CN113034305A - Non-invasive load monitoring event classification method and storage medium - Google Patents
Non-invasive load monitoring event classification method and storage medium Download PDFInfo
- Publication number
- CN113034305A CN113034305A CN202110182390.9A CN202110182390A CN113034305A CN 113034305 A CN113034305 A CN 113034305A CN 202110182390 A CN202110182390 A CN 202110182390A CN 113034305 A CN113034305 A CN 113034305A
- Authority
- CN
- China
- Prior art keywords
- load data
- power load
- power
- data segments
- classifying
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 230000003534 oscillatory effect Effects 0.000 claims description 19
- 230000010355 oscillation Effects 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 239000012634 fragment Substances 0.000 claims description 6
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 230000005611 electricity Effects 0.000 claims description 5
- 230000002441 reversible effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a classification method and a storage medium for non-intrusive load monitoring events, which are used for extracting power load data segments of different electric equipment from power load data, clustering based on the similarity among a plurality of power load data segments and classifying the different electric equipment.
Description
Technical Field
The invention relates to the technical field of power utilization, in particular to a classification method and a storage medium for non-invasive load monitoring events.
Background
Non-intrusive load monitoring (NILM) is a computational technique for estimating the power demand of a single device from a single electricity meter that measures data for multiple devices. The typical application scenario is the generation of the whole house smart meter by the item of electricity fee, and the purpose of the generation is to help a user/power grid monitor and manage the electricity consumption behavior of the equipment. The power and the like in the power data contain abundant electrical appliance characteristics, and a reliable basis can be provided for monitoring and identifying the load. The main technical difficulty in the prior art lies in how to accurately extract fragments of power utilization events, so that the robustness of an identification algorithm is improved, and an easy-to-use and reliable event fragment database is also established. Analyzing the transient characteristics of an event using high frequency data can improve the accuracy and speed of load identification, but high frequency signal acquisition can greatly increase the cost of the measurement device. In the prior art, most low frequency methods of non-intrusive load monitoring can be classified as: 1. the event fragments are extracted manually, and the sample collection is time-consuming and labor-consuming and lacks universality; 2. the variable point detection based on the statistical method has poor interpretability and is very sensitive to the setting of the hyper-parameters, so the reliability is low and the practical application is difficult.
Accordingly, a novel method for classifying non-intrusive load monitoring events and a storage medium are provided to retain the positive effects of existing non-intrusive load monitoring methods and to eliminate the negative effects of existing non-intrusive load monitoring methods.
Disclosure of Invention
The invention aims to provide a non-intrusive load monitoring event classification method, which is used for extracting power load data segments of different electric equipment from power load data and clustering based on the similarity among a plurality of power load data segments.
The invention provides a classification method of a non-intrusive load monitoring event, which comprises the following steps: acquiring power load data segments in a plurality of preset historical time periods, wherein the power load data segments in the preset historical time periods comprise a plurality of power load data sequences; performing oscillatory detection on the plurality of power load data segments and filtering to obtain a plurality of non-oscillatory power load data segments; and carrying out cluster analysis on a plurality of non-oscillatory power load data segments.
Further, in performing oscillation detection on each power load data segment and filtering out the power load data segment to obtain a non-oscillation power load data segment, the method specifically includes the following steps: collecting a plurality of power load data sequences of a power load data fragment; calculating a differential sequence of the plurality of power load data sequences; and counting a maximum number of consecutive inversions of the differential sequence of the plurality of power load data sequences; judging whether the maximum continuous reverse number of each differential sequence is greater than a threshold value; if yes, judging that the power load data sequence is an oscillation event sequence; if not, judging that the power load data sequence is a non-oscillation event sequence; the sequence of oscillation events in each segment of power load data is filtered out.
Further, in the step of performing cluster analysis on the non-oscillatory power load data segments, the method specifically includes the following steps: carrying out similarity calculation on a plurality of non-oscillatory power load data segments by using a dynamic time warping method; and classifying the non-oscillatory power load data segments with the similarity smaller than a preset value into the same power utilization equipment.
Further, in the step of calculating the similarity of the non-oscillatory power load data segments by using the dynamic time warping method, the similarity dtw is calculated according to the following formula:
where D (i, j) is the distance between the ith and jth moments of the first and second of the two sequences (p-order minkowski distance, usually taken as p 2, the euclidean distance), D (i, j) is the shortest regular distance between the first i and jth moments of the first and second of the two sequences, and D (i, j) is the distance between p-order minkowski distance, length (ES)i) Representing a sequence ESiThe total number of time instants involved.
Further, in the step of obtaining and storing the power load data segments in the plurality of preset historical time periods in the database, the method specifically includes the following steps: an intelligent electric meter is provided and connected with an electric bus of a user, and electric load data are continuously collected.
Further, in the step of continuously collecting the power load data and storing the power load data into the database, the collection frequency is 5-15 Hz, and the collection time period is more than or equal to 7 days.
Further, after the step of providing a smart meter and accessing the electricity bus of the user to continuously collect the power load data, the method further comprises the following steps: missing values in the collected power load data are filled.
Further, in the step of filling missing values in the collected power load data, the filling method is to fill data at a next time corresponding to a missing value to a time corresponding to the missing value.
Further, the power load data segments include active power segments and reactive power segments.
The present invention also provides a storage medium having a computer program stored thereon, which when executed by a processor, implements the method for non-intrusive load monitoring event classification set forth above.
The invention has the beneficial effects that: the invention provides a classification method and a storage medium for non-intrusive load monitoring events, which are used for extracting power load data segments of different electric equipment from power load data, clustering based on the similarity among a plurality of power load data segments and realizing classification of the different electric equipment.
Drawings
The invention is further described below with reference to the figures and examples.
Fig. 1 is a flowchart of a method for classifying a non-intrusive load monitoring event according to an embodiment of the present invention;
fig. 2 is a flowchart of step S4 in a method for classifying a non-intrusive load monitoring event according to an embodiment of the present invention;
fig. 3 is a flowchart of step S4 in a method for classifying a non-intrusive load monitoring event according to an embodiment of the present invention;
FIG. 4 is a timing diagram of two power load data segments according to an embodiment of the invention.
Fig. 5 is a timing chart of power load data of the same powered device according to an embodiment of the invention.
Detailed Description
The following description of the embodiments refers to the accompanying drawings for illustrating the specific embodiments in which the invention may be practiced. The names of the elements, such as the first, the second, etc., mentioned in the present invention are only used for distinguishing different elements and can be better expressed. In the drawings, like parts are designated by like reference numerals and adjacent or similar parts are designated by like reference numerals.
Embodiments of the present invention will be described in detail herein with reference to the accompanying drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. These embodiments are provided to explain the practical application of the invention and to enable others skilled in the art to understand the invention for various embodiments and with various modifications as are suited to the particular use contemplated.
As shown in FIG. 1, the present invention provides a method for classifying a non-intrusive load monitoring event, which includes the following steps S1-S5.
S1) providing an intelligent electric meter and accessing an electric bus of a user to continuously collect power load data; wherein the collection frequency is 5-15 Hz, and the collection time period is more than or equal to 7 days.
S2) filling missing values in the collected power load data. The filling method is to fill the data of the next time for a missing value to the time corresponding to the missing value.
S3) obtaining a plurality of pieces of power load data in a preset historical time period, the pieces of power load data in the preset historical time period including a plurality of power load data sequences. The power load data segments include active power segments and reactive power segments. The active power sequence refers to alternating current energy actually emitted or consumed by electric equipment in unit time, and reactive power in a historical time period is obtained by multiplying instantaneous voltage by instantaneous current of offset 1/4 cycles. The reactive power is reversible energy exchange between a reactive element in the circuit and the circuit, and is actually exchange power of electric energy and a magnetic field (does not actually do work outwards). The active power sequence refers to the ac energy actually emitted or consumed by the electric equipment in a unit time.
S4) performing oscillation detection on the plurality of pieces of power load dataAnd filtering to obtain a plurality of non-oscillatory power load data segments. As shown in fig. 2, step S4 specifically includes the following steps: s401) a plurality of power load data sequences of a power load data segment are collected. S402) calculating a differential sequence of the plurality of power load data sequences; s403) and counting the maximum number of consecutive inverses of the differential sequence of the plurality of power load data sequences; s404) judging whether the maximum continuous reverse number of the maximum continuous reverse numbers of each differential sequence is larger than a threshold value; if yes, judging that the power load data sequence is an oscillation event sequence; if not, judging that the power load data sequence is a non-oscillation event sequence; s405) filtering out the sequence of oscillation events in each segment of power load data. Specifically, the detection method of the oscillatory behavior is as follows: given power load data sequence
Calculating a corresponding difference sequence:
and counts the maximum number of consecutive inversions max (count) of the difference sequenceinverse) If the length is in the original sequence ESiIf the proportion exceeds a certain threshold value, the oscillation event sequence is judged.
S5) performing cluster analysis on the plurality of non-oscillatory power load data segments. As shown in fig. 3, step S5 specifically includes the following steps: s501) carrying out similarity calculation on a plurality of non-oscillatory power load data segments by using a dynamic time warping method; the similarity dtw is calculated as follows:
where D (i, j) is the distance between the ith and jth moments of the first and second of the two sequences (p-order minkowski distance, usually taken as p 2, the euclidean distance), D (i, j) is the shortest regular distance between the first i and jth moments of the first and second of the two sequences, and D (i, j) is the distance between p-order minkowski distance, length (ES)i) Representing a sequence ESiThe total number of times contained;the dynamic time warping method is essentially to extend and shorten any two time sequences in a power load data fragment at different positions to obtain the shortest warping distance of the two time sequences for measuring the similarity of the two sequences, wherein the shorter the distance is, the higher the similarity is; fig. 4 is a timing diagram of two power load data segments. S502) classifying the non-oscillatory power load data segments with similarity smaller than a predetermined value into the same power utilization device, as shown in fig. 5, the abscissa is time and the ordinate is power value, which are the power curves of the same power utilization device extracted and clustered from the power load data by using the method of the present invention.
The invention provides a classification method of non-invasive load monitoring events, which is used for extracting power load data segments of different electric equipment from power load data, clustering based on the similarity among a plurality of power load data segments and realizing classification of different electric equipment.
An embodiment of the present invention further provides a storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for classifying the non-intrusive load monitoring event can be implemented.
The classification method of the non-intrusive load monitoring event is used for extracting power load data segments of different electric equipment from power load data, clustering based on the similarity among the power load data segments, and classifying the different electric equipment.
It should be noted that many variations and modifications of the embodiments of the present invention fully described are possible and are not to be considered as limited to the specific examples of the above embodiments. The above examples are intended to be illustrative of the invention and are not intended to be limiting. In conclusion, the scope of the present invention should include those changes or substitutions and modifications which are obvious to those of ordinary skill in the art.
Claims (10)
1. A method for classifying a non-intrusive load monitoring event, comprising the steps of:
acquiring power load data segments in a plurality of preset historical time periods, wherein the power load data segments in the preset historical time periods comprise a plurality of power load data sequences;
performing oscillatory detection on the plurality of power load data segments and filtering to obtain a plurality of non-oscillatory power load data segments;
and carrying out cluster analysis on a plurality of non-oscillatory power load data segments.
2. The method for classifying a non-intrusive load monitoring event as defined in claim 1,
in the step of performing oscillation detection on each power load data segment and filtering out the power load data segments to obtain non-oscillation power load data segments, the method specifically comprises the following steps:
collecting a plurality of power load data sequences of a power load data fragment;
calculating a differential sequence of the plurality of power load data sequences;
and counting a maximum number of consecutive inversions of the differential sequence of the plurality of power load data sequences;
judging whether the maximum continuous reverse number of each differential sequence is greater than a threshold value; if yes, judging that the power load data sequence is an oscillation event sequence; if not, judging that the power load data sequence is a non-oscillation event sequence;
the sequence of oscillation events in each segment of power load data is filtered out.
3. The method for classifying a non-intrusive load monitoring event as defined in claim 1,
in the step of performing cluster analysis on the non-oscillatory power load data segments, the method specifically includes the following steps:
carrying out similarity calculation on a plurality of non-oscillatory power load data segments by using a dynamic time warping method;
and classifying the non-oscillatory power load data segments with the similarity smaller than a preset value into the same power utilization equipment.
4. The method for classifying a non-intrusive load monitoring event as defined in claim 3,
in the step of calculating the similarity of the non-oscillatory power load data segments by using the dynamic time warping method, the similarity dtw is calculated according to the following formula:
where D (i, j) is the distance between the ith and jth moments of the first and second of the two sequences (p-th minkowski distance, usually taken as p 2, the euclidean distance), D (i, j) is the shortest regular distance between the first i and jth moments of the first and second of the two sequences, and D (i, j) is the distance between p-th minkowski distance, length (ES)i) Representing a sequence ESiThe total number of time instants involved.
5. The method for classifying a non-intrusive load monitoring event as defined in claim 1,
in the step of obtaining and storing the power load data segments in the plurality of preset historical time periods in the database, the method specifically includes the following steps:
an intelligent electric meter is provided and connected with an electric bus of a user, and electric load data are continuously collected.
6. The method for classifying a non-intrusive load monitoring event as defined in claim 5,
in the step of continuously collecting power load data and storing the power load data in the database,
the collection frequency is 5-15 Hz, and the collection time period is more than or equal to 7 days.
7. The method for classifying a non-intrusive load monitoring event as defined in claim 5,
after the step of providing an intelligent electric meter and accessing the electricity utilization bus of a user and continuously collecting the power load data, the method further comprises the following steps:
missing values in the collected power load data are filled.
8. The non-invasive load monitoring method of claim 7,
in the step of filling missing values in the collected power load data, the filling method is to fill data at the next time corresponding to one missing value to the time corresponding to the missing value.
9. The method for classifying a non-intrusive load monitoring event as defined in claim 1,
the power load data segments include active power segments and reactive power segments.
10. A storage medium having stored thereon a computer program enabling the method of any one of claims 1-9 to be performed when the computer program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110182390.9A CN113034305B (en) | 2021-02-10 | 2021-02-10 | Non-invasive load monitoring event classification method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110182390.9A CN113034305B (en) | 2021-02-10 | 2021-02-10 | Non-invasive load monitoring event classification method and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113034305A true CN113034305A (en) | 2021-06-25 |
| CN113034305B CN113034305B (en) | 2022-08-30 |
Family
ID=76461270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110182390.9A Active CN113034305B (en) | 2021-02-10 | 2021-02-10 | Non-invasive load monitoring event classification method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034305B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113690859A (en) * | 2021-08-04 | 2021-11-23 | 国电南瑞科技股份有限公司 | Starting and acting method and system for power grid differential protection |
| CN116859169A (en) * | 2023-09-01 | 2023-10-10 | 国网浙江省电力有限公司余姚市供电公司 | Non-invasive power load decomposition method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279803A (en) * | 2013-04-27 | 2013-09-04 | 深圳供电局有限公司 | Load modeling method and system based on comprehensive information theory and modern interior point theory |
| CN105977977A (en) * | 2016-06-30 | 2016-09-28 | 南京工业大学 | Self-adaptive identification method for load model of wide area power system |
| CN108197817A (en) * | 2017-09-19 | 2018-06-22 | 济南大学 | A kind of method of the non-intrusion type load transient state monitoring based on big data |
| US20190049332A1 (en) * | 2017-08-10 | 2019-02-14 | Panoramic Power Ltd. | Identification of air leaks in a compressed air system using a plurality of current measurement sensors |
| CN109387712A (en) * | 2018-10-09 | 2019-02-26 | 厦门理工学院 | Non-intrusion type cutting load testing and decomposition method based on state matrix decision tree |
| CN110569876A (en) * | 2019-08-07 | 2019-12-13 | 武汉中原电子信息有限公司 | Non-invasive load identification method and device and computing equipment |
| CN110954744A (en) * | 2019-11-18 | 2020-04-03 | 浙江工业大学 | Non-invasive load monitoring method based on event detection |
| CN111126780A (en) * | 2019-10-31 | 2020-05-08 | 内蒙古电力(集团)有限责任公司包头供电局 | Non-invasive load monitoring method and storage medium |
| CN111327118A (en) * | 2020-03-31 | 2020-06-23 | 西安理工大学 | Non-invasive power load identification method |
| CN111985824A (en) * | 2020-08-25 | 2020-11-24 | 安徽南瑞中天电力电子有限公司 | Non-invasive load monitoring method and monitoring equipment for intelligent ammeter box |
| CN112327070A (en) * | 2020-09-18 | 2021-02-05 | 千居智人工智能科技昆山有限公司 | Non-invasive load real-time monitoring method and storage medium |
-
2021
- 2021-02-10 CN CN202110182390.9A patent/CN113034305B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279803A (en) * | 2013-04-27 | 2013-09-04 | 深圳供电局有限公司 | Load modeling method and system based on comprehensive information theory and modern interior point theory |
| CN105977977A (en) * | 2016-06-30 | 2016-09-28 | 南京工业大学 | Self-adaptive identification method for load model of wide area power system |
| US20190049332A1 (en) * | 2017-08-10 | 2019-02-14 | Panoramic Power Ltd. | Identification of air leaks in a compressed air system using a plurality of current measurement sensors |
| CN108197817A (en) * | 2017-09-19 | 2018-06-22 | 济南大学 | A kind of method of the non-intrusion type load transient state monitoring based on big data |
| CN109387712A (en) * | 2018-10-09 | 2019-02-26 | 厦门理工学院 | Non-intrusion type cutting load testing and decomposition method based on state matrix decision tree |
| CN110569876A (en) * | 2019-08-07 | 2019-12-13 | 武汉中原电子信息有限公司 | Non-invasive load identification method and device and computing equipment |
| CN111126780A (en) * | 2019-10-31 | 2020-05-08 | 内蒙古电力(集团)有限责任公司包头供电局 | Non-invasive load monitoring method and storage medium |
| CN110954744A (en) * | 2019-11-18 | 2020-04-03 | 浙江工业大学 | Non-invasive load monitoring method based on event detection |
| CN111327118A (en) * | 2020-03-31 | 2020-06-23 | 西安理工大学 | Non-invasive power load identification method |
| CN111985824A (en) * | 2020-08-25 | 2020-11-24 | 安徽南瑞中天电力电子有限公司 | Non-invasive load monitoring method and monitoring equipment for intelligent ammeter box |
| CN112327070A (en) * | 2020-09-18 | 2021-02-05 | 千居智人工智能科技昆山有限公司 | Non-invasive load real-time monitoring method and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 丁世敬: ""基于事件检测的住宅用电负荷非侵入式识别研究"", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113690859A (en) * | 2021-08-04 | 2021-11-23 | 国电南瑞科技股份有限公司 | Starting and acting method and system for power grid differential protection |
| CN116859169A (en) * | 2023-09-01 | 2023-10-10 | 国网浙江省电力有限公司余姚市供电公司 | Non-invasive power load decomposition method and system |
| CN116859169B (en) * | 2023-09-01 | 2023-11-17 | 国网浙江省电力有限公司余姚市供电公司 | Non-invasive power load decomposition method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113034305B (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106096726B (en) | A kind of non-intrusion type load monitoring method and device | |
| CN108021736B (en) | Load switching action monitoring method based on sliding window residual error model | |
| CN113034305B (en) | Non-invasive load monitoring event classification method and storage medium | |
| CN109840691B (en) | Non-invasive polynomial electric quantity estimation method based on deep neural network | |
| CN109470957B (en) | Non-invasive electrical appliance identification method based on Frey's distance | |
| CN116955895B (en) | Transformer operation abnormity monitoring method and system | |
| CN109613362B (en) | Non-invasive electric appliance quantity identification method | |
| CN112765149A (en) | System and method for calculating capacity of energy storage system | |
| CN103246814A (en) | Personal electric device state identification method based on K-means modeling | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| CN106228244A (en) | A kind of energy based on self adaptation association rule mining depolymerizes method | |
| CN113269478B (en) | Concentrator abnormal data reminding method and system based on multiple models | |
| CN113420728B (en) | Non-invasive air conditioner load identification method and system integrating multi-time scale information | |
| CN115133659A (en) | On-line monitoring method and system for low-voltage line loss of low-voltage distribution network | |
| CN112949563B (en) | Non-invasive load identification method based on variable point detection and improved KNN algorithm | |
| CN114186631A (en) | Load identification method based on non-invasive intelligent terminal | |
| CN102486502B (en) | Power feature identification device and method | |
| CN112345824B (en) | Variable frequency air conditioner non-invasive identification method based on piecewise linear approximation algorithm | |
| CN112711613B (en) | Electric appliance preference analysis method based on intelligent judgment of power utilization behavior | |
| CN111583063B (en) | Business start and end time detection method based on standard template and storage medium | |
| Reeg et al. | Algorithm development for non-intrusive load monitoring for verification and diagnostics | |
| CN113985125B (en) | Method, device and equipment for calculating electric quantity with few abnormal current climbing | |
| CN117081122B (en) | Running state analysis system based on distributed energy storage device | |
| CN110244149B (en) | Non-invasive electrical appliance identification method based on current amplitude standard deviation | |
| CN113033607B (en) | Non-invasive load monitoring event extraction method and storage medium |
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 |