CN109752613A - Default electricity use detection system and method based on non-intrusion type load monitoring - Google Patents
Default electricity use detection system and method based on non-intrusion type load monitoring Download PDFInfo
- Publication number
- CN109752613A CN109752613A CN201811651387.1A CN201811651387A CN109752613A CN 109752613 A CN109752613 A CN 109752613A CN 201811651387 A CN201811651387 A CN 201811651387A CN 109752613 A CN109752613 A CN 109752613A
- Authority
- CN
- China
- Prior art keywords
- user
- electric appliance
- default electricity
- suspicious
- electricity use
- 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
Abstract
The invention discloses a kind of default electricity use detection systems based on non-intrusion type load monitoring, it is characterized in that, it include: data acquisition module and information exchange module, suspicious user screening module, atypia civil electric appliance screening module, default electricity use Judging index computing module, default electricity use decision-making module and data information memory module.Its detection method specifically includes that the suspicious index of user's promise breaking of the single-phase user of low pressure calculates, suspicious user screening, the identification of atypia civil electric appliance, atypia civil electric appliance determines, default electricity use Judging index calculates, default electricity use decision, the present invention can be in the case where letting alone suspicious user, suspicious user is monitored, by determining whether suspicious user is truly present i.e. " people's electric business use " behavior to atypia civil electric appliance and the indicative electric appliance comprehensive analysis of industry and commerce, then the electricity charge are collected according to commercial user's the charge of electricity standard to user power utilization total amount.
Description
Technical field
The invention belongs to advanced measurement system field more particularly to a kind of default electricity uses based on non-intrusion type load monitoring
Detection system and method.
Background technique
With the rapid development of society, it is incident be the abnormal electricity consumption behavior such as stealing, default electricity use a large amount of appearance.
Power supply enterprise, China technological means in terms of electricity automatic management falls behind relatively at present, the exception electricity consumption behavior frequency such as default electricity use
Hair not only caused huge economic losses to Utilities Electric Co. and power consumer, but also the very disruptive order of the market economy[1]。
" people's electric business with " is a kind of common default electricity use type in ordinarily resident's cell.It is one kind without authorization by electricity price height
Electrical equipment connect in the low power supply line of electricity price or change electricity consumption classification privately, the electricity consumption row of electricity price difference is earned with this
For.Currently, direct-furnish electricity price in China some areas can be mainly divided into farming power, residential electricity consumption, big commercial power, general industry and commerce
4 major class such as industry and other electricity consumptions.Wherein, residential electricity consumption includes resident living power utility, school's electricity consumption etc., general industry and commerce and other
Electricity consumption includes general industry electricity consumption, commercial power, non-resident illumination, non-technical electricity etc..In 4 major class electricity prices, farming power and
Residential electricity consumption is low price electricity consumption relative to other two classes electricity consumption.According to Tianjin sales rate of electricity supplied to consumers tune disclosed in 2017
It grinds, according to above-mentioned classification, the electricity price of non-resident household electricity is usually 1.3 to 2.5 times of resident living power utility, this price difference meeting
Lure certain customers " people's electric business use " into.
Currently, being directed to the detection of " people's electric business use ", exist and be lack of pertinence, expend a large amount of human and material resources, height relies on
The problems such as the working attitude and business skill of staff.With the continuous developing in power supply enterprise market, the promise breaking of user
Electricity consumption behavior is more diversified and high-technicalization considerably increases so that the concealment of " people's electric business use " behavior is stronger and detects hardly possible
Degree；In addition, in many cases, even if detecting certain user, there are default electricity use behaviors, due to that can not register one's residence, can not effectively look into
Card.
According to engineering experience, there are two types of the performances of " people's electric business use " user: (1) substantially unused containing resident
Industry and commerce electric appliance, the use habit and normal civilian habit of (2) certain typical civil electric appliance are not inconsistent, and are in particular in electric appliance day
Electricity consumption total amount, accumulative operation duration and on-off frequency etc..
Situation is planted for (1), some electric appliances only use in industry and commerce user, and will not make substantially in resident
With.Such as high-power electric oven (roasted pachyrhizus machine, commercial Pizza oven), large capacity dry cleaner etc..In the present invention, by this electric appliances
It is referred to as atypia civil electric appliance.
Situation is planted for (2), some civil electric appliances have stronger industry and commerce behavior indicative, for example printer, blow
Blower, electric cooker (and electric appliance of similar functions), computer, washing machine etc., the present invention in, this electric appliances is referred to as industry and commerce row
For indicative electric appliance, referred to as indicative electric appliance.For different types of business activity, indicative electric appliance is different.It is private
There is plurality of printers in print shop shop, and printer can use incessantly for a long time, hair dryer, small meal is used for multiple times in small hairdressing place
It shop can be for a long time using electric cooker etc..
Obviously, analysis is carried out to the load electricity consumption data for being accurate to electric appliance and is more conducive to discovery " people's electric business use ".
Bibliography
[1] [D] is realized in Xiong Qiu, residential electricity consumption anomalous identification systematic research, Beijing University of Post & Telecommunication, 2018.
[2] Chen Da, the high fundamental type [J] for using default electricity use behavior of low price, public electricity consumption, 2016 (2).
[3] Yu Yixin, Liu Bo, Luan Wenpeng；Non-intrusion type residential power load monitoring and decomposition technique [J], south electric network
Technology, 2013,7 (04): 1-5.
[4] Yao Weizhi, Lin Muqun, Ji Suna, etc.；Analysis is monitored in low-voltage customer stealing based on electricity consumption behavioural analysis on-line
Technique study [J], Chinese new traffic, 2015 (2): 97-99.
Summary of the invention
For the prior art, The present invention gives the default electricity use detection systems based on non-intrusion type load monitoring, to quilt
Monitoring electricity consumption user can be convenient, accurately judge whether it is " people's electric business use ", to timely inhibit the promise breaking of low-voltage customer
Behavior.
To solve the above-mentioned problems, the present invention proposes a kind of default electricity use detection system based on non-intrusion type load monitoring
System, comprising: data acquisition module and information exchange module, suspicious user screening module, atypia civil electric appliance screening module are disobeyed
About electricity consumption Judging index computing module, default electricity use decision-making module and data information memory module；
The data acquisition module and information exchange module acquire low frequency load electricity consumption total amount number using data acquisition functions
According to, using non-intrusive electrical load monitoring technology by analysis load electricity consumption aggregate data obtain detection range in each electric appliance
Load electricity consumption detail data, including electrical work state, electric power and accumulative electricity；And it is transmitted by information exchange function
Other modules are given, while information exchange function is also responsible for internal system and the external world carries out data interaction, includes at least monitoring and divides
Analyse the display and output of result；Wherein, low frequency load electricity consumption aggregate data is the continuous data that Utilities Electric Co. is derived from electric energy meter, is used
In screening suspicious user, load electricity consumption detail data is for determining whether the suspicious user having determined is implicitly present in default electricity use
Behavior；
The suspicious user screening module is used to detect the suspicious user of default electricity use in low pressure resident, passes through calculating
The suspicious index of the default electricity use of user, and compared with the suspicious designation number of default electricity use, to determine whether user is suspicious user；
The atypia civil electric appliance screening module is for recognizing appliance type used in suspicious user man, the electricity
Device type includes at least the indicative electric appliance of industry and commerce behavior and atypia civil electric appliance, whether there is SARS in screening appliance type
Type civil electric appliance, to directly determine whether the user uses the electric appliances to implement default electricity use behavior；
The default electricity use Judging index computing module is for calculating default electricity use Judging index；
The default electricity use decision-making module is used for comprehensive analysis default electricity use Judging index, determines whether suspicious user is real
There are default electricity use behaviors；
The data information memory module is used to store the data acquisition module and information exchange module, suspicious user sieve
Look into module, atypia civil electric appliance screening module, default electricity use Judging index computing module, default electricity use decision-making module it is various
Data information.
Utilize the detection side of the carry out default electricity use of the above-mentioned default electricity use detection system based on non-intrusion type load monitoring
Method, comprising the following steps:
Step 1: the user of the single-phase user of low pressure breaks a contract, suspicious index is calculated:
Judge whether monitored user is abnormal according to the single-phase user power utilization abnormal behavior index of low pressure, includes following feelings
Shape:
1) user and industry electricity ratio average value are set as W1, work as W1>=1.4, then the monitored user is abnormal；
2) summer and autumn Winter-Spring electricity consumption ratio is set as W2, work as W2>=1.35, then the monitored user is abnormal；
3) trimestral average electricity ratio is W before and after setting user and industry October 13, as user and industry October one
Trimestral average electricity ratio W before and after day3> 1.5, then the monitored user is abnormal；
4) trimestral average electricity ratio is W before and after setting user and industry May 14, as user and industry May one
Trimestral average electricity ratio W before and after day4> 1.4, then the monitored user is abnormal；
5) user and industry electricity ratio are set as W5, work as W5> 1.45, then the monitored user is abnormal；
The suspicious index V of default electricity use of monitored user is calculated by formula (1):
In formula (1), KmFor abnormal index WmWeight, and Km∈[0.5,2]；
Step 2: suspicious user screening:
If V > S0, then the monitored user is suspicious user, enters step three, and otherwise there is no disobey by the monitored user
About electricity consumption behavior, goes to step 7；Wherein, S0For the suspicious designation number of default electricity use, S0Value is 7；
Step 3: atypia civil electric appliance recognizes:
By electricity consumption detail data in the suspicious user one week of analysis non-intrusion type load monitoring technology acquisition, to suspicious
The appliance type of user recognizes, including identification appliance type and operating status, identification finish, and enter step four；
Step 4: atypia civil electric appliance determines:
Whether the appliance type in the screening suspicious user includes the substantially unused industry and commerce electric appliance of resident, if depositing
Step 8 is then being gone to, is otherwise entering step five；
Step 5: default electricity use Judging index calculates:
Power P is determined including basic load0, indicative electric appliance determine operation duration TjAnd determine on-off frequency Nj；
The circular of indices is as follows:
1) it obtains basic load and determines power P0.If user power utilization general power is in a certain in the duration more than 5.5 hours
Power bracket, then using the center power value of this power bracket as basic load power, by the maximum of multiple basic load power
Value is known as basic load and determines power P0；If there is no the durations more than 5.5 hours to be in a certain power for user power utilization general power
Range then determines power P for the central point performance number of the longest a certain power bracket of duration as basic load0；
2) it calculates indicative electric appliance and determines operation duration.It is used by the suspicious user that non-intrusion type load monitoring technology obtains
Electric detail data, then counted from electricity consumption detail data and record each indicative electric appliance day to add up operation duration and day accumulative
On-off frequency obtains the state vector of each indicative electric applianceWith when long vectorWherein,Indicate suspicious user in jth day k-th of indicative electric appliance monitoring period of time i's
State, and0 indicates that indicative electric appliance is in close state, and 1 indicates that indicative electric appliance is in the open state,
For suspicious user in jth day duration of k-th of the indicative electric appliance in monitoring period of time i.According to resulting each indicative electricity
Device state vector and when long vector, calculate and each indicative electric appliance day add up operation duration:
In formula (2), Tk,jIt is suspicious user in jth day, the operation total duration of certain indicative electric appliance k, k is device numbering；
The maximum value added up indicative electric appliance day in operation duration is determined into operation duration T as indicative electric appliancej；
3) it calculates indicative electric appliance and determines on-off frequency.It is tired that its day is calculated according to resulting each indicative electrical appliance state vector
Count on-off frequency:
In formula (3), Nk,jIt is suspicious user in jth day, the on-off times of certain indicative electric appliance k；
The maximum value added up each indicative electric appliance day in on-off frequency is determined into on-off frequency N as indicative electric appliancej；
Step 6: default electricity use decision:
The basic load that step 5 is calculated is determined that power, indicative electric appliance determine that operation duration and judgement are opened respectively
Stop number to be compared with its respective threshold, therefore, it is determined that suspicious user whether there is default electricity use behavior, wherein with just common
The maximum empirical value P of family basic load powermaxThe threshold value of power is determined as basic load；With the indicative electric appliance of normal users
Day accumulative operation duration maximum empirical value TmaxThe threshold value of operation duration is determined as indicative electric appliance；It is indicative with normal users
Electric appliance day adds up on-off times maximum empirical value NmaxThe threshold value of on-off frequency is determined as indicative electric appliance.
Detailed process is as follows:
Step 6-1, comparison basis load determines power P0With Pmax；If P0> Pmax, Pmax=800~1200W, then it is suspicious
There are default electricity use behaviors by user, go to step 8, otherwise enter step 6-2；
Step 6-2, more indicative electric appliance determines operation duration TjWith Tmax；If Tj> Tmax, Tmax=8~12 hours,
Then there are default electricity use behaviors for suspicious user, go to step 8, otherwise enter step 6-3；
Step 6-3, more indicative electric appliance determines on-off frequency NjWith Nmax；If Nj> Nmax, Nmax=7~11, then may be used
There are default electricity use behaviors by doubtful user, go to step 8, otherwise enter step seven；
Step 7: default electricity use behavior is not present, the suspicious user is excluded there are the suspicion of default electricity use, is so far completed
It is tested and analyzed for the default electricity use of the user；
Step 8: being collected to the user power utilization total amount according to commercial user's the charge of electricity standard there are default electricity use behavior
The electricity charge so far complete the default electricity use detection and analysis for the user；
Step 9: repeating the above steps one to step 8, until completing the promise breaking to target complete user in specified region
Electricity consumption tests and analyzes；
Step 10: testing and analyzing the default electricity use case generated for this default electricity use, refer to according to based on each individual event
The degree of agreement of target abnormal user judging result and this detection and analysis result, in detection next time, to each single index
Weight score value be adjusted, and carry out default electricity use detection and analysis again using weight score value adjusted as next
Weight score value；
Wherein, the adjustment rule of the weight score value of each single index is: if the abnormal user based on some single index is sentenced
Disconnected result and the degree of agreement that this tests and analyzes result are higher, then corresponding weight score value tunes up, if being referred to based on some individual event
Target abnormal user judging result and the degree of agreement of this testing result are lower, then corresponding weight score value is turned down.
Compared with prior art, the beneficial effects of the present invention are:
The present invention is based on the default electricity use detection systems and method of non-intrusion type load monitoring, are letting alone suspicious user
In the case of, suspicious user is monitored, by being determined to atypia civil electric appliance and the indicative electric appliance comprehensive analysis of industry and commerce
Whether suspicious user is truly present " people's electric business use " behavior, then receives to user power utilization total amount according to commercial user's the charge of electricity standard
Take the electricity charge.
Detailed description of the invention
Fig. 1 is the system diagram of the default electricity use detection system the present invention is based on non-intrusion type load monitoring；
Fig. 2 is the default electricity use detection method flow diagram the present invention is based on non-intrusion type load monitoring；
Fig. 3 is active total power curve figure suspicious user A one day in detection method；
Fig. 4 is default electricity use decision flow diagram in detection method；
Fig. 5 is active total power curve figure suspicious user B one day in the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Whole description, it should be understood that preferred embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Base
In the embodiment described, those skilled in the art without making creative work, it is obtained other
Embodiment belongs to protection scope of the present invention.
As shown in Figure 1, a kind of default electricity use detection system based on non-intrusion type load monitoring of the present invention, comprising: data
Acquisition module and information exchange module, suspicious user screening module, atypia civil electric appliance screening module, default electricity use judgement refer to
Mark computing module, default electricity use decision-making module and data information memory module.
(1) data acquisition module and information exchange module, it is total using data acquisition functions acquisition low frequency load electricity consumption
Measure data and load electricity consumption detail data；And other specified modules, while information exchange are passed to by information exchange function
Function is also responsible for internal system and extraneous progress data interaction, including but not limited to monitors the display and output with analysis result；
Wherein, conventional low frequency load electricity consumption aggregate data is usually Utilities Electric Co.'s continuous data (generally resulting from common electric energy meter), is used
In screening suspicious user, load electricity consumption detail data is for determining whether the suspicious user having determined is implicitly present in default electricity use
Behavior；In addition, the present invention is using non-intrusive electrical load monitoring technology by dividing according to the actual demand that default electricity use detects
Load electricity consumption aggregate data is analysed to obtain the load electricity consumption detail data for being accurate to electric appliance[3], including electrical work state,
Electric power and accumulative electricity etc..
(2) the suspicious user screening module passes through for detecting the suspicious user of default electricity use in low pressure resident
Calculate user the suspicious index of default electricity use and compared with the suspicious designation number of default electricity use, to determine whether user is suspicious use
Family；
(3) the atypia civil electric appliance screening module, it is described for recognizing appliance type used in suspicious user man
Appliance type include at least the indicative electric appliance of industry and commerce behavior and atypia civil electric appliance etc., whether deposited in screening appliance type
In atypia civil electric appliance, to directly determine whether the user uses the electric appliances to implement default electricity use behavior.
(4) the default electricity use Judging index computing module, for calculating default electricity use Judging index.
(5) the default electricity use decision-making module is used for comprehensive analysis default electricity use Judging index, whether determines suspicious user
It is truly present default electricity use behavior.
(6) the data information memory module is used to store the data acquisition module and information exchange module, suspicious use
Family screening module, atypia civil electric appliance screening module, default electricity use Judging index computing module, default electricity use decision-making module
Various data informations, such as suspicious user electricity consumption data and electricity consumption detail data, including the default electricity use result of decision
Each module operation result data etc..
The detection method of default electricity use is carried out using the above-mentioned default electricity use detection system based on non-intrusion type load monitoring,
Method flow is as shown in Figure 2.The specific step that executes is described below: including:
Step 1: the user of the single-phase user of low pressure breaks a contract, suspicious index is calculated:
The suspicious index calculation method of user's promise breaking is varied, it is contemplated that the exploitativeness and universality of method, it is thus understood that
Different regions Utilities Electric Co. all has recorded the daily electricity consumption data of each user, and bibliography [4] of the present invention establishes and is directed to low pressure list
User's promise breaking suspicion index calculation method of phase user.Calculating is finished into next step.
Specifically, statistics obtains just according to the electricity consumption historical data of the normal users and default electricity use user that acquire
Common amount and promise breaking number of users proportionate relationship, then electricity consumption behavioral indicator range is divided into range of normal value by relationship in proportion
With exceptional value range；The normal users and promise breaking user's ratio obtained by statistical analysis may there are some inclined with true value
Difference, when division, are only used for the preliminary screening of default electricity use detection, to guarantee not omitting default electricity use user, allow in abnormal user
It include a small amount of normal users in range.
Judge whether monitored user is abnormal according to the single-phase user power utilization abnormal behavior index of low pressure, includes following feelings
Shape:
1) user and industry electricity ratio average value are set as W1, work as W1>=1.4, then the monitored user is abnormal；
2) summer and autumn Winter-Spring electricity consumption ratio is set as W2, work as W2>=1.35, then the monitored user is abnormal；
3) trimestral average electricity ratio is W before and after setting user and industry October 13, as user and industry October one
Trimestral average electricity ratio W before and after day3> 1.5, then the monitored user is abnormal；
4) trimestral average electricity ratio is W before and after setting user and industry May 14, as user and industry May one
Trimestral average electricity ratio W before and after day4> 1.4, then the monitored user is abnormal；
5) user and industry electricity ratio are set as W5, work as W5> 1.45, then the monitored user is abnormal；
The suspicious index V of default electricity use of monitored user is calculated by formula (1):
In formula (1), KmFor abnormal index WmWeight, and Km∈[0.5,2]；
To sum up, as shown in table 1.
1 user's default electricity use behavioral indicator of table and suspicious index table
Step 2: suspicious user screening: if V > S0, then the monitored user is suspicious user, enters step three, otherwise
Default electricity use behavior is not present in the monitored user, goes to step 7；Wherein, S0For the suspicious designation number of default electricity use, S0Value
It is 7.
The suspicious several V=7.39 of 3 default electricity use of user can be obtained greater than S by table 10, it is labeled as suspicious user B, into next step.
Step 3: atypia civil electric appliance recognizes: the suspicious use obtained by analysis non-intrusion type load monitoring technology
Electricity consumption detail data in family one week, if Fig. 5 is suspicious user B one day (wherein one day in one week) active total power curve figure,
The appliance type of the user is recognized, identification result is that the suspicious user common electric is refrigerator, electric cooker, water heater
With the electric appliances such as electric light, into next step.
Step 4: atypia civil electric appliance determines: according to identification result, whether the appliance type in the screening suspicious user
Including the substantially unused industry and commerce electric appliance of resident, and if it exists, then go to step 8, otherwise enter step five；Suspicious user B
There is no atypia civil electric appliances, into next step.If similarly suspicious user B goes to step 8 there are atypia civil electric appliance.
Step 5: default electricity use Judging index calculates.
(2) for mentioning " people's electric business use " in background of invention part plant situation, need to find and suitably sentence
Determine index.Default electricity use Judging index is calculated, including basic load determines that power, indicative electric appliance determine operation duration and sentences
Determine on-off frequency, calculating is finished into next step.
Firstly, in resident, add up that operation duration is shorter or day adds up start-stop indicative electric appliance normal day
Number is less.If there are certain industry and commerce behavior, the electricity consumption behaviors of certain indicative electric appliance will differ markedly from just by user
Common family.For example, small hairdressing place can multiple switching hair dryer in one day time.In view of there may be a variety of fingers in user
The property shown electric appliance differentiates to be reliable, the present invention will all add up the day of indicative electric appliances in user the maximum value of operation duration as
Determine operation duration, adds up on-off frequency maximum value day as judgement on-off frequency.
Secondly, either normal resident or industry and commerce user, the possible whole day of some indicative electric appliances, which is in, to be used
State, such as computer, refrigerator-freezer etc..Using only the judgement operation duration of indicative electric appliance and determine that on-off frequency can not can at this time
By differentiating that user whether there is " people's electric business use " behavior.In this regard, the invention proposes basic loads to determine power index.If user
Electricity consumption general power " long-time " is in a certain power bracket, then the center power value of this power bracket is considered as basic load function
The maximum value of multiple basic load power is known as basic load and determines power by rate；If there is no be more than user power utilization general power
5.5 hours durations are in a certain power bracket, then using the central point performance number of the longest a certain power bracket of duration as base
Plinth load determines power.Wherein, it is obtained by a large amount of normal users electricity consumption detail datas statistical analysis, was regarded as more than 5.5 hours
" long-time "；Center power value is related with the selection of clustering method hereinafter.For suspicious user A, the active general power of one day
Curve is as shown in figure 3, can mark three basic load performance numbers, respectively 85W, 3326W and 323W through analysis, final basis
Load determines that power is 3326W.
The circular of indices is as follows:
(1) it obtains basic load and determines power.The basic load determines that power index is, if user power utilization general power exists
Duration more than 5.5 hours is in a certain power bracket, then using the center power value of this power bracket as basic load power,
The maximum value of multiple basic load power is known as basic load and determines power P0；If there is no be more than user power utilization general power
5.5 hours durations are in a certain power bracket, then using the central point performance number of the longest a certain power bracket of duration as base
Plinth load determines power P0.To suspicious user day electricity consumption data carry out load power cluster, obtain multiple load power clusters and its
Duration；It is more than 5.5 hours load power cluster central point performance numbers as basic load function using duration in all load power clusters
Rate Pj, it is ranked up and selects maximum in multiple basic loads by operation watt levelPower is determined as basic load
P0；It, will be in the longest load power cluster of duration if in all load power clusters without duration being more than 5.5 hours load power clusters
Heart point performance number determines power P as basic load0；
By obtaining 3 load powers to B days electricity consumption datas of suspicious user progress load power cluster (as shown in Figure 5)
Cluster, wherein the central point performance number and duration of load power cluster are respectively as follows: 85W, and 14.4 hours；1310W, 7.8 hours；3326W,
0.5 hour.It is more than 5.5 hours load power cluster central point performance numbers as basic load power using duration in load power cluster
Pj.Therefore basic load power PjAre as follows: 85W, 1310W.It then selects maximum in multiple " basis " load powers=1310W as
" basis " load determines power P0。
(2) it calculates indicative electric appliance and determines operation duration.The suspicious user obtained by non-intrusion type load monitoring technology
Then electricity consumption detail data counts and remembers from electricity consumption detail data such as Fig. 5 suspicious user active total power curve figure B one day
That records each indicative electric appliance adds up operation duration and day accumulative on-off frequency day, obtains the state vector of each indicative electric applianceWith when long vectorWherein,Indicate suspicious user B the
In j days k-th of indicative electric appliance monitoring period of time i state, and0, which indicates that indicative electric appliance is in, closes shape
State, 1 indicates that indicative electric appliance is in the open state,For suspicious user B in jth day k-th of indicative electric appliance monitoring when
The duration of section i.Long vector when electrical appliance state vector sum indicative according to resulting each commercial activity, calculates each indicative
Electric appliance day adds up operation duration:
In formula (2), Tk,jIt is suspicious user in jth day, the operation total duration of certain indicative electric appliance k (device numbering).
Using the maximum value added up each commercial activity indicative electric appliance day in operation duration as judgement operation duration Tj。
The time duration up to 5 hours day of indicative electric appliance electric cooker, therefore a length of T when the judgement of suspicious user Bj=
18000s。
(3) it calculates indicative electric appliance and determines on-off frequency.Its day is calculated according to resulting each indicative electrical appliance state vector
Accumulative on-off frequency:
In formula (3), Nk,jIt is suspicious user B in jth day, the on-off times of certain indicative electric appliance k (device numbering).
It will add up maximum on-off times in on-off times each commercial activity indicative electric appliance day and work as judge times Nj, obtain
The day of indicative electric appliance electric cooker add up on-off times and be up to 13, therefore the judgement number of suspicious user is Nj=13.
Step 6: default electricity use decision.Basic load is determined into power, indicative electric appliance judgement operation duration respectively and is sentenced
Determine on-off frequency to be compared with its respective threshold, determines that suspicious user whether there is default electricity use behavior.
In the present invention, with the maximum empirical value P of normal users basic load powermaxPower is determined as basic load
Threshold value adds up operation duration maximum empirical value T with normal users indicative electric appliance daymaxWhen determining to run as indicative electric appliance
Long threshold value；Add up on-off times maximum empirical value N with normal users indicative electric appliance daymaxIt is opened as the judgement of indicative electric appliance
Stop the threshold value of number.
Decision process of the present invention is as shown in Fig. 4 decision tree.In the present invention, basic load determines that power, indicative electric appliance are sentenced
When determining operation duration and determining that on-off frequency threshold value is chosen, different scenes need the Stringency according to screening people screening, can
To there is about 20% adjustment.If screening is stringenter, each Judging index threshold value selects smaller value；If screening is looser, respectively sentence
Determine metrics-thresholds and selects the larger value.By taking basic load determines power typical threshold for 1000W as an example, consider in upper and lower 20% adjustment
Afterwards, then the threshold range is 800~1200W, and similarly, indicative electric appliance determines that operation duration typical threshold is for 10 hours,
The threshold range is 8~12 hours, and by taking indicative electric appliance determines that on-off frequency typical threshold is 9 as an example, which is=7
~11.It is common screening scene by what is considered in this present embodiment, i.e. the Stringency of screening people screening is normal, therefore related
What threshold value was chosen is the median of range.
Detailed process is as follows:
Step 6-1, comparison basis load determines power P0With the maximum empirical value P of normal users basic load powermax；
If P0> Pmax, Pmax=1000W, then there are default electricity use behaviors for suspicious user, go to step 8, otherwise enter step 6-2；
In the present embodiment, suspicious user B basic load determines power P0=1310W and normal users basic load power
Maximum empirical value Pmax=1000W compares；P0> Pmax, then suspicious user goes to step 8 there are default electricity use behavior.
Step 6-2, more indicative electric appliance determines operation duration TjWhen operation accumulative with normal users indicative electric appliance day
Long maximum empirical value Tmax；If Tj> Tmax, Tmax=10 hours, then suspicious user goes to step there are default electricity use behavior
Eight, otherwise enter step 6-3；
In the present embodiment, the indicative electric appliance of suspicious user B determines operation duration Tj=18000s (5 hours) with it is just common
Family indicative electric appliance day adds up the maximum empirical value T of operation durationmax(10 hours) compare.Tj< TmaxEnter step 6-3；
Step 6-3, more indicative electric appliance determines on-off frequency NjWith normal users indicative electric appliance day accumulative switch
Number maximum empirical value Nmax；If Nj> Nmax, Nmax=9, then there are default electricity use behaviors for suspicious user, go to step 8, otherwise
Enter step seven；
In the present embodiment, the indicative electric appliance of suspicious user B determines on-off frequency Nj=13 with the indicative electric appliance of normal users
Day accumulative on-off times maximum empirical value Nmax=9；Nj> Nmax, then suspicious user goes to step 8 there are default electricity use behavior.
Step 7: default electricity use behavior is not present, the suspicious user is excluded there are the suspicion of default electricity use, is so far completed
It is tested and analyzed for the default electricity use of the user；
Step 8: being collected to the user power utilization total amount according to commercial user's the charge of electricity standard there are default electricity use behavior
The electricity charge so far complete the default electricity use detection and analysis for the user；
Step 9: repeating the above steps one to step 8, until completing the promise breaking to target complete user in specified region
Electricity consumption tests and analyzes；
Step 10: testing and analyzing the default electricity use case generated for this default electricity use, refer to according to based on each individual event
The degree of agreement of target abnormal user judging result and this detection and analysis result, in detection next time, in the range of restriction
The weight score value of each single index is adjusted, and is broken a contract again using weight score value adjusted as next
The weight score value that electricity consumption tests and analyzes；
Wherein, the adjustment rule of the weight score value of each single index is: if the abnormal user based on some single index is sentenced
Disconnected result and the degree of agreement that this tests and analyzes result are higher, then corresponding weight score value can be tuned up suitably, if being based on certain
The abnormal user judging result and the degree of agreement of this testing result of a single index are lower, then corresponding weight score value can be with
Suitably turn down.So, with the development that deepens continuously of default electricity use detection work, the weight score value of each index is with tune
It is whole can be more reasonable, and gradually tend to be optimal, the final accuracy rate for improving default electricity use detection.
Although above in conjunction with attached drawing, invention has been described, and the invention is not limited to above-mentioned specific embodiment parties
Formula, the above mentioned embodiment is only schematical, rather than restrictive.Those skilled in the art are in this hair
Under bright enlightenment, without deviating from the spirit of the invention, many variations can also be made, these belong to guarantor of the invention
Within shield.
Claims (3)
1. a kind of default electricity use detection system based on non-intrusion type load monitoring characterized by comprising data acquisition module
With information exchange module, suspicious user screening module, atypia civil electric appliance screening module, default electricity use Judging index calculating mould
Block, default electricity use decision-making module and data information memory module；
The data acquisition module and information exchange module acquire low frequency load electricity consumption aggregate data using data acquisition functions,
Each electric appliance in detection range is obtained by analysis load electricity consumption aggregate data using non-intrusive electrical load monitoring technology
Load electricity consumption detail data, including electrical work state, electric power and accumulative electricity；And it is passed to by information exchange function
Other modules, while information exchange function is also responsible for internal system and extraneous progress data interaction, includes at least monitoring and analysis
As a result display and output；Wherein, low frequency load electricity consumption aggregate data is the continuous data that Utilities Electric Co. is derived from electric energy meter, is used for
Screening suspicious user, load electricity consumption detail data is for determining whether the suspicious user having determined is implicitly present in default electricity use row
For；
The suspicious user screening module is used to detect the suspicious user of default electricity use in low pressure resident, by calculating user
The suspicious index of default electricity use, and compared with the suspicious designation number of default electricity use, to determine whether user is suspicious user；
The atypia civil electric appliance screening module is for recognizing appliance type used in suspicious user man, the electric type
Type includes at least the indicative electric appliance of industry and commerce behavior and atypia civil electric appliance, whether there is the atypia people in screening appliance type
Electrical appliance, to directly determine whether the user uses the electric appliances to implement default electricity use behavior；
The default electricity use Judging index computing module is for calculating default electricity use Judging index；
The default electricity use decision-making module is used for comprehensive analysis default electricity use Judging index, determines whether suspicious user is truly present
Default electricity use behavior；
The data information memory module is used to store the data acquisition module and information exchange module, suspicious user screening mould
Block, atypia civil electric appliance screening module, default electricity use Judging index computing module, the various data of default electricity use decision-making module
Information.
2. a kind of default electricity use detection method based on non-intrusion type load monitoring, which is characterized in that using such as claim 1 institute
State the default electricity use detection system based on non-intrusion type load monitoring, and the following steps are included:
Step 1: the user of the single-phase user of low pressure breaks a contract, suspicious index is calculated:
Judge whether monitored user is abnormal according to the single-phase user power utilization abnormal behavior index of low pressure, include following scenario described:
1) user and industry electricity ratio average value are set as W1, work as W1>=1.4, then the monitored user is abnormal；
2) summer and autumn Winter-Spring electricity consumption ratio is set as W2, work as W2>=1.35, then the monitored user is abnormal；
3) trimestral average electricity ratio is W before and after setting user and industry October 13, before user and industry October 1
Trimestral average electricity ratio W afterwards3> 1.5, then the monitored user is abnormal；
4) trimestral average electricity ratio is W before and after setting user and industry May 14, before user and industry May 1
Trimestral average electricity ratio W afterwards4> 1.4, then the monitored user is abnormal；
5) user and industry electricity ratio are set as W5, work as W5> 1.45, then the monitored user is abnormal；
The suspicious index V of default electricity use of monitored user is calculated by formula (1):
In formula (1), KmFor abnormal index WmWeight, and Km∈[0.5,2]；
Step 2: suspicious user screening:
If V > S0, then the monitored user is suspicious user, enters step three, and otherwise default electricity use is not present in the monitored user
Behavior goes to step 7；Wherein, S0For the suspicious designation number of default electricity use, S0Value is 7；
Step 3: atypia civil electric appliance recognizes:
By electricity consumption detail data in the suspicious user one week of analysis non-intrusion type load monitoring technology acquisition, to suspicious user
Appliance type recognized, including identification appliance type and operating status, identification finish, enter step four；
Step 4: atypia civil electric appliance determines:
Whether the appliance type in the screening suspicious user includes the substantially unused industry and commerce electric appliance of resident, and if it exists, then
Step 8 is gone to, otherwise enters step five；
Step 5: default electricity use Judging index calculates:
Power P is determined including basic load0, indicative electric appliance determine operation duration TjAnd determine on-off frequency Nj,
The circular of indices is as follows:
1) it obtains basic load and determines power P0；If user power utilization general power is in a certain power model in the duration more than 5.5 hours
It encloses, then using the center power value of this power bracket as basic load power, the maximum value of multiple basic load power is known as
Basic load determines power P0；If there is no the durations more than 5.5 hours to be in a certain power bracket for user power utilization general power,
Power P is determined using the central point performance number of the longest a certain power bracket of duration as basic load0；
2) it calculates indicative electric appliance and determines operation duration Tj；The suspicious user electricity consumption obtained by non-intrusion type load monitoring technology
Detail data, then counts from electricity consumption detail data and add up day operation duration and the day for recording each indicative electric appliance accumulative open
Stop number, obtains the state vector of each indicative electric applianceWith when long vectorWherein,Indicate suspicious user in jth day k-th of indicative electric appliance monitoring period of time i's
State, and0 indicates that indicative electric appliance is in close state, and 1 indicates that indicative electric appliance is in the open state,
For suspicious user in jth day duration of k-th of the indicative electric appliance in monitoring period of time i；According to resulting each indicative electricity
Device state vector and when long vector, calculate and each indicative electric appliance day add up operation duration:
In formula (2), Tk,jIt is suspicious user in jth day, the operation total duration of certain indicative electric appliance k, k is device numbering；
The maximum value added up each indicative electric appliance day in operation duration is determined into operation duration T as indicative electric appliancej；
3) it calculates indicative electric appliance and determines on-off frequency Nj；It is accumulative that its day is calculated according to resulting each indicative electrical appliance state vector
On-off frequency:
In formula (3), Nk,jIt is suspicious user in jth day, the on-off times of certain indicative electric appliance k；
The maximum value added up each indicative electric appliance day in on-off frequency is determined into on-off frequency N as indicative electric appliancej；
Step 6: default electricity use decision:
The basic load that step 5 is calculated respectively determines that power, indicative electric appliance determine operation duration and determines start-stop
Number is compared with its respective threshold, therefore, it is determined that suspicious user whether there is default electricity use behavior, wherein with normal users base
The maximum empirical value P of plinth load powermaxThe threshold value of power is determined as basic load；It is tired with normal users indicative electric appliance day
Count operation duration maximum empirical value NmaxThe threshold value of operation duration is determined as indicative electric appliance；With the indicative electric appliance of normal users
Day accumulative on-off times maximum empirical value NmaxThe threshold value of on-off frequency is determined as indicative electric appliance；
Detailed process is as follows:
Step 6-1, comparison basis load determines power P0With Pmax；If P0> Pmax, Pmax=800~1200W, then suspicious user is deposited
In default electricity use behavior, step 8 is gone to, 6-2 is otherwise entered step；
Step 6-2, more indicative electric appliance determines operation duration TjWith Tmax；If Tj> Tmax, Tmax=8~12 hours, then may be used
There are default electricity use behaviors by doubtful user, go to step 8, otherwise enter step 6-3；
Step 6-3, more indicative electric appliance determines on-off frequency NjWith Nmax；If Nj> Nmax, Nmax=7~11, then suspicious use
There are default electricity use behaviors at family, go to step 8, otherwise enter step seven；
Step 7: default electricity use behavior is not present, the suspicious user is excluded there are the suspicion of default electricity use, so far completes and is directed to
The default electricity use of the user tests and analyzes；
Step 8: the electricity charge are collected according to commercial user's the charge of electricity standard to the user power utilization total amount there are default electricity use behavior,
So far the default electricity use detection and analysis for the user are completed；
Step 9: repeating the above steps one to step 8, until completing the default electricity use to target complete user in specified region
It tests and analyzes；
Step 10: the default electricity use case generated is tested and analyzed for this default electricity use, according to based on each single index
The degree of agreement of abnormal user judging result and this detection and analysis result, in detection next time, to the power of each single index
Weight score value is adjusted, and using weight score value adjusted as the next weight for carrying out default electricity use detection and analysis again
Score value；
Wherein, the adjustment rule of the weight score value of each single index is: if the abnormal user based on some single index judges knot
Fruit and the degree of agreement that this tests and analyzes result are higher, then corresponding weight score value tunes up, if based on some single index
Abnormal user judging result and the degree of agreement of this testing result are lower, then corresponding weight score value is turned down.
3. based on the default electricity use detection method of non-intrusion type load monitoring according to claim, which is characterized in that step
In six, Pmax=1000W, Tmax=10 hours, Nmax=9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811651387.1A CN109752613B (en) | 2018-12-31 | 2018-12-31 | Non-invasive load monitoring-based default electricity detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811651387.1A CN109752613B (en) | 2018-12-31 | 2018-12-31 | Non-invasive load monitoring-based default electricity detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109752613A true CN109752613A (en) | 2019-05-14 |
| CN109752613B CN109752613B (en) | 2021-01-26 |
Family
ID=66405001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811651387.1A Active CN109752613B (en) | 2018-12-31 | 2018-12-31 | Non-invasive load monitoring-based default electricity detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109752613B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412347A (en) * | 2019-08-12 | 2019-11-05 | 贵州电网有限责任公司 | A kind of electricity stealing recognition methods and device based on non-intrusion type load monitoring |
| CN110988420A (en) * | 2019-12-02 | 2020-04-10 | 深圳供电局有限公司 | Anti-electricity-theft system and anti-electricity-theft control method |
| CN111242161A (en) * | 2019-12-27 | 2020-06-05 | 国网山西省电力公司大同供电公司 | Non-invasive non-resident user load identification method based on intelligent learning |
| CN112765826A (en) * | 2021-01-27 | 2021-05-07 | 长沙理工大学 | Indoor hemp planting resident user identification method based on power consumption frequency distribution relative entropy |
| CN113341249A (en) * | 2021-06-01 | 2021-09-03 | 江西凯天电力科技发展有限公司 | Intelligent electricity consumption monitoring and alarming system and method |
| CN116660621A (en) * | 2023-07-27 | 2023-08-29 | 江西琰圭技术服务有限公司 | Electricity larceny prevention intelligent management system for local sampling analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103995161A (en) * | 2014-06-03 | 2014-08-20 | 深圳市康拓普信息技术有限公司 | Method and system for discriminating electricity stealing and leaking users |
| EP2801792A2 (en) * | 2013-05-08 | 2014-11-12 | Samsung Electronics Co., Ltd. | Non-intrusive load monitoring apparatus and method |
| CN105938610A (en) * | 2016-07-06 | 2016-09-14 | 国网天津宝坻供电有限公司 | Illegal electricity utilization judgment and report automatic generation method applied to electricity utilization collection system |
| CN106707099A (en) * | 2016-11-30 | 2017-05-24 | 国网上海市电力公司 | Monitoring and locating method based on abnormal electricity consumption detection module |
| CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
| CN107247737A (en) * | 2017-05-10 | 2017-10-13 | 国家电网公司 | Platform area promise breaking electrical energy consumption analysis and method for digging based on power consumption |
| CN107561354A (en) * | 2017-08-17 | 2018-01-09 | 江苏智臻能源科技有限公司 | More electrical equipment non-intruding discrimination methods based on power duration characteristic |
| CN108345906A (en) * | 2018-02-09 | 2018-07-31 | 无锡英臻科技有限公司 | A kind of non-intrusion type electrical appliance recognition methods based on Boost models |
| CN108693499A (en) * | 2018-08-02 | 2018-10-23 | 国网江苏省电力有限公司电力科学研究院 | A kind of user power utilization load identification intelligent electric energy meter detecting system and method |
-
2018
- 2018-12-31 CN CN201811651387.1A patent/CN109752613B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2801792A2 (en) * | 2013-05-08 | 2014-11-12 | Samsung Electronics Co., Ltd. | Non-intrusive load monitoring apparatus and method |
| CN103995161A (en) * | 2014-06-03 | 2014-08-20 | 深圳市康拓普信息技术有限公司 | Method and system for discriminating electricity stealing and leaking users |
| CN105938610A (en) * | 2016-07-06 | 2016-09-14 | 国网天津宝坻供电有限公司 | Illegal electricity utilization judgment and report automatic generation method applied to electricity utilization collection system |
| CN106707099A (en) * | 2016-11-30 | 2017-05-24 | 国网上海市电力公司 | Monitoring and locating method based on abnormal electricity consumption detection module |
| CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
| CN107247737A (en) * | 2017-05-10 | 2017-10-13 | 国家电网公司 | Platform area promise breaking electrical energy consumption analysis and method for digging based on power consumption |
| CN107561354A (en) * | 2017-08-17 | 2018-01-09 | 江苏智臻能源科技有限公司 | More electrical equipment non-intruding discrimination methods based on power duration characteristic |
| CN108345906A (en) * | 2018-02-09 | 2018-07-31 | 无锡英臻科技有限公司 | A kind of non-intrusion type electrical appliance recognition methods based on Boost models |
| CN108693499A (en) * | 2018-08-02 | 2018-10-23 | 国网江苏省电力有限公司电力科学研究院 | A kind of user power utilization load identification intelligent electric energy meter detecting system and method |
Non-Patent Citations (5)
| Title |
|---|
| KETING HU ET AL.: ""Wavelet Entropy-Based Traction Inverter Open Switch Fault Diagnosis in High-Speed Railways"", 《ENTROPY》 * |
| QUAN SUN ET AL.: ""Fault Diagnosis of SEPIC Converters Based on PSO-DBN and Wavelet Packet Energy Spectrum"", 《2017 PROGNOSTICS AND SYSTEM HEALTH MANAGEMENT CONFERENCE (PHM-HARBIN)》 * |
| 姜媛媛 等: ""基于小波包能量谱和 ELM 的光伏逆变器多故障在线诊断"", 《仪 器 仪 表 学 报》 * |
| 宋保业 等: ""基于小波包变换-主元分析-神经网络算法的多电平逆变器故障诊断"", 《山东科技大学学报（自然科学版）》 * |
| 赵海龙 等: ""小波包–能量谱在高压断路器机械故障诊断中的应用"", 《电 网 技 术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412347A (en) * | 2019-08-12 | 2019-11-05 | 贵州电网有限责任公司 | A kind of electricity stealing recognition methods and device based on non-intrusion type load monitoring |
| CN110412347B (en) * | 2019-08-12 | 2021-04-20 | 贵州电网有限责任公司 | Electricity stealing behavior identification method and device based on non-invasive load monitoring |
| CN110988420A (en) * | 2019-12-02 | 2020-04-10 | 深圳供电局有限公司 | Anti-electricity-theft system and anti-electricity-theft control method |
| CN111242161A (en) * | 2019-12-27 | 2020-06-05 | 国网山西省电力公司大同供电公司 | Non-invasive non-resident user load identification method based on intelligent learning |
| CN111242161B (en) * | 2019-12-27 | 2023-08-25 | 国网山西省电力公司大同供电公司 | Non-invasive non-resident user load identification method based on intelligent learning |
| CN112765826A (en) * | 2021-01-27 | 2021-05-07 | 长沙理工大学 | Indoor hemp planting resident user identification method based on power consumption frequency distribution relative entropy |
| CN113341249A (en) * | 2021-06-01 | 2021-09-03 | 江西凯天电力科技发展有限公司 | Intelligent electricity consumption monitoring and alarming system and method |
| CN116660621A (en) * | 2023-07-27 | 2023-08-29 | 江西琰圭技术服务有限公司 | Electricity larceny prevention intelligent management system for local sampling analysis |
| CN116660621B (en) * | 2023-07-27 | 2023-09-26 | 江西琰圭技术服务有限公司 | Electricity larceny prevention intelligent management system for local sampling analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109752613B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109752613A (en) | Default electricity use detection system and method based on non-intrusion type load monitoring | |
| Ma et al. | The role of data analysis in the development of intelligent energy networks | |
| Zhang et al. | Forecasting residential energy consumption: Single household perspective | |
| CN106815677A (en) | The recognition methods of non-intrusion type load and device | |
| CN109490679B (en) | Intelligent electricity stealing inspection system and method based on non-invasive load monitoring | |
| CN108280479A (en) | A kind of power grid user sorting technique based on Load characteristics index weighted cluster algorithm | |
| CN108776939A (en) | The analysis method and system of user power utilization behavior | |
| Kwac et al. | Utility customer segmentation based on smart meter data: Empirical study | |
| Chicco et al. | Emergent electricity customer classification | |
| CN110223196A (en) | Analysis method of opposing electricity-stealing based on typical industry feature database and sample database of opposing electricity-stealing | |
| CN108062627A (en) | A kind of demand response analysis method based on non-intrusion type electricity consumption data | |
| CN109345409A (en) | A kind of resident's comprehensive energy efficiency management method based on bandwidth carrier | |
| CN103675378A (en) | A non-intruding-type household-used electric load decomposition method and an apparatus | |
| CN103577883A (en) | Grid-load intelligent interaction method and device | |
| CN104749431B (en) | A kind of indirect metering system of public building air-conditioning system end-equipment power consumption | |
| CN110109971A (en) | A kind of low-voltage platform area user power utilization Load Characteristic Analysis method | |
| CN111291076A (en) | Abnormal water use monitoring and alarming system based on big data and construction method thereof | |
| CN108734602A (en) | A kind of user's electricity stealing identification system based on higher-dimension random matrix | |
| CN110321934A (en) | A kind of method and system detecting user power utilization abnormal data | |
| CN110222991A (en) | Metering device method for diagnosing faults based on RF-GBDT | |
| Hartmann et al. | Suspicious electric consumption detection based on multi-profiling using live machine learning | |
| CN108053074A (en) | A kind of computational methods and system of power consumption contributive rate | |
| CN110070256A (en) | Zero power user based on CRITIC method checks priority weighing computation method | |
| CN112834837B (en) | User behavior fine analysis method based on non-invasive load monitoring | |
| Chen et al. | Research on residents' electricity behaviour analysis and control strategy optimisation |
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 |