CN109188924A - The power consumption control method and device of smart home system - Google Patents
The power consumption control method and device of smart home system Download PDFInfo
- Publication number
- CN109188924A CN109188924A CN201811092932.8A CN201811092932A CN109188924A CN 109188924 A CN109188924 A CN 109188924A CN 201811092932 A CN201811092932 A CN 201811092932A CN 109188924 A CN109188924 A CN 109188924A
- Authority
- CN
- China
- Prior art keywords
- data
- electricity consumption
- smart home
- home system
- power consumption
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000005611 electricity Effects 0.000 claims abstract description 229
- 238000012549 training Methods 0.000 claims abstract description 68
- 238000006243 chemical reaction Methods 0.000 claims abstract description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 241001269238 Data Species 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 13
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000032696 parturition Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of power consumption control method and devices of smart home system.Wherein, this method comprises: obtaining reference data, wherein reference data is the foundation for generating the electricity consumption data of each electrical equipment in smart home system;By each data conversion in reference data at the input of power consumption prediction model, wherein power consumption prediction model is obtained by training data training, and every group of training data includes: reference data electricity consumption data corresponding with the reference data;Obtain the output of power consumption prediction model;Electricity consumption data is converted the output into, and generates the electricity consumption strategy of smart home system according to electricity consumption data;Electricity consumption strategy is sent to smart home system, wherein smart home system is according to each electrical equipment of electricity consumption policy control.The present invention solves cannot achieve the technical issues of controlling according to the power consumption of future time section each electric appliance in house system in the related technology.
Description
Technical field
The present invention relates to smart home fields, a kind of power consumption control method in particular to smart home system and
Device.
Background technique
In intelligent domestic Internet of Things, energy saving is to measure the important indicator of efficiency control.The electricity opened daily by user
Device and the function of application are different, therefore whole household electricity amount respectively has difference.However, user certain time (for example, some
Week, some moon or some season) electricity consumption may show certain regularity.But it cannot achieve in the related technology
The power consumption of following certain time is predicted according to historical time section whole power consumption, and then also can not be according to following certain time
Power consumption realizes the control or adjusting to electric appliance each in house system.
It cannot achieve the power consumption according to future time section in the related technology to each electricity in house system for above-mentioned
The problem of device is controlled, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the invention provides a kind of power consumption control method and devices of smart home system, at least to solve correlation
It cannot achieve the technical issues of controlling according to the power consumption of future time section each electric appliance in house system in technology.
According to an aspect of an embodiment of the present invention, a kind of power consumption control method of smart home system is provided, comprising:
Obtain reference data, wherein the reference data is the electricity consumption data for generating each electrical equipment in smart home system
Foundation;By each data conversion in the reference data at the input of power consumption prediction model, wherein the power consumption is pre-
Surveying model is obtained by training data training, and every group of training data includes: that reference data is corresponding with the reference data
Electricity consumption data;Obtain the output of the power consumption prediction model;The output is converted into the electricity consumption data, and according to described
Electricity consumption data generates the electricity consumption strategy of the smart home system;The electricity consumption strategy is sent to the smart home system,
Wherein, the smart home system each electrical equipment according to the electricity consumption policy control.
Optionally, obtaining the power consumption prediction model by training data training includes: to obtain historical time section
History reference data, and using the history reference data as training data;Each data in every group of training data are turned
Change numerical value into;Using the obtained corresponding numerical value of each data as the input layer of convolutional neural networks model and output
Node layer;It is trained to obtain the power consumption prediction model according to the input layer and the output node layer.
Optionally, the training data is a part of the history reference data.
Optionally, another part of the history reference data is as verify data, wherein the verify data for pair
The power consumption prediction model is verified.
It optionally, include: to judge the use according to the electricity consumption strategy that the electricity consumption data generates the smart home system
Whether electric data are not less than tentation data, wherein the tentation data is that the smart home system is corresponding when tripping
Electricity consumption data;In the case where judging result is that the electricity consumption data is not less than the tentation data, according to the electricity consumption data
Generate the electricity consumption strategy of the smart home system.
It optionally, include: by electricity consumption plan according to the electricity consumption strategy that the electricity consumption data generates the smart home system
Slightly model, determines the corresponding electricity consumption strategy of the electricity consumption data, wherein the electricity consumption Policy model is passed through using multi-group data
Machine learning training obtains, and every group of data in the multi-group data include: that electricity consumption data and the electricity consumption data are corresponding
Electricity consumption strategy.
Optionally, passing through electricity consumption Policy model, before determining the corresponding electricity consumption strategy of the electricity consumption data, the intelligence man
Occupy the power consumption control method of system further include: acquire the multiple history electricity consumption datas and multiple history electricity consumption plans in historical time section
Slightly model, wherein the multiple history electricity consumption Policy model is the model determined according to the multiple history electricity consumption data;To adopting
The multi-group data including the multiple history electricity consumption data and the multiple history electricity consumption Policy model of collection is trained, and is obtained
The electricity consumption Policy model.
Another aspect according to an embodiment of the present invention additionally provides a kind of power consumption control dress of smart home system
It sets, comprising: first acquisition unit, for obtaining reference data, wherein the reference data is for generating smart home system
In each electrical equipment electricity consumption data foundation;Converting unit, for by each data conversion in the reference data at
The input of power consumption prediction model, wherein the power consumption prediction model is obtained by training data training, every group of training
Data include: reference data electricity consumption data corresponding with the reference data;Second acquisition unit, for obtaining the power consumption
The output of prediction model;Generation unit, for the output to be converted to the electricity consumption data, and it is raw according to the electricity consumption data
At the electricity consumption strategy of the smart home system;Transmission unit, for the electricity consumption strategy to be sent to the smart home system
System, wherein the smart home system each electrical equipment according to the electricity consumption policy control.
Optionally, the converting unit includes: the first acquisition module, for obtaining the history reference number of historical time section
According to, and using the history reference data as training data;Conversion module, for turning each data in every group of training data
Change numerical value into;First determining module, the corresponding numerical value of each data for will obtain is as convolutional neural networks model
Input layer and output node layer;Second obtains module, for according to the input layer and the output node layer
It is trained to obtain the power consumption prediction model.
Optionally, the training data is a part of the history reference data.
Optionally, another part of the history reference data is as verify data, wherein the verify data for pair
The power consumption prediction model is verified.
Optionally, the generation unit includes: judgment module, for judging whether the electricity consumption data is not less than predetermined number
According to, wherein the tentation data is corresponding electricity consumption data when the smart home system trips;Generation module is used for
In the case where judging result is that the electricity consumption data is not less than the tentation data, the intelligence is generated according to the electricity consumption data
The electricity consumption strategy of energy house system.
Optionally, the generation unit includes: the second determining module, for determining the use by electricity consumption Policy model
The corresponding electricity consumption strategy of electric data, wherein the electricity consumption Policy model is to be obtained using multi-group data by machine learning training
, every group of data in the multi-group data include: electricity consumption data and the corresponding electricity consumption strategy of the electricity consumption data.
Optionally, the power consumption control device of the smart home system further include: acquisition module, for passing through electricity consumption strategy
Model, before determining the corresponding electricity consumption strategy of the electricity consumption data, acquire historical time section multiple history electricity consumption datas and
Multiple history electricity consumption Policy models, wherein the multiple history electricity consumption Policy model is according to the multiple history electricity consumption data
Determining model;Third acquiring unit, for using including the multiple history electricity consumption data and the multiple history to acquisition
The multi-group data of electric Policy model is trained, and obtains the electricity consumption Policy model.
Another aspect according to an embodiment of the present invention, additionally provides a kind of storage medium, the storage medium includes
The program of storage, wherein described program execute it is any one of above-mentioned described in smart home system power consumption control method.
Another aspect according to an embodiment of the present invention, additionally provides a kind of processor, the processor is for running
Program, wherein described program run when execute it is any one of above-mentioned described in smart home system power consumption control method.
In embodiments of the present invention, using acquisition reference data, wherein reference data is for generating smart home system
In each electrical equipment electricity consumption data foundation;By each data conversion in reference data at the defeated of power consumption prediction model
Enter, wherein power consumption prediction model be by training data training obtain, every group of training data include: reference data and
The corresponding electricity consumption data of the reference data;Obtain the output of power consumption prediction model;Convert the output into electricity consumption data, and according to
The electricity consumption strategy of electricity consumption data generation smart home system;Electricity consumption strategy is sent to smart home system, wherein smart home
System is according to each electrical equipment of electricity consumption policy control, the power consumption control of the smart home system provided through the embodiment of the present invention
Method may be implemented to be predicted according to following power consumption of the history power consumption condition to smart home system, and pass through predicted value
The purpose for formulating corresponding economize on electricity controlling planning in advance has not only reached the technology effect for the reliability for improving smart home system
Fruit, and reached the technical effect for saving electricity, and then solve and cannot achieve in the related technology according to future time section
The technical issues of power consumption controls each electric appliance in house system.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the power consumption control method of smart home system according to an embodiment of the present invention;
Fig. 2 is the flow chart of the power consumption control method of optional smart home system according to an embodiment of the present invention;
Fig. 3 is the schematic diagram of the power consumption control device of smart home system according to an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
In order to make it easy to understand, below in the embodiment of the present invention part noun or term be described in detail:
Convolutional neural networks: being a kind of feedforward neural network, and artificial neuron can respond surrounding cells, can carry out large size
Image procossing, including convolutional layer and pond layer.
Convolutional layer: it is primarily used to carry out feature extraction.
Pond layer: being to compress to the characteristic pattern of input, on the one hand characteristic pattern become smaller, and it is complicated to simplify network query function
On the other hand degree carries out Feature Compression, extract main feature.
Embodiment 1
According to embodiments of the present invention, the embodiment of the method for a kind of power consumption control method of smart home system is provided, is needed
It is noted that step shown in the flowchart of the accompanying drawings can be in the computer system of such as a group of computer-executable instructions
Middle execution, although also, logical order is shown in flow charts, and it in some cases, can be to be different from herein
Sequence executes shown or described step.
Fig. 1 is the flow chart of the power consumption control method of smart home system according to an embodiment of the present invention, as shown in Figure 1,
The power consumption control method of the smart home system includes the following steps:
Step S102 obtains reference data, wherein reference data is set for generating each electricity consumption in smart home system
The foundation of standby electricity consumption data.
In step s 102, reference data can include but is not limited to following several: certain following time, the time in future
Corresponding weather forecast, the member in user family constitutes and user and the living habit of kinsfolk etc., for example, when current
Between be Monday, then certain following time can be Tuesday, Wednesday, Thursday or later time.
Step S104, by each data conversion in reference data at the input of power consumption prediction model, wherein power consumption
Prediction model is obtained by training data training, and every group of training data includes: that reference data is corresponding with the reference data
Electricity consumption data.
Step S106 obtains the output of power consumption prediction model.
Step S108 converts the output into electricity consumption data, and the electricity consumption plan of smart home system is generated according to electricity consumption data
Slightly.
Electricity consumption strategy is sent to smart home system by step S110, wherein smart home system is according to electricity consumption strategy control
Make each electrical equipment.
Through the above steps, available reference data, wherein reference data is each in smart home system for generating
The foundation of the electricity consumption data of a electrical equipment;By each data conversion in reference data at the input of power consumption prediction model,
Wherein, power consumption prediction model is obtained by training data training, and every group of training data includes: reference data and the ginseng
Examine the corresponding electricity consumption data of data;Obtain the output of power consumption prediction model;Electricity consumption data is converted the output into, and according to electricity consumption
The electricity consumption strategy of data generation smart home system;Electricity consumption strategy is sent to smart home system, wherein smart home system
According to each electrical equipment of electricity consumption policy control.It can not be according to history entirety power consumption relative to smart home system in the related technology
Amount predicts the following power consumption situation, the disadvantage that also can not be accordingly controlled to adjust according to the following power consumption condition to each electrical equipment
End, the power consumption control method of the smart home system provided through the embodiment of the present invention may be implemented according to history power consumption condition pair
The following power consumption of smart home system is predicted, and formulates the mesh of corresponding economize on electricity controlling planning in advance by predicted value
, the technical effect for improving the reliability of smart home system is not only reached, and reached the technical effect for saving electricity,
And then it solves to cannot achieve in the related technology and each electric appliance in house system is carried out according to the power consumption of future time section
The technical issues of control.
In step S104, obtaining power consumption prediction model by training data training may include: acquisition historical time
The history reference data of section, and using history reference data as training data;By each data conversion in every group of training data
At numerical value;Using the obtained corresponding numerical value of each data as the input layer of convolutional neural networks model and output layer
Node;It is trained to obtain power consumption prediction model according to input layer and output node layer.
As a kind of optional embodiment, the smart home central control system in smart home system will record installing zone
The electricity consumption of the total electricity consumption of smart home system and each electrical equipment in the daily family in domain, and by above-mentioned smart home system
Total electricity consumption and each electrical equipment electricity consumption as training data, be input to convolutional neural networks model, predicted
Output data set, training obtain the power consumption prediction model of multilayer convolutional neural networks.
It should be noted that above-mentioned training data can be a part of history reference data.
It further, can be by history reference data in order to verify the reliability for training obtained power consumption prediction model
Another part as verify data, wherein verify data is for verifying power consumption prediction model.
For example, available electricity consumption measures test data, the not same date of multiple electrical equipments is extracted as test input
Test input data is input in convolutional neural networks, obtains corresponding prediction output data by data.In order to enable trained
The power consumption prediction model arrived is relatively reliable, which can be preferably multilayer convolutional neural networks.
In step S108, the electricity consumption strategy that smart home system is generated according to electricity consumption data may include: judgement electricity consumption
Whether data are not less than tentation data, wherein tentation data is corresponding electricity consumption data when smart home system trips;?
Judging result is electricity consumption data not less than in the case where tentation data, and the electricity consumption plan of smart home system is generated according to electricity consumption data
Slightly.
For example, after obtaining electricity consumption data, judgement obtains electricity consumption reference data to be input in power consumption prediction model
In the case that data are not less than tentation data, the smart home central control system in smart home system can be set each electricity consumption
Standby operating mechanism is carried out to be planned in advance, according to the hobby of user and same day weather, corresponding electrical equipment is arranged rationally to avoid the peak hour use
Electricity, and then avoid electricity consumption from increasing suddenly and cause trip phenomenon, and realize economize on electricity.
In step S108, the electricity consumption strategy that smart home system is generated according to electricity consumption data may include: to pass through electricity consumption
Policy model determines the corresponding electricity consumption strategy of electricity consumption data, wherein electricity consumption Policy model is to pass through engineering using multi-group data
Practise what training obtained, every group of data in multi-group data include: electricity consumption data and the corresponding electricity consumption strategy of electricity consumption data.
As a kind of optional embodiment, by electricity consumption Policy model, determine the corresponding electricity consumption strategy of electricity consumption data it
Before, the power consumption control method of the smart home system can also include: multiple history electricity consumption datas of the acquisition in historical time section
With multiple history electricity consumption Policy models, wherein multiple history electricity consumption Policy models are determined according to multiple history electricity consumption datas
Model;The multi-group data including multiple history electricity consumption datas and multiple history electricity consumption Policy models of acquisition is trained, is obtained
To electricity consumption Policy model.
In the power consumption control method of the smart home system provided in the embodiment of the present invention 1, smart home system can be with
Realization is met the needs of users to the greatest extent, while realizing the smallest multi-parameter optimizing process of power consumption, specifically, Ke Yigen
It is counted according to the daily power consumption situation of history and corresponding weather, obtains power consumption prediction model as training data training,
In, power consumption situation may include the whole power consumption condition of furniture intelligence system and the power consumption condition of each electrical equipment.According to
Power consumption prediction model can predict the following power consumption condition sometime, and then can be according to predicted value, and schedule ahead is corresponding
Electrical equipment peak load shifting, and then avoid the trip phenomenon caused because electricity consumption increases suddenly.Fig. 2 is to implement according to the present invention
The flow chart of the power consumption control method of the optional smart home system of example, as shown in Fig. 2, smart home center can be controlled
System will record the electricity consumption conduct of the total electricity consumption of smart home system and each electrical equipment in the daily family in installation region
Input data, after first layer process of convolution, into second layer convolution, after obtain output data.Wherein, first layer convolution sum
Second layer convolution includes two processes of convolution sum pondization.In addition, it is provided with weight in first layer convolution sum second layer convolution,
For example, w1, w2 and activation primitive, for example, y1, y2, y3, y4 and y5, wherein y5 can be obtained by y4, y5=y4*w3+
B, wherein b is the constant to optimize to power consumption prediction model, can be arranged as the case may be.Wherein, softmax
To normalize exponential function.It should be noted that above-mentioned input data and output data can show with a matrix type.Its
In, shown in Figure 2 is so that convolutional neural networks model is two layers of convolutional layer as an example, and certainly, convolutional neural networks model can also
Think other multilayer convolutional layers.
Relative to the relevant technologies, the power consumption control method of the smart home system provided in embodiment 1 can be effectively improved
The bad drawback of smart home system entirety power consumption performance will carry out power consumption prediction to future according to history power consumption condition, and passes through
Prediction data formulates corresponding economize on electricity controlling planning in advance.
Embodiment 2
Another aspect according to an embodiment of the present invention additionally provides a kind of power consumption control dress of smart home system
It sets, it should be noted that the power consumption control device of the smart home system of the embodiment of the present invention can be used for executing of the invention real
Apply the power consumption control method of smart home system provided by example 1.Below to smart home system provided in an embodiment of the present invention
Power consumption control device be introduced.
Fig. 3 is the schematic diagram of the power consumption control device of smart home system according to an embodiment of the present invention, as shown in figure 3,
The power consumption control device of the smart home system includes: first acquisition unit 31, converting unit 33, second acquisition unit 35, life
At unit 37 and transmission unit 39.The power consumption control device of the smart home system is described in detail below.
First acquisition unit 31, for obtaining reference data, wherein reference data is for generating in smart home system
The foundation of the electricity consumption data of each electrical equipment.
Converting unit 33, for the input by each data conversion in reference data at power consumption prediction model, wherein
Power consumption prediction model is obtained by training data training, and every group of training data includes: reference data and the reference number
According to corresponding electricity consumption data.
Second acquisition unit 35, for obtaining the output of power consumption prediction model.
Generation unit 37 generates smart home system for converting the output into electricity consumption data, and according to electricity consumption data
Electricity consumption strategy.
Transmission unit 39, for electricity consumption strategy to be sent to smart home system, wherein smart home system is according to electricity consumption
The each electrical equipment of policy control.
It should be noted that the first acquisition unit 31 in the embodiment can be used for executing the step in the embodiment of the present invention
Rapid S102, the converting unit 33 in the embodiment can be used for executing the step S104 in the embodiment of the present invention, in the embodiment
Second acquisition unit 35 can be used for executing the step S106 in the embodiment of the present invention, the generation unit 37 in the embodiment can
With for executing the step S108 in the embodiment of the present invention, the transmission unit 39 in the embodiment can be used for executing of the invention real
Apply the step S110 in example.Above-mentioned module is identical as example and application scenarios that corresponding step is realized, but is not limited to above-mentioned
Embodiment disclosure of that.
In this embodiment it is possible to obtain reference data using first acquisition unit 31, wherein reference data is for giving birth to
At the foundation of the electricity consumption data of electrical equipment each in smart home system;It then will be in reference data using converting unit 33
Each data conversion at power consumption prediction model input, wherein power consumption prediction model be by training data training obtain
, every group of training data includes: reference data electricity consumption data corresponding with the reference data;Recycle second acquisition unit 35
Obtain the output of power consumption prediction model;And electricity consumption data is converted the output into using generation unit 37, and according to electricity consumption number
According to the electricity consumption strategy for generating smart home system;And electricity consumption strategy is sent to smart home system using transmission unit 39,
In, smart home system is according to each electrical equipment of electricity consumption policy control.It can not relative to smart home system in the related technology
The following power consumption situation is predicted according to history whole power consumption, each electrical equipment can not also be carried out according to the following power consumption condition
Corresponding the drawbacks of controlling to adjust, root may be implemented in the power consumption control device of the smart home system provided through the embodiment of the present invention
It predicts according to following power consumption of the history power consumption condition to smart home system, and is formulated in advance accordingly by predicted value
The purpose of economize on electricity controlling planning, has not only reached the technical effect for improving the reliability of smart home system, and reached section
The technical effect of electricity is saved, and then solves and cannot achieve the power consumption according to future time section in the related technology to house system
In each electric appliance the technical issues of being controlled.
As a kind of optional embodiment, above-mentioned converting unit may include: the first acquisition module, when for obtaining history
Between section history reference data, and using history reference data as training data;Conversion module, being used for will be in every group of training data
Each data conversion at numerical value;First determining module, the corresponding numerical value of each data for will obtain is as convolution
The input layer and output node layer of neural network model;Second obtains module, for according to input layer and output layer
Node is trained to obtain power consumption prediction model.
As a kind of optional embodiment, above-mentioned training data can be a part of history reference data.
As a kind of optional embodiment, another part of above-mentioned history reference data can be used as verify data, wherein
Verify data is for verifying power consumption prediction model.
As a kind of optional embodiment, above-mentioned generation unit may include: judgment module, for judging that electricity consumption data is
It is no to be not less than tentation data, wherein tentation data is corresponding electricity consumption data when smart home system trips;Generate mould
Block, for generating smart home system according to electricity consumption data in the case where judging result is that electricity consumption data is not less than tentation data
The electricity consumption strategy of system.
As a kind of optional embodiment, above-mentioned generation unit may include: the second determining module, for passing through electricity consumption plan
Slightly model, determines the corresponding electricity consumption strategy of electricity consumption data, wherein electricity consumption Policy model is to pass through machine learning using multi-group data
What training obtained, every group of data in multi-group data include: electricity consumption data and the corresponding electricity consumption strategy of electricity consumption data.
As a kind of optional embodiment, the power consumption control device of the smart home system can also include: acquisition module,
For before determining the corresponding electricity consumption strategy of electricity consumption data, acquiring in the multiple of historical time section by electricity consumption Policy model
History electricity consumption data and multiple history electricity consumption Policy models, wherein multiple history electricity consumption Policy models are used according to multiple history
The model that electric data determine;Third acquiring unit, for acquisition include multiple history electricity consumption datas and multiple history electricity consumptions
The multi-group data of Policy model is trained, and obtains electricity consumption Policy model.
Above- mentioned information suggestion device includes processor and memory, above-mentioned first acquisition unit 31, converting unit 33, and second
Acquiring unit 35, generation unit 37 and transmission unit 39 etc. are stored in memory as program unit, are held by processor
Above procedure unit stored in memory go to realize corresponding function.
Include kernel in above-mentioned processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set
Electricity consumption strategy is sent to smart home system by adjusting kernel parameter by one or more, wherein smart home system according to
The each electrical equipment of electricity consumption policy control.
Above-mentioned memory may include the non-volatile memory in computer-readable medium, random access memory
(RAM) and/or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM), memory includes extremely
A few storage chip.
Another aspect according to an embodiment of the present invention, additionally provides a kind of storage medium, and storage medium includes storage
Program, wherein program executes the power consumption control method of any one of above-mentioned smart home system.
Another aspect according to an embodiment of the present invention additionally provides a kind of processor, and processor is used to run program,
Wherein, the power consumption control method of any one of above-mentioned smart home system is executed when program is run.
A kind of equipment is additionally provided in embodiments of the present invention, which includes processor, memory and be stored in storage
On device and the program that can run on a processor, processor perform the steps of acquisition reference data when executing program, wherein
Reference data is the foundation for generating the electricity consumption data of each electrical equipment in smart home system;It will be every in reference data
A data are converted into the input of power consumption prediction model, wherein and power consumption prediction model is obtained by training data training,
Every group of training data includes: reference data electricity consumption data corresponding with the reference data;Obtain the defeated of power consumption prediction model
Out;Electricity consumption data is converted the output into, and generates the electricity consumption strategy of smart home system according to electricity consumption data;Electricity consumption strategy is sent out
It send to smart home system, wherein smart home system is according to each electrical equipment of electricity consumption policy control.
A kind of computer program product is additionally provided in embodiments of the present invention, when being executed on data processing equipment,
It is adapted for carrying out the program of initialization there are as below methods step: obtaining reference data, wherein reference data is for generating intelligent family
Occupy the foundation of the electricity consumption data of each electrical equipment in system;Each data conversion in reference data is predicted into mould at power consumption
The input of type, wherein power consumption prediction model is obtained by training data training, and every group of training data includes: reference
Data electricity consumption data corresponding with the reference data;Obtain the output of power consumption prediction model;Electricity consumption data is converted the output into,
And the electricity consumption strategy of smart home system is generated according to electricity consumption data;Electricity consumption strategy is sent to smart home system, wherein intelligence
Energy house system is according to each electrical equipment of electricity consumption policy control.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of power consumption control method of smart home system characterized by comprising
Obtain reference data, wherein the reference data is the electricity consumption for generating each electrical equipment in smart home system
The foundation of data;
By each data conversion in the reference data at the input of power consumption prediction model, wherein the power consumption prediction
Model is obtained by training data training, and every group of training data includes: reference data use corresponding with the reference data
Electric data;
Obtain the output of the power consumption prediction model;
The output is converted into the electricity consumption data, and generates the electricity consumption of the smart home system according to the electricity consumption data
Strategy;
The electricity consumption strategy is sent to the smart home system, wherein the smart home system is according to the electricity consumption plan
Slightly control each electrical equipment.
2. the method according to claim 1, wherein it is pre- to obtain the power consumption by training data training
Surveying model includes:
The history reference data of historical time section are obtained, and using the history reference data as training data;
By each data conversion in every group of training data at numerical value;
Using the obtained corresponding numerical value of each data as the input layer of convolutional neural networks model and output layer section
Point;
It is trained to obtain the power consumption prediction model according to the input layer and the output node layer.
3. according to the method described in claim 2, it is characterized in that, the training data is one of the history reference data
Point.
4. according to the method described in claim 3, it is characterized in that, another part of the history reference data is as verifying number
According to, wherein the verify data is for verifying the power consumption prediction model.
5. the method according to claim 1, wherein generating the smart home system according to the electricity consumption data
Electricity consumption strategy include:
Judge whether the electricity consumption data is not less than tentation data, wherein the tentation data is smart home system hair
Corresponding electricity consumption data when raw tripping;
In the case where judging result is that the electricity consumption data is not less than the tentation data, institute is generated according to the electricity consumption data
State the electricity consumption strategy of smart home system.
6. the method according to claim 1, wherein generating the smart home system according to the electricity consumption data
Electricity consumption strategy include:
By electricity consumption Policy model, the corresponding electricity consumption strategy of the electricity consumption data is determined, wherein the electricity consumption Policy model is to make
It is obtained with multi-group data by machine learning training, every group of data in the multi-group data include: electricity consumption data and institute
State the corresponding electricity consumption strategy of electricity consumption data.
7. according to the method described in claim 6, it is characterized in that, determining the electricity consumption data by electricity consumption Policy model
Before corresponding electricity consumption strategy, further includes:
Acquire multiple history electricity consumption datas in historical time section and multiple history electricity consumption Policy models, wherein the multiple to go through
History electricity consumption Policy model is the model determined according to the multiple history electricity consumption data;
The multi-group data including the multiple history electricity consumption data and the multiple history electricity consumption Policy model of acquisition is carried out
Training, obtains the electricity consumption Policy model.
8. a kind of power consumption control device of smart home system characterized by comprising
First acquisition unit, for obtaining reference data, wherein the reference data is each in smart home system for generating
The foundation of the electricity consumption data of a electrical equipment;
Converting unit, for the input by each data conversion in the reference data at power consumption prediction model, wherein institute
Stating power consumption prediction model is obtained by training data training, and every group of training data includes: reference data and the reference
The corresponding electricity consumption data of data;
Second acquisition unit, for obtaining the output of the power consumption prediction model;
Generation unit for the output to be converted to the electricity consumption data, and generates the intelligence according to the electricity consumption data
The electricity consumption strategy of house system;
Transmission unit, for the electricity consumption strategy to be sent to the smart home system, wherein the smart home system root
According to each electrical equipment described in the electricity consumption policy control.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution
Benefit require any one of 1 to 7 described in smart home system power consumption control method.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 7 described in smart home system power consumption control method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811092932.8A CN109188924A (en) | 2018-09-18 | 2018-09-18 | The power consumption control method and device of smart home system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811092932.8A CN109188924A (en) | 2018-09-18 | 2018-09-18 | The power consumption control method and device of smart home system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109188924A true CN109188924A (en) | 2019-01-11 |
Family
ID=64908248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811092932.8A Pending CN109188924A (en) | 2018-09-18 | 2018-09-18 | The power consumption control method and device of smart home system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109188924A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110186157A (en) * | 2019-06-13 | 2019-08-30 | 宁波奥克斯电气股份有限公司 | A kind of control method, device and the air conditioner of electrical equipment electricity consumption |
CN110567104A (en) * | 2019-09-26 | 2019-12-13 | 珠海格力电器股份有限公司 | method and device for controlling operation of internal machine of multi-split air conditioning system and computer equipment |
CN111126673A (en) * | 2019-12-02 | 2020-05-08 | 珠海格力电器股份有限公司 | Equipment energy consumption prediction method and device and equipment controller |
CN112327648A (en) * | 2020-11-09 | 2021-02-05 | 睿住科技有限公司 | Control method and device for household equipment and computer readable storage medium |
CN115268269A (en) * | 2022-07-29 | 2022-11-01 | 无锡市低碳研究院有限公司 | Household energy consumption optimization system and method based on new energy low carbon |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012244897A (en) * | 2011-05-13 | 2012-12-10 | Fujitsu Ltd | Apparatus and method for predicting short-term power load |
CN106934497A (en) * | 2017-03-08 | 2017-07-07 | 青岛卓迅电子科技有限公司 | Wisdom cell power consumption real-time predicting method and device based on deep learning |
CN107423839A (en) * | 2017-04-17 | 2017-12-01 | 湘潭大学 | A kind of method of the intelligent building microgrid load prediction based on deep learning |
CN107544381A (en) * | 2017-08-31 | 2018-01-05 | 珠海格力电器股份有限公司 | Energy management method and device |
CN107689671A (en) * | 2017-08-31 | 2018-02-13 | 珠海格力电器股份有限公司 | Power consumption control method and device |
CN107958307A (en) * | 2017-11-28 | 2018-04-24 | 珠海格力电器股份有限公司 | Electricity charge Forecasting Methodology and device |
CN108022008A (en) * | 2017-11-30 | 2018-05-11 | 国网福建省电力有限公司经济技术研究院 | The training method of electricity demand forecasting model |
CN108090629A (en) * | 2018-01-16 | 2018-05-29 | 广州大学 | Load forecasting method and system based on nonlinear auto-companding neutral net |
-
2018
- 2018-09-18 CN CN201811092932.8A patent/CN109188924A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012244897A (en) * | 2011-05-13 | 2012-12-10 | Fujitsu Ltd | Apparatus and method for predicting short-term power load |
CN106934497A (en) * | 2017-03-08 | 2017-07-07 | 青岛卓迅电子科技有限公司 | Wisdom cell power consumption real-time predicting method and device based on deep learning |
CN107423839A (en) * | 2017-04-17 | 2017-12-01 | 湘潭大学 | A kind of method of the intelligent building microgrid load prediction based on deep learning |
CN107544381A (en) * | 2017-08-31 | 2018-01-05 | 珠海格力电器股份有限公司 | Energy management method and device |
CN107689671A (en) * | 2017-08-31 | 2018-02-13 | 珠海格力电器股份有限公司 | Power consumption control method and device |
CN107958307A (en) * | 2017-11-28 | 2018-04-24 | 珠海格力电器股份有限公司 | Electricity charge Forecasting Methodology and device |
CN108022008A (en) * | 2017-11-30 | 2018-05-11 | 国网福建省电力有限公司经济技术研究院 | The training method of electricity demand forecasting model |
CN108090629A (en) * | 2018-01-16 | 2018-05-29 | 广州大学 | Load forecasting method and system based on nonlinear auto-companding neutral net |
Non-Patent Citations (1)
Title |
---|
赵贺 等: "基于数据分析的智能用电设备自学习模型方案设计", 《科技创新》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110186157A (en) * | 2019-06-13 | 2019-08-30 | 宁波奥克斯电气股份有限公司 | A kind of control method, device and the air conditioner of electrical equipment electricity consumption |
CN110567104A (en) * | 2019-09-26 | 2019-12-13 | 珠海格力电器股份有限公司 | method and device for controlling operation of internal machine of multi-split air conditioning system and computer equipment |
CN110567104B (en) * | 2019-09-26 | 2020-09-11 | 珠海格力电器股份有限公司 | Method and device for controlling operation of internal machine of multi-split air conditioning system and computer equipment |
CN111126673A (en) * | 2019-12-02 | 2020-05-08 | 珠海格力电器股份有限公司 | Equipment energy consumption prediction method and device and equipment controller |
CN112327648A (en) * | 2020-11-09 | 2021-02-05 | 睿住科技有限公司 | Control method and device for household equipment and computer readable storage medium |
CN115268269A (en) * | 2022-07-29 | 2022-11-01 | 无锡市低碳研究院有限公司 | Household energy consumption optimization system and method based on new energy low carbon |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109188924A (en) | The power consumption control method and device of smart home system | |
Ye et al. | A scalable privacy-preserving multi-agent deep reinforcement learning approach for large-scale peer-to-peer transactive energy trading | |
Mohan et al. | An efficient two stage stochastic optimal energy and reserve management in a microgrid | |
Keerthisinghe et al. | Energy management of PV-storage systems: Policy approximations using machine learning | |
CN110084407A (en) | Load forecasting method and device based on Recognition with Recurrent Neural Network and meta learning strategy | |
CN104680339B (en) | A kind of household electrical appliance dispatching method based on Spot Price | |
KR20200081098A (en) | System for operation of virtual power plant based on hybrid prediction model and method thereof | |
CN108767866A (en) | Energy management method, apparatus and system | |
CN108988467A (en) | Electricity consumption strategy-generating method and device | |
CN115314343A (en) | Source-load-storage resource aggregation control gateway device and load and output prediction method | |
Bessa et al. | Data economy for prosumers in a smart grid ecosystem | |
Baek et al. | Short-term load forecasting for campus building with small-scale loads by types using artificial neural network | |
Venkatakrishnan et al. | An efficient energy management in smart grid based on IOT using ROAWFSA technique | |
CN107958307A (en) | Electricity charge Forecasting Methodology and device | |
CN110276638A (en) | A kind of Electricity price forecasting solution and system based on two-way shot and long term neural network | |
Chandrasekaran et al. | Multi-objective unit commitment problem using Cuckoo search Lagrangian method | |
Lizondo et al. | Multiagent model for distributed peak shaving system with demand-side management approach | |
Georgilakis | Market clearing price forecasting in deregulated electricity markets using adaptively trained neural networks | |
CN105302808B (en) | A kind of method and apparatus reducing load peak in user group matching process | |
CN116247676A (en) | Power distribution network topology deduction method based on real-time market electricity price | |
Nutakki et al. | Energy consumption forecasting in home energy management system using Deep Learning Techniques | |
KR102515287B1 (en) | Intelligent home energy mangement system and method based on federated learning | |
Yang et al. | Research on multi-agent systems in a smart small grid for resource apportionment and planning | |
Rodway et al. | Differential evolution optimized fuzzy controller for wireless sensor network energy management | |
Shaheen et al. | A hybrid algorithm for energy management in smart grid |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |