CN115859452A - Transferable load modeling method, device, equipment and medium based on data driving - Google Patents
Transferable load modeling method, device, equipment and medium based on data driving Download PDFInfo
- Publication number
- CN115859452A CN115859452A CN202310134024.5A CN202310134024A CN115859452A CN 115859452 A CN115859452 A CN 115859452A CN 202310134024 A CN202310134024 A CN 202310134024A CN 115859452 A CN115859452 A CN 115859452A
- Authority
- CN
- China
- Prior art keywords
- clustering
- transferable load
- data set
- processed data
- transferable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a transferable load modeling method, a transferable load modeling device, transferable load modeling equipment and transferable load modeling media based on data driving, which relate to the field of building load flexibility and comprise the following steps: acquiring actual operation data of a transferable load, and preprocessing the actual operation data to obtain a processed data set; determining the operation duration of single continuous operation of the transferable load from the processed data set, and performing clustering analysis on the processed data set by taking the operation duration as a characteristic vector to obtain a clustering curve result; and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration. Through the technical scheme, the power model of the transferable load of the residential building can be accurately established.
Description
Technical Field
The invention relates to the field of building load flexibility, in particular to a transferable load modeling method, a transferable load modeling device, transferable load modeling equipment and transferable load modeling media based on data driving.
Background
The continuous improvement of the power generation permeability of intermittent renewable energy sources such as photovoltaic power generation and wind power generation brings huge challenges to the stable operation of a power grid. Usually, energy storage is needed to be configured on the power generation side, so that the flexibility of the system is improved, redundant renewable intermittent renewable energy power is stored, the consumption of the renewable energy power is improved, and the stable operation of a power grid is ensured. However, the energy storage cost is high, so that the large-scale application in engineering is difficult at present. One of the more economical ways is to excavate and utilize the flexibility of the user demand side load. Transferable loads such as washing machines, dryers and dishwashers on the demand side of residential buildings have a great potential for flexibility through the bunching effect. The current methods for modeling the transferable loads of the residential building are all simple, and are all assumed by assuming that the power of the transferable loads is a constant value in the whole operation period. However, during actual operation, the power consumption of the transferable load is not a constant value, but varies with the operation mode and the operation stage.
From the above, how to establish a power model of a house building transferable load is a problem to be solved in the field.
Disclosure of Invention
In view of the above, the present invention provides a transferable load modeling method, apparatus, device and medium based on data driving, which can construct a rapid modeling tool for transferable loads of residential buildings. The specific scheme is as follows:
in a first aspect, the application discloses a transferable load modeling method based on data driving, which includes:
acquiring actual operation data of a transferable load, and preprocessing the actual operation data to obtain a processed data set;
determining the operation duration of single continuous operation of the transferable load from the processed data set, and performing clustering analysis on the processed data set by taking the operation duration as a characteristic vector to obtain a clustering curve result;
and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration.
Optionally, the preprocessing the actual operation data to obtain a processed data set includes:
determining missing values, abnormal values and noise values from the actual operation data;
and respectively processing the missing value, the abnormal value and the noise value by adopting a Lagrange difference method, a box type graph method and a Kalman filtering algorithm to obtain a processed data set.
Optionally, the determining the operation duration of the single continuous operation of the transferable load from the processed data set includes:
and performing characteristic parameter extraction operation on the actual operation data to obtain the operation duration of the single continuous operation of the transferable load.
Optionally, the performing cluster analysis on the processed data set by using the operating duration as a feature vector to obtain a clustering curve result includes:
performing clustering analysis on the processed data set by taking the running duration as a characteristic vector to obtain a clustering curve result;
and determining each operation mode based on the clustering curve result so as to obtain power utilization curves in different operation modes.
Optionally, the determining each operation mode based on the clustering curve result to obtain the power utilization curves in different operation modes includes:
and taking the running time as a characteristic vector, and then carrying out clustering analysis operation on the processed data set by adopting a K-means clustering algorithm to obtain power utilization curves in different running modes.
Optionally, the performing a cluster analysis operation on the processed data set by using a K-means clustering algorithm to obtain power consumption curves in different operation modes includes:
selecting different clustering center quantities by adopting an enumeration method to cluster the processed data set, and evaluating clustering curve results under the different clustering center quantities by adopting an outline coefficient index and a Theisenbergin index so as to determine the optimal clustering center quantity from the different clustering center quantities;
and taking the running time and the optimal clustering center number as input, and carrying out clustering operation on the processed data set by adopting a K-means clustering algorithm to obtain power utilization curves in different running modes.
Optionally, after the constructing the transferable load power model based on the power and the duration, the method further includes:
analyzing and calculating the transferable load power model to obtain parameters of the transferable load power model;
and sending the parameters to a client according to a preset parameter display method.
In a second aspect, the present application discloses a transferable load modeling apparatus based on data driving, including:
the data processing module is used for acquiring actual operation data of the transferable load and preprocessing the actual operation data to obtain a processed data set;
the cluster analysis module is used for determining the running time of single continuous running of the transferable load from the processed data set and carrying out cluster analysis on the processed data set by taking the running time as a characteristic vector to obtain a cluster curve result;
and the model construction module is used for determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result and constructing the transferable load power model based on the power and the continuous operation duration.
In a third aspect, the present application discloses an electronic device, comprising:
a memory for storing a computer program;
and the processor is used for executing the computer program to realize the transferable load modeling method based on the data drive.
In a fourth aspect, the present application discloses a computer storage medium for storing a computer program; wherein the computer program realizes the steps of the data-driven transferable load modeling method disclosed in the foregoing when executed by a processor.
The method comprises the steps of obtaining actual operation data of a transferable load, and preprocessing the actual operation data to obtain a processed data set; determining the operation duration of single continuous operation of the transferable load from the processed data set, and performing clustering analysis on the processed data set by taking the operation duration as a characteristic vector to obtain a clustering curve result; and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration. The method for the data-driven modeling of the transferable loads of the residential building is provided by utilizing the actual operation characteristics of the transferable loads of the residential building based on a K-means clustering method, the accuracy of a model is effectively improved, a tool for quickly modeling the transferable loads of the residential building is developed through programming languages such as Python and the like, the operation data of the transferable loads of the residential building are input into the tool, the tool can immediately obtain the modeling result of the transferable loads through calculation, and the established model of the transferable loads of the residential building is higher in accuracy, has universality and can be popularized and applied.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a data-driven transferable load modeling method disclosed herein;
FIG. 2 is a flow chart of a transferable load modeling method based on data driving disclosed in the present application;
FIG. 3 is a conceptual model operational characteristic diagram of load shifting as disclosed herein;
FIG. 4 is an exemplary graph of clustering curve results for different numbers of clustering centers disclosed in the present application;
FIG. 5 is an exemplary graph of clustering curve results for an optimal number of clustering centers as disclosed herein;
FIG. 6 is an exemplary graph of a power curve modeled for shifting loads as disclosed herein;
FIG. 7 is a schematic structural diagram of a data-driven transferable load modeling apparatus according to the present disclosure;
fig. 8 is a block diagram of an electronic device provided in the present application.
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.
The continuous improvement of the power generation permeability of intermittent renewable energy sources such as photovoltaic power generation and wind power generation brings huge challenges to the stable operation of a power grid. Usually, energy storage is required to be configured on the power generation side, the flexibility of the system is improved, redundant renewable intermittent renewable energy power is stored, the consumption of the renewable energy power is improved, and the stable operation of a power grid is ensured. However, the energy storage cost is high, so that the large-scale application in engineering is difficult at present. One of the more economical ways is to excavate and utilize the flexibility of the user demand side load. Transferable loads such as washing machines, dryers and dishwashers on the demand side of residential buildings have a great potential for flexibility through the bunching effect. The current modeling methods for the transferable loads of the residential buildings are all simple and all adopt a hypothetical method, and the power of the transferable loads in the whole operation period is assumed to be constant. However, during actual operation, the power consumption of the transferable load is not a constant value, but varies with the operation mode and the operation stage. From the above, how to establish a power model of a house building transferable load is a problem to be solved in the field.
Referring to fig. 1, an embodiment of the present invention discloses a transferable load modeling method based on data driving, which may specifically include:
step S11: and acquiring actual operation data of the transferable load, and preprocessing the actual operation data to obtain a processed data set.
Step S12: and determining the running time of the single continuous running of the transferable load from the processed data set, and carrying out cluster analysis on the processed data set by taking the running time as a characteristic vector to obtain a cluster curve result.
In this embodiment, a characteristic parameter extraction operation is performed on the actual operation data to obtain an operation duration of single continuous operation of the transferable load, and then the operation duration is used as a characteristic vector to perform cluster analysis on the processed data set to obtain a clustering curve result. Specifically, the operating duration is used as a feature vector to perform clustering analysis on the processed data set to obtain a clustering curve result, and then each operating mode is determined based on the clustering curve result to obtain power utilization curves in different operating modes. Generally, washing machines, dryers, dishwashers and the like have different modes of operation for transferable loads. Taking a washing machine as an example, the operation modes of the washing machine generally include: a normal mode, a power mode, a surf wash mode, a quick wash mode, a laundry mode, a rinse mode, etc. And each operation mode lasts for different time, so that the operation mode of the house building capable of transferring load can be identified through the clustering curve result.
In this embodiment, the running duration is selected as a characteristic parameter, and the running duration of each time of the transferable load can be extracted from the processed data set.
In this embodiment, the running duration is used as a feature vector, and then a K-means clustering algorithm is used to perform clustering analysis on the processed data set, so as to obtain power utilization curves in different running modes.
The specific process of the K-means clustering algorithm is as follows: selecting different clustering center quantities by adopting an enumeration method to cluster the processed data set, and evaluating clustering curve results under the different clustering center quantities by adopting an outline coefficient index and a Theisenbergin index so as to determine the optimal clustering center quantity from the different clustering center quantities; and taking the running time and the optimal clustering center number as input, and carrying out clustering operation on the processed data set by adopting a K-means clustering algorithm to obtain power utilization curves in different running modes.
Step S13: and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration.
In the embodiment, actual operation data of transferable loads are obtained, and the actual operation data are preprocessed to obtain a processed data set; determining the running time of single continuous running of the transferable load from the processed data set, and performing clustering analysis on the processed data set by taking the running time as a characteristic vector to obtain a clustering curve result; and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration. The method for the data-driven modeling of the transferable loads of the residential building is provided by utilizing the actual operation characteristics of the transferable loads of the residential building based on a K-means clustering method, the accuracy of a model is effectively improved, a tool for quickly modeling the transferable loads of the residential building is developed through programming languages such as Python and the like, the operation data of the transferable loads of the residential building are input into the tool, the tool can immediately obtain the modeling result of the transferable loads through calculation, and the established model of the transferable loads of the residential building is higher in accuracy, has universality and can be popularized and applied.
Referring to fig. 2, an embodiment of the present invention discloses a transferable load modeling method based on data driving, which may specifically include:
step S21: acquiring actual operation data of a transferable load, determining a missing value, an abnormal value and a noise value from the actual operation data, and then respectively processing the missing value, the abnormal value and the noise value by adopting a Lagrangian difference method, a box type graph method and a Kalman filtering algorithm to obtain a processed data set.
In this embodiment, gather the actual operation data that residential building can shift load high resolution, along with intelligent house, intelligent household electrical appliances, smart jack and internet of things's rapid development, it will become more and more convenient to obtain the actual operation data that can shift load such as washing machine, drying-machine, dish washer. After actual operation data of load transfer are obtained, processing missing values of the actual operation data by adopting a Lagrange difference method; processing the abnormal value of the actual operation data by adopting a box graph method; and processing the noise value of the actual operation data by adopting a Kalman filtering algorithm, thereby improving the quality of the data set.
Step S22: and determining the running time of the single continuous running of the transferable load from the processed data set, and carrying out cluster analysis on the processed data set by taking the running time as a characteristic vector to obtain a cluster curve result.
