CN112365090A - Deep learning-based non-invasive electrical load identification method and device - Google Patents
Deep learning-based non-invasive electrical load identification method and device Download PDFInfo
- Publication number
- CN112365090A CN112365090A CN202011366686.8A CN202011366686A CN112365090A CN 112365090 A CN112365090 A CN 112365090A CN 202011366686 A CN202011366686 A CN 202011366686A CN 112365090 A CN112365090 A CN 112365090A
- Authority
- CN
- China
- Prior art keywords
- data
- load
- deep learning
- model
- electrical load
- 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 37
- 238000013135 deep learning Methods 0.000 title claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000013145 classification model Methods 0.000 claims abstract description 13
- 238000010606 normalization Methods 0.000 claims abstract description 13
- 238000013136 deep learning model Methods 0.000 claims abstract description 10
- 238000013139 quantization Methods 0.000 claims abstract description 7
- 230000015654 memory Effects 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 13
- 238000012544 monitoring process Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000005611 electricity Effects 0.000 description 10
- 230000004044 response Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02B90/20—Smart grids as enabling technology in buildings sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Power Engineering (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to and discloses a non-invasive electrical load identification method based on deep learning, which comprises the following steps: obtaining data, wherein the data comprises: historical load data and external influence factor data; preprocessing the data, wherein the preprocessing specifically comprises: removing bad values, filling null values, calculating characteristic values and carrying out normalization processing on the historical load data; and carrying out quantization processing on the external influence data; and sequentially inputting the preprocessed data into a preset deep learning model, a time sequence model and a classification model, outputting a result and obtaining a load identification result. The invention can realize the purpose of identifying the states of different types of loads (electric appliances) of the household users through the conventional household load electric power monitoring device (household electric meter).
Description
Technical Field
The invention relates to the technical field of power load monitoring of a power system, in particular to a non-invasive power load identification method and device based on deep learning.
Background
A non-intrusive load monitoring (NILM) system is a system that analyzes and obtains the type and operation condition of a single load in a load cluster through measurement data of monitoring equipment installed at a power inlet. The non-invasive load monitoring of the resident user refers to the recognition of the electricity utilization behavior and the monitoring of the running state of the electric appliance through the household electric meter. The user can reduce unnecessary energy expenditure through the NILM, thereby achieving the purposes of energy conservation and consumption reduction. The electric power company can know the structure of the load of the power consumer through the NILM, strengthen the management of the load side, and achieve the purposes of adjusting the peak-valley difference, reducing the network loss and the like by guiding the reasonable consumption of the consumer and reasonably arranging the service time of the load; the method is beneficial to improving the prediction precision of the power load and providing more accurate data for simulation analysis and system planning of the power system.
Deep learning is one of machine learning, the root of the deep learning is an artificial neural network, and the artificial neural network can adaptively process complex nonlinear relations and excavate deep relations. At present, deep learning is widely applied to the fields of image, voice and character recognition, load prediction and the like. The deep learning models are various in types, different in model structures, large in application range and large in difference of advantages and disadvantages, and suitable model structures and model parameters are selected for different application scenes.
At present, there are two main types of non-invasive residential load monitoring methods: firstly, the load characteristics of different electrical appliances are extracted, and the load characteristics are identified and analyzed in a total load curve. And secondly, the accuracy of load identification is improved by applying and researching different load identification algorithms, and non-invasive load monitoring is realized mainly by methods such as a decision tree, a support vector machine, a hidden Markov chain, K nearest neighbor and the like. However, the above methods have several problems, one is that a part of schemes need to be additionally provided with a load monitoring device, the other is that the recognizable electric appliance has single category and low overall recognition rate, and the third is that the portability of the schemes is weak.
Disclosure of Invention
The purpose of the invention is: the non-invasive power load identification method and device based on deep learning can realize the purpose of identifying the states of different types of loads (electric appliances) of home users through the conventional home load power monitoring device (home electric meter).
In order to achieve the above object, the present invention provides a deep learning-based non-invasive electrical load identification method, including:
obtaining data, wherein the data comprises: historical load data and external influence factor data;
preprocessing the data, wherein the preprocessing specifically comprises: removing bad values, filling null values, calculating characteristic values and carrying out normalization processing on the historical load data; and carrying out quantization processing on the external influence data;
and sequentially inputting the preprocessed data into a preset deep learning model, a time sequence model and a classification model, outputting a result and obtaining a load identification result.
Further, the historical load data includes: total load data and appliance load data; the external factor influence data includes: maximum air temperature, minimum air temperature and date.
Further, the calculating the feature value includes: calculating a load change value of first preset time as a data change characteristic; calculating the load mean value of the second preset time as the data mean value characteristic; and calculating the load variance value of the third preset time as the data variance characteristic.
Further, the normalization process adopts the following formula:
wherein D ismaxAnd DminThe sequence maximum and minimum values, respectively.
Further, the time sequence model is a preset long-short term memory neural network; wherein, the unit formula of the long-short term memory neural network is as follows:
further, the classification model includes: support vector machine model, random forest model and multilayer perceptron model.
The embodiment of the invention also provides a deep learning-based non-invasive electrical load identification device, which comprises: the system comprises a data acquisition module, a data processing module and a model processing module;
the data acquisition module is configured to acquire data, where the data includes: historical load data and external influence factor data;
the data processing module is configured to perform preprocessing on the data, where the preprocessing specifically includes: removing bad values, filling null values, calculating characteristic values and carrying out normalization processing on the historical load data; and carrying out quantization processing on the external influence data;
and the model processing module is used for sequentially inputting the preprocessed data into a preset deep learning model, a time sequence model and a classification model, outputting a result and obtaining a load identification result.
Further, the historical load data includes: total load data and appliance load data; the external factor influence data includes: maximum air temperature, minimum air temperature and date.
An embodiment of the present invention further provides a computer terminal device, including: one or more processors; a memory coupled to the processor for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement a method for non-intrusive electrical load recognition based on deep learning as defined in any of the preceding claims.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the deep learning-based non-invasive electrical load identification method according to any of the above.
Compared with the prior art, the non-invasive power load identification method and device based on deep learning have the advantages that:
1. according to the resident user load monitoring method provided by the invention, on one hand, the purpose of non-invasive user load monitoring is achieved by only utilizing the measurement and acquisition data of the currently and commonly installed digital household electric meter, and the electricity utilization behavior of a resident user is identified; on the other hand, the identification model utilized by the invention is a composite cascade deep learning model which comprises a plurality of neural network models and machine learning models, so that the information of the electricity utilization behavior on the time dimension and the information on the data dimension can be fully learned and mined, and the electricity utilization behavior identification accuracy is improved.
2. After the model provided by the invention learns the historical data, the model can be used for analyzing and identifying the electricity utilization behavior of the user for hours to a year, and the identification rate can synchronize the load acquisition frequency; among users of the same type, the model has stronger portability and better universality.
3. The invention identifies the power consumption behavior of the user (monitors the working state of the electric appliance), can help the user to know and obtain the household energy consumption analysis and the running state of the electric appliance, and provides basis and support for implementing intelligent power consumption and automatic demand response; the power grid company is helped to deconstruct the user load, the participation demand response potential of the user can be evaluated in a fine mode, the load side management is enhanced, and the demand response is implemented; the method is beneficial to improving the prediction precision of the power load and providing more accurate data for simulation analysis and system planning of the power system.
Drawings
Fig. 1 is a schematic flowchart of a deep learning-based non-invasive electrical load identification method according to an embodiment of the present invention;
fig. 2 is a flowchart of a double-layer optimization model of a deep learning-based non-invasive electrical load recognition method according to an embodiment of the present invention;
FIG. 3 is a block diagram of a Long Short Term Memory (LSTM) unit according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a power curve of a household main electrical appliance according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an operating state of a household electrical appliance, that is, a user electrical behavior (0 represents working or suspended working, and 1 represents working) according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an operating state of an electrical appliance, i.e., an electrical behavior of the electrical appliance (0 represents working or suspended working, and 1 represents working), which is identified by a model according to an embodiment of the present invention;
fig. 7 is a schematic diagram of comparison between a real operating state of a user's home air conditioner and an operating state identified by a model according to an embodiment of the present invention (0 represents operating or suspended operating, and 1 represents operating);
FIG. 8 is a schematic diagram of comparison between the actual working status of a user's home washing machine and the working status identified by the model (0 represents working or suspended working, and 1 represents working) according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of the comparison between the actual operation status of the household dishwasher of a user and the operation status identified by the model (0 represents working or suspended operation, and 1 represents working) according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of comparison between a real operating status of a home electric vehicle of a user and an operating status identified by a model according to an embodiment of the present invention (0 represents working or suspended working, and 1 represents working);
fig. 11 is a schematic diagram of comparison between a real operating state of photovoltaic power generation in a certain area and an operating state identified by a model (0 represents operating or suspended operating, and 1 represents operating) according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of a device for configuring and controlling energy storage capacity on a long time scale in consideration of time-of-use electricity prices according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
The first embodiment of the present invention:
as shown in fig. 1, a method for identifying a non-invasive electrical load based on deep learning according to an embodiment of the present invention at least includes the following steps:
s101, acquiring data, wherein the data comprises: historical load data and external influence factor data;
it should be noted that, this step completes data collection work for monitoring users and external influence factors, specifically, collects data collected by the existing power collection device (electric meter), and includes: total load data and primary appliance load data.
