CN111126780B - Non-invasive load monitoring method and storage medium - Google Patents
Non-invasive load monitoring method and storage medium Download PDFInfo
- Publication number
- CN111126780B CN111126780B CN201911194849.6A CN201911194849A CN111126780B CN 111126780 B CN111126780 B CN 111126780B CN 201911194849 A CN201911194849 A CN 201911194849A CN 111126780 B CN111126780 B CN 111126780B
- Authority
- CN
- China
- Prior art keywords
- power
- power consumption
- time
- event
- period
- 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
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
- 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
- G06F18/24—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—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 a non-invasive load monitoring method and a storage medium. The invention is used for extracting the power utilization events of different electrical appliances from the total power curve of the power load, namely judging the opening event or the closing event of a single electrical appliance. The method comprises the steps of analyzing the instantaneous power consumption of a power consumption bus collected in advance to obtain a background reference value of the power load, and regarding all instantaneous power values in a fluctuation interval as background power so as to obtain continuous background power time periods of a plurality of time intervals. And defining a time period between two adjacent background power time periods as an electricity utilization time period, clustering a plurality of electricity utilization time periods to obtain an optimal electricity utilization time period, inputting instantaneous electricity consumption power of a target time sequence, calculating the similarity between the optimal electricity consumption time period and the instantaneous electricity consumption power of the target time sequence, and judging the turn-on event or the turn-off event of the single electric appliance, thereby extracting the electricity utilization event of the single electric appliance.
Description
Technical Field
The invention relates to the technical field of electricity utilization, in particular to a non-invasive load monitoring method and a storage medium.
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 the combined demand of multiple devices. One use case is to generate a piecemeal electricity bill using a single full house smart meter. The ultimate goal may be to help the user reduce energy consumption; or help operators manage the power grid; or finding out the electrical appliance with fault; or to investigate the behavior of the device. For human beings, electrical appliances implicit in the aggregated electricity power data, particularly electrical appliances with rich features (e.g., multi-state electric appliances such as washing machines, printers, etc.) can be detected with naked eyes. We can consider using a manually engineered feature extractor to obtain these rich features, but this would be time consuming and the resulting features may not be robust enough to noise, with large bias in the presence of noise. In addition, the high-frequency data can be used for extracting the switching characteristics of certain electrical appliances, but the high-frequency data can be acquired to greatly increase the cost, and the high-frequency data are not suitable for daily household conditions. Therefore, a load detection method based on low-frequency power consumption data is needed, and in the load monitoring method, the key technology lies in power consumption event extraction so as to facilitate subsequent correlation calculation by taking an event as a target.
Therefore, the invention provides a non-intrusive load monitoring method and a storage medium, which are used for extracting power utilization events of different electrical appliances from a power load total power curve, namely judging the opening events or the closing events of the different electrical appliances.
Disclosure of Invention
The invention aims to provide a non-invasive load monitoring method and a storage medium. The method acquires the background reference value of the power load by analyzing the instantaneous power consumption of the pre-acquired power consumption bus, and takes the instantaneous power values in the fluctuation interval as the background power so as to acquire continuous background power time periods of a plurality of time intervals. And according to the fact that the time period between two adjacent background power time periods is defined as a power utilization time period, clustering a plurality of power consumption time periods to obtain an optimal power consumption time period, inputting instantaneous power consumption of a target time sequence, calculating the similarity between the optimal power consumption time period and the instantaneous power consumption of the target time sequence, judging the starting event of a single electric appliance or the closing event of the single electric appliance, and further extracting the power utilization event of the single electric appliance.
The invention provides a non-invasive load monitoring method, which comprises the following steps: the method comprises the steps of establishing a database, recording instantaneous power consumption in a preset historical time period of a power utilization bus to the database, wherein the power utilization bus is at least connected with an electric appliance; the instantaneous power consumption of the electricity utilization bus in the preset historical time period is the sum of the instantaneous power consumption of the electric appliances connected with the electricity utilization bus; a first acquisition step, which is to acquire instantaneous power consumption of all power utilization buses in a preset historical time period in the database; a background power reference value obtaining step, wherein the instantaneous power consumption in the preset historical time period is rounded and a background power reference value is obtained according to power law distribution, and the background power reference value is the instantaneous power consumption which occurs the most times in the power law distribution; a background power obtaining step, namely setting a fluctuation interval, and collecting instantaneous power consumption in the fluctuation interval as background power, wherein the reference value of the background power is positioned in the fluctuation interval; a background power period acquisition step, namely setting a time interval, acquiring background power periods of a plurality of time intervals according to the background power and storing the background power periods into the database; a second acquisition step of acquiring instantaneous power consumption of a background power period of a first time series and a background power period of a second time series, wherein the first time series and the second time series are both included in the preset historical time period; a segmentation step, segmenting a background power period between the background power period of the first time sequence and the background power period of the second time sequence into a power consumption period; the method comprises a judging step, wherein multiple power consumption time periods are clustered to obtain an optimal power consumption time period, instantaneous power consumption power of a target time sequence is input, the similarity between the optimal power consumption time period and the instantaneous power consumption power of the target time sequence is calculated, and a single electric appliance opening event or a single electric appliance closing event is judged and recorded as a single electric appliance power consumption event.
Further, the method also comprises the following steps: and a single electrical appliance event classification step, namely calculating the similarity between different power consumption periods and the single electrical appliance event, and dividing the similarity into the same single electrical appliance event.
Further, still include: a power reduction step, namely shifting out the instantaneous power consumption of the opening and closing time sequence in the preset historical time period in a database according to the opening and closing time sequence of the power consumption event of the same single electric appliance; and a circulating step, wherein the first acquisition step to the judging step are executed to obtain the power utilization event of another single electric appliance.
Further, before the database establishing step, the method comprises a preparation step of providing an intelligent electric meter, wherein the intelligent electric meter is connected to the electricity utilization bus, and the intelligent electric meter uninterruptedly reads the instantaneous electricity consumption power of the electricity utilization bus at a fixed frequency; and a data preprocessing step, namely filling a vacancy value of the instantaneous power consumption of the power utilization bus read by the intelligent electric meter, smoothly removing noise to obtain the instantaneous power consumption of the power utilization bus in a preset historical time period, and storing the instantaneous power consumption in a database.
Further, the vacancy value is data of a previous sampling point collected by the electricity meter; and/or the presence of a gas in the gas,
the mode of smoothing and removing the noise comprises a weighted moving average method; and/or the fixed frequency is 5-15 Hz.
Further, the preset historical time period is more than or equal to 7 days; the starting value of the fluctuation interval is lower than 10-30% of the background power reference value, and the ending value of the fluctuation interval is higher than 10-30% of the background power reference value.
Further, in the slicing step, if the time length of the electricity utilization period is less than the time threshold, the electricity utilization period is regarded as a noise event.
Further, in the determining step, the method specifically includes: an extraction step of collecting M points of each power consumption period, wherein a plurality of power consumption periods have single electrical appliance turn-on events, namely
Wherein i is the ith power consumption time interval t i The starting time point of the ith power consumption time period is M, the selection duration is N, the number of the power consumption time periods is X, and the instantaneous power consumption is X;
calculating Euclidean distances between different ES sequences, namely:
Further, if the single electrical appliance is judged to be turned on, acquiring the first M points of each power consumption time interval in the extracting step; and if the single electric appliance is judged to be closed, acquiring the last M points of each power consumption time period in the extracting step.
The present invention also provides a storage medium having a computer program stored thereon, which when executed by a processor is operable to carry out the method as described above.
The invention has the beneficial effects that: the invention provides a non-invasive load monitoring method and a storage medium. The invention is used for extracting the power utilization events of different electrical appliances from the total power curve of the power load, namely judging the opening event or the closing event of a single electrical appliance. The method comprises the steps of analyzing the instantaneous power consumption of a power consumption bus collected in advance to obtain a background reference value of the power load, and regarding all instantaneous power values in a fluctuation interval as background power so as to obtain continuous background power time periods of a plurality of time intervals. And according to the fact that the time period between two adjacent background power time periods is defined as a power utilization time period, clustering a plurality of power consumption time periods to obtain an optimal power consumption time period, inputting instantaneous power consumption of a target time sequence, calculating the similarity between the optimal power consumption time period and the instantaneous power consumption of the target time sequence, judging the starting event of a single electric appliance or the closing event of the single electric appliance, and further extracting the power utilization event of the single electric appliance.
Drawings
The invention is further described below with reference to the figures and examples.
FIG. 1 is a flow chart of a non-intrusive load monitoring method provided by the present invention;
FIG. 2 is a power-law distribution diagram of the rounded instantaneous power consumption according to an embodiment of the data provided in the present invention;
FIG. 3 is a flowchart of the determining step provided by the present 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 elements are designated by like reference numerals, and adjacent or similar elements 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 non-intrusive load monitoring method, which includes the following steps S11) to S23).
Step S11), a preparation step, namely providing an intelligent electric meter, wherein the intelligent electric meter is connected to the electricity utilization bus, and the intelligent electric meter continuously reads the instantaneous electricity consumption power of the electricity utilization bus at a fixed frequency;
and S12) a data preprocessing step, namely filling vacancy values of the instantaneous power consumption of the power utilization bus read by the intelligent electric meter, smoothly removing noise to obtain the instantaneous power consumption of the power utilization bus in a preset historical time period, and storing the instantaneous power consumption in a database.
The vacancy value is data of a previous sampling point collected by the electricity meter; and/or the noise smoothing and removing way comprises a weighted moving average method.
Step S13) a database establishing step, namely inputting instantaneous power consumption of a preset historical time period of a power utilization bus to a database, wherein the power utilization bus is at least connected with an electric appliance; the preset historical time period instantaneous power consumption of the power utilization bus is the sum of the instantaneous power consumption of the power utilization bus connected with the power utilization bus.
The fixed frequency is 5-15 Hz; and/or the preset historical time period is more than or equal to 7 days.
Step S14) a first acquisition step, wherein instantaneous power consumption of all power utilization buses in the database in a preset historical time period is acquired.
Step S15) a background power reference value obtaining step, wherein the instantaneous power consumption power of the preset historical time period is rounded, and a background power reference value is obtained according to power law distribution, wherein the background power reference value is the instantaneous power consumption power which appears in the power law distribution most frequently.
As shown in fig. 2, an embodiment of data is provided as a power-law distribution graph after rounding the instantaneous power consumption for a predetermined historical time period.
The horizontal axis of the distribution diagram is the power value, and the vertical axis is the count of the power, and the distribution conforms to the power law distribution.
However, the power value with the largest occurrence number in the distribution can be used as the background power reference value, and generally in the non-invasive monitoring, if an electrical appliance is normally opened, the electrical appliance is considered not to be in the monitored object. The value with the highest number of occurrences is therefore considered the reference value, and in this figure the power with the highest number of occurrences is 116 watts, with the number of occurrences being 53629.
Step S16) background power obtaining, namely collecting instantaneous power consumption in a fluctuation interval as background power, wherein the reference value of the background power is positioned in the fluctuation interval.
The starting value of the fluctuation interval is lower than 10-30% of the background power reference value, and the optimal value is 20%; the ending value of the fluctuation interval is 10-30% higher than the background power reference value, and the optimal value is 20%.
Step S17) background power time interval obtaining step, obtaining background power time intervals of a plurality of time intervals according to the background power and storing the background power time intervals into the database, wherein the background power time intervals are all of electricity utilization events of electric appliances, so that the time intervals selected in the step S18) are used as electricity consumption time intervals.
The time interval is not limited, and the time interval does not exceed the length of the time sequence of the preset history.
Step S18) a second acquisition step of acquiring the instantaneous power consumption of the background power time interval of a first time sequence and the instantaneous power consumption of the background power time interval of a second time sequence, wherein the first time sequence and the second time sequence are both contained in the preset historical time interval.
Step S19), a segmentation step, wherein a background power period between the background power period of the first time sequence and the background power period of the second time sequence is segmented and recorded as a power consumption period.
In the cutting step, if the time length of the electricity utilization period is smaller than the time threshold, the electricity utilization period is regarded as a noise event.
Step S20), a judgment step, namely clustering a plurality of power consumption time intervals to obtain an optimal power consumption time interval, inputting instantaneous power consumption of a target time sequence, calculating the similarity between the optimal power consumption time interval and the instantaneous power consumption of the target time sequence, and judging a single electric appliance opening event or a single electric appliance closing event, wherein the single electric appliance opening event and the single electric appliance closing event are marked as a single electric appliance electricity utilization event.
As shown in fig. 3, the determination step specifically includes the following steps S201) to S203).
Step S201), an extraction step, wherein M points of each power consumption time interval are collected, wherein a plurality of power consumption time intervals have single electric appliance starting events, namely
Wherein i is the ith power consumption time interval, t i The starting time point of the ith power consumption time period is M, the selection duration is N, the number of the power consumption time periods is x, and the instantaneous power consumption is x;
step S202), calculating Euclidean distance between different ES sequences, namely:
selecting two ES sequences corresponding to the minimum distance value, and taking the average value of the two ES sequences as the event reference of the single electric appliance;
step S203) sequence similarity calculating step, in a power consumption period, selecting subsequent continuous q points every h points, wherein the jth sequence needing to calculate the similarity in the same power consumption period is a target sequence S ij And is recorded as:
If the single electrical appliance is judged to be started, acquiring the first M points of each power consumption time period in the extracting step; and if the single electric appliance is judged to be closed, acquiring the last M points of each power consumption time period in the extracting step.
Step S21) single electrical appliance event classification step, calculating the similarity between different power consumption time periods and the single electrical appliance event, and dividing the high similarity into the same single electrical appliance event.
Step S22) power reduction step, namely shifting out the instantaneous power consumption of the opening and closing time sequence in the preset historical time period in a database according to the opening and closing time sequence of the power consumption event of the same single electric appliance.
Step S23), a circulating step, namely executing the first acquisition step to the judging step to obtain the power utilization event of another single electric appliance.
The invention provides a non-invasive load monitoring method. The invention is used for extracting the power utilization events of different electrical appliances from the total power curve of the power load, namely judging the opening event or closing time of a single electrical appliance. The method comprises the steps of analyzing the instantaneous power consumption of a power consumption bus collected in advance to obtain a background reference value of the power load, and regarding all instantaneous power values in a fluctuation interval as background power so as to obtain continuous background power time periods of a plurality of time intervals. And defining a time period between two adjacent background power time periods as an electricity utilization time period, clustering a plurality of electricity utilization time periods to obtain an optimal electricity utilization time period, inputting instantaneous electricity consumption power of a target time sequence, calculating the similarity between the optimal electricity consumption time period and the instantaneous electricity consumption power of the target time sequence, and judging the turn-on event or the turn-off event of the single electric appliance, thereby extracting the electricity utilization event of the single electric appliance.
And the similarity with the single electric appliance event is judged from other power consumption time periods, so that the electric appliances can be classified, the instantaneous power consumption power corresponding to the power consumption event of the single electric appliance is subtracted from the total power, and the power consumption event of the next type of single electric appliance is extracted.
The invention can adapt to the electricity environment, can accurately extract the event of the electrical appliance without early configuration, and can accurately obtain the opening time and the closing time of the electrical appliance. In addition, the invention can accurately identify the use condition of a plurality of electrical appliances in the same time period.
The invention also provides a storage medium having a computer program stored thereon, wherein the non-invasive load monitoring method of the invention is implemented when the computer program is executed by a processor.
The invention also provides an electronic device, comprising a memory and a processor, wherein the memory is used for storing executable program codes; the processor executes the program corresponding to the executable program code by reading the executable program code to perform the steps of the non-intrusive load monitoring method as described above.
It should be noted that many variations and modifications of the embodiments of the present invention fully described are possible without limiting the invention 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 general, the scope of the present invention should include those alternatives or modifications as would be apparent to one of ordinary skill in the art.
Claims (10)
1. A method of non-intrusive load monitoring, comprising the steps of:
the method comprises the steps of establishing a database, recording instantaneous power consumption in a preset historical time period of a power utilization bus to the database, wherein the power utilization bus is at least connected with an electric appliance; the instantaneous power consumption in the preset historical time period of the power utilization bus is the sum of the instantaneous power consumption of the power utilization devices connected with the power utilization bus;
a first acquisition step, which is to acquire instantaneous power consumption of all power utilization buses in a preset historical time period in the database;
a background power reference value obtaining step, namely rounding the instantaneous power consumption in the preset historical time period and obtaining a background power reference value according to power law distribution, wherein the background power reference value is the instantaneous power consumption which occurs the most times in the power law distribution;
acquiring background power, namely acquiring instantaneous power consumption in a fluctuation interval as background power, wherein the reference value of the background power is positioned in the fluctuation interval;
a background power period obtaining step, wherein background power periods of a plurality of time intervals are obtained according to the background power and stored in the database;
a second acquisition step of acquiring instantaneous power consumption of a background power period of a first time series and a background power period of a second time series, wherein the first time series and the second time series are both included in the preset historical time period;
a segmentation step, segmenting a background power period between the background power period of the first time sequence and the background power period of the second time sequence into a power consumption period;
the method comprises a judging step, wherein multiple power consumption time periods are clustered to obtain an optimal power consumption time period, instantaneous power consumption power of a target time sequence is input, the similarity between the optimal power consumption time period and the instantaneous power consumption power of the target time sequence is calculated, and a single electric appliance opening event or a single electric appliance closing event is judged and recorded as a single electric appliance power consumption event.
2. The non-invasive load monitoring method of claim 1, further comprising:
and a single electrical appliance event classification step, namely calculating the similarity between different power consumption periods and the single electrical appliance event, and dividing the similarity into the same single electrical appliance event.
3. The non-invasive load monitoring method of claim 2, further comprising:
power reduction, namely removing instantaneous power consumption in the opening and closing time sequence in the preset historical time period in a database according to the opening and closing time sequence of the power consumption event of the same single electrical appliance;
and a circulating step, wherein the first acquisition step to the judging step are executed to obtain the power utilization event of another single electric appliance.
4. The non-invasive load monitoring method of claim 1,
before the step of establishing the database, the method comprises the following steps:
a preparation step, providing an intelligent electric meter, wherein the intelligent electric meter is connected to the electricity utilization bus and continuously reads instantaneous electricity consumption power of the electricity utilization bus at a fixed frequency;
and a data preprocessing step, namely filling a vacancy value of the instantaneous power consumption of the power utilization bus read by the intelligent electric meter, smoothly removing noise to obtain the instantaneous power consumption of the power utilization bus in a preset historical time period, and storing the instantaneous power consumption in a database.
5. The non-invasive load monitoring method of claim 4,
the vacancy value is data of a previous sampling point collected by the electricity meter; and/or the presence of a gas in the atmosphere,
the mode of smoothly removing the noise comprises a weighted moving average method; and/or the presence of a gas in the gas,
the fixed frequency is 5-15 Hz.
6. The non-invasive load monitoring method of claim 1,
the preset historical time period is more than or equal to 7 days;
the starting value of the fluctuation interval is lower than 10-30% of the background power reference value, and the ending value of the fluctuation interval is higher than 10-30% of the background power reference value.
7. The non-invasive load monitoring method of claim 1,
in the cutting step, if the time length of the electricity utilization period is smaller than the time threshold, the electricity utilization period is regarded as a noise event.
8. The non-invasive load monitoring method of claim 1,
in the judging step, the method specifically includes:
an extraction step of collecting M points of each power consumption period, wherein a plurality of power consumption periods have a single appliance on event, namely
Wherein i is the ith power consumption time interval t i The starting time point of the ith power consumption time period is M, the selection duration is N, the number of the power consumption time periods is x, and the instantaneous power consumption is x;
calculating Euclidean distances between different ES sequences, namely:
a sequence similarity calculation step, in which every h points in a power consumption period, subsequent continuous q points are selected, and the jth sequence needing to calculate the similarity in the same power consumption period is a target sequence S ij And is recorded as:
wherein h is the interval time, q is the sequence length, t i And calculating the similarity between the target sequence and the reference sequence by using a dynamic time warping algorithm for the starting time point of the ith power consumption time period, and judging the turn-on event or turn-off event of the single electrical appliance according to the similarity.
9. The non-invasive load monitoring method of claim 9,
if the single electrical appliance is judged to be started, acquiring the first M points of each power consumption time period in the extracting step;
and if the single electric appliance is judged to be closed, acquiring the last M points of each power consumption time interval in the extracting step.
10. A storage medium having stored thereon a computer program enabling to carry out the method according to any one of claims 1 to 9 when said computer program is executed by a processor.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2019110565881 | 2019-10-31 | ||
| CN201911056588 | 2019-10-31 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111126780A CN111126780A (en) | 2020-05-08 |
| CN111126780B true CN111126780B (en) | 2023-04-07 |
Family
ID=70496988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911194849.6A Active CN111126780B (en) | 2019-10-31 | 2019-11-28 | Non-invasive load monitoring method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126780B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033607B (en) * | 2021-02-10 | 2023-07-14 | 上海千居智科技有限公司 | Non-invasive load monitoring event extraction method and storage medium |
| CN113034305B (en) * | 2021-02-10 | 2022-08-30 | 上海千居智科技有限公司 | Non-invasive load monitoring event classification method and storage medium |
| CN113567794B (en) * | 2021-09-24 | 2022-04-08 | 国网江苏省电力有限公司营销服务中心 | Electric bicycle indoor charging identification method and system based on dynamic time warping |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5483153A (en) * | 1994-03-24 | 1996-01-09 | Massachusetts Institute Of Technology | Transient event detector for use in nonintrusive load monitoring systems |
| WO2015019584A1 (en) * | 2013-08-09 | 2015-02-12 | パナソニックＩｐマネジメント株式会社 | Power adjustment device, power adjustment method, and program |
| CN104483575A (en) * | 2014-12-22 | 2015-04-01 | 天津求实智源科技有限公司 | Self-adaptive load event detection method for noninvasive power monitoring |
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| CN106096726A (en) * | 2016-05-31 | 2016-11-09 | 华北电力大学 | A kind of non-intrusion type load monitoring method and device |
| CN106600074A (en) * | 2016-12-28 | 2017-04-26 | 天津求实智源科技有限公司 | DFHSMM-based non-intrusion type electric power load monitoring method and system |
| CN106786534A (en) * | 2016-12-28 | 2017-05-31 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load transient process discrimination method and system |
| CN108062627A (en) * | 2017-12-16 | 2018-05-22 | 广西电网有限责任公司电力科学研究院 | A kind of demand response analysis method based on non-intrusion type electricity consumption data |
| CN108256075A (en) * | 2018-01-17 | 2018-07-06 | 深圳市和拓创新科技有限公司 | A kind of technology based on non-intrusion type intellectual monitoring analysis user power utilization data |
| CN108333423A (en) * | 2017-12-27 | 2018-07-27 | 安徽机电职业技术学院 | Non-intrusion type residential power load testing method |
| 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 |
| CN110322063A (en) * | 2019-06-27 | 2019-10-11 | 上海极熵数据科技有限公司 | A kind of power consumption simulated prediction method and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140207398A1 (en) * | 2013-01-23 | 2014-07-24 | Samsung Electronics Co., Ltd | Transient Normalization for Appliance Classification, Disaggregation, and Power Estimation in Non-Intrusive Load Monitoring |
-
2019
- 2019-11-28 CN CN201911194849.6A patent/CN111126780B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5483153A (en) * | 1994-03-24 | 1996-01-09 | Massachusetts Institute Of Technology | Transient event detector for use in nonintrusive load monitoring systems |
| WO2015019584A1 (en) * | 2013-08-09 | 2015-02-12 | パナソニックＩｐマネジメント株式会社 | Power adjustment device, power adjustment method, and program |
| CN104483575A (en) * | 2014-12-22 | 2015-04-01 | 天津求实智源科技有限公司 | Self-adaptive load event detection method for noninvasive power monitoring |
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| CN106096726A (en) * | 2016-05-31 | 2016-11-09 | 华北电力大学 | A kind of non-intrusion type load monitoring method and device |
| CN106600074A (en) * | 2016-12-28 | 2017-04-26 | 天津求实智源科技有限公司 | DFHSMM-based non-intrusion type electric power load monitoring method and system |
| CN106786534A (en) * | 2016-12-28 | 2017-05-31 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load transient process discrimination method and system |
| CN108062627A (en) * | 2017-12-16 | 2018-05-22 | 广西电网有限责任公司电力科学研究院 | A kind of demand response analysis method based on non-intrusion type electricity consumption data |
| CN108333423A (en) * | 2017-12-27 | 2018-07-27 | 安徽机电职业技术学院 | Non-intrusion type residential power load testing method |
| CN108256075A (en) * | 2018-01-17 | 2018-07-06 | 深圳市和拓创新科技有限公司 | A kind of technology based on non-intrusion type intellectual monitoring analysis user power utilization data |
| 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 |
| CN110322063A (en) * | 2019-06-27 | 2019-10-11 | 上海极熵数据科技有限公司 | A kind of power consumption simulated prediction method and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 非侵入式负荷监测与分解研究综述;程祥;《电网技术》;3108-3117 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111126780A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126780B (en) | Non-invasive load monitoring method and storage medium | |
| CN109387712B (en) | Non-invasive load detection and decomposition method based on state matrix decision tree | |
| Munshi et al. | Unsupervised nonintrusive extraction of electrical vehicle charging load patterns | |
| WO2019155214A1 (en) | Method and apparatus for power signal disaggragation using a convolutional neural network | |
| US20140207398A1 (en) | Transient Normalization for Appliance Classification, Disaggregation, and Power Estimation in Non-Intrusive Load Monitoring | |
| EP2715376A1 (en) | Transition detection method for automatic-setup non-intrusive appliance load monitoring | |
| Altrabalsi et al. | A low-complexity energy disaggregation method: Performance and robustness | |
| CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
| CN116956198B (en) | Intelligent electricity consumption data analysis method and system based on Internet of things | |
| CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
| CN115049410A (en) | Electricity stealing behavior identification method and device, electronic equipment and computer readable storage medium | |
| CN109377052B (en) | Power load matching method, device, equipment and readable storage medium | |
| CN114076841A (en) | Electricity stealing behavior identification method and system based on electricity utilization information data | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| CN111191908B (en) | Load event detection method, system and storage medium | |
| CN113034305A (en) | Non-invasive load monitoring event classification method and storage medium | |
| CN111967919A (en) | System and method for analyzing electricity consumption behavior of residents based on autoregressive and adaptive boosting algorithm | |
| CN115112989B (en) | Non-invasive load monitoring method based on low-frequency data | |
| CN114884075A (en) | Event type non-intrusive load monitoring method based on supervised learning | |
| CN106228244A (en) | A kind of energy based on self adaptation association rule mining depolymerizes method | |
| CN115825602A (en) | Load identification method and system for comprehensive multivariate information similarity analysis | |
| CN110889465B (en) | Power demand side equipment identification method and system based on self-adaptive resonant network | |
| CN114662576A (en) | Non-invasive storage battery car charging detection method and system based on supervised classification | |
| CN113642421A (en) | Event detection method, system, equipment and storage medium for periodic multi-state electric appliance | |
| CN112926777A (en) | Day-ahead load prediction method and system considering commercial building energy consumption behaviors |
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 |