CN113297957A - Electricity utilization characteristic waveform extraction and analysis framework based on edge calculation - Google Patents
Electricity utilization characteristic waveform extraction and analysis framework based on edge calculation Download PDFInfo
- Publication number
- CN113297957A CN113297957A CN202110562439.3A CN202110562439A CN113297957A CN 113297957 A CN113297957 A CN 113297957A CN 202110562439 A CN202110562439 A CN 202110562439A CN 113297957 A CN113297957 A CN 113297957A
- Authority
- CN
- China
- Prior art keywords
- terminal
- cloud
- data
- characteristic
- lightweight
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 16
- 238000004458 analytical method Methods 0.000 title claims abstract description 15
- 238000004364 calculation method Methods 0.000 title claims abstract description 13
- 230000005611 electricity Effects 0.000 title description 5
- 238000013145 classification model Methods 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 22
- 238000003745 diagnosis Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Water Supply & Treatment (AREA)
- Signal Processing (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power utilization characteristic waveform extraction and analysis framework based on edge calculation, which comprises a terminal and a cloud end, wherein the terminal comprises an equipment real-time data collection module, a real-time data calculation and analysis module and a lightweight feature library, and the cloud end comprises a fault classification model module based on machine learning and a lightweight feature library extraction module; the terminal is deployed on a power utilization side, collects a time sequence of power utilization data of a user in real time and high frequency, calculates a characteristic value of the time sequence data in real time, uploads the characteristic value to the cloud, the cloud establishes a lightweight characteristic library through a fault classification model module and a lightweight characteristic library extraction module and feeds the lightweight characteristic library back to the terminal, and the terminal performs characteristic extraction and fault analysis on the collected power utilization data according to the deployed lightweight characteristic library. According to the invention, the abnormal fault detection of the power utilization side is realized efficiently by utilizing edge cloud cooperation.
Description
Technical Field
The invention relates to the technical fields of electric power data analysis, electric power data abnormity prediction, edge cloud cooperative computing and the like, in particular to an electric power utilization characteristic waveform extraction and analysis framework based on edge computing.
Background
In recent years, there are two typical methods around the problem of abnormal failure detection on the electricity-consuming side. The first method sets a simple threshold value at the terminal equipment for diagnosis, simultaneously stores data in a storage device, and after power utilization abnormity occurs, extracts data from the terminal through an off-line method on site and analyzes the data, and the method focuses more on post analysis; in the second method, the terminal transmits data to the cloud in real time, and the cloud performs model training and online fault diagnosis. The first method adopts a simple fault diagnosis method with unsatisfactory effect, and the second method improves the accuracy of fault identification even if the cloud participates in fault diagnosis, but because the fault diagnosis is not performed locally, delay is generated in the data transmission process, and the requirement of timely response when a fault occurs cannot be met. Therefore, a large amount of calculation tasks cannot be simply put on the cloud for processing, and the terminal equipment is only used for collecting and uploading data, and the cloud needs to be subjected to load reduction and the terminal equipment needs to be subjected to appropriate load increase so as to achieve the aims of fully utilizing resources and responding to fault data in time.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides an electricity utilization characteristic waveform extraction and analysis framework based on edge calculation, and realizes the abnormal fault detection of the electricity utilization side by utilizing edge cloud cooperation.
One technical scheme for achieving the above purpose is as follows: an electricity utilization characteristic waveform extraction and analysis framework based on edge calculation comprises a terminal and a cloud end;
the terminal comprises an equipment real-time data collection module, a real-time data calculation and analysis module and a lightweight feature library, and the cloud end comprises a fault classification model module based on machine learning and a lightweight feature library extraction module;
the terminal is deployed on a power utilization side, collects a time sequence of power utilization data of a user in real time and high frequency, calculates a characteristic value of the time sequence data in real time, uploads the characteristic value to the cloud, the cloud establishes a lightweight characteristic library through a fault classification model module and a lightweight characteristic library extraction module and feeds the lightweight characteristic library back to the terminal, and the terminal performs characteristic extraction and fault analysis on the collected power utilization data according to the deployed lightweight characteristic library.