In the embodiment, the maximum air temperature, the minimum air temperature, and the date are used as the external influence factor data.
S102, preprocessing the data, wherein the preprocessing specifically comprises the following steps: removing bad values, filling null values, calculating characteristic values and carrying out normalization processing on the historical load data; and carrying out quantization processing on the external influence data;
it should be noted that the step is mainly to preprocess the collected data, including the processes of removing bad values, filling null values, calculating characteristic values, normalizing and the like, wherein the calculated characteristic values include load change values calculated for 2 minutes, 3 minutes, 5 minutes and 15 minutes respectively as data change characteristics; calculating load mean values of 5 minutes, 15 minutes, 30 minutes and 60 minutes as data mean characteristics; variance values of the loads at 5 minutes, 15 minutes, 30 minutes and 60 minutes were calculated as data variance characteristics, respectively; the normalization processing refers to mapping data to [0, 1]In the formula of
Wherein DmaxAnd DminRespectively, the maximum value and the minimum value of the sequence, normalizing each value in the sequence to be normalized,thereby realizing the linear normalization of the sequence to be normalized; normalization prevents model saturation due to excessive differences between data, which ultimately results in large deviations in the resulting industry.
S103, inputting the preprocessed data into a preset deep learning model, a time sequence model and a classification model in sequence, outputting a result and obtaining a load identification result.
It should be noted that the time sequence model is used for extracting a characteristic link, and the link deeply excavates data characteristics and information through an LSTM neural network; the classification models are used for predicting the load state, the identification of the working state of the electric appliance is realized through different classification models, and the classification models are respectively a support vector machine model, a random forest model and a multilayer perceptron model.
In one embodiment of the present invention, the historical load data includes: total load data and appliance load data; the external factor influence data includes: maximum air temperature, minimum air temperature and date.
In one embodiment of the present invention, the calculating the feature value includes: calculating a load change value of first preset time as a data change characteristic; calculating the load mean value of the second preset time as the data mean value characteristic; and calculating the load variance value of the third preset time as the data variance characteristic.
The first preset time is 2 minutes, 3 minutes, 5 minutes, and 15 minutes, the second preset time is 5 minutes, 15 minutes, 30 minutes, and 60 minutes, and the third preset time is 5 minutes, 15 minutes, 30 minutes, and 60 minutes.
In an embodiment of the present invention, the normalization process uses the following formula:
wherein D ismaxAnd DminThe sequence maximum and minimum values, respectively.
In one embodiment of the present invention, the timing model is a preset long-short term memory neural network; wherein, the unit formula of the long-short term memory neural network is as follows:
in one embodiment of the present invention, the classification model includes: support vector machine model, random forest model and multilayer perceptron model.
Compared with the prior art, the non-invasive power load identification method based on deep learning has the beneficial effects that:
1. according to the resident user load monitoring method provided by the invention, on one hand, the purpose of non-invasive user load monitoring is achieved by only utilizing the measurement and acquisition data of the currently and commonly installed digital household electric meter, and the electricity utilization behavior of a resident user is identified; on the other hand, the identification model utilized by the invention is a composite cascade deep learning model which comprises a plurality of neural network models and machine learning models, so that the information of the electricity utilization behavior on the time dimension and the information on the data dimension can be fully learned and mined, and the electricity utilization behavior identification accuracy is improved.
