CN110135763A - Monitoring method, readable storage medium storing program for executing and the electronic equipment of power consumption - Google Patents
Monitoring method, readable storage medium storing program for executing and the electronic equipment of power consumption Download PDFInfo
- Publication number
- CN110135763A CN110135763A CN201910453544.6A CN201910453544A CN110135763A CN 110135763 A CN110135763 A CN 110135763A CN 201910453544 A CN201910453544 A CN 201910453544A CN 110135763 A CN110135763 A CN 110135763A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- type
- optional
- data
- consumption type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 title claims abstract description 10
- 230000008859 change Effects 0.000 claims abstract description 41
- 238000005265 energy consumption Methods 0.000 claims abstract description 39
- 230000005611 electricity Effects 0.000 claims abstract description 23
- 239000013598 vector Substances 0.000 claims description 45
- 238000013145 classification model Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 10
- 241001269238 Data Species 0.000 claims description 9
- 230000008901 benefit Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000013527 convolutional neural network Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 231100001261 hazardous Toxicity 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 201000003373 familial cold autoinflammatory syndrome 3 Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The embodiment of the invention discloses a kind of monitoring method of power consumption, readable storage medium storing program for executing and electronic equipments.The embodiment of the present invention is by obtaining data of the Targeted Tributary within the period 1 with the power consumption parameter in second round, and Targeted Tributary is obtained respectively within the period 1 and in second round in the probability of each electricity consumption type consumption electric energy according to the data of the power consumption parameter in the period 1 and in second round, to whether change according in the period 1 and in the power consumption type of the determine the probability Targeted Tributary of each electricity consumption type consumption electric energy in second round, to carry out fault pre-alarming to Targeted Tributary.In inventive embodiments, the data of power consumption parameter of the Targeted Tributary within the period 1 and in second round are obtained by metering ammeter, Targeted Tributary is obtained in the probability of each electricity consumption type consumption electric energy by energy consumption disaggregated model within the period 1 and in second round, therefore cost of labor is reduced, while improves the timeliness and accuracy of detection.
Description
Technical field
The present invention relates to data processing fields, and in particular to a kind of monitoring method of power consumption, readable storage medium storing program for executing and
Electronic equipment.
Background technique
With the continuous increase of construction scope, the consumption rate of electric energy is also being continuously increased.Modern architecture it is larger, and
The line construction of building interior is complicated, therefore when the somewhere route of building interior is abnormal, can not often find in time.It is existing
Some fault detection methods carry out usually in a manner of manually periodically checking, but aforesaid way cost of labor is higher, and detect effect
Rate and accuracy rate are lower, have larger possibly that can not find failure in time, therefore be easy to happen relatively hazardous fortuitous event.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of monitoring method of power consumption, readable storage medium storing program for executing and electronics
Equipment can effectively promote the accuracy and timeliness of the monitoring of power consumption, reduce the possibility that fortuitous event occurs.
According to a first aspect of the embodiments of the present invention, a kind of monitoring method of power consumption is provided, which comprises
Obtain first power consumption data of the Targeted Tributary within period first time and in second time period the
Two power consumption datas, first power consumption data and second power consumption data are with the acquisition of predetermined sampling period
The Targeted Tributary power consumption parameter data；
It is input with first power consumption data, corresponding first probability vector is determined according to energy consumption disaggregated model,
Each element in first probability vector belongs to corresponding power consumption type for characterizing first power consumption data
Probability；
With second power consumption data be input, according to the energy consumption disaggregated model determine corresponding second probability to
It measures, each element in second probability vector belongs to corresponding power consumption class for characterizing second power consumption data
The probability of type；
The power consumption class of the Targeted Tributary is determined according to first probability vector and/or second probability vector
The change situation of type.
Preferably, the energy consumption disaggregated model obtains as follows:
Multiple optional sample sets are determined according to the sample power consumption data of multiple branches and corresponding power consumption type
Conjunction and corresponding optional power consumption type set, the multiple branch includes the Targeted Tributary；
The energy consumption is obtained according to multiple optional sample sets and the corresponding optional power consumption type set
Disaggregated model.
Preferably, the sample power consumption data and corresponding power consumption type according to multiple branches determines multiple
Optional sample set and corresponding optional power consumption type set include:
According to the quantity of the corresponding sample power consumption data of each power consumption type to the electric energy
Consumption type is ranked up；
Multiple optional power consumption set of types are determined according to the power consumption type that sequence meets first condition
It closes；
In a parallel fashion according to the corresponding sample power consumption data of each optional power consumption type set
Determine corresponding optional sample set.
Preferably, the first condition be the corresponding sample power consumption data quantity sequence maximum n first,
Minimum number and the power consumption class of the n according to the corresponding power consumption type of total amount of the branch of predetermined ratio
The sum of type determines.
