CN113077138A - Power load identification method based on waveform data characteristic analysis - Google Patents
Power load identification method based on waveform data characteristic analysis Download PDFInfo
- Publication number
- CN113077138A CN113077138A CN202110343324.5A CN202110343324A CN113077138A CN 113077138 A CN113077138 A CN 113077138A CN 202110343324 A CN202110343324 A CN 202110343324A CN 113077138 A CN113077138 A CN 113077138A
- Authority
- CN
- China
- Prior art keywords
- data
- load identification
- characteristic
- harmonic
- method based
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 230000005611 electricity Effects 0.000 claims abstract description 9
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 238000010606 normalization Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000012544 monitoring process Methods 0.000 claims description 8
- 230000001052 transient effect Effects 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910010293 ceramic material Inorganic materials 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention provides an electrical load identification method based on waveform data characteristic analysis, which comprises the following steps: acquiring electrical appliance characteristic data and electricity utilization process data; respectively carrying out normalization processing on the data acquired in the previous step from each dimension, carrying out feature extraction on the preprocessed sample data set, classifying according to features, taking data of corresponding relations between classification features and electrical appliance parts and power utilization processes as a data source of machine learning or classification decision of a load identification process, establishing a classification decision model, and carrying out load identification; the invention extracts harmonic data characteristic models of different components by decomposing different types of electric appliances, and improves the accuracy of load identification by adapting to the change of different electric appliance types through combined characteristics.
Description
Technical Field
The invention belongs to the field of electric load identification, and particularly relates to an electric load identification technology based on waveform data characteristic analysis.
Background
With the continuous construction of the power internet of things, the power demand side management shows the trend of gradually developing towards refinement. The method is not only the requirement of power users on energy management and electricity economy, but also one of the requirements of social management on fine management and treatment.
Non-intrusive power load identification is used as one of key technologies of fine management of a demand side, and important reference basis is provided for efficient electric energy dispatching and power grid structure optimization by monitoring information such as categories, running states and power consumption conditions of all electric equipment of a user in real time. The load identification result can provide information such as the running condition and power consumption of household appliances and enterprise electric equipment for a user, and a foundation is provided for reasonably improving the energy efficiency management level. Meanwhile, in the aspect of social governance, the identification of the electrical load is of great significance. For example, aiming at the standard electricity utilization behavior of a dormitory of a college, the electricity utilization load identification technology can distinguish whether the dormitory uses a high-power electric appliance illegally and information such as the use time and the type of the electric appliance is provided for a management party, so that a monitoring means is provided for reducing the occurrence of electrical safety events. The power load identification can also provide a technical means for intelligent community and home safety management, and support is provided for reducing the life risk of the elderly living alone.
At present, the algorithm of non-intrusive power load identification mostly adopts methods based on statistical analysis, such as data mining, machine learning, neural network and the like, and the analyzed data basis is waveform data obtained by sampling voltage and current waveform data of power utilization. The algorithms are mature, and effective appliance type recognition can be performed after pre-input appliance characteristic samples, such as typical appliance device characteristic data of V-I track image characteristics and the like, are trained and learned. However, the prior art has the following two problems:
1. the analysis and recognition time is long. The statistical and learning based approach requires a large number of samples to be input and the recognition process requires long statistical analysis;
2. with the change of the electrical technology, the existing scheme needs to continuously input new samples, otherwise, the recognition rate is reduced.
Therefore, aiming at the above problems of electrical load identification, the invention provides an identification method of electrical appliance combination characteristics, and transient characteristic data is adopted as one of judgment bases.
Disclosure of Invention
The invention aims to provide an electrical load identification method based on waveform data characteristic analysis, aiming at solving the problems in the existing non-intrusive load identification process, so that the load identification efficiency and the identification accuracy are effectively improved.
The technical scheme of the invention is as follows:
a power load identification method based on waveform data characteristic analysis comprises the following steps:
s1, electric appliance characteristic data acquisition step: the method comprises the steps of carrying out component decomposition on the existing electric appliance, obtaining waveform data according to the electrical characteristics of different components, and extracting corresponding characteristic data;
s2, acquiring power utilization process data: carrying out data acquisition on each power utilization process of the electrical appliance component, and extracting corresponding characteristic data;
s3, establishing a classification decision model: respectively carrying out normalization processing on the data acquired in the steps S1 and S2 from each dimension, carrying out feature extraction on the preprocessed sample data set, classifying according to features, taking data of the corresponding relation of the classification features, the electrical appliance parts and the power utilization process as a database of machine learning or classification decision of the load identification process, and establishing a classification decision model;
s4, load identification: acquiring power grid waveform data of a load to be identified in real time, and extracting characteristic data; and inputting the data to be recognized into a classification decision model, and matching the data to be recognized with the corresponding combination of the type and the component of the electric appliance and the electricity utilization process.
Further, the characteristic data are transient characteristics, including harmonic characteristic data, V-I characteristic data and power characteristic data.
Further, the electricity utilization process comprises the processes of starting, stopping and operating the equipment.
Further, the harmonic feature data is high-frequency harmonic feature analysis data of more than 21 times.
Further, the harmonic characteristics include: the harmonic wave monitoring system comprises a voltage, a current and harmonic wave content, harmonic wave power, a harmonic wave total distortion rate and harmonic wave upstream and downstream relations among nodes in a monitoring network in different time periods.
Further, the classification decision model adopts K-Means cluster analysis, decision tree classification and a support vector machine algorithm.
The invention has the beneficial effects that:
the invention improves the accuracy of identification by adopting an identification method combining transient characteristic data and steady-state characteristic data. The steady-state characteristic data analysis adopts the existing algorithms of data mining, machine learning and the like; the transient characteristic data is subjected to harmonic analysis in the running process of the electric appliance, in particular to high-frequency harmonic characteristic analysis for more than 21 times.
The invention extracts harmonic data characteristic models of different components by decomposing different types of electric appliances, thereby providing the combination characteristics of the electric appliances. The load identification method can adapt to the change of different electrical appliance types through the combined characteristics, and improves the accuracy of load identification.
The invention relates to a method for preparing a high-temperature-resistant ceramic material.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.
FIG. 1 shows a flow chart for implementing the technical solution of the present invention
FIG. 2 illustrates a characteristic data acquisition and analysis flow diagram of the present invention.
FIG. 3 shows a typical compressor section V-I trace image of the present invention.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein.
As shown in fig. 1, a method for identifying an electrical load based on waveform data feature analysis includes the following steps:
1. typical appliance feature decomposition
The typical electric appliance characteristic decomposition is to decompose the existing typical electric appliance structure, and meanwhile, according to the electric characteristics of different parts, corresponding characteristic data extracted according to waveform data mainly comprise transient characteristics such as harmonic analysis and the like. For example, a refrigerator is composed of electrical parts such as a compressor, a condenser, an electrical system and accessories; the air conditioner consists of electric parts such as a refrigeration compressor, a condenser, a capillary tube, an evaporator, a motor and the like.
2. Electrical characteristic component data analysis
The method comprises the steps of extracting characteristics of data acquired in the power utilization process of electrical components such as a compressor, a condenser and the like, wherein the data comprises V-I characteristics, power characteristics and harmonic characteristics in the starting, stopping and running processes of equipment, carrying out normalization processing on the data, then carrying out characteristic extraction, and reconstructing a sample data set based on a characteristic sample data set. These sample data sets serve as data sources for machine learning or classification decisions of the late stage load recognition process.
V-I characteristics: the V-I track characteristics belong to high-frequency characteristics and can reflect equipment characteristics such as current waveforms, impedance characteristics and the like when the equipment runs in a steady state. The V-I track is usually extracted from high-frequency aggregated data, and assuming that only one electrical component device is opened at a time, the voltage and current waveforms of the single device can be extracted by calculating the difference between the steady-state voltage and the steady-state current before and after the opening event, so that the V-I track is extracted. Figure 3 shows a compressor section V-I trace image of the present invention.
Harmonic characteristics: harmonics (harmonics) are sinusoidal components of a periodic electrical quantity, the frequency of which is an integer multiple of the fundamental frequency. An important indicator of harmonics is the Total Harmonic Distortion (THD), defined as the degree to which a distorted waveform deviates from a sinusoidal waveform due to harmonics. The harmonic characteristics include frequency, content, total distortion rate, and other data characteristics. The harmonic characteristics generated in the starting, closing and running stages of the electric appliance are different.
3. The data of the feature samples is obtained by sampling the feature samples,
after waveform data analysis, normalization processing needs to be performed on the data, then feature extraction is performed, and a sample data set is reconstructed based on the feature sample data set. The sample data sets are used as data sources for machine learning or classification decision in the load identification process, machine learning is carried out, and a classification model is established.
4. Real-time waveform signature data analysis
During load identification, high-frequency sampling is carried out on the waveform data of the power grid entering the home, wherein the waveform data comprises transient state and steady state data such as active power, voltage, current, harmonic waves, voltage noise and the like which are applied and used. Then, normalization operation is carried out on the data of each dimension of the load characteristic, and characteristic analysis is carried out on the preprocessed data set.
Taking harmonic characteristic analysis as an example, a harmonic source analysis and positioning model based on monitoring data is adopted to position a harmonic source and separate specific harmonic characteristics for classification and matching.
And (3) screening harmonic data: calculating the content of each harmonic of voltage and current, calculating harmonic power, calculating the total distortion rate of harmonic, calculating the upstream and downstream relations of harmonic in different time periods among nodes in a monitoring network, and separating out a specific harmonic characteristic sample set of a certain time point;
5. appliance type identification
After waveform characteristic data is analyzed and extracted, classification matching is carried out according to characteristic types, and a classification decision model is adopted, namely algorithms such as K-Means cluster analysis, decision tree classification and a support vector machine are used for classifying sample data to obtain the combination of the type of an electric appliance, components and the electricity utilization process.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
Claims (6)
1. A power load identification method based on waveform data characteristic analysis is characterized by comprising the following steps:
s1, electric appliance characteristic data acquisition step: the method comprises the steps of carrying out component decomposition on the existing electric appliance, obtaining waveform data according to the electrical characteristics of different components, and extracting corresponding characteristic data;
s2, acquiring power utilization process data: carrying out data acquisition on each power utilization process of the electrical appliance component, and extracting corresponding characteristic data;
s3, establishing a classification decision model: respectively carrying out normalization processing on the data acquired in the steps S1 and S2 from each dimension, carrying out feature extraction on the preprocessed sample data set, classifying according to features, taking data of the corresponding relation of the classification features, the electrical appliance parts and the power utilization process as a database of machine learning or classification decision of the load identification process, and establishing a classification decision model;
s4, load identification: acquiring power grid waveform data of a load to be identified in real time, and extracting characteristic data; and inputting the data to be recognized into a classification decision model, and matching the data to be recognized with the corresponding combination of the type and the component of the electric appliance and the electricity utilization process.
2. The electrical load identification method based on waveform data feature analysis according to claim 1, characterized in that: the characteristic data are transient characteristics, including harmonic characteristic data, V-I characteristic data and power characteristic data.
3. The electrical load identification method based on waveform data feature analysis according to claim 1, characterized in that: the electricity utilization process comprises the processes of starting, stopping and running of the equipment.
4. The electrical load recognition method based on waveform data feature analysis according to claim 3, wherein: the harmonic characteristic data adopts high-frequency harmonic characteristic analysis data of more than 21 times.
5. The electrical load identification method based on waveform data feature analysis according to claim 1, characterized in that: the harmonic characteristics include: the harmonic wave monitoring system comprises a voltage, a current and harmonic wave content, harmonic wave power, a harmonic wave total distortion rate and harmonic wave upstream and downstream relations among nodes in a monitoring network in different time periods.
6. The electrical load identification method based on waveform data feature analysis according to claim 1, characterized in that: the classification decision model adopts K-Means cluster analysis, decision tree classification and support vector machine algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110343324.5A CN113077138A (en) | 2021-03-30 | 2021-03-30 | Power load identification method based on waveform data characteristic analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110343324.5A CN113077138A (en) | 2021-03-30 | 2021-03-30 | Power load identification method based on waveform data characteristic analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113077138A true CN113077138A (en) | 2021-07-06 |
Family
ID=76611893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110343324.5A Pending CN113077138A (en) | 2021-03-30 | 2021-03-30 | Power load identification method based on waveform data characteristic analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113077138A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114386767A (en) * | 2021-12-14 | 2022-04-22 | 南通联拓信息科技有限公司 | Fault early warning method and system for power distribution operation and maintenance management system |
| CN114689975A (en) * | 2022-04-01 | 2022-07-01 | 深圳市华检测试技术服务有限公司 | Harmonic current-based product testing method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009048960A1 (en) * | 2007-10-12 | 2009-04-16 | Edsa Micro Corporation | Converting cad drawing files into intelligent objects for the design, analysis of electrical power systems |
| CN201726430U (en) * | 2010-07-29 | 2011-01-26 | 上海康汇通信信息网络有限公司 | Vehicle data acquiring terminal |
| CN107832705A (en) * | 2017-11-08 | 2018-03-23 | 天津大学 | A kind of non-intrusion type load recognition methods based on canonical correlation analysis |
| CN109492667A (en) * | 2018-10-08 | 2019-03-19 | 国网天津市电力公司电力科学研究院 | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring |
| CN109579220A (en) * | 2018-10-15 | 2019-04-05 | 平安科技（深圳）有限公司 | Air-conditioning system fault detection method, device, electronic equipment |
| CN111598330A (en) * | 2020-05-13 | 2020-08-28 | 国网河北省电力有限公司电力科学研究院 | Residential electricity load prediction method based on load identification technology |
| CN112149510A (en) * | 2020-08-27 | 2020-12-29 | 广东工业大学 | Non-invasive load detection method |
-
2021
- 2021-03-30 CN CN202110343324.5A patent/CN113077138A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009048960A1 (en) * | 2007-10-12 | 2009-04-16 | Edsa Micro Corporation | Converting cad drawing files into intelligent objects for the design, analysis of electrical power systems |
| CN201726430U (en) * | 2010-07-29 | 2011-01-26 | 上海康汇通信信息网络有限公司 | Vehicle data acquiring terminal |
| CN107832705A (en) * | 2017-11-08 | 2018-03-23 | 天津大学 | A kind of non-intrusion type load recognition methods based on canonical correlation analysis |
| CN109492667A (en) * | 2018-10-08 | 2019-03-19 | 国网天津市电力公司电力科学研究院 | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring |
| CN109579220A (en) * | 2018-10-15 | 2019-04-05 | 平安科技（深圳）有限公司 | Air-conditioning system fault detection method, device, electronic equipment |
| CN111598330A (en) * | 2020-05-13 | 2020-08-28 | 国网河北省电力有限公司电力科学研究院 | Residential electricity load prediction method based on load identification technology |
| CN112149510A (en) * | 2020-08-27 | 2020-12-29 | 广东工业大学 | Non-invasive load detection method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114386767A (en) * | 2021-12-14 | 2022-04-22 | 南通联拓信息科技有限公司 | Fault early warning method and system for power distribution operation and maintenance management system |
| CN114689975A (en) * | 2022-04-01 | 2022-07-01 | 深圳市华检测试技术服务有限公司 | Harmonic current-based product testing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106483370B (en) | Non-intrusion type household loads real-time identification method and device based on multi-feature fusion | |
| CN109598451B (en) | Non-invasive load identification method based on PCA (principal component analysis) and LSTM (least Square TM) neural network | |
| CN111830347B (en) | Two-stage non-invasive load monitoring method based on event | |
| CN113077138A (en) | Power load identification method based on waveform data characteristic analysis | |
| CN106093565B (en) | A kind of electricity subentry measurement method and device based on steady state characteristic Waveform Matching | |
| CN108197817A (en) | A kind of method of the non-intrusion type load transient state monitoring based on big data | |
| CN106655160A (en) | Non-intrusion electric power load decomposition identification decision method and system | |
| Luan et al. | An adaptive two-stage load event detection method for nonintrusive load monitoring | |
| CN112198385A (en) | Non-invasive load monitoring method | |
| Yu et al. | Non-intrusive adaptive load identification based on siamese network | |
| CN108510165A (en) | A kind of analysis method for user power utilization behavior | |
| CN112909923A (en) | Non-invasive household load behavior recognition device based on DTW algorithm | |
| CN111327118B (en) | Non-invasive power load identification method | |
| CN114139820A (en) | Improved modal decomposition method for non-invasive electric energy load prediction | |
| CN105550450B (en) | Electric energy quality interference source characteristic harmonic modeling method | |
| CN113193654A (en) | Event-driven non-intrusive power load monitoring method based on transient and steady state combination characteristics | |
| CN115112989B (en) | Non-invasive load monitoring method based on low-frequency data | |
| CN115169382A (en) | Low-frequency signal non-invasive load decomposition algorithm | |
| CN116340759A (en) | Nonlinear load state identification method based on time-frequency analysis | |
| Guohua et al. | Research on non-intrusive load monitoring based on random forest algorithm | |
| CN115825602A (en) | Load identification method and system for comprehensive multivariate information similarity analysis | |
| CN114662576A (en) | Non-invasive storage battery car charging detection method and system based on supervised classification | |
| Huang et al. | An online non-intrusive load monitoring method based on Hidden Markov model | |
| CN115293195A (en) | Analysis and prediction method and device applied to coal-to-electricity load characteristics | |
| Yao et al. | AdaBoost-CNN: a hybrid method for electricity theft detection |
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 |