2. After the model provided by the invention learns the historical data, the model can be used for analyzing and identifying the electricity utilization behavior of the user for hours to a year, and the identification rate can synchronize the load acquisition frequency; among users of the same type, the model has stronger portability and better universality.
3. The invention identifies the power consumption behavior of the user (monitors the working state of the electric appliance), can help the user to know and obtain the household energy consumption analysis and the running state of the electric appliance, and provides basis and support for implementing intelligent power consumption and automatic demand response; the power grid company is helped to deconstruct the user load, the participation demand response potential of the user can be evaluated in a fine mode, the load side management is enhanced, and the demand response is implemented; the method is beneficial to improving the prediction precision of the power load and providing more accurate data for simulation analysis and system planning of the power system.
Second embodiment of the invention:
as shown in fig. 2, an apparatus 200 for identifying a non-invasive electrical load based on deep learning according to an embodiment of the present invention includes: a data acquisition module 201, a data processing module 202 and a model processing module 203;
the data obtaining module 201 is configured to obtain data, where the data includes: historical load data and external influence factor data;
the data processing module 202 is configured to perform preprocessing on the data, where the preprocessing specifically includes: removing bad values, filling null values, calculating characteristic values and carrying out normalization processing on the historical load data; and carrying out quantization processing on the external influence data;
the model processing module 203 is configured to sequentially input the preprocessed data into a preset deep learning model, a time sequence model and a classification model, output a result, and obtain a result of load identification.
In one embodiment of the present invention, the historical load data includes: total load data and appliance load data; the external factor influence data includes: maximum air temperature, minimum air temperature and date.
Third embodiment of the invention:
an embodiment of the present invention further provides a computer terminal device, including: one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement any of the deep learning based non-intrusive electrical load recognition methods as described above.
It should be noted that the processor may be a Central Processing Unit (CPU), other general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an application-specific programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., the general-purpose processor may be a microprocessor, or the processor may be any conventional processor, the processor is a control center of the terminal device, and various interfaces and lines are used to connect various parts of the terminal device.
The memory mainly includes a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like, and the data storage area may store related data and the like. In addition, the memory may be a high speed random access memory, may also be a non-volatile memory, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card (FlashCard), and the like, or may also be other volatile solid state memory devices.
It should be noted that the terminal device may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the terminal device is only an example and does not constitute a limitation of the terminal device, and may include more or less components, or combine some components, or different components.
The fourth embodiment of the present invention:
an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the deep learning-based non-invasive electrical load identification method according to any of the above.
It should be noted that the computer program may be divided into one or more modules/units (e.g., computer program), and the one or more modules/units are stored in the memory and executed by the processor to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and are not intended to limit the scope of the present invention. It should be understood that any modifications, equivalents, improvements and the like, which come within the spirit and principle of the invention, may occur to those skilled in the art and are intended to be included within the scope of the invention.
Claims (10)
1. A non-invasive electrical load identification method based on deep learning is characterized by comprising the following steps:
obtaining data, wherein the data comprises: historical load data and external influence factor data;
preprocessing the data, wherein the preprocessing specifically comprises: removing bad values, filling null values, calculating characteristic values and carrying out normalization processing on the historical load data; and carrying out quantization processing on the external influence data;
and sequentially inputting the preprocessed data into a preset deep learning model, a time sequence model and a classification model, outputting a result and obtaining a load identification result.
2. The deep learning-based non-invasive electrical load recognition method according to claim 1, wherein the historical load data comprises: total load data and appliance load data; the external factor influence data includes: maximum air temperature, minimum air temperature and date.
3. The deep learning based non-invasive electrical load recognition method according to claim 1, wherein the calculating the characteristic value comprises: calculating a load change value of first preset time as a data change characteristic; calculating the load mean value of the second preset time as the data mean value characteristic; and calculating the load variance value of the third preset time as the data variance characteristic.
4. The deep learning-based non-invasive electrical load identification method according to claim 1, wherein the normalization process adopts the following formula:
wherein D ismaxAnd DminThe sequence maximum and minimum values, respectively.
5. The deep learning-based non-invasive electrical load recognition method according to claim 1, wherein the time sequence model is a preset long-short term memory neural network; wherein, the unit formula of the long-short term memory neural network is as follows:
It＝σ(XtWxi+Ht-1Whi+bi)
Ft＝σ(XtWxf+Ht-1Whf+bf)。
Ot＝σ(XtWxo+Ht-1Who+bo) 。
6. the deep learning-based non-invasive electrical load recognition method according to claim 1, wherein the classification model comprises: support vector machine model, random forest model and multilayer perceptron model.
7. A non-invasive electrical load recognition device based on deep learning, comprising: the system comprises a data acquisition module, a data processing module and a model processing module;
the data acquisition module is configured to acquire data, where the data includes: historical load data and external influence factor data;
the data processing module is configured to perform preprocessing on the data, where the preprocessing specifically includes: removing bad values, filling null values, calculating characteristic values and carrying out normalization processing on the historical load data; and carrying out quantization processing on the external influence data;
and the model processing module is used for sequentially inputting the preprocessed data into a preset deep learning model, a time sequence model and a classification model, outputting a result and obtaining a load identification result.
8. The deep learning based non-invasive electrical load recognition device according to claim 7, wherein the historical load data comprises: total load data and appliance load data; the external factor influence data includes: maximum air temperature, minimum air temperature and date.
9. A computer terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the deep learning based non-intrusive electrical load recognition method as recited in any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the deep learning based non-invasive electrical load recognition method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011366686.8A CN112365090A (en) | 2020-11-26 | 2020-11-26 | Deep learning-based non-invasive electrical load identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011366686.8A CN112365090A (en) | 2020-11-26 | 2020-11-26 | Deep learning-based non-invasive electrical load identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112365090A true CN112365090A (en) | 2021-02-12 |
Family
ID=74535603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011366686.8A Pending CN112365090A (en) | 2020-11-26 | 2020-11-26 | Deep learning-based non-invasive electrical load identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112365090A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113408210A (en) * | 2021-07-12 | 2021-09-17 | 内蒙古电力（集团）有限责任公司乌兰察布电业局 | Deep learning based non-intrusive load splitting method, system, medium, and apparatus |
| CN115130830A (en) * | 2022-06-08 | 2022-09-30 | 山东科技大学 | Non-intrusive load decomposition method based on cascade width learning and sparrow algorithm |
| CN116914760A (en) * | 2023-06-21 | 2023-10-20 | 国网湖北省电力有限公司营销服务中心(计量中心) | Novel power system flexible load response potential quantitative evaluation method based on random forest algorithm |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| CN107122790A (en) * | 2017-03-15 | 2017-09-01 | 华北电力大学 | Non-intrusion type load recognizer based on hybrid neural networks and integrated study |
| CN109598451A (en) * | 2018-12-27 | 2019-04-09 | 东北大学 | A kind of non-intrusion type load discrimination method based on PCA Yu LSTM neural network |
| CN109685314A (en) * | 2018-11-20 | 2019-04-26 | 中国电力科学研究院有限公司 | A kind of non-intruding load decomposition method and system based on shot and long term memory network |
| CN109904854A (en) * | 2019-01-14 | 2019-06-18 | 中国电力科学研究院有限公司 | A kind of home circuit load decomposition method and system of Demand-Oriented response |
| CN110188826A (en) * | 2019-05-31 | 2019-08-30 | 湖南科技大学 | Household electrical appliance operating status non-invasive inspection methods based on intelligent electric meter data |
| CN111199014A (en) * | 2019-12-27 | 2020-05-26 | 国家电网有限公司 | Time sequence based seq2point NILM method and device |
| CN111428755A (en) * | 2020-02-29 | 2020-07-17 | 国网(苏州)城市能源研究院有限责任公司 | Non-invasive load monitoring method |
-
2020
- 2020-11-26 CN CN202011366686.8A patent/CN112365090A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105972761A (en) * | 2016-05-25 | 2016-09-28 | 华北电力大学（保定） | Non-invasive air conditioner load monitoring method |
| CN107122790A (en) * | 2017-03-15 | 2017-09-01 | 华北电力大学 | Non-intrusion type load recognizer based on hybrid neural networks and integrated study |
| CN109685314A (en) * | 2018-11-20 | 2019-04-26 | 中国电力科学研究院有限公司 | A kind of non-intruding load decomposition method and system based on shot and long term memory network |
| CN109598451A (en) * | 2018-12-27 | 2019-04-09 | 东北大学 | A kind of non-intrusion type load discrimination method based on PCA Yu LSTM neural network |
| CN109904854A (en) * | 2019-01-14 | 2019-06-18 | 中国电力科学研究院有限公司 | A kind of home circuit load decomposition method and system of Demand-Oriented response |
| CN110188826A (en) * | 2019-05-31 | 2019-08-30 | 湖南科技大学 | Household electrical appliance operating status non-invasive inspection methods based on intelligent electric meter data |
| CN111199014A (en) * | 2019-12-27 | 2020-05-26 | 国家电网有限公司 | Time sequence based seq2point NILM method and device |
| CN111428755A (en) * | 2020-02-29 | 2020-07-17 | 国网(苏州)城市能源研究院有限责任公司 | Non-invasive load monitoring method |
Non-Patent Citations (3)
| Title |
|---|
| 文武: "基于混合神经网络和集成学习的非侵入式负荷识别算法", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 蒋惠凤: "《中长期电力负荷预测技术与应用》", 31 October 2016, 东南大学出版社 * |
| 赵树平 等: "《海洋渔业3S系统研究与应用》", 31 July 2017, 西安电子科技大学出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113408210A (en) * | 2021-07-12 | 2021-09-17 | 内蒙古电力（集团）有限责任公司乌兰察布电业局 | Deep learning based non-intrusive load splitting method, system, medium, and apparatus |
| CN113408210B (en) * | 2021-07-12 | 2023-08-01 | 内蒙古电力(集团)有限责任公司乌兰察布供电分公司 | Deep learning-based non-invasive load decomposition method, system, medium and equipment |
| CN115130830A (en) * | 2022-06-08 | 2022-09-30 | 山东科技大学 | Non-intrusive load decomposition method based on cascade width learning and sparrow algorithm |
| CN115130830B (en) * | 2022-06-08 | 2024-05-14 | 山东科技大学 | Non-invasive load decomposition method based on cascade width learning and sparrow algorithm |
| CN116914760A (en) * | 2023-06-21 | 2023-10-20 | 国网湖北省电力有限公司营销服务中心(计量中心) | Novel power system flexible load response potential quantitative evaluation method based on random forest algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114298863B (en) | Data acquisition method and system of intelligent meter reading terminal | |
| Harell et al. | Wavenilm: A causal neural network for power disaggregation from the complex power signal | |
| CN112365090A (en) | Deep learning-based non-invasive electrical load identification method and device | |
| CN106936129B (en) | Power load identification method and system based on multi-feature fusion | |
| CN109598451B (en) | Non-invasive load identification method based on PCA (principal component analysis) and LSTM (least Square TM) neural network | |
| Kang et al. | Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters | |
| CN111382789B (en) | Power load identification method and system based on machine learning | |
| CN113126019A (en) | Intelligent ammeter error remote estimation method, system, terminal and storage medium | |
| CN112433907A (en) | Method and device for processing host operation parameter data of uninterruptible power supply and electronic device | |
| CN103018611B (en) | Non-invasive load monitoring method and system based on current decomposition | |
| CN117094478B (en) | Energy scheduling management method, device, equipment and storage medium | |
| Kumar et al. | Data-driven electrical load disaggregation using graph signal processing | |
| CN116861316B (en) | Electrical appliance monitoring method and device | |
| Rueda et al. | Transient event classification based on wavelet neuronal network and matched filters | |
| CN111199014B (en) | Time sequence based seq2point NILM method and device | |
| CN112001578A (en) | Generalized energy storage resource optimization scheduling method and system | |
| CN111898694A (en) | Non-invasive load identification method and device based on random tree classification | |
| CN108964016B (en) | User electric appliance operation condition identification method considering discrete total power consumption data | |
| Chang et al. | Research of power consumers behavior using fuzzy c-means algorithm | |
| CN118539511B (en) | Wind power grid connection power grid control method and device | |
| CN118300101B (en) | Method, apparatus and storage medium for predicting electric load | |
| CN118114137B (en) | Non-invasive load identification method, device and computer storage medium | |
| El Kababji et al. | Power appliance disaggregation framework via hybrid hidden Markov model | |
| CN118399460B (en) | Management method, device, equipment and storage medium of distributed energy storage system | |
| CN115859452B (en) | Data-driven-based transferable load modeling method, device, equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210212 |
|
| RJ01 | Rejection of invention patent application after publication |