Further, the working method of issuing the lightweight feature library by the cloud comprises three processes of generating the lightweight feature library by the cloud, collecting and diagnosing data in real time by the terminal, and interacting the cloud and the terminal;
step 1, the cloud generates a lightweight feature library: extracting the characteristics of a fault classification model through a fault classification model module based on machine learning, and simplifying a row description on a fault data characteristic library so that the fault data characteristic library can be sent to a terminal and identified and utilized by the terminal;
Furthermore, when the cloud end interacts with the terminal, the mutual agreement is observed, the agreed content comprises rules of uploading, issuing and updating the feature library, so that the situation that the edge cloud collaborates to complete power failure diagnosis is guaranteed, and the cloud end adjusts the computing work of the cloud end according to the diagnosis effect of the terminal.
Compared with the prior art, the method can make up for the defect of weak computing capability of the terminal and the low timeliness of online diagnosis. By fully utilizing the characteristics of data, the training result of the cloud is applied to the terminal equipment in a lightweight form by adopting an edge calculation method, and is uploaded to the cloud in different ways according to different diagnosis results, so that a more rapid and simple diagnosis way is formed, and due to the fact that the terminal and the cloud are constantly in contact, timely interaction is carried out, and the timeliness of a terminal characteristic library is guaranteed.
Drawings
Fig. 1 is a schematic diagram of an electrical characteristic waveform extraction and analysis architecture based on edge calculation according to the present invention.
Detailed Description
Referring to fig. 1, in order to better understand the technical solution of the present invention, the following detailed description is made by specific examples:
the terminal mainly comprises the following modules for realizing real-time data collection and fault discovery:
the real-time data acquisition module 1 is used for collecting three-phase voltage electric current data of a power utilization side in real time at the frequency of 6.4khz, and in the experimental process, the AD value of one phase is extracted, and the following conversion is required to be carried out:
I＝Idata/104.9
U＝Udata/12482.5
the real current value and the real voltage value can be obtained after conversion, and the unit is milliampere (mA) and volt (V) respectively.
The real-time computing module 2: the real-time computing module provides a computing library through a terminal, the computing library comprises computing methods of specific indexes, but in actual use, all the methods do not need to be called, and only specified characteristics are computed according to configuration files issued by a cloud, which is an important step in collaborative computing.
The fault diagnosis module 3: the module comprises two sub-modules, a configuration file and a diagnosis method. The method for diagnosing the fault identification is provided by the server side, and classification results of the server side are fully utilized.
The data uploading module 4: considering the timeliness of fault diagnosis, the energy consumption problem of terminal equipment and the bandwidth problem of transmission, it is necessary to adopt different uploading modes for normal and abnormal data, so in the module, the normal data is uploaded at time intervals and the abnormal data is uploaded in real time.
The cloud terminal is matched with the terminal in the edge cloud coordination process to realize diagnosis, and the cloud terminal comprises the following modules:
the data collecting module 5: the cloud needs to face the problem of uploading a large amount of data, so the problem that the processing speed is not matched needs to be solved, the uploaded data is temporarily stored by setting a cache mechanism at the cloud, and when the processing speed of the cloud can be matched, the data is cached and taken out.
The machine learning module 6: and selecting a proper machine learning method, learning the characteristics of the electric power data uploaded to the cloud end, and realizing the purpose of classifying the electric power data, wherein the characteristic library can be better extracted only if the data classification of the cloud end is accurate enough.
And (3) extracting a characteristic library module 7: extracting features from fault data, describing the features into a feature library form, and using the feature library as a means and a method for judging abnormity by a terminal. In order to realize a lighter-weight feature library, the dimension reduction of the features is needed; and obtaining a more meaningful feature library and sending the more meaningful feature library to the terminal.
The file issuing module 8: the module is an important step in the interaction process of the terminal and the cloud. The diagnosis method and the configuration file in the module are issued to the terminal, and the terminal can accurately and efficiently finish the work of fault diagnosis only by diagnosing according to the content in the issued file; and the module ensures timeliness of the feature library, and the problem of asynchronism between the cloud and the terminal cannot occur.
The specific method for realizing the cooperative computing of the terminal device and the cloud device can make up for the defect of poor computing performance of the terminal and reduce computing tasks of the cloud.
It should be understood by those skilled in the art that the above embodiments are only for illustrating the present invention and are not to be used as a limitation of the present invention, and that changes and modifications to the above described embodiments are within the scope of the claims of the present invention as long as they are within the spirit and scope of the present invention.
Claims (3)
1. The utility model provides a power consumption characteristic waveform draws and analysis framework based on edge calculation, includes terminal and high in the clouds, its characterized in that:
the terminal comprises an equipment real-time data collection module, a real-time data calculation and analysis module and a lightweight feature library, and the cloud end comprises a fault classification model module based on machine learning and a lightweight feature library extraction module;
the terminal is deployed on a power utilization side, collects a time sequence of power utilization data of a user in real time and high frequency, calculates a characteristic value of the time sequence data in real time, uploads the characteristic value to the cloud, the cloud establishes a lightweight characteristic library through a fault classification model module and a lightweight characteristic library extraction module and feeds the lightweight characteristic library back to the terminal, and the terminal performs characteristic extraction and fault analysis on the collected power utilization data according to the deployed lightweight characteristic library.
2. The architecture for extracting and analyzing power consumption characteristic waveforms based on edge computing according to claim 1, wherein the working method of issuing the lightweight feature library by the cloud comprises three processes of generating the lightweight feature library by the cloud, collecting and diagnosing data in real time by the terminal, and interacting between the cloud and the terminal;
step 1, the cloud generates a lightweight feature library: extracting the characteristics of a fault classification model through a fault classification model module based on machine learning, and simplifying a row description on a fault data characteristic library so that the fault data characteristic library can be sent to a terminal and identified and utilized by the terminal;
step 2, the terminal collects data in real time and diagnoses: the terminal collects power utilization data in a real-time high-frequency mode, and according to the instruction provided by the cloud, the collected data are calculated and analyzed through the locally deployed lightweight feature library. A
3. The architecture of claim 2, wherein the cloud and the terminal follow conventions during interaction, the conventions include rules for uploading, issuing, and updating the feature library, so that the cloud cooperatively completes power failure diagnosis, and the cloud adjusts computing work of the cloud according to the diagnosis effect of the terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110562439.3A CN113297957A (en) | 2021-05-24 | 2021-05-24 | Electricity utilization characteristic waveform extraction and analysis framework based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110562439.3A CN113297957A (en) | 2021-05-24 | 2021-05-24 | Electricity utilization characteristic waveform extraction and analysis framework based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113297957A true CN113297957A (en) | 2021-08-24 |
Family
ID=77324044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110562439.3A Pending CN113297957A (en) | 2021-05-24 | 2021-05-24 | Electricity utilization characteristic waveform extraction and analysis framework based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113297957A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114338743A (en) * | 2021-12-30 | 2022-04-12 | 上海众人智能科技有限公司 | Intelligent recognition defense system for cloud side end data interaction |
| CN114416415A (en) * | 2022-01-17 | 2022-04-29 | 南京新联电子股份有限公司 | Remote online fault detection method and system for Hongmon operating system and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130195321A1 (en) * | 2010-09-22 | 2013-08-01 | Matteo Sacchi | Pantograph monitoring system and method |
| CN111062651A (en) * | 2020-03-18 | 2020-04-24 | 南京中电科能技术有限公司 | Safe power utilization management system and method based on edge calculation and big data analysis |
| CN111428606A (en) * | 2020-03-19 | 2020-07-17 | 华南师范大学 | Lightweight face comparison verification method facing edge calculation |
| CN111562538A (en) * | 2020-05-11 | 2020-08-21 | 昆明能讯科技有限责任公司 | Expert diagnosis method and device for electric energy meter operation |
| CN111985561A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Fault diagnosis method and system for intelligent electric meter and electronic device |
| CN112286751A (en) * | 2020-11-24 | 2021-01-29 | 华中科技大学 | Intelligent diagnosis system and method for high-end equipment fault based on edge cloud cooperation |
| CN112379214A (en) * | 2020-10-27 | 2021-02-19 | 广东电网有限责任公司广州供电局 | Power grid fault detection method and device |
| CN112527613A (en) * | 2020-11-30 | 2021-03-19 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
-
2021
- 2021-05-24 CN CN202110562439.3A patent/CN113297957A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130195321A1 (en) * | 2010-09-22 | 2013-08-01 | Matteo Sacchi | Pantograph monitoring system and method |
| CN111062651A (en) * | 2020-03-18 | 2020-04-24 | 南京中电科能技术有限公司 | Safe power utilization management system and method based on edge calculation and big data analysis |
| CN111428606A (en) * | 2020-03-19 | 2020-07-17 | 华南师范大学 | Lightweight face comparison verification method facing edge calculation |
| CN111562538A (en) * | 2020-05-11 | 2020-08-21 | 昆明能讯科技有限责任公司 | Expert diagnosis method and device for electric energy meter operation |
| CN111985561A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Fault diagnosis method and system for intelligent electric meter and electronic device |
| CN112379214A (en) * | 2020-10-27 | 2021-02-19 | 广东电网有限责任公司广州供电局 | Power grid fault detection method and device |
| CN112286751A (en) * | 2020-11-24 | 2021-01-29 | 华中科技大学 | Intelligent diagnosis system and method for high-end equipment fault based on edge cloud cooperation |
| CN112527613A (en) * | 2020-11-30 | 2021-03-19 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114338743A (en) * | 2021-12-30 | 2022-04-12 | 上海众人智能科技有限公司 | Intelligent recognition defense system for cloud side end data interaction |
| CN114416415A (en) * | 2022-01-17 | 2022-04-29 | 南京新联电子股份有限公司 | Remote online fault detection method and system for Hongmon operating system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022228049A1 (en) | Method for diagnosing malfunction in aero-engine on basis of 5g edge computing and deep learning | |
| CN106662072B (en) | Wind-driven generator method for monitoring state and system | |
| CN109492667A (en) | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring | |
| CN113297957A (en) | Electricity utilization characteristic waveform extraction and analysis framework based on edge calculation | |
| CN108197817A (en) | A kind of method of the non-intrusion type load transient state monitoring based on big data | |
| CN103116090A (en) | Three-phrase pulse-width modulation (PWM) rectifier fault diagnosis method based on wavelet packet analysis and support vector machine | |
| CN111628494B (en) | Low-voltage distribution network topology identification method and system based on logistic regression method | |
| CN104680612A (en) | Automatic IT equipment inspection method | |
| CN109325936A (en) | Controller switching equipment defect image identification terminal and method based on neural network deep learning | |
| CN108228683A (en) | A kind of distributed intelligence electric network data analysis platform based on cloud computing | |
| CN113030723A (en) | Alternating current asynchronous motor state monitoring system | |
| CN108872743A (en) | A kind of electric energy quality real-time monitoring analysis system and method based on wavelet transformation | |
| Liu et al. | Cloud-edge-end cooperative detection of wind turbine blade surface damage based on lightweight deep learning network | |
| CN115828091A (en) | Non-invasive load identification method and system based on end-cloud cooperation | |
| CN111881793A (en) | Non-invasive load monitoring method and system based on capsule network | |
| CN111024820B (en) | Health monitoring system for offshore wind power blade and data processing method thereof | |
| CN105445577A (en) | Power quality disturbance source working condition identifying method | |
| Wang et al. | Survey on Advanced Equipment Fault Diagnosis and Warning Based on Big Data Technique | |
| CN114200203B (en) | Fault monitoring method and system for transformer substation metering device | |
| CN116911161A (en) | Data-enhanced deep learning transient voltage stability evaluation method | |
| CN115186935A (en) | Electromechanical device nonlinear fault prediction method and system | |
| CN111882284A (en) | Operation monitoring method and system for distributed power supply grid connection | |
| CN111447284A (en) | Dynamic data compression, communication and restoration method and device based on Fourier transform algorithm, terminal equipment and readable storage medium | |
| CN209692433U (en) | The online monitoring system of renewable energy station | |
| CN113420832B (en) | Power grid fault diagnosis system and method based on multidimensional data similarity matching |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210824 |
|
| WD01 | Invention patent application deemed withdrawn after publication |