In this embodiment, the operation duration of the transferable load is used as a feature vector, the processed data set is used as input, and a K-means clustering algorithm is adopted for clustering. The basic principle of the K-means algorithm is as follows, which can be expressed as: for a given sample set, the sample set is divided into k clusters according to the distance between samples, so that the points in the clusters are connected as closely as possible, and the distance between the clusters is as large as possible.
Wherein the content of the first and second substances,
represents a sample i; n represents the number of samples; />
Represents the centroid j; />
Representing a matrix of cluster centers.
Since the clustering curve result is greatly influenced by the number of clustering centers, it is necessary to determine the optimal number of clustering centers. And analyzing the clustering effect under different clustering center numbers by adopting an enumeration method. The clustering effect was evaluated here using the contour coefficient Index (Silhouette score) and Davison Cast Ding Zhishu (Davies Bouldin Index). The calculation formula of the contour coefficient index is shown as the following, the value range of the index is [ -1,1], and the larger the index is, the better the clustering effect is; the davison bauxid index calculation formula is shown as follows, and the smaller the index is, the better the clustering effect is. Therefore, the number of cluster centers which can simultaneously maximize the contour coefficient and minimize the davison castle Ding Zhishu is the optimal number of cluster centers. Taking fig. 4 as an example, fig. 4 shows the clustering effect under different numbers of clustering centers, the clustering effect is evaluated by davison baume indexes and contour coefficient indexes, fig. 4 (a) shows the change rule of davison baume Ding Zhishu (ordinate) along with the number of clustering centers (abscissa), and it can be seen that when the number of clustering centers is 5, davison baume indexes reach the minimum value; fig. 4 (b) shows a change rule of the profile coefficient index (ordinate) with the number of cluster centers (abscissa), and the profile coefficient index reaches the maximum value when the number of cluster centers is 5. Therefore, the number of optimal cluster centers is 5.
Wherein k represents the number of cluster centers;
and &>
Respectively representing the dispersity of the data points in the ith class and the jth class; />
Indicating the distance of the ith class from the center of the jth class.
Step S23: and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration.
In this embodiment, based on the determined optimal clustering number, K-means clustering is performed to obtain a clustering curve result under the optimal clustering number, the clustering curve result is analyzed, and an operation mode of the transferable load and a power curve corresponding to each operation mode are determined according to the operation duration. Generally, a certain operating mode of a residential building, which can transfer loads, has a fixed operating cycle consisting of different operating phases, both in power and in duration, but in power the same operating phase. The operating characteristics can be represented by fig. 3, the mathematical model of which can be represented by the following formula,
wherein the content of the first and second substances,
represents the power of the transferable load in the operating phase w in the j operating mode, is->
Indicates the duration of an operating phase w in the j operating mode, in which the transferable load is present>
Indicating the duration of the entire operating cycle of the transferable load in the j operating mode. Therefore, in order to model the building transferable loads in different operating modes, it is necessary to determine a parameter->
。
Based on the clustering curve result of the power curve containing each operation mode of the flexible load, the following formula is utilized to calculate and obtain the model parameters
And &>
；
Wherein the content of the first and second substances,
representing the power of the obtained transferable load in the z period in the w operation stage of the operation mode j; z represents the number of all sample points of the transferable load in the w running stage of the running mode j; />
Indicating the obtained sample u is in the running modeDuration in the w operating phase of j; u denotes the number of all sample points in the w run phase of the run mode j. Taking fig. 5 as an example, based on the number of the optimal clustering centers, clustering is performed by using a K-means clustering algorithm to obtain a clustering curve result when the number of the clustering centers is 5, so as to obtain 5 types of operation curves, wherein each type of operation curve represents an operation mode, the type 0 represents a soft washing mode, and the duration is 36 minutes; category 1 represents conventional mode, with a duration of 46 minutes; category 2 represents a rinse mode with a duration of 56 minutes; category 3 represents surf wash mode for 68 minutes; category 4 represents a brute force mode with a duration of 80 minutes. In addition, all the operation curves in each operation mode in the sample data are obtained, and fig. 6 shows all the obtained operation curves in the conventional mode, wherein a black operation curve represents the result in the operation mode obtained by clustering in fig. 6, and a gray curve represents the collected operation curve in the conventional mode.
And finally, modeling and analyzing the clustering curve results of the power curves comprising the operation modes based on the clustering curve results, and calculating the operation power and the operation duration of the model by taking the model parameters of the washing machine as an example in the conventional operation mode as shown in table 1.
TABLE 1
Step S24: and analyzing and calculating the transferable load power model to obtain parameters of the transferable load power model, and then sending the parameters to a client according to a preset parameter display method.
In addition, to accomplish the same object, transferable loads such as washing machines, dryers, dishwashers and the like can be modeled using a white box model. However, a model established based on the white box model is very complex, and high calculation time cost is caused in the actual application process, so that the model is difficult to popularize and apply on a large scale. Therefore, the key points of the application are as follows: the application considers the actual running characteristic of the transferable load of the residential building, and provides a data-driven modeling method of the transferable load of the residential building based on a K-means clustering method; based on the proposed modeling method, a tool for rapidly modeling the transferable load of the residential building is developed through a programming language such as Python, the operation data of the transferable load of the residential building is input into the tool, and the tool can immediately obtain the modeling result of the transferable load through calculation.
In the embodiment, actual operation data of transferable loads are obtained, and the actual operation data are preprocessed to obtain a processed data set; determining the operation duration of single continuous operation of the transferable load from the processed data set, and performing clustering analysis on the processed data set by taking the operation duration as a characteristic vector to obtain a clustering curve result; and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration. The data-driven modeling method for the transferable loads of the residential buildings is provided by utilizing the actual running characteristics of the transferable loads of the residential buildings and based on a K-means clustering method, the accuracy of the models is effectively improved, a tool for quickly modeling the transferable loads of the residential buildings is developed through Python and other programming languages, the running data of the transferable loads of the residential buildings are input into the tool, the tool can immediately obtain the modeling result of the transferable loads through calculation, and the established transferable load model of the residential buildings is higher in accuracy, has universality and can be popularized and applied.
Referring to fig. 7, an embodiment of the present invention discloses a transferable load modeling apparatus based on data driving, which may specifically include:
the data processing module 11 is configured to obtain actual operation data of a transferable load, and preprocess the actual operation data to obtain a processed data set;
the cluster analysis module 12 is configured to determine an operation duration of single continuous operation of the transferable load from the processed data set, and perform cluster analysis on the processed data set by using the operation duration as a feature vector to obtain a clustering curve result;
and the model construction module 13 is configured to determine power and continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and construct the transferable load power model based on the power and the continuous operation duration.
In the embodiment, actual operation data of a transferable load are obtained, and the actual operation data are preprocessed to obtain a processed data set; determining the operation duration of single continuous operation of the transferable load from the processed data set, and performing clustering analysis on the processed data set by taking the operation duration as a characteristic vector to obtain a clustering curve result; and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration. The method for the data-driven modeling of the transferable loads of the residential building is provided by utilizing the actual operation characteristics of the transferable loads of the residential building based on a K-means clustering method, the accuracy of a model is effectively improved, a tool for quickly modeling the transferable loads of the residential building is developed through programming languages such as Python and the like, the operation data of the transferable loads of the residential building are input into the tool, the tool can immediately obtain the modeling result of the transferable loads through calculation, and the established model of the transferable loads of the residential building is higher in accuracy, has universality and can be popularized and applied.
In some specific embodiments, the data processing module 11 may specifically include:
the numerical value determining module is used for determining a missing value, an abnormal value and a noise value from the actual operation data;
and the processed data set determining module is used for respectively processing the missing value, the abnormal value and the noise value by adopting a Lagrange difference method, a box graph method and a Kalman filtering algorithm to obtain a processed data set.
In some specific embodiments, the cluster analysis module 12 may specifically include:
and the running duration determining module is used for extracting the characteristic parameters of the actual running data to obtain the running duration of the single continuous running of the transferable load.
In some specific embodiments, the cluster analysis module 12 may specifically include:
a clustering curve result determining module, configured to perform clustering analysis on the processed data set with the operating duration as a feature vector to obtain a clustering curve result;
and the power utilization curve determining module is used for determining each operation mode based on the clustering curve result so as to obtain power utilization curves in different operation modes.
In some specific embodiments, the cluster analysis module 12 may specifically include:
and the clustering algorithm analysis module is used for taking the running duration as a characteristic vector and then performing clustering analysis operation on the processed data set by adopting a K-means clustering algorithm to obtain power utilization curves in different running modes.
In some specific embodiments, the cluster analysis module 12 may specifically include:
the optimal clustering center quantity determining module is used for selecting different clustering center quantities by adopting an enumeration method to cluster the processed data set, and evaluating clustering curve results under the different clustering center quantities by adopting an outline coefficient index and a Theisenbergin index so as to determine the optimal clustering center quantity from the different clustering center quantities;
and the power utilization curve determining module is used for performing clustering operation on the processed data set by adopting a K-means clustering algorithm by taking the operation duration and the optimal clustering center number as input, and carrying out power utilization curves in different operation modes.
In some embodiments, the model building module 13 may specifically include:
the parameter determining module is used for analyzing and calculating the transferable load power model to obtain parameters of the transferable load power model;
and the parameter sending module is used for sending the parameters to the client according to a preset parameter display method.
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. Wherein the memory 22 is used for storing a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the data-driven transferable load modeling method executed by an electronic device disclosed in any of the foregoing embodiments.
In this embodiment, the power supply 23 is configured to provide a working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and a communication protocol followed by the communication interface is any communication protocol applicable to the technical solution of the present application, and is not specifically limited herein; the input/output interface 25 is configured to acquire external input data or output data to the outside, and a specific interface type thereof may be selected according to specific application requirements, which is not specifically limited herein.
In addition, the storage 22 is used as a carrier for storing resources, and may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., the resources stored thereon include an operating system 221, a computer program 222, data 223, etc., and the storage may be a transient storage or a permanent storage.
The operating system 221 is used for managing and controlling each hardware device and the computer program 222 on the electronic device 20, so as to realize the operation and processing of the data 223 in the memory 22 by the processor 21, which may be Windows, unix, linux, and the like. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the data-driven transferable load modeling method executed by the electronic device 20 disclosed in any of the foregoing embodiments. The data 223 may include data received by the transferable load modeling device driven by the data and transmitted from an external device, data collected by the input/output interface 25, and the like.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Further, an embodiment of the present application further discloses a computer-readable storage medium, where a computer program is stored in the storage medium, and when the computer program is loaded and executed by a processor, the steps of the transferable load modeling method based on data driving disclosed in any of the foregoing embodiments are implemented.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
The transferable load modeling method, the device, the equipment and the storage medium based on data driving provided by the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A transferable load modeling method based on data driving is characterized by comprising the following steps:
acquiring actual operation data of a transferable load, and preprocessing the actual operation data to obtain a processed data set;
determining the running time of single continuous running of the transferable load from the processed data set, and performing clustering analysis on the processed data set by taking the running time as a characteristic vector to obtain a clustering curve result;
and determining the power and the continuous operation duration of different operation stages in each operation mode based on the clustering curve result, and constructing the transferable load power model based on the power and the continuous operation duration.
2. The data-driven transferable load modeling method in accordance with claim 1, wherein the preprocessing the actual operation data to obtain a processed data set comprises:
determining missing values, abnormal values and noise values from the actual operation data;
and respectively processing the missing value, the abnormal value and the noise value by adopting a Lagrange difference method, a box type graph method and a Kalman filtering algorithm to obtain a processed data set.
3. The data-driven-based transferable load modeling method according to claim 1, wherein the determining the run length of the transferable load for a single continuous run from the processed data set comprises:
and performing characteristic parameter extraction operation on the actual operation data to obtain the operation duration of the single continuous operation of the transferable load.
4. The data-driven transferable load modeling method in accordance with claim 3, wherein the clustering the processed data set with the run length as the feature vector to obtain a clustering curve result comprises:
performing clustering analysis on the processed data set by taking the running duration as a characteristic vector to obtain a clustering curve result;
and determining each operation mode based on the clustering curve result so as to obtain power utilization curves in different operation modes.
5. The data-driven transferable load modeling method according to claim 4, wherein the determining each operation mode based on the clustering curve result to obtain the power utilization curve under different operation modes comprises:
and taking the running time as a characteristic vector, and then carrying out clustering analysis operation on the processed data set by adopting a K-means clustering algorithm to obtain power utilization curves in different running modes.
6. The data-driven transferable load modeling method according to claim 5, wherein the clustering analysis operation is performed on the processed data set by adopting a K-means clustering algorithm to obtain power utilization curves in different operation modes, and the method comprises the following steps:
selecting different clustering center quantities by adopting an enumeration method to cluster the processed data set, and evaluating clustering curve results under the different clustering center quantities by adopting an outline coefficient index and a Theisenbergin index so as to determine the optimal clustering center quantity from the different clustering center quantities;
and taking the running time and the optimal clustering center number as input, and carrying out clustering operation on the processed data set by adopting a K-means clustering algorithm to obtain power utilization curves in different running modes.
7. The data-driven-based transferable load modeling method according to any one of claims 1-6, wherein after constructing the transferable load power model based on the power and the duration of operation, further comprising:
analyzing and calculating the transferable load power model to obtain parameters of the transferable load power model;
and sending the parameters to a client according to a preset parameter display method.
8. A transferable load modeling apparatus based on data driving, comprising:
the data processing module is used for acquiring actual operation data of the transferable load and preprocessing the actual operation data to obtain a processed data set;
the cluster analysis module is used for determining the running time of single continuous running of the transferable load from the processed data set and carrying out cluster analysis on the processed data set by taking the running time as a characteristic vector to obtain a cluster curve result;
and the model construction module is used for determining the power and the continuous operation time length of different operation stages in each operation mode based on the clustering curve result and constructing the transferable load power model based on the power and the continuous operation time length.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the data-driven transferable load modeling method in accordance with any one of claims 1-7.
10. A computer-readable storage medium for storing a computer program; wherein the computer program when executed by a processor implements the data-driven based transferable load modeling method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310134024.5A CN115859452B (en) | 2023-02-20 | 2023-02-20 | Data-driven-based transferable load modeling method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310134024.5A CN115859452B (en) | 2023-02-20 | 2023-02-20 | Data-driven-based transferable load modeling method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115859452A true CN115859452A (en) | 2023-03-28 |
| CN115859452B CN115859452B (en) | 2023-05-02 |
Family
ID=85658376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310134024.5A Active CN115859452B (en) | 2023-02-20 | 2023-02-20 | Data-driven-based transferable load modeling method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115859452B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097474A (en) * | 2019-03-25 | 2019-08-06 | 国网辽宁省电力有限公司 | A kind of duty control method for realizing power distribution network peak load shifting |
| CN110245878A (en) * | 2019-06-27 | 2019-09-17 | 华翔翔能电气股份有限公司 | The Distributed Integration energy demand of intelligent building group responds cooperative optimization method |
| CN110571793A (en) * | 2019-08-23 | 2019-12-13 | 华北电力大学 | multidimensional identification method for flexible load demand response effect |
| US20210136122A1 (en) * | 2015-10-28 | 2021-05-06 | Qomplx, Inc. | Crowdsourced innovation laboratory and process implementation system |
| CN113361587A (en) * | 2021-06-02 | 2021-09-07 | 东南大学 | Electric vehicle charging station load characteristic clustering modeling method based on POI information |
| CN114048976A (en) * | 2021-10-28 | 2022-02-15 | 上海电力大学 | Variable frequency air conditioner load regulation and control method considering multiple response potential influence factors |
| CN114429172A (en) * | 2021-12-07 | 2022-05-03 | 国网北京市电力公司 | Load clustering method, device, equipment and medium based on transformer substation user constitution |
| CN114638124A (en) * | 2022-04-14 | 2022-06-17 | 广东电网有限责任公司 | Power system optimization method and system and computer readable storage medium |
| CN115618248A (en) * | 2022-09-28 | 2023-01-17 | 国网北京市电力公司 | Load abnormity identification method and device for public building, storage medium and equipment |
-
2023
- 2023-02-20 CN CN202310134024.5A patent/CN115859452B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210136122A1 (en) * | 2015-10-28 | 2021-05-06 | Qomplx, Inc. | Crowdsourced innovation laboratory and process implementation system |
| CN110097474A (en) * | 2019-03-25 | 2019-08-06 | 国网辽宁省电力有限公司 | A kind of duty control method for realizing power distribution network peak load shifting |
| CN110245878A (en) * | 2019-06-27 | 2019-09-17 | 华翔翔能电气股份有限公司 | The Distributed Integration energy demand of intelligent building group responds cooperative optimization method |
| CN110571793A (en) * | 2019-08-23 | 2019-12-13 | 华北电力大学 | multidimensional identification method for flexible load demand response effect |
| CN113361587A (en) * | 2021-06-02 | 2021-09-07 | 东南大学 | Electric vehicle charging station load characteristic clustering modeling method based on POI information |
| CN114048976A (en) * | 2021-10-28 | 2022-02-15 | 上海电力大学 | Variable frequency air conditioner load regulation and control method considering multiple response potential influence factors |
| CN114429172A (en) * | 2021-12-07 | 2022-05-03 | 国网北京市电力公司 | Load clustering method, device, equipment and medium based on transformer substation user constitution |
| CN114638124A (en) * | 2022-04-14 | 2022-06-17 | 广东电网有限责任公司 | Power system optimization method and system and computer readable storage medium |
| CN115618248A (en) * | 2022-09-28 | 2023-01-17 | 国网北京市电力公司 | Load abnormity identification method and device for public building, storage medium and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 李毅等: "一种基于时间序列的集成电力负荷预测方法研究" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115859452B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105823948A (en) | Non-invasive resident load identification method | |
| CN113902104A (en) | Non-invasive load monitoring method combining unsupervised domain self-adaptive strategy and attention mechanism | |
| CN110580502A (en) | Factor hidden Markov load decomposition method based on Gaussian mixture | |
| CN114977176A (en) | Power load decomposition method, device, equipment and storage medium | |
| CN113131482B (en) | Probabilistic optimal power flow calculation method and system considering photovoltaic output characteristics | |
| CN116796403A (en) | Building energy saving method based on comprehensive energy consumption prediction of commercial building | |
| CN115859452A (en) | Transferable load modeling method, device, equipment and medium based on data driving | |
| CN112365090A (en) | Deep learning-based non-invasive electrical load identification method and device | |
| CN116933216A (en) | Management system and method based on flexible load resource aggregation feature analysis | |
| CN111934318A (en) | Non-invasive power load decomposition method, device, equipment and storage medium | |
| CN112070625A (en) | User electricity consumption behavior pattern recognition method and system | |
| CN116595395A (en) | Inverter output current prediction method and system based on deep learning | |
| CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
| CN115526737A (en) | Power grid energy management method and system based on digital twinning and terminal equipment | |
| CN113158134B (en) | Method, device and storage medium for constructing non-invasive load identification model | |
| CN111125630B (en) | Energy decomposition method based on L1/2 norm and homogeneity constraint | |
| CN115358473A (en) | Power load prediction method and prediction system based on deep learning | |
| CN114118812A (en) | Hydropower station energy efficiency analysis and evaluation method and device based on improved fuzzy mean clustering | |
| CN112746442A (en) | Intelligent dehydration method and device | |
| CN113622134A (en) | Laundry control method, device, equipment and storage medium | |
| CN111476316A (en) | Method and system for clustering mean value of power load characteristic data based on cloud computing | |
| CN111401624A (en) | Wind power prediction method and device and computer readable storage medium | |
| CN112149826A (en) | Profile graph-based optimization method in deep neural network inference calculation | |
| CN110244149B (en) | Non-invasive electrical appliance identification method based on current amplitude standard deviation | |
| CN116957365B (en) | Maintenance effect evaluation method and system for water pump motor |
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 |