Preferably, described to be obtained according to multiple optional sample sets and the corresponding optional power consumption type set
The energy consumption disaggregated model is taken to include:
In a parallel fashion according to multiple optional sample sets and the corresponding optional power consumption type set
The multiple candidate classification models of training；
Obtain the accuracy rate of each candidate classification model；
Meet second condition in response to the accuracy rate, the corresponding candidate classification model is determined as the energy consumption point
Class model.
Preferably, described that the Targeted Tributary is determined according to first probability vector and/or second probability vector
The change situation of power consumption type include:
Corresponding element in first probability vector and second probability vector is compared, determines each group element
In smaller value；
The change situation of the power consumption type is determined according to each smaller value.
Preferably, the change situation that the power consumption type is determined according to each smaller value includes:
Meet third condition in response to the sum of each smaller value, determines that the power consumption type changes；
It is unsatisfactory for the third condition in response to the sum of each smaller value, determines that the power consumption type does not change
Become.
Preferably, described that the Targeted Tributary is determined according to first probability vector and/or second probability vector
The change situation of power consumption type include:
The branch type of the Targeted Tributary is determined according to first probability vector or second probability vector；
The corresponding power change range of the Targeted Tributary is determined according to the corresponding thresholding algorithm of the branch type；
It is true according to the power change range and first power consumption data or second power consumption data
The change situation of the fixed power consumption type.
Preferably, described according to the power change range and first power consumption data and/or described second
Power consumption data determines that the change situation of the power consumption type includes:
Belong to the power change range in response to first power consumption data or second power consumption data,
Determine that the power consumption type does not change；
The power change model is not belonging in response to first power consumption data or second power consumption data
It encloses, determines that the power consumption type changes.
Preferably, the step of training energy consumption disaggregated model further include:
There are the sample datas of deviation for the prediction result and actually detected result for obtaining the energy consumption disaggregated model；
There are the sample datas of deviation to update the optional sample set and corresponding optional power consumption class according to described
Type set；
According to the updated optional sample set and the corresponding optional power consumption type set update
Energy consumption disaggregated model.
According to a second aspect of the embodiments of the present invention, a kind of computer readable storage medium is provided, stores computer thereon
Program instruction, wherein the computer program instructions are realized as described in any one of first aspect when being executed by processor
Method.
According to a third aspect of the embodiments of the present invention, a kind of electronic equipment, including memory and processor are provided, wherein
The memory is for storing one or more computer program instructions, wherein one or more computer program instructions
It is executed by the processor to realize the method as described in any one of first aspect.
The embodiment of the present invention is by obtaining power consumption parameter of the Targeted Tributary within the period 1 and in second round
Data, and Targeted Tributary is obtained respectively at first week according to the data of the power consumption parameter in the period 1 and in second round
In the probability of each electricity consumption type consumption electric energy in phase and in second round, thus according in the period 1 and in second round each
Whether the power consumption type of the determine the probability Targeted Tributary of electricity consumption type consumption electric energy changes, to carry out to Targeted Tributary
Fault pre-alarming.In inventive embodiments, the data of power consumption parameter of the Targeted Tributary within the period 1 and in second round
It is obtained by metering ammeter, Targeted Tributary is logical in the probability of each electricity consumption type consumption electric energy within the period 1 and in second round
The acquisition of energy consumption disaggregated model is crossed, therefore significantly reduces cost of labor, while improving the timeliness and accuracy of detection.
Detailed description of the invention
By referring to the drawings to the description of the embodiment of the present invention, the above and other purposes of the present invention, feature and
Advantage will be apparent from, in the accompanying drawings:
Fig. 1 is the flow chart of the monitoring method of the power consumption of first embodiment of the invention；
Fig. 2 is that the method for first embodiment of the invention obtains the data flowchart of energy consumption disaggregated model；
Fig. 3 is the schematic diagram of the electronic equipment of second embodiment of the invention.
Specific embodiment
Below based on embodiment, present invention is described, but the present invention is not restricted to these embodiments.Under
Text is detailed to describe some specific detail sections in datail description of the invention.Do not have for a person skilled in the art
The present invention can also be understood completely in the description of these detail sections.In order to avoid obscuring essence of the invention, well known method, mistake
There is no narrations in detail for journey, process, element and circuit.
In addition, it should be understood by one skilled in the art that provided herein attached drawing be provided to explanation purpose, and
What attached drawing was not necessarily drawn to scale.
Unless the context clearly requires otherwise, "include", "comprise" otherwise throughout the specification and claims etc. are similar
Word should be construed as the meaning for including rather than exclusive or exhaustive meaning；That is, be " including but not limited to " contains
Justice.
In the description of the present invention, it is to be understood that, term " first ", " second " etc. are used for description purposes only, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " multiple "
It is two or more.
Modern architecture it is larger, and the line construction of building interior is complicated, therefore in the somewhere route of building interior
When being abnormal (for example, the electricity consumption of somewhere route happens change), it can not often find in time.Existing fault detection side
Method carries out usually in a manner of manually periodically checking, but aforesaid way cost of labor is higher, and detection efficiency and accuracy rate compared with
It is low, not noticeable exception even is generated sometimes, for example, the electronic equipment of building interior works well but partial circuit generates and breaks
The case where road, therefore have larger possibly that can not find failure in time, it is easy to happen relatively hazardous fortuitous event.
Fig. 1 is the flow chart of the monitoring method of the power consumption of first embodiment of the invention.As shown in Figure 1, the present embodiment
Method include the following steps:
Step S101 obtains first power consumption data of the Targeted Tributary within period first time and in week the second time
The second power consumption data in phase.
In the present embodiment, the first power consumption data and the second power consumption data are to be obtained with the predetermined sampling period
The data of the power consumption parameter of Targeted Tributary can be specifically the waveform image of the power consumption parameter of Targeted Tributary.Its
In, power consumption parameter may include voltage consumption amount, power consumption etc..Optionally, the first power consumption data and second
Power consumption data can acquire metering electricity within period first time and in second time period respectively with the predetermined sampling period
The measurement data of table (such as electric energy meter, single-phase watt-hour meter etc.) obtains.Sampling period and time cycle can be according to actual needs
It is set with design conditions etc..
Preferably due to the consumption of Targeted Tributary electric energy within the different time period may be different, for example, in summer, electricity
The consumption of energy could possibly be higher than spring, and power consumption is chiefly used in air conditioner refrigerating.In order to enable the first power consumption data and
Two power consumption datas have stronger contrastive, and period first time and second time period are the same time of different times
Section.
For example, if the power consumption of Targeted Tributary with week for variation (that is, the power consumption situation of identical number of days is big weekly
Cause identical), the time cycle is 8 hours, then period first time can be the 9:00-17:00 of first week Monday, week the second time
Phase can be the 9:00-17:00 of second week Monday.
It optionally, can be within period first time and in week the second time in order to promote the accuracys of monitored results
The power consumption parameter of the Targeted Tributary obtained in phase is pre-processed, to obtain the first power consumption data and the second electric energy
Consumption data.
For example, can be gone to there is abnormal parameter if a certain parameter in power consumption parameter is deposited when abnormal
Except processing；If a certain parameter in power consumption parameter has missing, interpolation processing can be carried out to the parameter that there is missing
(for example, if the voltage consumption amount of second sampling instant of the missing Targeted Tributary within period first time, it can be by Targeted Tributary
The voltage consumption amount of first sampling instant adjacent with the second sampling instant and third sampling instant within period first time
Voltage consumption amount of the average value as the second sampling instant).
Step S102 is input with the first power consumption data, determines corresponding first probability according to energy consumption disaggregated model
Vector.
In the present embodiment, each element in the first probability vector belongs to corresponding for the first power consumption data of characterization
The probability of power consumption type.For example, power consumption type includes air conditioning electricity, electric consumption on lighting, water pump electricity consumption, elevator electricity consumption
Deng, wherein the air conditioning electricity of Targeted Tributary is 0.17, electric consumption on lighting 0.41, and water pump electricity consumption is 0.32, and elevator electricity consumption is 0.1,
Then the first probability vector of Targeted Tributary is (0.17,0.41,0.32,0.1).
Step S103 is input with the second power consumption data, determines corresponding second probability according to energy consumption disaggregated model
Vector.
In the present embodiment, each element in the second probability vector belongs to corresponding for the second power consumption data of characterization
The probability of power consumption type.The representation of second probability vector is identical as the representation of the first probability vector, herein not
It repeats again.
It is readily appreciated that, step S102 and step S103 may be performed simultaneously, and can also successively execute, it is not necessary to it is suitable to distinguish execution
Sequence.
In the present embodiment, it is possible to which consuming disaggregated model can be convolutional neural networks (Convolutional Neural
Networks, CNN).CNN is a kind of comprising convolutional calculation and with the feedforward neural network of depth structure, is deep learning
Represent one of algorithm.Convolution kernel parameter sharing in the hidden layer of CNN, and the connection between convolutional layer has sparsity, so that
CNN can be revealed feature (for example, waveform, pixel, audio etc.) with lesser calculation amount plaid matching and stablize, efficiently learn.
The waveform image of power consumption parameter, which is directly inputted CNN, can be avoided feature extraction, while reduce the instruction of power consumption type
The complexity of data reconstruction in experienced and application process, thus in the subsequent acquisition effect for promoting estimated result (that is, probability vector)
Rate.Common CNN includes time delay network (Time Delay Neural Network, TDNN), LeNet-5 etc..
Optionally, energy consumption disaggregated model can also be Recognition with Recurrent Neural Network etc..
Be readily appreciated that, energy consumption disaggregated model be other models when, model input can for power consumption parameter when
Between sequence.
Fig. 2 is that the method for first embodiment of the invention obtains the data flowchart of energy consumption disaggregated model.As shown in Fig. 2,
In a kind of optional implementation, energy consumption disaggregated model can obtain as follows:
Step S201, according to the sample power consumption data of multiple branches and corresponding power consumption type determine it is multiple can
Select sample set and corresponding optional power consumption type set.
In this step, multiple branches include Targeted Tributary, and each branch corresponds to multiple sample power consumption datas, each
Branch corresponds to multiple power consumption types, and power consumption type is by being investigated acquisition to each branch.Sample power consumption number
According to acquisition modes it is similar with the acquisition modes of the first power consumption data, details are not described herein.
It is alternatively possible to according to the quantity of the corresponding sample power consumption data of each power consumption type to power consumption class
Type is ranked up, and determines optional power consumption type set 21A- according to the power consumption type that sequence meets first condition
21D is corresponded to be determined in a parallel fashion according to the corresponding sample power consumption data of each optional power consumption type set
Optional sample set 22A-22D.Wherein, first condition be sample power consumption data quantity sequence maximum n first,
Wherein, n is according to the minimum number of the corresponding power consumption type of total amount of the branch of predetermined ratio and power consumption type
Sum determines.It is readily appreciated that, the total amount of optional power consumption type set and optional sample set in Fig. 2 is only schematic
's.
For example, the total amount of branch is X, the total amount of corresponding power consumption type is M.Randomly select 0.9X branch
(that is, total amount of the branch of predetermined ratio), the quantity of corresponding power consumption type be it is N number of, N+1 and N+2, then n
Value can be N, N+1, N+2 ..., M-1, M.Then according to the number of the corresponding sample power consumption data of each power consumption type
Amount is ranked up power consumption type, and by taking n=N as an example, the quantity of sample power consumption data is sorted in maximum top N
Multiple power consumption types be determined as optional power consumption type set 21A, and it is corresponding sample power consumption data is true
It is set to optional sample set 22A.
Step S202 obtains energy consumption classification according to multiple optional sample sets and corresponding optional power consumption type set
Model.
It is alternatively possible in a parallel fashion according to optional sample set 21A-21D and corresponding optional power consumption class
Type set 22A-22D trains candidate classification model 23A-23D, and obtains the accuracy rate of each candidate classification model, and in accuracy rate
When meeting second condition, corresponding model is determined as energy consumption disaggregated model 24.By taking candidate classification model 23A as an example, candidate point
Class model 23A is obtained according to optional sample set 21A and optional power consumption type set 22A training.It is readily appreciated that, in Fig. 2
Optional power consumption type set and optional sample set total amount it is only schematical.
Specifically, in the training process of each candidate classification model, can be by each optional sample set random division can
Training sample set and optional test sample set are selected, corresponding each optional power consumption type set is divided into optional training
Power consumption type set and optional test power consumption type set, and according to each optional test sample set and it is corresponding can
Choosing test power consumption type set tests corresponding candidate classification model, to obtain the standard of each candidate classification model
True rate.
In the training process of each candidate classification model, each candidate classification model can also be determined by Adam optimization algorithm
Parameter, and the network losses value of each candidate classification model be less than predetermined threshold when, obtain the accurate of each candidate classification model
Rate.Adam algorithm passes through the training method for improving disaggregated model, to minimize or maximize the loss function of disaggregated model, therefore
The convergence rate of loss function and the learning effect of disaggregated model can be promoted.
Wherein, second condition not less than first threshold and can come maximum first for accuracy rate.Thus, it is possible to protect
Energy consumption disaggregated model is demonstrate,proved to the classification results accuracy rate highest of sample power consumption data.
Second condition can also be not less than first threshold for accuracy rate.Meanwhile in order to guarantee that it is pre- that energy consumption disaggregated model is treated
The accuracy of power consumption data (including the first power consumption data and the second power consumption data) prediction is surveyed, it is multiple if it exists
Meet the candidate classification model of second condition, it can will be according to the quantity of power consumption type in optional power consumption type set
It sorts and is determined as energy consumption disaggregated model in the candidate classification model that maximum first training obtains.
For example, the accuracy rate of candidate classification model 23A is a%, the accuracy rate of candidate classification model 23B is b%, is all satisfied
Second condition.Candidate classification model 23A is obtained according to 5 power consumption type training, and candidate classification model 23B is according to 7 electricity
Type training can be consumed to obtain, then candidate classification model 23B is determined as energy consumption disaggregated model.
Optionally, in order to promote the accuracy of energy consumption disaggregated model, can also obtain energy consumption disaggregated model prediction result with
There are the sample datas of deviation for actually detected result, and according to there are the sample datas of deviation to update optional sample set and correspondence
Optional power consumption type set, thus according to updated optional sample set and corresponding optional power consumption set of types
Close more new energy consumption disaggregated model.
Step S104 determines the power consumption type of Targeted Tributary according to the first probability vector and/or the second probability vector
Change situation.
In an optional implementation manner, can by corresponding element in the first probability vector and the second probability vector into
Row compares, and determines the smaller value in each element, and determine the power consumption type of Targeted Tributary according to the smaller value of each element
Change situation.
It specifically, can be according to the change situation of each smaller value and determining Targeted Tributary.Each smaller value and can lead to
Following formula is crossed to calculate:
Wherein, PdiffFor the sum of the smaller value in corresponding element in the first probability vector and the second probability vector,For
First power consumption data belongs to the probability of i-th of power consumption type,Belong to i-th of electricity for the second power consumption data
The probability of type can be consumed.
In PdiffWhen meeting third condition, determine that the power consumption type of Targeted Tributary changes, thus to target branch
Road carries out fault pre-alarming；In PdiffWhen being unsatisfactory for third condition, determining the power consumption type of Targeted Tributary, no change has taken place.
In the present embodiment, third condition can be PdiffNot less than second threshold.Wherein, second threshold can be according to reality
Border demand is set.
In another optional implementation, target branch can be determined according to the first probability vector or the second probability vector
The branch type on road, and the corresponding power change range of Targeted Tributary is determined according to the corresponding thresholding algorithm of branch type, thus
The electric energy type of Targeted Tributary is determined according to power change range and the first power consumption data or the second power consumption data
Change situation.Wherein, thresholding algorithm can be average threshold method, greatly (small) threshold method, bayesian statistical analysis method etc..It is optional
Ground, the corresponding relationship of available each branch type and thresholding algorithm, it is possible thereby to corresponding with thresholding algorithm according to each branch
The corresponding thresholding algorithm of Relation acquisition Targeted Tributary.
Specifically, maximum element in the first probability vector or the second probability vector can be determined as to the use of Targeted Tributary
Electric type, to determine the branch type of Targeted Tributary according to the electricity consumption type of Targeted Tributary.Corresponding according to branch type
It, can be according to power change range to the first power consumption number after thresholding algorithm determines the corresponding power change range of Targeted Tributary
According to or the second power consumption data judged.If the first power consumption data or the second power consumption data belong to corresponding electricity
Energy variation range, it is determined that no change has taken place for the power consumption type of Targeted Tributary；If the first power consumption data or second
Power consumption data is not belonging to corresponding power change range, it is determined that and the power consumption type of Targeted Tributary changes, from
And fault pre-alarming is carried out to Targeted Tributary.
The data of power consumption parameter of the present embodiment by acquisition Targeted Tributary within the period 1 and in second round,
And Targeted Tributary is obtained respectively within the period 1 according to the data of the power consumption parameter in the period 1 and in second round
With in second round each electricity consumption type consumption electric energy probability, thus according in the period 1 and second round in each electricity consumption
Whether the power consumption type of the determine the probability Targeted Tributary of type consumption electric energy changes, to carry out failure to Targeted Tributary
Early warning.In embodiment, the data of power consumption parameter of the Targeted Tributary within the period 1 and in second round pass through metering
Ammeter obtains, and Targeted Tributary passes through energy consumption point in the probability of each electricity consumption type consumption electric energy within the period 1 and in second round
Class model obtains, therefore significantly reduces cost of labor, while improving the timeliness and accuracy of detection.
Fig. 3 is the schematic diagram of the electronic equipment of second embodiment of the invention.Electronic equipment shown in Fig. 3 is at general data
Manage device comprising general computer hardware structure includes at least processor 31 and memory 32.Processor 31 and storage
Device 32 is connected by bus 33.Memory 32 is suitable for the instruction or program that storage processor 31 can be performed.Processor 31 can be
Independent microprocessor is also possible to one or more microprocessor set.Processor 31 is by executing memory 32 as a result,
The order stored, thereby executing embodiment present invention as described above method flow realize for data processing and for
The control of other devices.Bus 33 links together above-mentioned multiple components, while said modules are connected to display controller
34 and display device and input/output (I/O) device 35.Input/output (I/O) device 35 can be mouse, keyboard, modulation
Demodulator, network interface, touch-control input device, body-sensing input unit, printer and other devices well known in the art.It is typical
Ground, input/output (I/O) device 35 are connected by input/output (I/O) controller 36 with system.
Wherein, memory 32 can store component software, such as operating system, communication module, interactive module and application
Program.Above-described each module and application program are both corresponded to complete one or more functions and be retouched in inventive embodiments
One group of executable program instructions of the method stated.
It is above-mentioned according to the method for the embodiment of the present invention, the flow chart and/or frame of equipment (system) and computer program product
Figure describes various aspects of the invention.It should be understood that each of flowchart and or block diagram piece and flow chart legend and/or frame
The combination of block in figure can be realized by computer program instructions.These computer program instructions can be provided to general meter
The processor of calculation machine, special purpose computer or other programmable data processing devices, to generate machine so that (via computer or
What the processors of other programmable data processing devices executed) instruction creates for realizing in flowchart and or block diagram block or block
The device of specified function action.
Meanwhile as skilled in the art will be aware of, the various aspects of the embodiment of the present invention may be implemented as be
System, method or computer program product.Therefore, the various aspects of the embodiment of the present invention can take following form: complete hardware
Embodiment, complete software embodiment (including firmware, resident software, microcode etc.) usually can all claim herein
For the embodiment for combining software aspects with hardware aspect of circuit, " module " or " system ".In addition, side of the invention
Face can take following form: the computer program product realized in one or more computer-readable medium, computer can
Reading medium has the computer readable program code realized on it.
It can use any combination of one or more computer-readable mediums.Computer-readable medium can be computer
Readable signal medium or computer readable storage medium.Computer readable storage medium can be such as (but not limited to) electronics,
Magnetic, optical, electromagnetism, infrared or semiconductor system, device or any suitable combination above-mentioned.Meter
The more specific example (exhaustive to enumerate) of calculation machine readable storage medium storing program for executing will include the following terms: with one or more electric wire
Electrical connection, hard disk, random access memory (RAM), read-only memory (ROM), erasable is compiled portable computer diskette
Journey read-only memory (EPROM or flash memory), optical fiber, portable optic disk read-only storage (CD-ROM), light storage device,
Magnetic memory apparatus or any suitable combination above-mentioned.In the context of the embodiment of the present invention, computer readable storage medium
It can be that can include or store the program used by instruction execution system, device or combine instruction execution system, set
Any tangible medium for the program that standby or device uses.
Computer-readable signal media may include the data-signal propagated, and the data-signal of the propagation has wherein
The computer readable program code realized such as a part in a base band or as carrier wave.The signal of such propagation can use
Any form in diversified forms, including but not limited to: electromagnetism, optical or its any combination appropriate.It is computer-readable
Signal media can be following any computer-readable medium: not be computer readable storage medium, and can be to by instructing
Program that is that execution system, device use or combining instruction execution system, device to use is communicated, is propagated
Or transmission.
Computer program code for executing the operation for being directed to various aspects of the present invention can be with one or more programming languages
Any combination of speech is write, the programming language include: programming language such as Java, Smalltalk of object-oriented, C++,
PHP, Python etc.；And conventional process programming language such as " C " programming language or similar programming language.Program code can be made
It fully on the user computer, is partly executed on the user computer for independent software package；Partly in subscriber computer
Above and partly execute on the remote computer；Or it fully executes on a remote computer or server.In latter feelings
It, can be by remote computer by including that any type of network connection of local area network (LAN) or wide area network (WAN) are extremely used under condition
Family computer, or (such as internet by using ISP) can be attached with outer computer.
The above description is only a preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For, the invention can have various changes and changes.All any modifications made within the spirit and principles of the present invention are equal
Replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of monitoring method of power consumption, which is characterized in that the described method includes:
Obtain first power consumption data of the Targeted Tributary within period first time and the second electricity in second time period
Can consumption data, first power consumption data and second power consumption data are the institute that is obtained with the predetermined sampling period
State the data of the power consumption parameter of Targeted Tributary；
It is input with first power consumption data, corresponding first probability vector is determined according to energy consumption disaggregated model, it is described
Each element in first probability vector belongs to the general of corresponding power consumption type for characterizing first power consumption data
Rate；
It is input with second power consumption data, corresponding second probability vector is determined according to the energy consumption disaggregated model,
Each element in second probability vector belongs to corresponding power consumption type for characterizing second power consumption data
Probability；
The power consumption type of the Targeted Tributary is determined according to first probability vector and/or second probability vector
Change situation.
2. the method according to claim 1, wherein the energy consumption disaggregated model obtains as follows:
According to the sample power consumption data of multiple branches and corresponding power consumption type determine multiple optional sample sets and
Corresponding optional power consumption type set, the multiple branch include the Targeted Tributary；
The energy consumption classification is obtained according to multiple optional sample sets and the corresponding optional power consumption type set
Model.
3. according to the method described in claim 2, it is characterized in that, the sample power consumption data according to multiple branches and
Corresponding power consumption type determines multiple optional sample sets and corresponding optional power consumption type set includes:
According to the quantity of the corresponding sample power consumption data of each power consumption type to the power consumption
Type is ranked up；
Multiple optional power consumption type set are determined according to the power consumption type that sequence meets first condition；
It is determined in a parallel fashion according to the corresponding sample power consumption data of each optional power consumption type set
Corresponding optional sample set.
4. according to the method described in claim 3, it is characterized in that, the first condition is the corresponding sample power consumption number
According to quantity sort in maximum n first, n power consumption type according to corresponding to the total amount of the branch of predetermined ratio
Minimum number and the sum of the power consumption type determine.
5. according to the method described in claim 2, it is characterized in that, described according to multiple optional sample sets and corresponding
The optional power consumption type set obtains the energy consumption disaggregated model
In a parallel fashion according to multiple optional sample sets and the corresponding optional power consumption type set training
Multiple candidate classification models；
Obtain the accuracy rate of each candidate classification model；
Meet second condition in response to the accuracy rate, the corresponding candidate classification model is determined as the energy consumption classification mould
Type.
6. the method according to claim 1, wherein described according to first probability vector and described second general
Rate vector determines that the change situation of the power consumption type of the Targeted Tributary includes:
Corresponding element in first probability vector and second probability vector is compared, is determined in each group element
Smaller value；
The change situation of the power consumption type is determined according to each smaller value.
7. according to the method described in claim 6, it is characterized in that, described determine the power consumption according to each smaller value
The change situation of type includes:
Meet third condition in response to the sum of each smaller value, determines that the power consumption type changes；
It is unsatisfactory for the third condition in response to the sum of each smaller value, determines that the power consumption type does not change.
8. the method according to claim 1, wherein described according to first probability vector and/or described
Two probability vectors determine that the change situation of the power consumption type of the Targeted Tributary includes:
The branch type of the Targeted Tributary is determined according to first probability vector or second probability vector；
The corresponding power change range of the Targeted Tributary is determined according to the corresponding thresholding algorithm of the branch type；
Institute is determined according to the power change range and first power consumption data or second power consumption data
State the change situation of power consumption type.
9. according to the method described in claim 8, it is characterized in that, described according to the power change range and described first
Power consumption data or second power consumption data determine that the change situation of the power consumption type includes:
Belong to the power change range in response to first power consumption data or second power consumption data, determines
The power consumption type does not change；
It is not belonging to the power change range in response to first power consumption data or second power consumption data, really
The fixed power consumption type changes.
10. according to the method described in claim 2, it is characterized in that, the step of training the energy consumption disaggregated model further include:
There are the sample datas of deviation for the prediction result and actually detected result for obtaining the energy consumption disaggregated model；
There are the sample datas of deviation to update the optional sample set and corresponding optional power consumption set of types according to described
It closes；
The energy consumption is updated according to the updated optional sample set and the corresponding optional power consumption type set
Disaggregated model.
11. a kind of computer readable storage medium, stores computer program instructions thereon, which is characterized in that the computer journey
Such as method of any of claims 1-10 is realized in sequence instruction when being executed by processor.
12. a kind of electronic equipment, including memory and processor, which is characterized in that the memory is for storing one or more
Computer program instructions, wherein one or more computer program instructions are executed by the processor to realize such as power
Benefit requires method described in any one of 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910453544.6A CN110135763B (en) | 2019-05-28 | 2019-05-28 | Method for monitoring power consumption, readable storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910453544.6A CN110135763B (en) | 2019-05-28 | 2019-05-28 | Method for monitoring power consumption, readable storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110135763A true CN110135763A (en) | 2019-08-16 |
| CN110135763B CN110135763B (en) | 2022-03-25 |
Family
ID=67582438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910453544.6A Active CN110135763B (en) | 2019-05-28 | 2019-05-28 | Method for monitoring power consumption, readable storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135763B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012026589A1 (en) * | 2010-08-26 | 2012-03-01 | パナソニック株式会社 | Electricity quantity management system and center server |
| CN103176101A (en) * | 2013-03-05 | 2013-06-26 | 中联重科股份有限公司 | Line fault detection method, equipment and system |
| CN103487644A (en) * | 2013-09-09 | 2014-01-01 | 北京博锐尚格节能技术有限公司 | Electric energy subentry energy consumption metering method and device |
| CN104749431A (en) * | 2015-03-23 | 2015-07-01 | 同济大学 | Indirect measuring system for electricity consumption of end device of air conditioning system of public building |
| CN105259752A (en) * | 2015-11-13 | 2016-01-20 | 北京博锐尚格节能技术股份有限公司 | Load distribution method, device and system for device cluster |
| CN105446139A (en) * | 2015-12-18 | 2016-03-30 | 华南理工大学 | Construction energy consumption analysis method and construction energy consumption analysis system based on BP neural network |
| CN107045094A (en) * | 2017-04-25 | 2017-08-15 | 云南电力试验研究院(集团)有限公司 | A kind of distribution line failure localization method and device |
| CN109061396A (en) * | 2018-10-10 | 2018-12-21 | 国网江苏省电力有限公司无锡供电分公司 | A kind of power distribution network traveling wave fault positioning method, apparatus and system |
-
2019
- 2019-05-28 CN CN201910453544.6A patent/CN110135763B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012026589A1 (en) * | 2010-08-26 | 2012-03-01 | パナソニック株式会社 | Electricity quantity management system and center server |
| CN103176101A (en) * | 2013-03-05 | 2013-06-26 | 中联重科股份有限公司 | Line fault detection method, equipment and system |
| CN103487644A (en) * | 2013-09-09 | 2014-01-01 | 北京博锐尚格节能技术有限公司 | Electric energy subentry energy consumption metering method and device |
| CN104749431A (en) * | 2015-03-23 | 2015-07-01 | 同济大学 | Indirect measuring system for electricity consumption of end device of air conditioning system of public building |
| CN105259752A (en) * | 2015-11-13 | 2016-01-20 | 北京博锐尚格节能技术股份有限公司 | Load distribution method, device and system for device cluster |
| CN105446139A (en) * | 2015-12-18 | 2016-03-30 | 华南理工大学 | Construction energy consumption analysis method and construction energy consumption analysis system based on BP neural network |
| CN107045094A (en) * | 2017-04-25 | 2017-08-15 | 云南电力试验研究院(集团)有限公司 | A kind of distribution line failure localization method and device |
| CN109061396A (en) * | 2018-10-10 | 2018-12-21 | 国网江苏省电力有限公司无锡供电分公司 | A kind of power distribution network traveling wave fault positioning method, apparatus and system |
Non-Patent Citations (6)
| Title |
|---|
| SHEN QI: "An analysis of the optimization disaggregation algorithm in the estimation related to energy consumption of appliances in buildings", 《APPLIED MATHEMATICS AND COMPUTATION》 * |
| SHEN QI: "Establishing target-oriented energy consumption quotas for buildings", 《UTILITIES POLICY》 * |
| 严哲钦: "办公建筑能耗监测系统关键技术研究", 《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》 * |
| 卿晓霞等: "能耗实时监测的数据挖掘方法", 《重庆大学学报》 * |
| 周璇: "办公建筑逐时能耗异常数据在线插补方法", 《建筑科学》 * |
| 沈启: "大型公共建筑用电分项计量系统研究与进展(2):统一的能耗分类模型与方法", 《暖通空调》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110135763B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Traffic flow imputation using parallel data and generative adversarial networks | |
| Hong et al. | Probabilistic electric load forecasting: A tutorial review | |
| US10379146B2 (en) | Detecting non-technical losses in electrical networks based on multi-layered statistical techniques from smart meter data | |
| US20150317589A1 (en) | Forecasting system using machine learning and ensemble methods | |
| US20150377935A1 (en) | Signal identification methods and systems | |
| Chou et al. | Hybrid machine learning system to forecast electricity consumption of smart grid-based air conditioners | |
| CN107704946B (en) | Electronic device, Voice Navigation needing forecasting method and storage medium | |
| US20170315855A1 (en) | Method of detecting anomalies on appliances and system thereof | |
| CN113837596B (en) | Fault determination method and device, electronic equipment and storage medium | |
| CN110998465B (en) | Turbine diagnostic feature selection system | |
| CN103020459A (en) | Method and system for sensing multiple-dimension electric utilization activities | |
| CN110334816A (en) | A kind of industrial equipment detection method, device, equipment and readable storage medium storing program for executing | |
| Shirajuddin et al. | Optimization problems in water distribution systems using Non-dominated Sorting Genetic Algorithm II: An overview | |
| CN109344967B (en) | Intelligent electric meter life cycle prediction method based on artificial neural network | |
| CN109583086A (en) | Distribution transformer heavy-overload prediction technique and terminal device | |
| CN114925938B (en) | Electric energy meter running state prediction method and device based on self-adaptive SVM model | |
| CN115081673B (en) | Abnormality prediction method and device for oil and gas pipeline, electronic equipment and medium | |
| CN115128438A (en) | Chip internal fault monitoring method and device | |
| CN109635996A (en) | Room rate tendency look-forward model construction method, device and storage medium | |
| CN109740818A (en) | A kind of probability density forecasting system applied to en-route sector traffic | |
| Wang et al. | A factorial hidden markov model for energy disaggregation based on human behavior analysis | |
| Ferreira et al. | NSGA-II parameterization for the optimal pressure sensor location in water distribution networks | |
| JP2019101681A (en) | Quotation acquisition device, quotation acquisition method, and program | |
| CN110135763A (en) | Monitoring method, readable storage medium storing program for executing and the electronic equipment of power consumption | |
| CN113822441B (en) | Decision model training method, device, terminal equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |