monitoring process Methods 0.000 claims abstract description 159
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000012360 testing method Methods 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 26
- 238000007781 pre-processing Methods 0.000 claims description 23
- 238000004806 packaging method and process Methods 0.000 claims description 14
- 238000002790 cross-validation Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 14
- 238000011084 recovery Methods 0.000 abstract description 5
- 230000002159 abnormal effect Effects 0.000 description 11
- 239000007788 liquid Substances 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000001419 dependent effect Effects 0.000 description 4
- 239000013307 optical fiber Substances 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000002955 isolation Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000005452 bending Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/61—Installation
- G06F8/63—Image based installation; Cloning; Build to order
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/70—Software maintenance or management
- G06F8/76—Adapting program code to run in a different environment; Porting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application discloses a container technology-based early warning method, device, equipment and storage medium. When the method provided by the embodiment of the application is executed, the monitoring software of the power equipment can be packaged into the first container mirror image and stored in the container warehouse. And acquiring a container image corresponding to the target power equipment from the container warehouse as a target container image, and deploying the target container image into a monitoring tool for operation. The monitoring tool monitors the target power equipment in real time through the target container mirror image to obtain monitoring data, and then analyzes the monitoring data based on the SVM machine learning algorithm to obtain a prediction result. And generating early warning information according to the prediction result and sending the early warning information to the client. The application improves the monitoring efficiency of the power equipment, reduces the operation and maintenance cost of the power equipment monitoring, realizes the self-healing and automatic recovery of faults, and provides better safety. Meanwhile, the reliability, flexibility and expandability of the power equipment monitoring software are effectively improved.
Description
Technical Field
The present application relates to the field of cloud computing technologies, and in particular, to a container technology-based early warning method, apparatus, device, and storage medium.
Background
The power industry is one of the important basic industries in national economy. With the continuous advancement of technology and the improvement of informatization level, the power industry is also faced with new opportunities and challenges. Accordingly, research and application of intelligent operation and maintenance methods and systems are receiving increasing attention.
The operation and maintenance method and system of the power industry is a complex system engineering, and needs organic combination of various technologies. Only if new technology is continuously innovated and applied, the requirements of the power industry can be better met, and the development of the power industry is promoted. In practical application, the traditional power equipment monitoring and fault diagnosis method often needs manual inspection or periodic maintenance, which is time-consuming and labor-consuming, and is easy to generate the problems of missing report, misjudgment and the like.
Therefore, how to improve the monitoring efficiency of the power equipment and avoid the problems of missing report, misjudgment and the like at the same time is a technical problem which needs to be solved by the technicians in the field.
Disclosure of Invention
Based on the problems, the application provides a container technology-based early warning method, device, equipment and storage medium, which improve the monitoring efficiency of power equipment and avoid the problems of missing report, misjudgment and the like. The embodiment of the application discloses the following technical scheme:
A method of early warning based on container technology, the method comprising:
packaging monitoring software of the power equipment into a first container mirror image, and storing the first container mirror image into a container warehouse;
acquiring a container image corresponding to target power equipment from the container warehouse as a target container image, and deploying the target container image into a monitoring tool for operation; the monitoring tool monitors the target power equipment in real time through the target container mirror to obtain monitoring data;
analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result;
and generating early warning information according to the prediction result and sending the early warning information to the client.
In one possible implementation, the packaging the power device monitoring software to be deployed into a container image and storing the container image in a container warehouse includes:
acquiring a Dockerfile configuration file of the monitoring software;
constructing a second container mirror image according to the Dockerfile configuration file;
testing the second container image to obtain a test result;
and uploading the second container image as a first container image into the container warehouse when the test result meets a preset standard.
In one possible implementation manner, the analyzing the monitored data by the SVM-based machine learning algorithm to obtain a prediction result includes:
acquiring historical monitoring data of the power equipment acquired by a monitoring tool;
preprocessing the history monitoring data to obtain preprocessed data;
dividing the preprocessing data into a training set and a testing set;
model training is carried out according to the training set by utilizing an SVM algorithm, and a first prediction model is obtained;
and performing parameter tuning on the first prediction model in a cross-validation mode to obtain a second prediction model, and inputting the monitoring data into the second prediction model to perform prediction to obtain a prediction result.
In one possible implementation manner, the preprocessing the historical monitoring data to obtain preprocessed data includes:
and carrying out preprocessing operations of data classification, data cleaning, missing value processing and feature extraction on the historical monitoring data according to the sensor type, so as to obtain the preprocessing data.
In one possible implementation manner, the performing parameter tuning on the first prediction model through the cross-validation manner to obtain a second prediction model includes:
Dividing the monitoring data in the test set into K subsets with equal size, wherein K is a positive integer greater than 1;
training an SVM model on the remaining K-1 subsets to obtain K-1 sub-models, carrying out error test on each sub-model by using the subsets i, repeating the operation K times, and selecting different subsets each time as test sets to obtain K prediction errors, wherein i is a positive integer greater than or equal to 1;
and calculating the average error of the K prediction errors, and performing parameter tuning on the penalty factors of the first prediction model according to the average error to obtain a second prediction model.
In one possible implementation, the monitoring tool monitors the target power device in real time through the target container mirror to obtain monitoring data, including:
creating a custom resource definition based on an API extension mechanism of Kubernetes;
deploying a custom resource definition controller in the first Kubernetes cluster based on the custom resource definition, thereby obtaining a second Kubernetes cluster;
creating a power service application in the second Kubernetes cluster using a Kubernetes resource inventory, wherein the power service application is comprised of a plurality of the target container images;
And using a monitoring tool in the second Kubernetes cluster to monitor the target power equipment in real time through the power business application program to obtain monitoring data.
In one possible implementation manner, after the obtaining, from the container warehouse, a container image corresponding to a target power device as a target container image, and deploying the target container image into a monitoring tool, the method further includes:
the monitoring data is converted into a visual report using the monitoring tool in the second Kubernetes cluster.
An early warning device based on container technology, the device comprising:
the packaging storage unit is used for packaging the monitoring software of the power equipment into a first container mirror image and storing the first container mirror image into a container warehouse;
the first deployment unit is used for acquiring a container image corresponding to the target power equipment from the container warehouse as a target container image, and deploying the target container image into a monitoring tool for operation; the monitoring tool monitors the target power equipment in real time through the target container mirror to obtain monitoring data;
the analysis unit is used for analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result;
And the generating unit is used for generating early warning information according to the prediction result and sending the early warning information to the client.
An electronic device, comprising: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the early warning method based on the container technology is realized when the processor executes the computer program.
A computer readable storage medium having instructions stored therein which, when executed on a terminal device, cause the terminal device to perform a container technology based pre-warning method as described above.
Compared with the prior art, the application has the following beneficial effects: the application discloses a container technology-based early warning method, device, equipment and storage medium. Specifically, when the early warning method based on the container technology provided by the embodiment of the application is executed, monitoring software of the power equipment can be packaged into a first container mirror image and stored in a container warehouse. And acquiring a container image corresponding to the target power equipment from the container warehouse as a target container image, deploying the target container image into a monitoring tool for operation, and carrying out real-time monitoring on the target power equipment by the monitoring tool through the target container image to obtain monitoring data. And then analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result. And generating early warning information according to the prediction result and sending the early warning information to the client. According to the application, the monitoring of the operation data of the power equipment is realized based on the container technology, and the predicted abnormal result is sent to the client when the operation data of the power equipment is abnormal, so that the monitoring efficiency of the power equipment is improved, the operation and maintenance cost of the power equipment monitoring is reduced, the self-healing and the automatic recovery of faults are realized, and better safety is provided. Meanwhile, the reliability, flexibility and expandability of the power equipment monitoring software can be effectively improved.
Drawings
In order to more clearly illustrate this embodiment or the technical solutions of the prior art, the drawings that are required for the description of the embodiment or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an early warning method based on container technology provided by an embodiment of the application;
fig. 2 is a schematic structural diagram of an early warning device based on container technology according to an embodiment of the present application.
Detailed Description
In order to make the present application better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In order to facilitate understanding of the technical solution provided by the embodiments of the present application, the following description will first explain the background technology related to the embodiments of the present application.
The power industry is one of the important basic industries in national economy. With the continuous advancement of technology and the improvement of informatization level, the power industry is also faced with new opportunities and challenges. Accordingly, research and application of intelligent operation and maintenance methods and systems are receiving increasing attention.
In the power industry, the application of intelligent operation and maintenance methods and systems is receiving increasing attention. The intelligent operation and maintenance method and system mainly comprise the following technologies:
1. sensor technology: and monitoring the power equipment in real time by utilizing various sensors, and collecting related data. For example, temperature sensors, pressure sensors, humidity sensors, etc. may be used to monitor the status and environmental parameters of the transformer, switchgear, etc. devices.
2. The technology of the Internet of things: and various electric devices are connected through the internet of things technology, and communication and cooperative work among the devices are realized. For example, wireless communication technologies such as Zigbee and LoRa may be used to implement low power consumption, long distance device connection and data transmission.
3. Big data technology: and analyzing and mining the data acquired by the power equipment by utilizing a big data technology, and extracting valuable information. For example, predictive maintenance, fault diagnosis, and the like of the power equipment may be performed using techniques such as data analysis, data mining, and machine learning.
4. Cloud computing technology: and storing and processing the data acquired by the power equipment by utilizing a cloud computing technology, and realizing remote access and management. For example, remote monitoring and management of power devices may be implemented using techniques such as cloud storage, cloud computing platforms, and the like.
5. The container technology comprises the following steps: the power plant monitoring software is packaged into a portable container by a containerization technique and can be run in the same manner anywhere. Thus, version control and quick deployment can be conveniently carried out, and portability and cross-platform performance of software can be improved.
In summary, the operation and maintenance method and system in the power industry is a complex system engineering, and needs an organic combination of multiple technologies. Only if new technology is continuously innovated and applied, the requirements of the power industry can be better met, and the development of the power industry is promoted. In practical application, the traditional power equipment monitoring and fault diagnosis method often needs manual inspection or periodic maintenance, which is time-consuming and labor-consuming, and is easy to generate the problems of missing report, misjudgment and the like.
In order to solve the problem, the embodiment of the application provides a container technology-based early warning method, device, equipment and storage medium, wherein monitoring software of power equipment is packaged into a first container mirror image and stored in a container warehouse. And then, acquiring a container image corresponding to the target power equipment from the container warehouse as a target container image, deploying the target container image into a monitoring tool for operation, and carrying out real-time monitoring on the target power equipment by the monitoring tool through the target container image to obtain monitoring data. And then, analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result. And finally, generating early warning information according to the prediction result and sending the early warning information to the client. According to the application, the monitoring of the operation data of the power equipment is realized based on the container technology, and the predicted abnormal result is sent to the client when the operation data of the power equipment is abnormal, so that the monitoring efficiency of the power equipment is improved, the operation and maintenance cost of the power equipment monitoring is reduced, the self-healing and the automatic recovery of faults are realized, and better safety is provided. Meanwhile, the reliability, flexibility and expandability of the power equipment monitoring software can be effectively improved.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, which is a flowchart of a method for early warning based on container technology according to an embodiment of the present application, as shown in fig. 1, the early warning method based on container technology may include steps S101 to S104:
s101: the monitoring software of the power device is packaged as a first container image and stored in a container warehouse.
In order to realize early warning based on the container technology, the early warning system based on the container technology firstly needs to package monitoring software of the power equipment into a first container mirror image, and stores the first container mirror image into a container warehouse so that a monitoring tool can acquire a corresponding container mirror image from the container warehouse and deploy and operate the corresponding container mirror image on the container mirror image to realize real-time monitoring of the power equipment and collection of operation state information.
The container mirror image is a static file used for creating a container and comprises components such as an application program, a library, a dependent item, an operating system kernel and the like. The first container image, which contains all the components and dependencies required to run the software, acts as a portable and self-contained software unit. Therefore, the software can be ensured to have consistent behaviors in different environments, and the problems of dependence item conflict and the like are avoided. The first container image can be conveniently deployed and copied, so that the software deployment process is simpler and faster. The first container mirror image can provide isolation, so that the software is isolated from other application programs and system resources during running, and safety and stability are improved.
The container warehouse provides centralized storage and management, facilitating team members to share and access container images. The container repository may provide versioning and historian functionality so that changes and updates to container images may be easily managed and tracked. The container warehouse may be integrated with other tools and platforms, such as a continuous integration/continuous deployment (CI/CD) system, enabling automated deployment and release procedures.
In one possible implementation, when the constructed first container image is uploaded to the container warehouse, the image is pushed to the container warehouse by adopting a dock push command, and the container warehouse serves the dock Hub or the ali cloud container image. Wherein, the dock push command is a run command docker push myapp:latest, wherein myapp is the mirror name and latest is the tag.
In one possible implementation, the packaging the power device monitoring software to be deployed into a container image and storing the container image in a container warehouse includes A1-A4:
a1: and acquiring a Dockerfile configuration file of the monitoring software.
When packaging the power device monitoring software to be deployed into a container image, a Dockerfile configuration file for describing the construction of the first container image needs to be acquired first.
Wherein, dockerfile is a file used to construct a Docker image, and consists of a series of instructions and corresponding parameters. The base image, install dependencies, and replicate application operations may be specified in the Dockerfile configuration file.
A2: and constructing a second container mirror image according to the Dockerfile configuration file.
After the Dockerfile configuration file of the monitoring software is obtained, a second container image is further required to be constructed according to the Dockerfile configuration file.
In one possible implementation manner, the building of the second container image according to the Dockerfile configuration file may be, but is not limited to, building the second container image according to the compiled Dockerfile configuration file by using a docker build command, and when the container image is built, executing the command docker build-t myapp: last. Where myapp is the mirror name, last is the tag, "" indicates the current directory.
A3: and testing the second container mirror image, thereby obtaining a test result.
After the second container image is built according to the Dockerfile configuration file, in order to obtain a container image that operates normally, the obtained second container image needs to be tested.
In one possible implementation, the test results may be, but are not limited to, normal or abnormal operation.
In one possible implementation, the second container image is built according to the Dockerfile configuration file, which may be, but is not limited to, whether the second container image is operating normally or not using a docker run command, and when tested, an operating command docker run-d—name myapp: last, where-d represents operating the container in the background, and-name specifies the name of the container.
A4: and uploading the second container image as a first container image into the container warehouse when the test result meets a preset standard.
After the second container mirror image is tested to obtain a test result, the test result is required to be judged to meet a preset standard, and when the test result meets the preset standard, the second container mirror image is used as the first container mirror image to be uploaded to a container warehouse.
In one possible implementation, the test results meeting the preset criteria may be, but are not limited to, the second container image functioning properly.
S102: acquiring a container image corresponding to target power equipment from the container warehouse as a target container image, and deploying the target container image into a monitoring tool for operation; and the monitoring tool monitors the target power equipment in real time through the target container mirror to obtain monitoring data.
Since the container image stored in the container warehouse contains the operating environment of the power device monitoring software and the packaging unit of the dependent items. The monitoring tool may be deployed and run by retrieving the corresponding container image from the container warehouse. The monitoring tool may utilize power device monitoring software in the container image to monitor the power device in real time and collect operational status information, i.e., monitoring data. By container technology, the deployment and running process of container mirroring can be more flexible and efficient while also providing isolation and portability advantages.
In one possible implementation manner, the monitoring tool may be based on a cloud monitoring platform and connected to the sensor of the target power device through a network for real-time monitoring, and the early warning system of the container technology may record, in real time, the running state, the performance index, and the like of the device monitored by the sensor of the target power device as the monitoring data.
The sensor of the target power equipment comprises a temperature sensor, a vibration sensor, a pressure sensor, a liquid level sensor, a current sensor, an optical fiber sensor and a humidity sensor.
The specific temperature sensor is arranged at the position of a transformer and a generator of the target power equipment and is used for monitoring the temperature change of the power equipment; the vibration sensor is arranged at the positions of the motor and the fan of the target power equipment and is used for detecting vibration information of the motor and the fan; the pressure sensors are arranged in the hydraulic system and the air source system of the target electric equipment and are used for monitoring pressure changes of the hydraulic system and the air source system; the liquid level sensor is arranged in the oil tank and the water tank of the target power equipment and is used for monitoring the liquid level change of the liquid in the oil tank and the water tank; the current sensor is arranged in the low-voltage switch cabinet and the power distribution cabinet of the target power equipment and is used for monitoring the current change of the power equipment; the optical fiber sensor monitors the cable line on line, monitors the temperature, the tension and the bending parameters of the cable in real time, and finds out in real time to eliminate line faults; humidity sensors are mounted on the target electrical equipment for monitoring humidity data around the electrical equipment.
S103: and analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result.
In order to identify abnormal conditions and generate early warning, an early warning system of the container technology needs to analyze monitoring data by adopting an SVM machine learning algorithm.
In one possible implementation manner, the SVM-based machine learning algorithm analyzes the monitored data to obtain a prediction result, including B1-B5:
b1: and acquiring historical monitoring data of the power equipment acquired by the monitoring tool.
When the monitoring data is analyzed based on an SVM machine learning algorithm to obtain a prediction result, firstly, the historical monitoring data of the power equipment needs to be acquired, and the historical monitoring data is acquired by a monitoring tool.
B2: and preprocessing the historical monitoring data to obtain preprocessed data.
After the historical monitoring data of the power equipment is acquired by the monitoring tool, the historical monitoring data also needs to be preprocessed, so that preprocessed data is obtained.
In one possible implementation manner, the preprocessing the historical monitoring data to obtain preprocessed data includes:
and carrying out preprocessing operations of data classification, data cleaning, missing value processing and feature extraction on the historical monitoring data according to the sensor type, so as to obtain the preprocessing data.
B3: the preprocessing data is divided into a training set and a testing set.
After the pre-processed data is obtained, the pre-processed data also needs to be divided into a training set and a testing set.
B4: and performing model training according to the training set by using an SVM algorithm to obtain a first prediction model.
After the training set is obtained, model training can be performed according to the training set by using an SVM algorithm to obtain a first prediction model.
B5: and performing parameter tuning on the first prediction model in a cross-validation mode to obtain a second prediction model, and inputting the monitoring data into the second prediction model to perform prediction to obtain a prediction result.
In one possible implementation manner, the performing parameter tuning on the first prediction model through a cross-validation manner to obtain a second prediction model includes C1-C3:
c1: dividing the monitoring data in the test set into K subsets with equal size, wherein K is a positive integer greater than 1.
When the first prediction model is subjected to parameter tuning in a cross-validation mode to obtain a second prediction model, monitoring data in a test set is firstly required to be divided into K subsets with equal sizes, wherein K is a positive integer greater than 1. In cross-validation, the monitored data is divided into K equal-sized subsets for model evaluation and tuning.
C2: and training an SVM model on the remaining K-1 subsets for each subset i to obtain K-1 sub-models, carrying out error test on each sub-model by using the subset i, repeating the operation K times, and selecting different subsets each time as test sets to obtain K prediction errors, wherein i is a positive integer greater than or equal to 1.
After dividing the monitoring data in the test set into K subsets of equal size, training the SVM model on the remaining K-1 subsets to obtain K-1 sub-models for each subset i of the K subsets, and carrying out error test on each sub-model by using the subset i, repeating the above operation K times, and selecting different subsets each time as the test set to obtain K prediction errors, wherein i is a positive integer greater than or equal to 1. By training the model on K-1 subsets and testing on the ith subset, the performance of the model can be verified multiple times. This approach may reduce the risk of over-fitting or under-fitting while providing a consistency assessment of the model over different data subsets.
And C3: and calculating the average error of the K prediction errors, and performing parameter tuning on the penalty factors of the first prediction model according to the average error to obtain a second prediction model.
After obtaining K prediction errors, calculating the average error of the K prediction errors, performing parameter tuning on the penalty factor of the first prediction model according to the average error, and taking the tuned first prediction model as a second prediction model. And calculating the average value of the K prediction errors as an evaluation index of the performance of the first prediction model, and then performing parameter tuning on a penalty factor C of the first prediction model according to the average error, so as to obtain parameter configuration which enables the model to perform well on different subsets. The accuracy and the robustness of the first prediction model can be improved by performing parameter tuning through average errors.
S104: and generating early warning information according to the prediction result and sending the early warning information to the client.
After the prediction result is obtained, the early warning system based on the container technology can generate early warning information according to the prediction result and send the early warning information to the client, so that a user can manage the target power equipment according to the early warning information.
In one possible implementation, the monitoring tool monitors the target power device in real time through the target container mirror to obtain monitoring data, including D1-D4:
d1: the Kubernetes-based API extension mechanism creates custom resource definitions.
When the monitoring tool monitors the target power equipment in real time through the target container mirror image to obtain monitoring data, firstly, a user-defined resource definition is required to be created based on an API (application program interface) expansion mechanism of Kubernetes.
Wherein the custom resource definition describes the attributes, state and behavior information of the power business application.
D2: and deploying a custom resource definition controller in the first Kubernetes cluster based on the custom resource definition, thereby obtaining a second Kubernetes cluster.
After creating the custom resource definition based on the API extension mechanism of Kubernetes, a custom resource definition controller may be deployed in the first Kubernetes cluster based on the created custom resource definition to obtain the second Kubernetes cluster.
In one possible implementation, the first Kubernetes cluster is a distributed system consisting of a plurality of working nodes (nodes) and a control plane. The Control Plane (Control Plane) is composed of a plurality of Master nodes and is responsible for managing the state of the entire cluster and various resource objects, such as Pod, service, replicaSet, deployment. The working nodes are hosts for running the containerized application program, and each node can run multiple Pod.
D3: a power business application is created in the second Kubernetes cluster using a Kubernetes resource inventory, wherein the power business application is comprised of a plurality of the target container images.
After the second Kubernetes cluster is obtained, a power service application may be created in the second Kubernetes cluster using the Kubernetes resource inventory, the power service application being comprised of a plurality of target container images.
The Kubernetes resource list is a YAML or JSON file, and is used to describe various resource objects in the Kubernetes cluster, such as Pod, service, deployment. Through the resource list, a user can quickly create, update and delete the Kubernetes resource object, and automatic deployment and management are realized.
D4: and using a monitoring tool in the second Kubernetes cluster to monitor the target power equipment in real time through the power business application program to obtain monitoring data.
After the power business application program is obtained, the monitoring tool in the second Kubernetes cluster can be used for monitoring the target power equipment in real time through the power business application program to obtain monitoring data.
Based on the content of S101-S104, first, the monitoring software of the power device is packaged into a first container image and stored in a container warehouse. And then, acquiring a container image corresponding to the target power equipment from the container warehouse as a target container image, deploying the target container image into a monitoring tool for operation, and carrying out real-time monitoring on the target power equipment by the monitoring tool through the target container image to obtain monitoring data. And then, analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result. And finally, generating early warning information according to the prediction result and sending the early warning information to the client. According to the application, the monitoring of the operation data of the power equipment is realized based on the container technology, and the predicted abnormal result is sent to the client when the operation data of the power equipment is abnormal, so that the monitoring efficiency of the power equipment is improved, the operation and maintenance cost of the power equipment monitoring is reduced, the self-healing and the automatic recovery of faults are realized, and better safety is provided. Meanwhile, the reliability, flexibility and expandability of the power equipment monitoring software can be effectively improved.
The embodiment of the application provides some specific implementation modes of the early warning method based on the container technology, and based on the implementation modes, the application also provides a corresponding early warning device applied to the early warning method based on the container technology. The apparatus provided by the embodiment of the present application will be described in terms of functional modularization.
Referring to fig. 2, the structure of an early warning device based on container technology according to an embodiment of the present application is shown. As shown in fig. 2, the early warning device based on the container technology includes:
and the packaging storage unit 201 is used for packaging the monitoring software of the power equipment into a first container image and storing the first container image into a container warehouse.
The container mirror image is a static file used for creating a container and comprises components such as an application program, a library, a dependent item, an operating system kernel and the like. The first container image, which contains all the components and dependencies required to run the software, acts as a portable and self-contained software unit. Therefore, the software can be ensured to have consistent behaviors in different environments, and the problems of dependence item conflict and the like are avoided. The first container image can be conveniently deployed and copied, so that the software deployment process is simpler and faster. The first container mirror image can provide isolation, so that the software is isolated from other application programs and system resources during running, and safety and stability are improved.
The container warehouse provides centralized storage and management, facilitating team members to share and access container images. The container repository may provide versioning and historian functionality so that changes and updates to container images may be easily managed and tracked. The container warehouse may be integrated with other tools and platforms, such as a continuous integration/continuous deployment (CI/CD) system, enabling automated deployment and release procedures.
In one possible implementation, when the constructed first container image is uploaded to the container warehouse, the image is pushed to the container warehouse by adopting a dock push command, and the container warehouse serves the dock Hub or the ali cloud container image. Wherein, the dock push command is a run command docker push myapp:latest, wherein myapp is the mirror name and latest is the tag.
In one possible implementation, the apparatus further includes:
the first acquisition unit is used for acquiring the Dockerfile configuration file of the monitoring software.
Wherein, dockerfile is a file used to construct a Docker image, and consists of a series of instructions and corresponding parameters. The base image, install dependencies, and replicate application operations may be specified in the Dockerfile configuration file.
And the construction unit is used for constructing a second container mirror image according to the Dockerfile configuration file.
In one possible implementation manner, the building of the second container image according to the Dockerfile configuration file may be, but is not limited to, building the second container image according to the compiled Dockerfile configuration file by using a docker build command, and when the container image is built, executing the command docker build-t myapp: last. Where myapp is the mirror name, last is the tag, "" indicates the current directory.
And the testing unit is used for testing the second container mirror image so as to obtain a testing result.
In one possible implementation, the test results may be, but are not limited to, normal or abnormal operation.
In one possible implementation, the second container image is built according to the Dockerfile configuration file, which may be, but is not limited to, whether the second container image is operating normally or not using a docker run command, and when tested, an operating command docker run-d—name myapp: last, where-d represents operating the container in the background, and-name specifies the name of the container.
And the uploading unit is used for uploading the second container image into the container warehouse as the first container image when the test result meets the preset standard.
In one possible implementation, the test results meeting the preset criteria may be, but are not limited to, the second container image functioning properly.
The deployment unit 202 is configured to obtain a container image corresponding to a target power device from the container warehouse as a target container image, and deploy the target container image into a monitoring tool for operation; and the monitoring tool monitors the target power equipment in real time through the target container mirror to obtain monitoring data.
In one possible implementation manner, the monitoring tool may be based on a cloud monitoring platform and connected to the sensor of the target power device through a network for real-time monitoring, and the early warning system of the container technology may record, in real time, the running state, the performance index, and the like of the device monitored by the sensor of the target power device as the monitoring data.
The sensor of the target power equipment comprises a temperature sensor, a vibration sensor, a pressure sensor, a liquid level sensor, a current sensor, an optical fiber sensor and a humidity sensor.
The specific temperature sensor is arranged at the position of a transformer and a generator of the target power equipment and is used for monitoring the temperature change of the power equipment; the vibration sensor is arranged at the positions of the motor and the fan of the target power equipment and is used for detecting vibration information of the motor and the fan; the pressure sensors are arranged in the hydraulic system and the air source system of the target electric equipment and are used for monitoring pressure changes of the hydraulic system and the air source system; the liquid level sensor is arranged in the oil tank and the water tank of the target power equipment and is used for monitoring the liquid level change of the liquid in the oil tank and the water tank; the current sensor is arranged in the low-voltage switch cabinet and the power distribution cabinet of the target power equipment and is used for monitoring the current change of the power equipment; the optical fiber sensor monitors the cable line on line, monitors the temperature, the tension and the bending parameters of the cable in real time, and finds out in real time to eliminate line faults; humidity sensors are mounted on the target electrical equipment for monitoring humidity data around the electrical equipment.
And the analysis unit 203 is used for analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result.
In one possible implementation, the apparatus further includes:
and the second acquisition unit is used for acquiring historical monitoring data of the power equipment acquired by the monitoring tool.
And the preprocessing unit is used for preprocessing the history monitoring data so as to obtain preprocessed data.
In one possible implementation, the preprocessing unit is specifically configured to:
and carrying out preprocessing operations of data classification, data cleaning, missing value processing and feature extraction on the historical monitoring data according to the sensor type, so as to obtain the preprocessing data.
The first dividing unit is used for dividing the preprocessing data into a training set and a testing set.
And the model training unit is used for carrying out model training according to the training set by utilizing an SVM algorithm to obtain a first prediction model.
And the parameter tuning unit is used for performing parameter tuning on the first prediction model in a cross verification mode to obtain a second prediction model, and inputting the monitoring data into the second prediction model to perform prediction to obtain a prediction result.
In one possible implementation, the apparatus further includes:
And the second dividing unit is used for dividing the monitoring data in the test set into K subsets with equal sizes, wherein K is a positive integer greater than 1.
And the error prediction unit is used for training the SVM model on the remaining K-1 subsets to obtain K-1 sub-models for each subset i, carrying out error test on each sub-model by using the subset i, repeating the operation K times, and selecting different subsets each time as test sets to obtain K prediction errors, wherein i is a positive integer greater than or equal to 1.
And the calculating unit is used for calculating the average error of the K prediction errors and carrying out parameter tuning on the penalty factors of the first prediction model according to the average error to obtain a second prediction model.
And the generating unit 204 is used for generating early warning information according to the prediction result and sending the early warning information to the client.
In one possible implementation, the apparatus further includes:
the first creating unit is used for creating custom resource definition based on an API extension mechanism of the Kubernetes.
And the second deployment unit is used for deploying the custom resource definition controller in the first Kubernetes cluster based on the custom resource definition, so as to obtain a second Kubernetes cluster.
In one possible implementation, the first Kubernetes cluster is a distributed system consisting of a plurality of working nodes (nodes) and a control plane. The Control Plane (Control Plane) is composed of a plurality of Master nodes and is responsible for managing the state of the entire cluster and various resource objects, such as Pod, service, replicaSet, deployment. The working nodes are hosts for running the containerized application program, and each node can run multiple Pod.
And the second creating unit is used for creating a power business application program in the second Kubernetes cluster by using a Kubernetes resource list, wherein the power business application program is composed of a plurality of target container images.
The Kubernetes resource list is a YAML or JSON file, and is used to describe various resource objects in the Kubernetes cluster, such as Pod, service, deployment. Through the resource list, a user can quickly create, update and delete the Kubernetes resource object, and automatic deployment and management are realized.
And the monitoring unit is used for monitoring the target power equipment in real time by using a monitoring tool in the second Kubernetes cluster through the power service application program to obtain monitoring data.
In addition, the embodiment of the application also provides a warning method device based on the container technology, which comprises a memory and a processor, wherein the memory is used for storing programs or codes, and the processor is used for running the programs or codes stored in the memory so as to realize the warning method based on the container technology.
In addition, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores codes, and when the codes are operated, equipment for operating the codes realizes the early warning method based on the container technology.
The embodiment of the application provides a warning method device based on a container technology, after a packaging storage unit 201 packages monitoring software of power equipment into a first container image, the first deployment unit 202 acquires the container image corresponding to target power equipment from the container warehouse as a target container image, deploys the target container image into a monitoring tool for operation, and the monitoring tool monitors the target power equipment in real time through the target container image to obtain monitoring data. The analysis unit 203 then analyzes the monitored data based on the SVM machine learning algorithm to obtain a prediction result. The generating unit 204 generates early warning information according to the prediction result and sends the early warning information to the client. According to the application, the monitoring of the operation data of the power equipment is realized based on the container technology, and the predicted abnormal result is sent to the client when the operation data of the power equipment is abnormal, so that the monitoring efficiency of the power equipment is improved, the operation and maintenance cost of the power equipment monitoring is reduced, the self-healing and the automatic recovery of faults are realized, and better safety is provided. Meanwhile, the reliability, flexibility and expandability of the power equipment monitoring software can be effectively improved.
The early warning method, the device, the equipment and the storage medium based on the container technology provided by the application are described in detail. In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the application can be made without departing from the principles of the application and these modifications and adaptations are intended to be within the scope of the application as defined in the following claims.
It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. A method of early warning based on container technology, the method comprising:
packaging monitoring software of the power equipment into a first container mirror image, and storing the first container mirror image into a container warehouse;
acquiring a container image corresponding to target power equipment from the container warehouse as a target container image, and deploying the target container image into a monitoring tool for operation; the monitoring tool monitors the target power equipment in real time through the target container mirror to obtain monitoring data;
analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result;
generating early warning information according to the prediction result and sending the early warning information to a client;
The SVM-based machine learning algorithm analyzes the monitoring data to obtain a prediction result, and comprises the following steps:
acquiring historical monitoring data of the power equipment acquired by a monitoring tool;
preprocessing the history monitoring data to obtain preprocessed data;
dividing the preprocessing data into a training set and a testing set;
model training is carried out according to the training set by utilizing an SVM algorithm, and a first prediction model is obtained;
and performing parameter tuning on the first prediction model in a cross-validation mode to obtain a second prediction model, and inputting the monitoring data into the second prediction model to perform prediction to obtain a prediction result.
2. The method of claim 1, wherein packaging the monitoring software of the power device as a first container image and storing in a container warehouse comprises:
acquiring a Dockerfile configuration file of the monitoring software;
constructing a second container mirror image according to the Dockerfile configuration file;
testing the second container image to obtain a test result;
and uploading the second container image as a first container image into the container warehouse when the test result meets a preset standard.
3. The method of claim 1, wherein preprocessing the historical monitoring data to obtain preprocessed data comprises:
and carrying out preprocessing operations of data classification, data cleaning, missing value processing and feature extraction on the historical monitoring data according to the sensor type, so as to obtain the preprocessing data.
4. The method according to claim 1, wherein the performing parameter tuning on the first prediction model by the cross-validation method to obtain a second prediction model includes:
dividing the monitoring data in the test set into K subsets with equal size, wherein K is a positive integer greater than 1;
training an SVM model on the remaining K-1 subsets to obtain K-1 sub-models, carrying out error test on each sub-model by using the subsets i, repeating the operation K times, and selecting different subsets each time as test sets to obtain K prediction errors, wherein i is a positive integer greater than or equal to 1;
and calculating the average error of the K prediction errors, and performing parameter tuning on the penalty factors of the first prediction model according to the average error to obtain a second prediction model.
5. The method of claim 1, wherein the monitoring tool monitors the target power device in real time via the target container mirror to obtain monitoring data, comprising:
creating a custom resource definition based on an API extension mechanism of Kubernetes;
deploying a custom resource definition controller in the first Kubernetes cluster based on the custom resource definition, thereby obtaining a second Kubernetes cluster;
creating a power service application in the second Kubernetes cluster using a Kubernetes resource inventory, wherein the power service application is comprised of a plurality of the target container images;
and using a monitoring tool in the second Kubernetes cluster to monitor the target power equipment in real time through the power business application program to obtain monitoring data.
6. The method of claim 5, further comprising, after the obtaining the container image corresponding to the target power device from the container warehouse as the target container image and deploying the target container image into a monitoring tool for operation:
the monitoring data is converted into a visual report using the monitoring tool in the second Kubernetes cluster.
7. An early warning device based on container technology, characterized in that the device comprises:
the packaging storage unit is used for packaging the monitoring software of the power equipment into a first container mirror image and storing the first container mirror image into a container warehouse;
the first deployment unit is used for acquiring a container image corresponding to the target power equipment from the container warehouse as a target container image, and deploying the target container image into a monitoring tool for operation; the monitoring tool monitors the target power equipment in real time through the target container mirror to obtain monitoring data;
the analysis unit is used for analyzing the monitoring data based on an SVM machine learning algorithm to obtain a prediction result;
the generating unit is used for generating early warning information according to the prediction result and sending the early warning information to the client;
the SVM-based machine learning algorithm analyzes the monitoring data to obtain a prediction result, and comprises the following steps:
acquiring historical monitoring data of the power equipment acquired by a monitoring tool;
preprocessing the history monitoring data to obtain preprocessed data;
dividing the preprocessing data into a training set and a testing set;
model training is carried out according to the training set by utilizing an SVM algorithm, and a first prediction model is obtained;
And performing parameter tuning on the first prediction model in a cross-validation mode to obtain a second prediction model, and inputting the monitoring data into the second prediction model to perform prediction to obtain a prediction result.
8. An electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed, implements the container technology based pre-warning method of any one of claims 1-6.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein instructions, which when run on a terminal device, cause the terminal device to perform the container technology based pre-warning method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310765060.1A CN116523077B (en) | 2023-06-27 | 2023-06-27 | Early warning method, device, equipment and storage medium based on container technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310765060.1A CN116523077B (en) | 2023-06-27 | 2023-06-27 | Early warning method, device, equipment and storage medium based on container technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116523077A CN116523077A (en) | 2023-08-01 |
| CN116523077B true CN116523077B (en) | 2023-09-15 |
Family
ID=87401475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310765060.1A Active CN116523077B (en) | 2023-06-27 | 2023-06-27 | Early warning method, device, equipment and storage medium based on container technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116523077B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613041A (en) * | 2020-12-25 | 2021-04-06 | 南方电网深圳数字电网研究院有限公司 | Container mirror image detection method and device, electronic equipment and storage medium |
| CN112965785A (en) * | 2021-03-05 | 2021-06-15 | 食亨(上海)科技服务有限公司 | Container-based micro-service application development method and development platform |
| CN113037802A (en) * | 2021-01-27 | 2021-06-25 | 东南大学 | Cloud-side data cooperation method for power Internet of things |
| CN114489693A (en) * | 2021-12-27 | 2022-05-13 | 国网冀北电力有限公司 | Comprehensive transformer state monitoring system based on edge application |
| CN116028157A (en) * | 2022-11-09 | 2023-04-28 | 新浪技术（中国）有限公司 | Risk identification method and device and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9557723B2 (en) * | 2006-07-19 | 2017-01-31 | Power Analytics Corporation | Real-time predictive systems for intelligent energy monitoring and management of electrical power networks |
-
2023
- 2023-06-27 CN CN202310765060.1A patent/CN116523077B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613041A (en) * | 2020-12-25 | 2021-04-06 | 南方电网深圳数字电网研究院有限公司 | Container mirror image detection method and device, electronic equipment and storage medium |
| CN113037802A (en) * | 2021-01-27 | 2021-06-25 | 东南大学 | Cloud-side data cooperation method for power Internet of things |
| CN112965785A (en) * | 2021-03-05 | 2021-06-15 | 食亨(上海)科技服务有限公司 | Container-based micro-service application development method and development platform |
| CN114489693A (en) * | 2021-12-27 | 2022-05-13 | 国网冀北电力有限公司 | Comprehensive transformer state monitoring system based on edge application |
| CN116028157A (en) * | 2022-11-09 | 2023-04-28 | 新浪技术（中国）有限公司 | Risk identification method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116523077A (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112579653B (en) | Gradual contextualization and analysis of industrial data | |
| US20200371857A1 (en) | Methods and systems for autonomous cloud application operations | |
| Dowdeswell et al. | Finding faults: A scoping study of fault diagnostics for Industrial Cyber–Physical Systems | |
| CN107835964B (en) | Control contextualization and reasoning about controls | |
| CN112580813B (en) | Contextualization of industrial data at device level | |
| EP3101599A2 (en) | Advanced analytical infrastructure for machine learning | |
| US11868101B2 (en) | Computer system and method for creating an event prediction model | |
| US20170372224A1 (en) | Deep learning for imputation of industrial multivariate time-series | |
| CN112581303A (en) | Artificial intelligence channel for industrial automation | |
| CN113614359A (en) | Method and system for predicting risk of observable damage in wind turbine gearbox assembly | |
| CN111026409A (en) | Automatic monitoring method, device, terminal equipment and computer storage medium | |
| US10810508B1 (en) | Methods and apparatus for classifying and discovering historical and future operational states based on Boolean and numerical sensor data | |
| US20200174462A1 (en) | Method and system for elimination of fault conditions in a technical installation | |
| Wöstmann et al. | A retrofit approach for predictive maintenance | |
| CN104572232A (en) | Agentless baseline profile compilation for application monitoring solution | |
| CN117235524A (en) | Learning training platform of automatic valuation model | |
| CN116523077B (en) | Early warning method, device, equipment and storage medium based on container technology | |
| Hernández et al. | Design of an AI-based workflow-guiding system for stratified sampling | |
| Moin et al. | Supporting AI engineering on the IoT edge through model-driven TinyML | |
| Franco et al. | Predictive maintenance: An embedded system approach | |
| CN115277473A (en) | Remote operation and maintenance method and device for edge gateway, computer equipment and storage medium | |
| EP4071670A1 (en) | Technical system for a centralized generation of a plurality of trained, retrained and/or monitored machine learning models, wherein the generated machine learning models are executed decentral | |
| Mayadevi et al. | SCADA-based operator support system for power plant equipment fault forecasting | |
| CN117851269B (en) | Cloud-based automatic test environment management method and system | |
| Fan | Wisdom of the crowd for fault detection and prognosis |
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 |