CN115018011B - Power load type identification method, device, equipment and storage medium - Google Patents
Power load type identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115018011B CN115018011B CN202210845252.9A CN202210845252A CN115018011B CN 115018011 B CN115018011 B CN 115018011B CN 202210845252 A CN202210845252 A CN 202210845252A CN 115018011 B CN115018011 B CN 115018011B
- Authority
- CN
- China
- Prior art keywords
- power
- load
- data
- electrical appliance
- power data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000005070 sampling Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 23
- 230000005611 electricity Effects 0.000 claims description 5
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 3
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 10
- 238000013135 deep learning Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000004804 winding 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- 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
- Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
- Y04S20/20—End-user application control systems
- Y04S20/242—Home appliances
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention belongs to the technical field of power electronics, and discloses a method, a device, equipment and a storage medium for identifying a power load type. The method comprises the following steps: acquiring sampling power data and a load label corresponding to the sampling power data; constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data; acquiring power data in a power bus; and inputting the power data into a load identification model to obtain the load type of the user. Through the method, a load identification model is constructed, and through experimental data, model training is carried out on the electric load to help a power supplier to determine the load type of a user in real time. The intelligent power grid power consumption habit learning method is beneficial to improving the knowledge of the intelligent power grid on the power consumption habits of the user, can be used for helping the user to master the power consumption conditions of various electrical appliances, and can save power in a targeted manner, so that the power waste is avoided, and the power expenditure of the user is reduced.
Description
Technical Field
The present invention relates to the field of power electronics technologies, and in particular, to a method, an apparatus, a device, and a storage medium for identifying a power load type.
Background
In the context of smart grids, a number of advanced sensing and measurement devices and techniques are used in the monitoring and scheduling of power grids. Due to the rapid development of big data, deep learning and edge computing technology, the intelligent measurement equipment can extract useful information from massive power data, so that loads in a power system can be understood more systematically and deeply, and the management level of the power loads and the safety and the economy of the operation of the power system are improved.
By means of intelligent measuring equipment in a power grid, load identification is paid more and more attention by researchers as a brand new technology in power system monitoring. The decomposition and identification of the power load are beneficial to an electric power system operator to know the load composition of the power system and master the change rule and the development trend of the power load, and the method has very important significance for formulating power planning. However, the prior art can only detect the power utilization condition, cannot accurately identify the type of the power utilization load, and how to accurately identify the type of the power utilization load of the user becomes a technical problem to be solved urgently.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a power load type identification method, a power load type identification device, power load type identification equipment and a storage medium, and aims to solve the technical problem of how to identify a load type without invading an internal electric circuit of a user scene in the prior art.
In order to achieve the above object, the present invention provides a power load type identification method, including the steps of:
acquiring sampling power data and a load label corresponding to the sampling power data;
constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data;
acquiring power data in a power bus;
and inputting the power data into a load identification model to obtain the load type of the user.
Optionally, the constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data includes:
determining a target electrical appliance starting time node according to the sampled power data;
determining characteristic parameters according to the starting time node of the target electrical appliance;
and constructing a load identification model according to the characteristic parameters and the load labels corresponding to the sampled power data.
Optionally, the determining a target electrical appliance turn-on time node according to the sampled power data includes:
calculating the active power of the target electrical appliance according to the sampled power data;
performing convolution calculation on the active power to obtain a calculation result;
and determining the starting time node of the target electrical appliance according to the calculation result.
Optionally, the determining the characteristic parameter according to the target electrical appliance turn-on time node includes:
acquiring target power data of the target electrical appliance starting time node;
determining active power at the starting moment, reactive power at the starting moment, a power factor of the target electrical appliance, active power of the target electrical appliance and reactive power of the target electrical appliance according to the target power data;
and determining characteristic parameters according to the active power at the starting moment, the reactive power at the starting moment, the power factor of the target electrical appliance, the active power of the target electrical appliance and the reactive power of the target electrical appliance.
Optionally, the constructing a load identification model according to the characteristic parameters and the load labels corresponding to the sampled power data includes:
acquiring a load identification model to be trained;
and training the load identification model to be trained according to the characteristic parameters and the load labels corresponding to the sampled power data until the model converges to obtain the load identification model.
Optionally, before acquiring the power data in the power bus, the method further includes:
detecting initial power data in a power bus from a household electricity meter;
and carrying out jitter elimination processing on the initial power data to obtain power data in the power bus.
Optionally, the performing jitter elimination processing on the initial power data to obtain power data in a power bus includes:
performing moving average processing on the initial power data to obtain processed initial power data;
identifying invalid data and error data according to the processed initial power data;
and eliminating the invalid data and the error data from the initial power data to obtain power data in the power bus.
Further, to achieve the above object, the present invention also provides a power load type identification device including:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring sampling power data and a load label corresponding to the sampling power data;
the processing module is used for constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data;
the acquisition module is also used for acquiring power data in the power bus;
and the processing module is also used for inputting the power data into a load identification model to obtain the user load type.
Further, to achieve the above object, the present invention also proposes a power load type identification device including: a memory, a processor and a power load type identification program stored on the memory and executable on the processor, the power load type identification program being configured to implement the steps of the power load type identification method as described above.
Furthermore, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a power load type identification program which, when executed by a processor, implements the steps of the power load type identification method as described above.
The method comprises the steps of obtaining sampled power data and a load label corresponding to the sampled power data; constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data; acquiring power data in a power bus; and inputting the power data into a load identification model to obtain the load type of the user. Through the method, a load identification model is constructed, and through experimental data, model training is carried out on the electric load to help a power supplier to determine the load type of a user in real time. The intelligent power grid power consumption habit learning method is beneficial to improving the knowledge of the intelligent power grid on the power consumption habits of the user, can be used for helping the user to master the power consumption conditions of various electrical appliances, and can save power in a targeted manner, so that the power waste is avoided, and the power expenditure of the user is reduced.
Drawings
Fig. 1 is a schematic structural diagram of a power load type identification device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of a method for identifying a type of an electrical load according to the present invention;
FIG. 3 is a flowchart illustrating a power load type identification method according to a second embodiment of the present invention;
FIG. 4 is a schematic overall flowchart of an embodiment of the power load type identification apparatus of the present invention;
fig. 5 is a block diagram showing the structure of a first embodiment of the power load type identification device according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a power load type identification device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the power load type identification device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
It will be appreciated by those skilled in the art that the configuration shown in fig. 1 does not constitute a limitation of the power load type identification device, and may include more or less components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a power load type identification program.
In the power load type identification device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the power load type identification device of the present invention may be provided in the power load type identification device that calls the power load type identification program stored in the memory 1005 through the processor 1001 and executes the power load type identification method provided by the embodiment of the present invention.
An embodiment of the present invention provides a method for identifying a power load type, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the method for identifying a power load type according to the present invention.
In this embodiment, the method for identifying the type of the power load includes the following steps:
step S10: and acquiring sampling power data and a load label corresponding to the sampling power data.
It should be noted that an execution subject of this embodiment is a smart grid management system, and the smart grid management system may be a system composed of a non-invasive electrical signal acquisition device and a data processing device, and may also be other devices with the same or similar functions, which is not limited in this embodiment.
It can be understood that, in the context of the application of the present embodiment to the smart grid, in a scenario where there is a need to identify a power consumption habit of a user, the present embodiment is mainly applied to provide a data processing basis for non-invasive compliance identification, where non-invasive load identification refers to installing a load monitoring device outside a factory building or a home of the user, usually on an electricity meter of the user, and detecting and identifying an electrical load inside the user on the basis that the user does not need to know and master the type of an electrical appliance owned by the user. Since the installation difficulty of the invasive load identification is high and the cooperation of users is required, the non-invasive load identification method attracts more attention and obtains a plurality of research results. The non-invasive load monitoring is one of key technologies for smart grid fine management, and a power grid operator who recognizes the non-invasive load can master and know the operation state of a power system at any time, monitor the power consumption behavior of families or factories in a district, arrange reasonable power dispatching planning and predict the power consumption condition of users in the district. Through monitoring information such as the type and the running state of electric equipment of a user in real time, the non-invasive load monitoring technology provides an important reference basis for efficient electric energy dispatching and power grid structure optimization. Meanwhile, the load monitoring result can help the user to master the running condition and the power consumption information of the household appliance, and important reference is provided for reasonable power utilization of the user and avoiding power waste. Therefore, it is of far reaching importance to study the recognition of non-invasive loads.
It should be noted that the sampled power data is power data detected by the electrical appliance for testing through a non-invasive detection means, where the power data may include one or more sets of power data such as current information, voltage information, phase angle information, and the like in the power utilization bus of the user.
In addition, the load label corresponding to the sampled power data is the type of the electrical appliance for testing corresponding to the sampled power data, and the load label is associated with the sampled power data to provide a data sample for training of the load identification model.
Step S20: and constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data.
It can be understood that the process of constructing the load identification model according to the sampled power data and the load labels corresponding to the sampled power data is mainly divided into two parts, namely feature extraction and model training. This is because the sampled power data just collected cannot be directly used as the characteristic parameters of the input model, and the power data needs to be preprocessed and extracted, for example: the power is an important reference factor for load identification, so that smoothing processing and denoising can be performed according to the current and the voltage in the sampled power data, and then the power characteristic is obtained through calculation to form a characteristic parameter which can be used for training a model.
It should be noted that after the characteristic parameters are obtained, the model can be trained according to the characteristic parameters, the output result of the model is judged through the load labels, the loss value is calculated according to the result, the intermediate parameters in the model are adjusted according to the loss value, and the process is repeated until the model converges, so that the construction of the load identification model can be completed.
Step S30: and acquiring power data in the power bus.
It should be noted that the power data in the power bus is the power data in the actual user usage scenario, and the method for acquiring the power data in the power bus is to first acquire the data on the power bus of the detected user through the block chain. The data is processed according to the processing steps designed in the first part of data acquisition; then, an acquisition device externally connected to a user electric meter uploads the electric power data of the user to an electric power block chain; finally, the embodiment obtains the voltage and current data to be detected after preprocessing on the power bus through the data search function of the power block chain. Wherein the power data may be obtained from a power block chain.
In the embodiment, initial power data in a power bus is detected from a household electricity meter; and carrying out jitter elimination processing on the initial power data to obtain power data in the power bus.
It should be noted that, since the directly collected initial data is unstable and may have a lot of noise, the directly collected initial power data needs to be preprocessed, and the main task of this part is to measure and collect the power data of the user. The main function of the part is to sample the current and the voltage on the power bus of the monitored user at low frequency by using a measuring device arranged at a household electric meter; then preprocessing the acquired power data; finally, the processed data is sent to the power block chain for use by the load identification function.
In this embodiment, performing a moving average process on the initial power data to obtain processed initial power data; identifying invalid data and error data according to the processed initial power data; and eliminating the invalid data and the error data from the initial power data to obtain power data in the power bus.
It can be understood that the current I and voltage V data in the measured initial point data are jittered due to the large randomness and instability of the operation state of the power system. For this purpose, the acquired data is processed in a moving average mode in the step, and data jitter is eliminated. The specific calculation method is as follows:
wherein Vt and It are the processing result after eliminating the jitter at the time t; vi and Ii are original sampling results at the moment i; t is a parameter of the moving average algorithm for specifying how long the data over a time span is used for moving average.
In addition, due to the unstable working state of the measuring equipment, the situation that data is not collected occasionally occurs. Aiming at the problem, two effective data before and after the moment of lacking numerical values are used for averaging in the step, and the data which are not collected are supplemented. And finally, removing invalid data and error data, and supplementing the removed data by using the difference method, so that the data quality is improved, and the data confusion are avoided. And uploading the processed voltage and current data (power data) to a power block chain, and performing chain winding operation on the data to realize persistent storage of the acquired data.
Step S40: and inputting the power data into a load identification model to obtain the load type of the user.
It should be noted that inputting the power data and the trained load recognition model can obtain the user load type of the model output. The user load type is the type of the electrical appliance used by the user.
The embodiment acquires sampling power data and a load tag corresponding to the sampling power data; constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data; acquiring power data in a power bus; and inputting the power data into a load identification model to obtain the load type of the user. Through the method, a load identification model is constructed, and through experimental data, model training is carried out on the electric load to help a power supplier to determine the load type of a user in real time. The intelligent power grid power consumption habit learning method is beneficial to improving the knowledge of the intelligent power grid on the power consumption habits of the user, can be used for helping the user to master the power consumption conditions of various electrical appliances, and can save power in a targeted manner, so that the power waste is avoided, and the power expenditure of the user is reduced.
Referring to fig. 3, fig. 3 is a flowchart illustrating a method for identifying a type of an electrical load according to a second embodiment of the present invention.
Based on the first embodiment, in the step S20, the method for identifying the type of the power load according to this embodiment further includes:
step S21: and determining a target electrical appliance starting time node according to the sampled power data.
It should be noted that the target appliance is the appliance used for the test.
It should be noted that before training, feature extraction needs to be performed on the sampled power data, and feature data before and after the electrical appliance is turned on is extracted, so that the turn-on time needs to be determined to help the system to screen the feature data, and the collected feature parameters are further used to train the load recognition model. The main function of the part is to detect the electric appliance starting event from the electric power data of the monitored user; then, intercepting a current and voltage time sequence of a period of time before and after the electric appliance is started, and performing feature extraction; and finally, training a load identification model based on a deep learning technology by using the characteristic data when the electric appliance is started.
In the embodiment, the active power of the target electrical appliance is calculated according to the sampled power data; performing convolution calculation on the active power to obtain a calculation result; and determining the starting time node of the target electrical appliance according to the calculation result.
Specifically, the starting time node of the target electrical appliance is obtained, and the following preferred scheme is proposed in this embodiment, for example: downloading sequence data of voltage V, current I and phase angle phi of electric power data from the electric power block chain, and calculating to obtain active power consumption and reactive power consumption of the electric appliance, wherein the calculation formula is as follows:
wherein, pt and Qt are the active power consumption and the reactive power consumption of the electric appliance at the moment t respectively.
This step then detects the on state of the appliance. The detection method comprises the following steps:
firstly, setting the time window width of opening event detection to be Tw, and further constructing a one-dimensional convolution kernel K = [1,1, …,1, -1, …, -1, -1], wherein K has Tw elements in total, and 1 and-1 respectively account for half of the number.
The convolution calculation is performed according to the following formula:
wherein Zt is a result for next electric appliance starting detection; pi is the active power on the bus of the user electric meter at the ith moment; k (i + TW/2) is the i + TW/2 th element in the one-dimensional convolution kernel K. And acquiring the obtained calculation result Z, and obtaining the time t _ max corresponding to the maximum value in the result. The moment at which the appliance is turned on at this moment is t _ max.
Step S22: and determining characteristic parameters according to the starting time node of the target electrical appliance.
It should be noted that, in order to pursue the accuracy of feature extraction, feature extraction needs to be performed according to the on-time node of the target appliance, and the on-time node is actually a means for feature classification.
In the embodiment, target power data of the target electrical appliance starting time node is obtained; determining active power at the starting moment, reactive power at the starting moment, a power factor of the target electrical appliance, active power of the target electrical appliance and reactive power of the target electrical appliance according to the target power data; and determining characteristic parameters according to the active power at the starting moment, the reactive power at the starting moment, the power factor of the target electrical appliance, the active power of the target electrical appliance and the reactive power of the target electrical appliance.
In a specific implementation, in the process of feature extraction, the following preferred scheme is proposed in the present implementation: around the time t _ max, the characteristics of the switched-on appliance are extracted. The extracted features include: active power of electric appliance
Reactive power
Power factor F, and active power and reactive power before and after the turn-on time. Specifically, the calculation formula of each feature is as follows:
the active power and the reactive power of the electric appliance before and after the starting time are as follows:
and finally, combining all the extracted characteristics to obtain the characteristics of the finally started electric appliance at the time t _ max.
Step S23: and constructing a load identification model according to the characteristic parameters and the load labels corresponding to the sampled power data.
It should be noted that as deep learning techniques develop and advance, more and more fields begin to use deep learning and have a series of successes. Therefore, in the patent, a non-invasive load identification model is constructed by utilizing a deep learning technology based on the electrical appliance characteristics obtained in the last step. Specifically, in the training stage of the recognition model, the feature vector of the electric appliance starting time obtained in the previous step is marked with corresponding electric appliance type information, and then training data are obtained
Wherein Y is the corresponding appliance type. And then, constructing a deep learning classification model on the training data, wherein the input of the model is a characteristic vector when the electric appliance is turned on, and the prediction output of the model is the type of the electric appliance.
The model obtained in this step can be formally expressed as follows:
in the formula
And (4) constructing a load detection model for deep learning, wherein y is a detection result output by the model.
In the embodiment, a load identification model to be trained is obtained; and training the load identification model to be trained according to the characteristic parameters and the load labels corresponding to the sampled power data until the model converges to obtain the load identification model.
In the concrete implementation, the training process of the model is to train the load recognition model to be trained according to the extracted features, input the extracted feature parameters into the load recognition model to be trained, calculate the loss value according to the output result, adjust the weight parameters in the load recognition model to be trained according to the loss value, and repeat the steps until the model converges to obtain the accurate load recognition model, wherein the whole using process of the model is as shown in fig. 4.
The embodiment determines a target electrical appliance starting time node according to the sampled power data; determining characteristic parameters according to the starting time node of the target electrical appliance; and constructing a load identification model according to the characteristic parameters and the load labels corresponding to the sampled power data. By the method, the load identification model is constructed, the electric appliance starting time node is introduced, characteristics of the electric appliance before and after the electric appliance is started are extracted through the electric appliance starting time node, model training is completed, and the accuracy of load identification is improved.
Furthermore, an embodiment of the present invention further provides a storage medium, where a power load type identification program is stored, and the power load type identification program implements the steps of the power load type identification method as described above when executed by a processor.
Referring to fig. 5, fig. 5 is a block diagram illustrating a first embodiment of the power load type identifier according to the present invention.
As shown in fig. 5, the power load type identification apparatus according to the embodiment of the present invention includes:
the acquiring module 10 is configured to acquire sampled power data and a load tag corresponding to the sampled power data;
the processing module 20 is configured to construct a load identification model according to the sampled power data and the load tag corresponding to the sampled power data;
the obtaining module 10 is further configured to obtain power data in a power bus;
the processing module 20 is further configured to input the power data into a load identification model to obtain a user load type.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
The embodiment acquiring module 10 acquires sampled power data and a load tag corresponding to the sampled power data; the processing module 20 constructs a load identification model according to the sampled power data and the load label corresponding to the sampled power data; the obtaining module 10 obtains power data in the power bus; the processing module 20 inputs the power data into the load identification model to obtain the user load type. Through the method, a load identification model is constructed, and through experimental data, model training is carried out on the electric load to help a power supplier to determine the load type of a user in real time. The intelligent power grid power consumption habit learning method is beneficial to improving the knowledge of the intelligent power grid on the power consumption habits of the user, can be used for helping the user to master the power consumption conditions of various electrical appliances, and can save power in a targeted manner, so that the power waste is avoided, and the power expenditure of the user is reduced.
In this embodiment, the processing module 20 is further configured to determine a target electrical appliance turn-on time node according to the sampled power data;
determining characteristic parameters according to the starting time node of the target electrical appliance;
and constructing a load identification model according to the characteristic parameters and the load labels corresponding to the sampled power data.
In this embodiment, the processing module 20 is further configured to calculate an active power of the target electrical appliance according to the sampled power data;
performing convolution calculation on the active power to obtain a calculation result;
and determining the starting time node of the target electrical appliance according to the calculation result.
In this embodiment, the processing module 20 is further configured to obtain target power data of the target electrical appliance on-time node;
determining active power at the starting moment, reactive power at the starting moment, a power factor of the target electrical appliance, active power of the target electrical appliance and reactive power of the target electrical appliance according to the target power data;
and determining characteristic parameters according to the active power at the starting moment, the reactive power at the starting moment, the power factor of the target electrical appliance, the active power of the target electrical appliance and the reactive power of the target electrical appliance.
In this embodiment, the processing module 20 is further configured to obtain a load recognition model to be trained;
and training the load identification model to be trained according to the characteristic parameters and the load labels corresponding to the sampled power data until the model converges to obtain the load identification model.
In this embodiment, the processing module 20 is further configured to detect initial power data in a power bus from a service electricity meter;
and carrying out jitter elimination processing on the initial power data to obtain power data in the power bus.
In this embodiment, the processing module 20 is further configured to perform a moving average processing on the initial power data to obtain processed initial power data;
identifying invalid data and error data according to the processed initial power data;
and eliminating the invalid data and the error data from the initial power data to obtain power data in the power bus.
It should be noted that the above-mentioned work flows are only illustrative and do not limit the scope of the present invention, and in practical applications, those skilled in the art may select some or all of them according to actual needs to implement the purpose of the solution of the present embodiment, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may refer to the power load type identification method provided in any embodiment of the present invention, and are not described herein again.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. A power load type identification method, characterized by comprising:
acquiring sampling power data and a load label corresponding to the sampling power data;
constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data;
acquiring power data in a power bus;
inputting the power data into a load identification model to obtain a user load type;
wherein, the constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data comprises:
determining a target electrical appliance starting time node according to the sampled power data;
determining characteristic parameters according to the starting time node of the target electrical appliance;
constructing a load identification model according to the characteristic parameters and the load labels corresponding to the sampled power data;
wherein, the determining the characteristic parameters according to the target electrical appliance starting time node comprises:
acquiring target power data of the target electrical appliance starting time node;
determining active power at the starting moment, reactive power at the starting moment, a power factor of the target electrical appliance, active power of the target electrical appliance and reactive power of the target electrical appliance according to the target power data;
determining characteristic parameters according to the active power at the starting time, the reactive power at the starting time, the power factor of the target electrical appliance, the active power of the target electrical appliance and the reactive power of the target electrical appliance, wherein the characteristic of the starting time of the target electrical appliance is
，
Is the time of the turning-on of the target appliance,
is the active power of the target electrical appliance,
is the reactive power of the target appliance, F is the power factor of the target appliance,
is a stand forThe active power at the moment of the start-up,
the reactive power at the starting moment;
wherein, the determining the target electrical appliance starting time node according to the sampled power data comprises:
calculating the active power of the target electrical appliance according to the sampled power data;
performing convolution calculation on the active power to obtain a calculation result, wherein the convolution calculation formula is
In the formula, the window width of the event for detecting the opening event of the target electrical appliance is set to
Further, a one-dimensional convolution kernel K = [1,1, …,1, -1, …, -1 is constructed]In which K is shared
Each of elements, 1 and-1, in half the number,
calculating results for detecting the starting of the target electrical appliance;
is as follows
At any moment, the active power on the bus of the user electric meter;
is the first in a one-dimensional convolution kernel K
An element;
and determining the starting time node of the target electrical appliance according to the calculation result.
2. The method of claim 1, wherein the constructing a load identification model from the characteristic parameters and load labels corresponding to the sampled power data comprises:
acquiring a load identification model to be trained;
and training the load identification model to be trained according to the characteristic parameters and the load labels corresponding to the sampled power data until the model converges to obtain the load identification model.
3. The method of claim 1 or 2, wherein prior to obtaining power data in the power bus, further comprising:
detecting initial power data in a power bus from a household electricity meter;
and carrying out jitter elimination processing on the initial power data to obtain power data in the power bus.
4. The method of claim 3, wherein de-jittering the initial power data to obtain power data in a power bus comprises:
performing moving average processing on the initial power data to obtain processed initial power data;
identifying invalid data and error data according to the processed initial power data;
and eliminating the invalid data and the error data from the initial power data to obtain power data in the power bus.
5. An electric load type identification device, characterized in that the electric load type identification device comprises:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring sampling power data and a load label corresponding to the sampling power data;
the processing module is used for constructing a load identification model according to the sampled power data and the load label corresponding to the sampled power data;
the acquisition module is also used for acquiring power data in the power bus;
the processing module is further used for inputting the power data into a load identification model to obtain a user load type;
the processing module is further used for determining a target electrical appliance starting time node according to the sampled power data;
determining characteristic parameters according to the starting time node of the target electrical appliance;
constructing a load identification model according to the characteristic parameters and the load labels corresponding to the sampled power data;
the processing module is further used for acquiring target power data of the target electrical appliance starting time node;
determining active power at the starting moment, reactive power at the starting moment, a power factor of the target electrical appliance, active power of the target electrical appliance and reactive power of the target electrical appliance according to the target power data;
determining characteristic parameters according to the active power at the starting moment, the reactive power at the starting moment, the power factor of the target electrical appliance, the active power of the target electrical appliance and the reactive power of the target electrical appliance, wherein the characteristic at the starting moment of the target electrical appliance is
，
Is the time of the turning-on of the target appliance,
is the active power of the target electrical appliance,
reactive power for the target applianceAnd F is the power factor of the target appliance,
for the active power at the moment of said switching on,
reactive power for the starting moment;
wherein, the determining the target electrical appliance starting time node according to the sampled power data comprises:
calculating the active power of the target electrical appliance according to the sampled power data;
performing convolution calculation on the active power to obtain a calculation result, wherein the convolution calculation formula is
Wherein the window width of the event for detecting the opening event of the target electrical appliance is set to
Further, a one-dimensional convolution kernel K = [1,1, …,1, -1, …, -1 is constructed]In which K is shared
Each of elements, 1 and-1, in half the number,
calculating results for detecting the starting of the target electrical appliance;
is as follows
At any moment, the active power on the bus of the user electric meter;
is the first in a one-dimensional convolution kernel K
An element;
and determining the starting time node of the target electrical appliance according to the calculation result.
6. An electric load type identification device, characterized in that the device comprises: memory, a processor and a power load type identification program stored on the memory and executable on the processor, the power load type identification program being configured to implement the steps of the power load type identification method as claimed in any one of claims 1 to 4.
7. A storage medium having stored thereon a power load type identification program which, when executed by a processor, implements the steps of the power load type identification method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210845252.9A CN115018011B (en) | 2022-07-19 | 2022-07-19 | Power load type identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210845252.9A CN115018011B (en) | 2022-07-19 | 2022-07-19 | Power load type identification method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115018011A CN115018011A (en) | 2022-09-06 |
| CN115018011B true CN115018011B (en) | 2022-11-29 |
Family
ID=83080252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210845252.9A Active CN115018011B (en) | 2022-07-19 | 2022-07-19 | Power load type identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115018011B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091536A (en) * | 2021-11-19 | 2022-02-25 | 上海梦象智能科技有限公司 | Load decomposition method based on variational self-encoder |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10325150B2 (en) * | 2012-08-29 | 2019-06-18 | Eaton Intelligent Power Limited | System and method for electric load identification and classification employing support vector machine |
| CN105186693A (en) * | 2015-09-28 | 2015-12-23 | 南方电网科学研究院有限责任公司 | Non-intrusive mode electrical load identification system and method |
| CN110954744A (en) * | 2019-11-18 | 2020-04-03 | 浙江工业大学 | Non-invasive load monitoring method based on event detection |
| CN111242391B (en) * | 2020-03-06 | 2023-10-31 | 云南电网有限责任公司电力科学研究院 | Machine learning model training method and system for power load identification |
| WO2022141330A1 (en) * | 2020-12-31 | 2022-07-07 | Guizhou Power Grid Company Limited | A non-intrusive load identification method based on fingerprint characteristics of load power |
| CN113901973A (en) * | 2021-09-29 | 2022-01-07 | 北京智芯微电子科技有限公司 | Power load identification method and device, storage medium and chip equipment |
-
2022
- 2022-07-19 CN CN202210845252.9A patent/CN115018011B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091536A (en) * | 2021-11-19 | 2022-02-25 | 上海梦象智能科技有限公司 | Load decomposition method based on variational self-encoder |
Non-Patent Citations (1)
| Title |
|---|
| 基于卷积神经网络的非侵入负荷辨识算法;张玉天等;《电网技术》;20200630;第44卷(第06期);第2038-2044页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115018011A (en) | 2022-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Athanasiadis et al. | Real-time non-intrusive load monitoring: A light-weight and scalable approach | |
| US11002773B2 (en) | Monitoring apparatus, monitoring method, and storage medium | |
| CN114977176B (en) | Power load decomposition method, device, equipment and storage medium | |
| CN111985824A (en) | Non-invasive load monitoring method and monitoring equipment for intelligent ammeter box | |
| Holweger et al. | Unsupervised algorithm for disaggregating low-sampling-rate electricity consumption of households | |
| CN112149510A (en) | Non-invasive load detection method | |
| CN109447473B (en) | Power load monitoring method, device, equipment and readable storage medium | |
| US10942205B2 (en) | Method and system for analyzing electricity consumption | |
| US20150355247A1 (en) | Apparatus, server, system and method for energy measuring | |
| CN111178393A (en) | Electric appliance power consumption classification metering method and device based on intelligent electric meter | |
| Ghosh et al. | Non-intrusive identification of harmonic polluting loads in a smart residential system | |
| US20160109492A1 (en) | Method and system for analysing electricity consumption | |
| CN109377052B (en) | Power load matching method, device, equipment and readable storage medium | |
| EP2840402B1 (en) | Operating state estimating device for electrical apparatus, operating state estimating method for electrical apparatus, program, feature vector registration device for electrical apparatus, feature vector registration method for electrical apparatus, server apparatus, and operating state estimating system for electrical apparatus | |
| Welikala et al. | A real-time non-intrusive load monitoring system | |
| CN115018011B (en) | Power load type identification method, device, equipment and storage medium | |
| Azizi et al. | Quantification of disaggregation difficulty with respect to the number of smart meters | |
| CN116681186B (en) | Power quality analysis method and device based on intelligent terminal | |
| CN111934318A (en) | Non-invasive power load decomposition method, device, equipment and storage medium | |
| CN111784042A (en) | Power utilization node safety risk prediction method and device and storage medium | |
| TWI504095B (en) | Non - invasive load monitoring system and its method | |
| Held et al. | Parameter optimized event detection for NILM using frequency invariant transformation of periodic signals (FIT-PS) | |
| CN115454466A (en) | Method, apparatus, device and medium for automatic updating of machine learning model | |
| Kommey et al. | An artificial intelligence‐based non‐intrusive load monitoring of energy consumption in an electrical energy system using a modified K‐Nearest Neighbour algorithm | |
| CN113011482A (en) | Non-invasive load identification method, terminal device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |