CN116437244A - Ammeter anomaly detection method and system - Google Patents
Ammeter anomaly detection method and system Download PDFInfo
- Publication number
- CN116437244A CN116437244A CN202310291156.9A CN202310291156A CN116437244A CN 116437244 A CN116437244 A CN 116437244A CN 202310291156 A CN202310291156 A CN 202310291156A CN 116437244 A CN116437244 A CN 116437244A
- Authority
- CN
- China
- Prior art keywords
- electric appliance
- control command
- subsystem
- home gateway
- event
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 230000005611 electricity Effects 0.000 claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000007405 data analysis Methods 0.000 claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000009191 jumping Effects 0.000 claims description 7
- 230000000977 initiatory effect Effects 0.000 claims description 2
- 238000012216 screening Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 23
- 230000009471 action Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2823—Reporting information sensed by appliance or service execution status of appliance services in a home automation network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q2209/00—Arrangements in telecontrol or telemetry systems
- H04Q2209/60—Arrangements in telecontrol or telemetry systems for transmitting utility meters data, i.e. transmission of data from the reader of the utility meter
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q2209/00—Arrangements in telecontrol or telemetry systems
- H04Q2209/70—Arrangements in the main station, i.e. central controller
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention provides an ammeter anomaly detection method and system, wherein the method comprises the following steps: step 1, a home gateway subsystem receives an electrical control command of a resident, generates an electrical collection and electricity utilization event and reports the event to a Yun Pingtai subsystem; step 2, the cloud platform subsystem queries the ammeter reading value of the household ammeter in the period accompanied by the electricity utilization event and stores the ammeter reading value into a database; and step 3, the data analysis subsystem completes data clustering and anomaly analysis and outputs an ammeter anomaly detection result. By adopting the method, the home gateway and the cloud platform are combined to form the electric appliance set power utilization original database in each form, the data clustering is used for screening the same set of the same form original data, and finally, whether the power metering function of the power meter is normal or not is judged by the feature analysis.
Description
Technical Field
The invention relates to the field of ammeter anomaly detection, in particular to an ammeter anomaly detection method and system.
Background
In recent years, with the rapid development of social intelligence, the intelligent transformation of the aspects of social life operation is rapid, the penetration rate of electric equipment operation or auxiliary operation is very high, the range of requirements of various layers of society for power supply is also becoming wider and wider, and obviously, power supply enterprises as important basic industries of China become important supporting forces of national economy and become key factors for promoting the healthy development of various industries.
The power supply firstly needs to consider the balance of supply and demand, and only can effectively control the power generation cost and provide low-cost power supply for power utilization parties only by ensuring the power utilization requirement and wasting as little as possible, then in the practical society, various electricity stealing phenomena are extremely serious, and partial households steal power by various methods in order to save the power cost, so that the power supply and demand are unbalanced, and in serious cases, the load overload directly causes the switch-off of a sheet area, so that great negative influence is brought to the folk life, and therefore, the problems of high-efficiency power utilization detection, electricity larceny prevention detection and the like become the hot attention problem of the power industry.
The ordinary households have complicated electricity consumption behaviors, and have the characteristics of diversified electrical appliance forms, discrete use time periods, time duration and the like, so that abnormal electricity consumption monitoring of the ordinary households, especially abnormal electricity meter monitoring of the ordinary households, is very difficult, but at present, the permeability of household electrical appliances is unprecedented, the daily electricity consumption of the households already occupies a considerable proportion of electricity supply, if the household electricity consumption of the households is not actually monitored, great challenges are brought to the power supply and demand budget, and further potential electricity utilization hazards are caused, therefore, the problem that the industry is to be solved is how to overcome the abnormal electricity meter monitoring under the complicated electricity consumption behaviors, and timely monitor whether the electric meters of the ubiquitous households are abnormal or not by combining the intelligent characteristics of the electrical appliances.
Disclosure of Invention
The beneficial effects of the invention are as follows: compared with the prior art, the invention has the following advantages and beneficial effects: by adopting the method, the home gateway and the cloud platform are combined to form the electric appliance set power utilization original database in each form, the data clustering is used for screening the same set of the same form original data, and finally, whether the power metering function of the power meter is normal or not is judged by the feature analysis.
Drawings
Fig. 1 is a flowchart of an abnormality detection method of an electric meter.
Fig. 2 is a meter anomaly detection system.
Fig. 3 is a schematic of the electricity consumption behavior of the method a.
Fig. 4 is a schematic of electricity consumption behavior of the method B.
Detailed Description
For the purpose of making the technical solutions and advantages of the present invention more apparent, the present invention will be described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the method for detecting the abnormality of the ammeter specifically comprises the following steps:
step 1, a home gateway subsystem receives an electrical control command of a resident, generates an electrical collection and electricity utilization event and reports the event to a Yun Pingtai subsystem;
step 2, the cloud platform subsystem queries the ammeter reading value of the household ammeter in the period accompanied by the electricity utilization event and stores the ammeter reading value into a database;
and step 3, the data analysis subsystem completes data clustering and anomaly analysis and outputs an ammeter anomaly detection result.
In the step 1, the electrical control command of the resident is sent by the APP, the electrical appliance and the APP initiating the electrical control command are connected to the home gateway subsystem through wireless signals such as WIFI, bluetooth and the like, and the control command sent by the APP is forwarded to the corresponding electrical appliance by the home gateway subsystem, so that the operation control of the electrical appliance is realized;
in the step 1, the electrical control command is sent by a terminal APP through wireless signals such as WIFI, bluetooth and the like, and then received and analyzed by a home gateway subsystem;
in the step 1, the method for generating the electric appliance collection and electricity utilization event comprises the following steps:
step 1.1A, capturing an electric appliance control command by a home gateway subsystem, storing the command into a home gateway database DB1 according to a time sequence, and defining the moment as T2;
step 1.2A, the home gateway subsystem inquires the moment point of the last electric appliance opening or closing command from the moment point of T2 from the database DB1 and marks the moment point as the moment point of T1, judges whether the time period from T1 to T2 is a command except the electric appliance opening or closing command, if so, jumps to step 1.6A, and if not, jumps to step 1.3A;
step 1.3A, the home gateway subsystem searches whether a command which is different from the operation type of the T1 time point exists in the period from T1_Delta0 to T1, if so, the step 1.6A is skipped, if not, the step 1.4A is skipped, and the operation types are opened, closed and other (other include temperature increasing, temperature reducing and the like);
step 1.4A, the home gateway subsystem searches a time point T0 of capturing an electric appliance control command last time before the time of T1_Delta0, if T1_Delta0-T0 is larger than a threshold Delta1, the step 1.5A is skipped, and if not, the step 1.6A is skipped;
step 1.5A, the home gateway subsystem gathers { practice A, resident ID, T0, T1_Delta0, T1, T2, control command set and electric appliance model set } information of the time period from T1_Delta0 to T1 to form an electric appliance set electricity utilization event, and jumps to step 1.7A;
capturing 1.6A, enabling the home gateway subsystem not to generate an electric appliance collection electricity utilization event, and jumping to the step 1.7A;
and step 1.7A, ending the operation of generating the electric appliance collection electricity utilization event.
In the step 1, the method for generating the electric event for the electric appliance collection comprises the following steps:
step 1.1B, capturing an electric appliance control command by a home gateway subsystem, storing the command into a home gateway database DB1 according to a time sequence, and defining the moment as T2;
step 1.2B, the home gateway subsystem inquires the moment point of the last electric appliance opening or closing command from the moment point of T2 from the database DB1 and marks the moment point as the moment point of T1, judges whether the time period from T1 to T2 is a command except the electric appliance opening or closing command, if so, jumps to step 1.5B, and if not, jumps to step 1.3B;
step 1.3B, the home gateway subsystem searches a time point T0 of the last capturing of the electric appliance control command before the time T1, if T1-T0 is larger than a threshold Delta1, the step 1.4B is skipped, and if not, the step 1.5B is skipped;
step 1.4B, the home gateway subsystem gathers { the information of the operation B, the resident ID, the control command set at the moment T0, the control command set at the moment T1, the control command set at the moment T2 and the control command set at the moment T1 } to form an electric appliance set electricity utilization event, and jumps to the step 1.6B;
capturing 1.5B, enabling the home gateway subsystem not to generate an electric appliance collection electricity utilization event, and jumping to the step 1.6B;
and step 1.6B, ending the operation of generating the electric appliance collection electricity utilization event.
In the step 1, the electric appliance collection and electricity utilization event can adopt three operations of a method A, a method B, and a combination of the method A and the method B;
in the step 2, the cloud platform subsystem queries the meter reading value of the household meter in the electricity utilization event accompanying time period and stores the meter reading value into a database, and the specific method is as follows: after the cloud platform subsystem inquires that the electric appliance collection power utilization event is received,
events generated for the a-practice: querying the ammeter reading { R0, R10, R11, R2} of the households corresponding to the households ID at the four time points { T0, T1_Delta0, T1, T2}, and then storing { practice A, household ID, { T0, R0}, { T1_Delta0, R10}, { T1, R11}, { T2, R2}, and a control command set and an electric appliance model set of the time period from T1_Delta0 to T1 into a database;
events generated for B practice: inquiring the ammeter reading values { R0, R1 and R2} of residents corresponding to the resident IDs at three time points { T0, T1 and T2}, and then storing { practice B, resident IDs, { T0, R0}, { T1 and R1}, { T2 and R2}, control command set and electric appliance model set at the time point T1 into a database;
and 3, the data analysis subsystem completes data clustering and anomaly analysis and outputs an ammeter anomaly detection result, which comprises the following specific steps:
step 3.1, the data analysis subsystem divides the same items of a control command set and an electric appliance model set in the database into the same category to form a clustering set C;
and 3.2, the data analysis subsystem calculates the electricity consumption of the control command set and the electric appliance model set in unit time for each item i (i has the value of 1, & gt, numC, wherein NumC is the total number of elements of the cluster set C), and the calculation method is as follows:
if the "control command set" is that the electric appliance is turned on, and the method is that the method A is that the unit power consumption COST (i) of the "electric appliance model set" is calculated as follows:
COST（i）=（（R2-R11）-（（（R10-R0）/T1_Delta0-T0）*（T2-T1）））/（T2-T1）;
if the "control command set" is that the electric appliance is turned off, and the method is that the method A is that the unit power consumption COST of the "electric appliance model set" is calculated as follows:
COST（i）=（（R10-R0）-（（R2-R11）/（T2-T1））*T1_Delta0-T0）/T1_Delta0-T0；
if the "control command set" is that the electric appliance is turned on, and the method is that the unit power consumption COST of the "electric appliance model set" is calculated as follows:
COST（i）=（（R2-R1）-（（（R1-R0）/T1-T0）*（T2-T1）））/（T2-T1）;
if the "control command set" is that the electric appliance is turned off, and the method of calculating the unit power consumption COST of the "electric appliance model set" is as follows:
COST（i）=（（R1-R0）-（（R2-R1）/（T2-T1））*T1-T0）/T1-T0；
step 3.3, the data analysis subsystem sorts COST (i) from large to small, then averages Avg, subtracts Avg from the maximum value in COST (i) to obtain DeltaCost, and determines households lower than Avg-DeltaCost Threshold as abnormal households; or, determining that the householder with the ratio of the times less than Avg-DeltaCost to the total event number of times greater than N in all events of the householder is an abnormal household; the N, threshold is finished through presetting, preferably, the value of N is 20% of the total power utilization time of the corresponding resident, and the Threshold is set to be 1.2.
An embodiment of the present invention is illustrated in fig. 2, which is a schematic diagram of an electric meter anomaly detection system.
As shown in fig. 2, an ammeter anomaly detection system includes: the system comprises a home gateway subsystem, a cloud platform subsystem and a data analysis subsystem, wherein the functions of the subsystems are described as follows:
the household gateway subsystem is responsible for receiving an electrical control command of a resident, generating an electrical appliance collection and electricity utilization event and reporting the event to the Yun Pingtai subsystem;
yun Pingtai subsystem, which is responsible for inquiring the ammeter reading value of the household ammeter in the period accompanied by the electricity utilization event and storing the ammeter reading value into a database;
and the data analysis subsystem is responsible for completing data clustering and anomaly analysis and outputting an ammeter anomaly detection result.
Specific embodiments of an ammeter anomaly detection system are described below with specific examples:
examples: in this embodiment, assuming that a plurality of electricity behavior data of 10000 households are sampled, the following describes the detection process of the electric meter anomaly detection method provided by the invention:
firstly, according to step 1, a home gateway subsystem receives an electrical control command of a resident, generates an electrical appliance set electrical event and reports the electrical appliance set electrical event to a cloud platform subsystem, and the specific operation process for generating the electrical appliance set electrical event is divided into a method and a method B, and is described as follows:
first, generate appliance collection electrical events based on "a-practice" (illustrated by way of example in fig. 3):
firstly, capturing an electric appliance control command according to the step 1.1A, storing the command into a home gateway database DB1 according to a time sequence, and defining the moment as T2 (see T2 in FIG. 3 for details);
next, according to step 1.2A, the home gateway subsystem queries the time point of the last electric appliance on or off command from the time point T2 from the database DB1 and records the time point as the time point T1 (see T1 in fig. 3 in detail), and determines whether the time period T1 to T2 is a command other than the electric appliance on or off command, if yes, it jumps to step 1.6A, if no, it jumps to step 1.3A, in this embodiment, the "electric appliance 5 lifting temperature 3 degrees" action occurs due to the fact that the time period T1 to T2 is a command other than the electric appliance on or off command, so that the "electric appliance 5 lifting temperature 3 degrees" action jumps to step 1.6A, and the "electric appliance 2" and "electric appliance 3" actions jump to step 1.3A because no command other than the electric appliance on or off command occurs in the time period T1 to T2;
then, according to step 1.3A, the home gateway subsystem searches whether there is a command different from the operation type of the T1 time point in the period from t1_delta0 to T1, if yes, it jumps to step 1.6A, if no, it jumps to step 1.4A, the operation type is divided into on, off, other (other include increasing temperature, decreasing temperature, etc.), in this embodiment, fig. 3 only "user action 2", "user action 3" goes to step 1.3A, and "user action 2" has "electric appliance 7 on" in the period from t1_delta0 to T1, the operation type is different from the operation type of the T1 time point "electric appliance 3 off", so "user action 2" jumps directly to step 1.6A, and "user action 3" has "electric appliance 1 off" in the period from t1_delta0 to T1, the operation type is the same as the operation type of the T1 time point "electric appliance 3 off", so "user action 3" jumps to step 1.4A;
then, according to step 1.4A, the home gateway subsystem searches for the time point T0 at which the appliance control command was last captured before the time t1_delta0, if t1_delta0-T0 is greater than the threshold Delta1, then jump to step 1.5A, if not, jump to step 1.6A, in this embodiment, assume that t1_delta0-T0 is greater than Delta1, and therefore jump to step 1.5A;
then, according to step 1.5A, the home gateway subsystem assembles the information of the electricity consumption behavior 3 in FIG. 3 into { practice A, household ID, T0, T1_Delta0, T1, T2, a control command set and an electric appliance model set in the period from T1_Delta0 to T1 }, forms an electric appliance set electricity consumption event, and jumps to step 1.7A;
capturing 1.6A, wherein the home gateway subsystem does not generate an electric appliance collection electricity utilization event, and in the embodiment, jumping and collocating the steps of 'electricity utilization behavior 1' and 'electricity utilization behavior 2' in the figure 3, namely, the corresponding electricity utilization behavior does not generate the electric appliance collection electricity utilization event, and jumping to the step 1.7A;
and step 1.7A, ending the operation of generating the electric appliance collection electricity utilization event.
Second, generating appliance collection electrical events based on "B-practices" (illustrated by way of example in fig. 4):
according to the step 1.1B, the home gateway subsystem captures the electrical control command, the command is stored in the home gateway database DB1 according to the time sequence, and the time point is defined as T2, and is shown as T2 in the detail in FIG. 4;
then, according to step 1.2B, the home gateway subsystem queries the time point when the electric appliance on or off command occurs the last time from the time point of T2 from the database DB1 and marks the time point as the time point of T1, and determines whether the command other than the electric appliance on or off command occurs in the time period of T1 to T2, if yes, the process jumps to step 1.5B, if not, the process jumps to step 1.3B, in this embodiment, "power consumption behavior 1" in fig. 4, because the command other than the electric appliance on or off command occurs in the time period of T1 to T2, namely, the electric appliance 5 increases the temperature by 3 degrees, so that the "power consumption behavior 1" jumps to step 1.5B, whereas the "power consumption behavior 2" and "power consumption behavior 3" have no command other than the electric appliance on or off command occurs in the time period of T1 to T2, so that the "power consumption behavior 2" jumps to step 1.3B;
then according to the step 1.3B, the home gateway subsystem searches the time point T0 of the last capturing of the appliance control command before the time T1, if T1-T0 is greater than the threshold Delta1, the step 1.4B is skipped, if not, the step 1.5B is skipped, in this embodiment, it is assumed that the "power consumption behavior 2" T1-T0 in fig. 4 is less than the threshold Delta1, and the "power consumption behavior 3" T1-T0 is greater than the threshold Delta1, so that the "power consumption behavior 2" determination result is skipped to the step 1.5B, and the "power consumption behavior 3" determination result is skipped to the step 1.4B;
then, according to the step 1.4B, the home gateway subsystem composes the information of electricity consumption behavior 3 in the figure 4 into { an operation B, a resident ID, a control command set and an electric appliance model set at the moment of T0, T1, T2 and T1 }, forms an electric appliance set electricity consumption event, and jumps to the step 1.6B;
capturing 1.5B, wherein the home gateway subsystem does not generate an appliance collection electricity utilization event, in the embodiment, "electricity utilization behavior 2" and "electricity utilization behavior 3" in FIG. 4 do not generate an appliance collection electricity utilization event, and jumping to step 1.6B;
and step 1.6B, ending the operation of generating the electric appliance collection electricity utilization event.
Then, according to the step 2, the cloud platform subsystem queries the ammeter reading value of the household ammeter in the electricity utilization event accompanying time period and stores the ammeter reading value in the database, and the cloud platform subsystem queries the ammeter reading value of the household ammeter in the electricity utilization event accompanying time period and stores the ammeter reading value in the database, which comprises the following specific steps: after the cloud platform subsystem inquires that the electric appliance collection power utilization event is received,
events generated for the a-practice: querying the ammeter reading { R0, R10, R11, R2} of the households corresponding to the households ID at the four time points { T0, T1_Delta0, T1, T2}, and then storing { practice A, household ID, { T0, R0}, { T1_Delta0, R10}, { T1, R11}, { T2, R2}, and a control command set and an electric appliance model set of the time period from T1_Delta0 to T1 into a database;
events generated for B practice: inquiring the ammeter reading values { R0, R1 and R2} of residents corresponding to the resident IDs at three time points { T0, T1 and T2}, and then storing { practice B, resident IDs, { T0, R0}, { T1 and R1}, { T2 and R2}, control command set and electric appliance model set at the time point T1 into a database;
and then, completing data clustering and anomaly analysis according to the step 3 and the data analysis subsystem, and outputting an ammeter anomaly detection result.
The specific method comprises the following steps:
according to step 3.1, the data analysis subsystem divides the same items of the control command set and the electric appliance model set in the database into the same category to form a clustering set C, taking the electricity consumption behavior 3 in fig. 3 as an example, the condition of dividing the same items into the same category is other electricity consumption behaviors, wherein the control command set and the electric appliance model set at the moment T1 are also the electric appliance 1 is closed and the electric appliance 3 is closed, and the electric appliance model sets are the electric appliance 1 and the electric appliance 3 corresponding models;
then, according to step 3.2, the data analysis subsystem calculates the electricity consumption per unit time in the control command set and the electric appliance model set according to the values of i (i is 1,..and NumC, wherein NumC is the total number of elements of the cluster set C), and the calculation method is as follows:
if the "control command set" is that the electric appliance is turned on, and the method is that the method A is that the unit power consumption COST (i) of the "electric appliance model set" is calculated as follows:
COST（i）=（（R2-R11）-（（（R10-R0）/T1_Delta0-T0）*（T2-T1）））/（T2-T1）;
if the "control command set" is that the electric appliance is turned off, and the method is that the method A is that the unit power consumption COST of the "electric appliance model set" is calculated as follows:
COST（i）=（（R10-R0）-（（R2-R11）/（T2-T1））*T1_Delta0-T0）/T1_Delta0-T0；
if the "control command set" is that the electric appliance is turned on, and the method is that the unit power consumption COST of the "electric appliance model set" is calculated as follows:
COST（i）=（（R2-R1）-（（（R1-R0）/T1-T0）*（T2-T1）））/（T2-T1）;
if the "control command set" is that the electric appliance is turned off, and the method of calculating the unit power consumption COST of the "electric appliance model set" is as follows:
COST（i）=（（R1-R0）-（（R2-R1）/（T2-T1））*T1-T0）/T1-T0；
to this end, according to the above calculation, assuming that 10 households can generate events of an appliance set for an electric event in each household, the event codes are 1 to 10, and the events of the 10000 households are the same, according to step 3.3, firstly processing the event 1, sorting the COST (i) of the event from large to small, i takes a value of 1 to 10000, then averaging Avg, subtracting Avg from the maximum value of the COST (i) to obtain DeltaCost, then identifying households lower than Avg-DeltaCost, then sequentially processing event 2, term, event 10, and finally, as shown in table 1, then entering into an ammeter anomaly determination, if adopting the determination principle that "households lower than Avg-DeltaCost are anomaly", in this embodiment, household 1, household 9, household 800, and household 901 are determined to be anomaly "if the number of households lower than Avg-DeltaCost is lower than 20%, and the number of households lower than Avg-DeltaCost is determined to be anomaly" as being greater than 20%, and the number of households are determined to be anomaly "as being greater than 20, in this embodiment is achieved.
By adopting the method, the home gateway and the cloud platform are combined to form the electric appliance set power utilization original database in each form, the data clustering is used for screening the same set of the same form of original data, and finally, whether the power metering function of the power meter is normal or not is checked through the characteristic analysis.
Table 1 single event satisfies "Avg-DeltaCost Threshold" resident identification
| Household ID | Event 1 | Event 2 | Event 3 | Event 4 | Event 5 | Event 6 | Event 7 | Event 8 | Event 9 | Event 10 |
| 1 | Satisfy the following requirements | Satisfy the following requirements | Satisfy the following requirements | |||||||
| 9 | Satisfy the following requirements | |||||||||
| 800 | Satisfy the following requirements | |||||||||
| 901 | Satisfy the following requirements |
Claims (10)
1. An ammeter anomaly detection method is characterized in that:
step 1, a home gateway subsystem receives an electrical control command of a resident, generates an electrical collection and electricity utilization event and reports the event to a Yun Pingtai subsystem;
step 2, the cloud platform subsystem queries the ammeter reading value of the household ammeter in the period accompanied by the electricity utilization event and stores the ammeter reading value into a database;
and step 3, the data analysis subsystem completes data clustering and anomaly analysis and outputs an ammeter anomaly detection result.
2. The method for detecting an abnormality of an electric meter according to claim 1, wherein:
in the step 1, the electrical control command of the resident is sent by the APP, the APP initiating the electrical control command of the electrical appliance is connected to the home gateway subsystem through wireless signals such as WIFI and Bluetooth, and the control command sent by the APP is forwarded to the corresponding electrical appliance by the home gateway subsystem, so that the operation control of the electrical appliance is realized.
3. The method for detecting an abnormality of an electric meter according to claim 2, wherein:
in the step 1, the electrical control command is sent by the terminal APP through wireless signals such as WIFI, bluetooth and the like, and then received and analyzed by the home gateway subsystem.
4. A meter anomaly detection method according to claim 2 or 3, wherein:
in the step 1, the method for generating the electric appliance collection and electricity utilization event comprises the following steps:
step 1.1A, capturing an electric appliance control command by a home gateway subsystem, storing the command into a home gateway database DB1 according to a time sequence, and defining the moment as T2;
step 1.2A, the home gateway subsystem inquires the moment point of the last electric appliance opening or closing command from the moment point of T2 from the database DB1 and marks the moment point as the moment point of T1, judges whether the time period from T1 to T2 is a command except the electric appliance opening or closing command, if so, jumps to step 1.6A, and if not, jumps to step 1.3A;
step 1.3A, the home gateway subsystem searches whether a command with a different operation type from a T1 time point exists in a period from T1_Delta0 to T1, if so, the step 1.6A is skipped, and if not, the step 1.4A is skipped;
step 1.4A, the home gateway subsystem searches a time point T0 of capturing an electric appliance control command last time before the time of T1_Delta0, if T1_Delta0-T0 is larger than a threshold Delta1, the step 1.5A is skipped, and if not, the step 1.6A is skipped;
step 1.5A, the home gateway subsystem gathers { practice A, resident ID, T0, T1_Delta0, T1, T2, control command set and electric appliance model set } information of the time period from T1_Delta0 to T1 to form an electric appliance set electricity utilization event, and jumps to step 1.7A;
capturing 1.6A, enabling the home gateway subsystem not to generate an electric appliance collection electricity utilization event, and jumping to the step 1.7A;
and step 1.7A, ending the operation of generating the electric appliance collection electricity utilization event.
5. A meter anomaly detection method according to claim 2 or 3, wherein:
in the step 1, the method for generating the electric appliance collection and electricity utilization event comprises the following steps:
step 1.1B, capturing an electric appliance control command by a home gateway subsystem, storing the command into a home gateway database DB1 according to a time sequence, and defining the moment as T2;
step 1.2B, the home gateway subsystem inquires the moment point of the last electric appliance opening or closing command from the moment point of T2 from the database DB1 and marks the moment point as the moment point of T1, judges whether the time period from T1 to T2 is a command except the electric appliance opening or closing command, if so, jumps to step 1.5B, and if not, jumps to step 1.3B;
step 1.3B, the home gateway subsystem searches a time point T0 of the last capturing of the electric appliance control command before the time T1, if T1-T0 is larger than a threshold Delta1, the step 1.4B is skipped, and if not, the step 1.5B is skipped;
step 1.4B, the home gateway subsystem gathers { the information of the operation B, the resident ID, the control command set at the moment T0, the control command set at the moment T1, the control command set at the moment T2 and the control command set at the moment T1 } to form an electric appliance set electricity utilization event, and jumps to the step 1.6B;
capturing 1.5B, enabling the home gateway subsystem not to generate an electric appliance collection electricity utilization event, and jumping to the step 1.6B;
and step 1.6B, ending the operation of generating the electric appliance collection electricity utilization event.
6. The method for detecting an abnormality of an electric meter according to claim 4, wherein:
in the step 2, the cloud platform subsystem queries the meter reading value of the household meter in the electricity utilization event accompanying time period and stores the meter reading value into a database, and the specific method is as follows: after the cloud platform subsystem inquires and receives the electric appliance collection power utilization event:
the method comprises the steps of inquiring ammeter reading values { R0, R10, R11 and R2} of residents corresponding to resident IDs at four time points { T0, T1_Delta0, T1 and T2}, and storing { practice A, resident IDs, { T0, R0}, { T1_Delta0, R10}, { T1, R11}, { T2 and R2}, and a control command set and an electric appliance model set from (T1_Delta 0) to a time period T1 into a database.
7. The method for detecting an abnormality of an electric meter according to claim 5, wherein:
in the step 2, the cloud platform subsystem queries the meter reading value of the household meter in the electricity utilization event accompanying time period and stores the meter reading value into a database, and the specific method is as follows: after the cloud platform subsystem inquires and receives the electric appliance collection power utilization event:
the method comprises the steps of inquiring ammeter reading values { R0, R1 and R2} of residents corresponding to resident IDs at three time points { T0, T1 and T2}, and then storing { practice B, resident IDs, { T0, R0}, { T1 and R1}, { T2 and R2}, a control command set and an appliance model set at the time point T1 into a database.
8. The method for detecting an abnormality of an electric meter according to claim 4, wherein:
and 3, the data analysis subsystem completes data clustering and anomaly analysis and outputs an ammeter anomaly detection result, which comprises the following specific steps:
step 3.1, the data analysis subsystem divides the same items of a control command set and an electric appliance model set in the database into the same category to form a clustering set C;
and 3.2, the data analysis subsystem calculates the electricity consumption of the control command set and the electric appliance model set in unit time for each item i (i has the value of 1, & gt, numC, wherein NumC is the total number of elements of the cluster set C), and the calculation method is as follows:
if the "control command set" is that the electric appliance is turned on, the calculation method of the unit power consumption COST (i) of the "electric appliance model set" is as follows:
COST（i）=（（R2-R11）-（（（R10-R0）/（T1_Delta0-T0））*（T2-T1）））/（T2-T1）;
if the "control command set" is that the electric appliance is turned off, the calculation method of the unit power consumption COST of the "electric appliance model set" is as follows:
COST（i）=（（R10-R0）-（（R2-R11）/（T2-T1））*（T1_Delta0-T0））/（T1_Delta0-T0）；
step 3.3, the data analysis subsystem sorts COST (i) from large to small, then averages Avg, subtracts Avg from the maximum value in COST (i) to obtain DeltaCost, and determines households lower than Avg-DeltaCost Threshold as abnormal households; alternatively, a resident having a ratio of less than Avg-DeltaCost to total event number of times greater than N among all events of the resident is determined to be an abnormal resident.
9. The method for detecting an abnormality of an electric meter according to claim 5, wherein:
and 3, the data analysis subsystem completes data clustering and anomaly analysis and outputs an ammeter anomaly detection result, which comprises the following specific steps:
step 3.1, the data analysis subsystem divides the same items of a control command set and an electric appliance model set in the database into the same category to form a clustering set C;
and 3.2, the data analysis subsystem calculates the electricity consumption of the control command set and the electric appliance model set in unit time for each item i (i has the value of 1, & gt, numC, wherein NumC is the total number of elements of the cluster set C), and the calculation method is as follows:
if the control command set is that the electric appliance is started, the calculation method of the unit power consumption COST of the electric appliance model set is as follows:
COST（i）=（（R2-R1）-（（（R1-R0）/（T1-T0））*（T2-T1）））/（T2-T1）;
if the "control command set" is that the electric appliance is turned off, the calculation method of the unit power consumption COST of the "electric appliance model set" is as follows:
COST（i）=（（R1-R0）-（（R2-R1）/（T2-T1））*（T1-T0））/（T1-T0）；
step 3.3, the data analysis subsystem sorts COST (i) from large to small, then averages Avg, subtracts Avg from the maximum value in COST (i) to obtain DeltaCost, and determines households lower than Avg-DeltaCost Threshold as abnormal households; alternatively, a resident having a ratio of less than Avg-DeltaCost to total event number of times greater than N among all events of the resident is determined to be an abnormal resident.
10. The electric meter abnormality detection method according to claim 8 or 9, characterized in that:
the N, threshold is finished through presetting, the value of N is 20% of the total power utilization time of the corresponding resident, and the Threshold is set to be 1.2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310291156.9A CN116437244A (en) | 2023-03-23 | 2023-03-23 | Ammeter anomaly detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310291156.9A CN116437244A (en) | 2023-03-23 | 2023-03-23 | Ammeter anomaly detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116437244A true CN116437244A (en) | 2023-07-14 |
Family
ID=87078877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310291156.9A Pending CN116437244A (en) | 2023-03-23 | 2023-03-23 | Ammeter anomaly detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116437244A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103532745A (en) * | 2013-09-25 | 2014-01-22 | 国家电网公司 | Metering online monitoring system based on power user power consumption information acquisition system |
| CN106296465A (en) * | 2016-08-23 | 2017-01-04 | 四川大学 | A kind of intelligent grid exception electricity consumption behavioral value method |
| CN113032454A (en) * | 2021-03-01 | 2021-06-25 | 南京谱隘网络科技有限公司 | Interactive user power consumption abnormity monitoring and early warning management cloud platform based on cloud computing |
| CN113709592A (en) * | 2021-07-19 | 2021-11-26 | 杭州锉盾晟科技有限公司 | Electricity consumption information acquisition system based on intelligent ammeter and operation method thereof |
-
2023
- 2023-03-23 CN CN202310291156.9A patent/CN116437244A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103532745A (en) * | 2013-09-25 | 2014-01-22 | 国家电网公司 | Metering online monitoring system based on power user power consumption information acquisition system |
| CN106296465A (en) * | 2016-08-23 | 2017-01-04 | 四川大学 | A kind of intelligent grid exception electricity consumption behavioral value method |
| CN113032454A (en) * | 2021-03-01 | 2021-06-25 | 南京谱隘网络科技有限公司 | Interactive user power consumption abnormity monitoring and early warning management cloud platform based on cloud computing |
| CN113709592A (en) * | 2021-07-19 | 2021-11-26 | 杭州锉盾晟科技有限公司 | Electricity consumption information acquisition system based on intelligent ammeter and operation method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108021736B (en) | Load switching action monitoring method based on sliding window residual error model | |
| Chen et al. | Non-intrusive occupancy monitoring using smart meters | |
| US9797935B2 (en) | Device, arrangement and method for verifying the operation of electricity meter | |
| Ruzzelli et al. | Real-time recognition and profiling of appliances through a single electricity sensor | |
| Li et al. | Systematic data mining-based framework to discover potential energy waste patterns in residential buildings | |
| Schoofs et al. | Annot: Automated electricity data annotation using wireless sensor networks | |
| CN110672934A (en) | Non-invasive load identification method, terminal and system | |
| CN106340884B (en) | Non-intrusion type non-frequency refrigerator based on combined power criterion starts discrimination method | |
| GB2606284A (en) | Non-intrusive load monitoring method | |
| Barker et al. | Non-intrusive load identification for smart outlets | |
| CN111553444A (en) | Load identification method based on non-invasive load terminal data | |
| Xu et al. | A new non-intrusive load monitoring algorithm based on event matching | |
| Srinivasarengan et al. | A framework for non intrusive load monitoring using bayesian inference | |
| Chen et al. | Non-intrusive load monitoring based on feature extraction of change-point and xgboost classifier | |
| Rathore et al. | Non intrusive load monitoring and load disaggregation using transient data analysis | |
| CN116437244A (en) | Ammeter anomaly detection method and system | |
| CN107767037A (en) | A kind of user power utilization forms analytic method | |
| CN107356827A (en) | A kind of washing machine operation non-intruding discrimination method based on active power fluctuation | |
| KR101642044B1 (en) | A method of deciding uncommonness of electric device usage associated with electric energy consuming device | |
| CN102072976A (en) | Method and system for identifying electrical appliance state | |
| CN205809165U (en) | A kind of load identification system for domestic intelligent electricity meter based on similarity algorithm | |
| Cannas et al. | NILM techniques applied to a real-time monitoring system of the electricity consumption | |
| Abubakar et al. | Recent approaches and applications of non-intrusive load monitoring | |
| Liu et al. | Non-intrusive load monitoring method considering the time-segmented state probability | |
| CN115267320A (en) | Method suitable for non-contact measurement of power consumption of electric equipment |
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 |