Simulation identification method and device for building electrical load and computer equipment

Abstract

The invention relates to a simulation identification method and device for a building electrical load and computer equipment. The method comprises the following steps: acquiring historical power consumption data and building group power consumption structure information of a target building group, and splitting the building power consumption structure information and sub historical power consumption data of each building structure type; constructing a power consumption prediction model of each building structure type; identifying each electrical load change feature of each building structure type, and a change corresponding relationship between the sub-building electrical structure information of each building structure type and the electrical load change feature; and on the basis of the change corresponding relationship, through the power consumption prediction model and the power consumption structure change strategy of each building structure type, simulating the power consumption process of each building structure type, and obtaining simulated power consumption load information of each building structure type, thereby determining each piece of predicted power consumption load information of the target building group. By adopting the method, the electrical load analysis accuracy of different building structures can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of simulation and power load calculation, and in particular to a simulation identification method, device and computer equipment for building power load. Background Art

[0002] During the transformation of the new power system, the seasonal peak of electricity consumption in the building sector has a huge impact on the stable operation of the power grid installation. Therefore, in order to ensure the stability of electricity and reduce the load, the accurate calculation and prediction of building power load is the basis for assisting the peak load regulation of the power grid and optimizing building power consumption. In particular, the rapid development of smart buildings and smart grids has provided an opportunity for the application of accurate calculation technology for building power load. The power load of a building is affected by many factors, such as the purpose of the building, the performance of the enclosure structure, the type and use of internal equipment, and external environmental conditions (such as temperature and humidity). Therefore, how to improve the accuracy of the analysis of building power load is the current research focus.

[0003] Traditional power load analysis methods rely on physical models, historical data, and statistical analysis. In order to achieve accurate simulation of building power load, the physical model method faces the problem of difficulty in obtaining a large number of building-related input parameters and reduced accuracy caused by input parameter uncertainty. In addition, methods based on data and statistical analysis are mostly designed for specific types of buildings, lacking versatility and scalability, and are difficult to adapt to the load simulation needs of different types of buildings, resulting in low accuracy in power load analysis of different building structures. Summary of the invention

[0004] Based on this, it is necessary to provide a simulation identification method, device, computer equipment, computer readable storage medium and computer program product for building power load in response to the above technical problems.

[0005] In a first aspect, the present application provides a simulation identification method for building power load, comprising:

[0006] Acquire historical electricity consumption data of a target building complex and building complex electricity consumption structure information of the target building complex, and split the building complex electricity consumption structure information into building electricity consumption structure information of each building structure type;

[0007] Based on the building electricity consumption structure information of each building structure type, construct an electricity consumption prediction model for each building structure type, and split the historical electricity consumption data into sub-historical electricity consumption data corresponding to each building structure type;

[0008] Based on the sub-historical electricity consumption data corresponding to each building structure type, identifying the electricity load change characteristics of each building structure type, and based on the electricity consumption change characteristics of each building structure type, identifying the change correspondence between the sub-building electricity consumption structure information of each building structure type and the electricity load change characteristics of each building structure type;

[0009] Based on the change correspondence, the power consumption process of each building structure type is simulated through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type to obtain the simulated power load information of each building structure type, and based on the simulated power load information of all building structure types, the predicted power load information of the target building complex is determined.

[0010] Optionally, splitting the building complex electricity consumption structure information into building electricity consumption structure information of each building structure type includes:

[0011] Splitting the target building complex into individual building structures, and identifying the building structure type of each building structure in the building structure diagram of the target building complex;

[0012] The electricity consumption structure information of the building complex is split into sub-building electricity consumption structure information corresponding to each building structure, and the sub-building electricity consumption structure information corresponding to each building structure is aggregated according to each building structure type to obtain the building electricity consumption structure information of each building structure type.

[0013] Optionally, constructing a power consumption prediction model for each building structure type based on the building power consumption structure information of each building structure type includes:

[0014] For each building structure type, splitting the building power structure information of the building structure type into building structure data of each structure type and power environment data of each power environment type;

[0015] Performing data cleaning processing on the building structure data of each of the structural types and the power environment data of each of the power environment types to obtain the structural parameter values ​​of each of the structural types and the power environment parameter values ​​of each of the power environment types;

[0016] Based on the structural parameter values ​​of each of the structural types and the power consumption environment parameter values ​​of each of the power consumption environment types, a power consumption prediction model of the building structure type is constructed through a prediction model building strategy.

[0017] Optionally, the identifying the power load change characteristics of each building structure type based on the sub-historical power consumption data corresponding to each building structure type includes:

[0018] For each building structure type, performing data distribution processing on the sub-historical power consumption data of the building structure type to obtain power load distribution information of the building structure type;

[0019] Filter the target power load distribution information in the power load distribution information through a distribution screening strategy, and respectively extract the distribution change characteristics of each feature type in the target power load distribution information through a distribution feature extraction network;

[0020] The distribution change characteristics of each characteristic type are used as the power load change characteristics of each building structure type.

[0021] Optionally, the identifying, based on the electricity consumption change characteristics of each of the building structure types, the change correspondence between the sub-building electricity consumption structure information of each of the building structure types and the electricity load change characteristics of each of the building structure types includes:

[0022] For each building structure type, based on the sub-historical electricity consumption data based on the building structure type, identifying the historical building electricity consumption structure information of the building structure type;

[0023] Based on the distribution change characteristics of each characteristic type of the building structure type and the historical building electricity structure information of the building structure type, identifying the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of each characteristic type;

[0024] The sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of all feature types is used as the change correspondence between the sub-building electricity structure information of the building structure type and the electricity load change characteristics of the building structure type.

[0025] Optionally, based on the change correspondence, the power consumption process of each building structure type is simulated through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type to obtain the simulated power load information of each building structure type, and based on the simulated power load information of all building structure types, the predicted power load information of the target building complex is determined, including:

[0026] Acquire the power consumption structure change strategy of each of the building structure types, and identify each simulated power consumption structure information corresponding to each power consumption structure change strategy;

[0027] For each building structure type, based on the power consumption prediction model corresponding to the building structure type and the corresponding change correspondence relationship of the building structure type, through each simulated power consumption structure information of the building structure type, the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information is simulated to obtain the simulated power load information corresponding to each simulated power consumption structure information of the building structure type;

[0028] Splitting the simulated power load information corresponding to each simulated power structure information of the building structure type into sub-simulated power load information of each building structure in each simulated power structure information corresponding to the building structure type;

[0029] The sub-simulated power load information of all building structures in each simulated power structure information is distributed and arranged according to the position information of each building structure in the target building complex to obtain the predicted power load information of the target building complex in each simulated power structure information.

[0030] In a second aspect, the present application also provides a simulation identification device for building power load, comprising:

[0031] An acquisition module, used to acquire historical electricity consumption data of a target building complex and building electricity consumption structure information of the target building complex, and split the building electricity consumption structure information into building electricity consumption structure information of each building structure type;

[0032] A splitting module, for constructing a power consumption prediction model for each building structure type based on the building power consumption structure information of each building structure type, and splitting the historical power consumption data into sub-historical power consumption data corresponding to each building structure type;

[0033] An identification module is used to identify the power load change characteristics of each building structure type based on the sub-historical power consumption data corresponding to each building structure type, and based on the power consumption change characteristics of each building structure type, identify the change correspondence between the sub-building power consumption structure information of each building structure type and the power load change characteristics of each building structure type;

[0034] A determination module is used to simulate the power consumption process of each building structure type based on the change correspondence, through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type, to obtain the simulated power load information of each building structure type, and determine the predicted power load information of the target building complex based on the simulated power load information of all building structure types.

[0035] Optionally, the acquisition module is specifically used to:

[0036] Splitting the target building complex into individual building structures, and identifying the building structure type of each building structure in the building structure diagram of the target building complex;

[0037] The electricity consumption structure information of the building complex is split into sub-building electricity consumption structure information corresponding to each building structure, and the sub-building electricity consumption structure information corresponding to each building structure is aggregated according to each building structure type to obtain the building electricity consumption structure information of each building structure type.

[0038] Optionally, the splitting module is specifically used to:

[0039] For each building structure type, splitting the building power structure information of the building structure type into building structure data of each structure type and power environment data of each power environment type;

[0040] Performing data cleaning processing on the building structure data of each of the structural types and the power environment data of each of the power environment types to obtain the structural parameter values ​​of each of the structural types and the power environment parameter values ​​of each of the power environment types;

[0041] Based on the structural parameter values ​​of each of the structural types and the power consumption environment parameter values ​​of each of the power consumption environment types, a power consumption prediction model of the building structure type is constructed through a prediction model building strategy.

[0042] Optionally, the identification module is specifically used to:

[0043] For each building structure type, performing data distribution processing on the sub-historical power consumption data of the building structure type to obtain power load distribution information of the building structure type;

[0044] Filter the target power load distribution information in the power load distribution information through a distribution screening strategy, and respectively extract the distribution change characteristics of each feature type in the target power load distribution information through a distribution feature extraction network;

[0045] The distribution change characteristics of each characteristic type are used as the power load change characteristics of each building structure type.

[0046] Optionally, the identification module is specifically used to:

[0047] For each building structure type, based on the sub-historical electricity consumption data based on the building structure type, identifying the historical building electricity consumption structure information of the building structure type;

[0048] Based on the distribution change characteristics of each characteristic type of the building structure type and the historical building electricity structure information of the building structure type, identifying the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of each characteristic type;

[0049] The sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of all feature types is used as the change correspondence between the sub-building electricity structure information of the building structure type and the electricity load change characteristics of the building structure type.

[0050] Optionally, the determining module is specifically used to:

[0051] Acquire the power consumption structure change strategy of each of the building structure types, and identify each simulated power consumption structure information corresponding to each power consumption structure change strategy;

[0052] For each building structure type, based on the power consumption prediction model corresponding to the building structure type and the corresponding change correspondence relationship of the building structure type, through each simulated power consumption structure information of the building structure type, the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information is simulated to obtain the simulated power load information corresponding to each simulated power consumption structure information of the building structure type;

[0053] Splitting the simulated power load information corresponding to each simulated power structure information of the building structure type into sub-simulated power load information of each building structure in each simulated power structure information corresponding to the building structure type;

[0054] The sub-simulated power load information of all building structures in each simulated power structure information is distributed and arranged according to the position information of each building structure in the target building complex to obtain the predicted power load information of the target building complex in each simulated power structure information.

[0055] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0056] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0057] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0058] The above-mentioned simulation identification method, device and computer equipment of building power load obtain the historical power consumption data of the target building group and the building power consumption structure information of the target building group, and split the building power consumption structure information into the building power consumption structure information of each building structure type; based on the building power consumption structure information of each building structure type, construct a power consumption prediction model for each building structure type, and split the historical power consumption data into sub-historical power consumption data corresponding to each building structure type; based on the sub-historical power consumption data corresponding to each building structure type, identify the change characteristics of each power load of each building structure type, and based on the power consumption change characteristics of each building structure type, identify the change correspondence between the sub-building power consumption structure information of each building structure type and the power load change characteristics of each building structure type; based on the change correspondence, simulate the power consumption process of each building structure type through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type to obtain the simulated power consumption load information of each building structure type, and determine the predicted power load information of the target building group based on the simulated power consumption load information of all building structure types. This scheme constructs a power consumption prediction model for each building structure type of different building structure groups, and then comprehensively considers the physical characteristics, usage and environmental conditions of the building to achieve generalizable calculation of power loads of different types of buildings. The module gets rid of the dependence on computing resources and personalized building simulation models in traditional computing methods, adopts modular design, makes full use of the advantages of distributed computing, improves computing efficiency and system flexibility, and adapts to the processing needs of large-scale building power load data. It can be flexibly configured according to the computing needs of different types of buildings, with high versatility and scalability. Finally, by combining the analyzed sub-building power structure information of each building structure type and the corresponding relationship between the power load change characteristics of each building structure type, the power load simulation of the regional building group can be realized. The module integrates data acquisition and transmission interfaces, can monitor the internal and external environmental conditions and the status of power equipment in real time, and performs real-time analysis and processing through the data processing unit to ensure the real-time and accuracy of load simulation. Thereby comprehensively improving the accuracy of power load analysis of different building structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 A schematic diagram of a flow chart of a simulation identification method for building power load in one embodiment;

[0061] Figure 2 A schematic diagram of a data cleaning process in one embodiment;

[0062] Figure 3 Simplified flow chart of input parameters of a building electricity consumption prediction model in one embodiment

[0063] Figure 4 A training flow chart of the XGB algorithm in one embodiment;

[0064] Figure 5 A flow chart of clustering daily electricity consumption curves in one embodiment

[0065] Figure 6 A schematic diagram of a flow chart of an example of simulation identification of building power loads in one embodiment;

[0066] Figure 7 It is a structural block diagram of a simulation identification device for building power load in one embodiment;

[0067] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] The simulation identification method of building power load provided by the embodiment of the present application can be applied to the application environment of building power load simulation. Among them, the method can be applied to a terminal, a server, or a system including a terminal and a server, and is realized through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, etc. Among them, the terminal constructs a power consumption prediction model for each building structure type of different building structure groups, and then comprehensively considers the physical characteristics, usage and environmental conditions of the building to realize the generalizable calculation of different types of building power loads. The module gets rid of the dependence on computing resources and personalized building simulation models in traditional computing methods, adopts modular design, makes full use of the advantages of distributed computing, improves computing efficiency and system flexibility, and adapts to the processing requirements of large-scale building power load data. It can be flexibly configured according to the computing requirements of different types of buildings, and has high versatility and scalability. Finally, by combining the analyzed sub-building power structure information of each building structure type and the corresponding relationship between the power load change characteristics of each building structure type, the power load simulation of the regional building group can be realized. The module integrates data acquisition and transmission interfaces, can monitor the environmental conditions inside and outside the building and the status of electrical equipment in real time, and conduct real-time analysis and processing through the data processing unit to ensure the real-time and accuracy of load simulation, thereby comprehensively improving the accuracy of power load analysis for different building structures.

[0070] In an exemplary embodiment, Figure 1 As shown, a simulation identification method for building power load is provided, and the method is applied to a terminal as an example for explanation, including the following steps S101 to S104. Among them:

[0071] Step S101, obtaining historical electricity consumption data of a target building complex and building complex electricity consumption structure information of the target building complex, and splitting the building complex electricity consumption structure information into building electricity consumption structure information of each building structure type.

[0072] In this embodiment, the terminal identifies the first historical electricity consumption record of the target building complex by querying the electricity consumption history of the target building complex at the power company, and queries the historical electricity consumption structure information corresponding to each first historical electricity consumption record in the historical detection information of the target building complex. Each first historical electricity consumption is based on, and the historical electricity consumption structure information corresponding to each first historical electricity consumption record is used as each historical electricity consumption data of the target building complex, wherein the historical electricity consumption data includes the sub-historical electricity consumption data of each building structure of the target building complex. Then, the terminal collects the current electricity consumption structure information of the target building complex to obtain the building complex electricity consumption structure information of the target building complex. Among them, the building complex electricity consumption structure data includes the sub-electricity consumption structure information of each building structure. The sub-electricity consumption structure information includes, but is not limited to, internal building sensor data, external environment data, or building structure data of the building structure type belonging to the electricity consumption environment type. The internal sensor data of the building includes sensors such as temperature sensors, crowd detection sensors, and current sensors of various electrical equipment. The external environmental data includes but is not limited to crowd density, environmental area data (such as commercial areas, industrial areas, residential areas, abandoned areas, rural areas, urban areas), etc. Finally, the terminal splits the power structure information of the building complex into the power structure information of each building structure type. Among them, each building structure corresponds to a building structure type, and each building structure type can correspond to one or more building structures. Among them, the building structure type includes but is not limited to industrial buildings, commercial buildings and residential buildings, among which commercial buildings include offices, shopping malls, hotels, schools, hospitals, etc. The specific splitting process will be described in detail later.

[0073] Step S102: construct a power consumption prediction model for each building structure type based on the building power consumption structure information of each building structure type, and split the historical power consumption data into sub-historical power consumption data corresponding to each building structure type.

[0074] In this embodiment, the terminal constructs a power consumption prediction model for each building structure type based on the building power consumption structure information of each building structure type, and splits the historical power consumption data into sub-historical power consumption data corresponding to each building structure type. Among them, the way to construct the power consumption prediction model is to use the principal component analysis (PCA) method to perform preliminary dimensionality reduction on the input parameters (i.e., power consumption structure information) of buildings (i.e., building structures) of different types (i.e., building structure types), and then use recursive feature elimination (RFE) based on support vector regression to simplify the input parameters. Finally, the eXtreme Gradient Boosting (XGB) algorithm is used to establish a prediction model between the input parameters of different types of buildings and daily power consumption. The specific establishment process will be described in detail later.

[0075] Step S103, based on the sub-historical electricity consumption data corresponding to each building structure type, identify the power load change characteristics of each building structure type, and based on the power consumption change characteristics of each building structure type, identify the sub-building power consumption structure information of each building structure type and the change correspondence between the power load change characteristics of each building structure type.

[0076] In this embodiment, the terminal identifies the change characteristics of each power load of each building structure type based on the sub-historical power consumption data corresponding to each building structure type, and identifies the change correspondence between the sub-building power structure information of each building structure type and the power load change characteristics of each building structure type based on the power consumption change characteristics of each building structure type. Among them, each power load change characteristic includes distribution change characteristics of different feature types, and the feature types include but are not limited to time characteristics, statistical characteristics, and environmental characteristics. The specific feature identification process will be described in detail later. The change correspondence includes the change correspondence between the sub-building power structure information of each building structure type and the distribution change graph characteristics of each feature type.

[0077] Step S104, based on the change correspondence, through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type, simulate the power consumption process of each building structure type to obtain the simulated power load information of each building structure type, and determine the predicted power load information of the target building complex based on the simulated power load information of all building structure types.

[0078] In this embodiment, based on the change correspondence, the terminal simulates the power consumption process of each building structure type through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type, obtains the simulated power load information of each building structure type, and determines the predicted power load information of the target building complex based on the simulated power load information of all building structure types. Among them, the power consumption structure change strategy of each building structure type includes each simulated power structure information. Among them, the difference between each simulated power structure information is that the internal sensor data and external environment data of each power environment type are different. The specific simulation process will be described in detail later. Among them, each predicted power load information is the predicted power load information corresponding to each simulated power structure information. The predicted power load information includes the sub-simulated power load information of each building structure in the target building complex. The specific determination process will be described in detail later.

[0079] Based on the above scheme, by constructing the electricity consumption prediction model of each building structure type of different building structure groups, and then comprehensively considering the physical characteristics, usage and environmental conditions of the building, the generalizable calculation of the electricity load of different types of buildings is realized. The module gets rid of the dependence on computing resources and personalized building simulation models in traditional calculation methods, adopts modular design, makes full use of the advantages of distributed computing, improves computing efficiency and system flexibility, and adapts to the processing needs of large-scale building electricity load data. It can be flexibly configured according to the computing needs of different types of buildings, with high versatility and scalability. Finally, by combining the analyzed sub-building electricity structure information of each building structure type and the corresponding relationship between the change characteristics of the electricity load of each building structure type, the electricity load simulation of the regional building group can be realized. The module integrates data acquisition and transmission interfaces, can monitor the internal and external environmental conditions and the status of electrical equipment in real time, and performs real-time analysis and processing through the data processing unit to ensure the real-time and accuracy of load simulation. Thereby comprehensively improving the accuracy of the analysis of the electricity load of different building structures.

[0080] Optionally, the electricity consumption structure information of the building complex is split into building electricity consumption structure information of each building structure type, including: splitting the target building complex into each building structure, and identifying the building structure type of each building structure in the building structure diagram of the target building complex; splitting the electricity consumption structure information of the building complex into sub-building electricity consumption structure information corresponding to each building structure, and aggregating and processing the sub-building electricity consumption structure information corresponding to each building structure according to each building structure type to obtain the building electricity consumption structure information of each building structure type.

[0081] In this embodiment, the terminal divides the target building complex into various building structures, and identifies the building structure type of each building structure in the building structure diagram of the target building complex. Each building structure in the building structure diagram includes building structure type identification information, and the terminal determines the building structure type of each building structure by querying the building structure type corresponding to each building structure type identification information in the building structure database.

[0082] Then, the terminal splits the building complex power structure information into sub-building power structure information corresponding to each building structure, and aggregates and processes the sub-building power structure information corresponding to each building structure according to each building structure type to obtain the building power structure information of each building structure type.

[0083] Based on the above scheme, by splitting each building structure type, the building power structure information of each building structure type is identified, thereby improving the comprehensiveness and accuracy of the identification.

[0084] Optionally, based on the building electricity structural information of each building structure type, an electricity consumption prediction model for each building structure type is constructed, including: for each building structure type, splitting the building electricity structural information of the building structure type into building structure data of each structure type and electricity environment data of each electricity environment type; performing data cleaning processing on the building structure data of each structure type and the electricity environment data of each electricity environment type to obtain structural parameter values ​​of each structure type and electricity environment parameter values ​​of each electricity environment type; based on the structural parameter values ​​of each structure type and the electricity environment parameter values ​​of each electricity environment type, a power consumption prediction model for the building structure type is constructed through a prediction modeling strategy.

[0085] In this embodiment, for each building structure type, the terminal splits the building power structure information of the building structure type into building structure data of each structure type and power environment data of each power environment type. Then, the terminal performs data cleaning processing on the building structure data of each structure type and the power environment data of each power environment type to obtain the structure parameter value of each structure type and the power environment parameter value of each power environment type.

[0086] Specifically, Figure 2As shown in the figure, the data cleaning process is to unify the format of the building structure data of each structure type and the power environment data of each power environment type, and then obtain the structural parameter values ​​of each structure type and the power environment parameter values ​​of each power environment type through data deduplication, time alignment, granularity alignment, and abnormal data detection and removal. Among them, the first step is to remove duplicate data, including repeated acquisition of building data and repeated records in time. There are inconsistencies in the recording duration and recording frequency of time series data from different sources. The second step of data cleaning is to align the recording duration and align the recording frequency by interpolation of the previous and next points. For missing values ​​in the data, the previous and next point interpolation method is used to fill in; for continuous missing values, the average value of the same time data of the previous and next days is used instead. The Z-score method is used to detect outliers in the data. The calculation formula is as follows: for each data point in the data, its Z-score is calculated. According to the set threshold (usually 3 or -3), it is judged whether the Z-score is outside the threshold. Data points exceeding the threshold are considered outliers and are treated in the same way as missing values.

[0087]

[0088] In the formula, and are the time series data and the mean of the data respectively.

[0089] Then, the terminal constructs a power consumption prediction model for the building structure type based on the structural parameter values ​​of each structural type and the power consumption environment parameter values ​​of each power consumption environment type through a prediction model modeling strategy. Figure 3 As shown in the figure, the input parameters of each building structure are diverse, covering building parameters, thermal parameters, system parameters, usage, and climate conditions. The importance of the subdivided parameters varies greatly, and there is a coupling relationship between the parameters. Considering the simplification and accessibility of the input parameters, while ensuring the accuracy of the calculation results, it is necessary to perform feature engineering on the input parameters of the building electricity consumption prediction model.

[0090] First, the terminal uses the PCA (principle component analysis) strategy to screen out the main independent parameters. In this process, the covariance matrix of the input parameters is calculated and the eigenvalue decomposition is performed. Then, the terminal sorts them according to the size of the eigenvalues ​​and selects the principal components based on the availability and eigenvalues ​​of the parameters.

[0091] Afterwards, the principal components obtained by the terminal through PCA are orthogonal (i.e., independent of each other), which can capture the main information in the data and retain the characteristics and variability of the original parameter data to the greatest extent. Subsequently, the recursive feature elimination method (RFE) based on support vector regression is used to eliminate the independent parameters to obtain the target structural parameter values ​​of each structural type of each building structure type and the target power environment parameter values ​​of each power environment type. Finally, the terminal uses the eXtreme Gradient Boosting (XGB) algorithm to establish a power consumption prediction model for each building structure type through the target structural parameter values ​​of each structural type of each building structure type and the target power environment parameter values ​​of each power environment type.

[0092] Among them, the method of establishing the electricity consumption prediction model for the building structure type is to train the initial XGB algorithm by using the data set composed of the historical target structural parameter values ​​of each structure type in the historical electricity consumption data of each building structure type and the historical target electricity consumption environment parameter values ​​of each electricity consumption environment type, and obtain the XGB algorithm for constructing the electricity consumption prediction model for each building structure type.

[0093] The training process is as follows: Figure 4 As shown, the terminal first initializes a simple decision tree model. , for example, all predicted values ​​are the mean of the target variable. Each iteration calculates the residual between the predicted value and the actual value of the current model and the objective function, and the calculation formula is:

[0094]

[0095]

[0096] In the formula, and is the actual value and the predicted value output by the model, is the loss function, is the regularization term, and the calculation formula is:

[0097]

[0098] In the formula, is the number of leaf nodes in the tree, is the leaf node weight.

[0099] Each new tree is added to reduce the residual of the previous model. Therefore, the residual and the objective function gradient are used as the target variables of the new tree to train the new tree. The new tree is then added to the model and a scaling factor is used. To control the contribution of the new tree to the output of the entire model, the calculation formula is:

[0100]

[0101]

[0102] In the formula, is the output of the new tree fitting residual, is the overall model output after adding the new tree, is the output of the previous round of overall model.

[0103] The iterative process continues until the predetermined number of iterations is reached or the error on the validation set no longer decreases after consecutive iterations, resulting in the XGB algorithm.

[0104] Based on the above scheme, the accuracy of data analysis is improved through data cleaning and processing, avoiding analysis anomalies caused by different parameter relationships. Then, the input parameters of different types of buildings are initially reduced in dimension by using the principal component analysis (PCA) method, and then the input parameters are simplified by using recursive feature elimination (RFE) based on support vector regression. Finally, the eXtreme Gradient Boosting (XGB) algorithm is used to establish a prediction model between the input parameters of different types of buildings and daily electricity consumption, which improves the accuracy of the electricity consumption prediction model constructed for each type of building structure.

[0105] Optionally, based on the sub-historical electricity consumption data corresponding to each building structure type, the power load change characteristics of each building structure type are identified, including: for each building structure type, performing data distribution processing on the sub-historical electricity consumption data of the building structure type to obtain power load distribution information of the building structure type; filtering the target power load distribution information in the power load distribution information through a distribution screening strategy, and extracting the distribution change characteristics of each feature type in the target power load distribution information through a distribution feature extraction network; and using the distribution change characteristics of each feature type as the power load change characteristics of each building structure type.

[0106] In this embodiment, the terminal performs data distribution processing on the sub-historical power consumption data of each building structure type to obtain power load distribution information of the building structure type. Figure 4As shown, the power load distribution information is obtained by sorting the distribution of each power load data and then performing curve smoothing processing to obtain the power load curve distribution data. Finally, the terminal uses the power load curve distribution data as the power load distribution information.

[0107] Then, the terminal uses the distribution screening strategy to screen the target power load distribution information in the power load distribution information, and extracts the distribution change characteristics of each feature type in the target power load distribution information through the distribution feature extraction network. Among them, the feature extraction process is that the terminal extracts the distribution change characteristics of each feature type through the curve feature extraction network. The curve feature extraction network can be any convolutional neural network that can realize the above technical process. Finally, the terminal uses the distribution change characteristics of each feature type as the power load change characteristics of each building structure type.

[0108] Among them, the method of screening the target power load distribution information is as follows: Figure 5 As shown in the figure, the building power load data is first normalized and the data dimension is converted to form a series of time series data with a length of day. The K-means algorithm is used to cluster the daily power consumption curves. First, several curves are randomly selected as the center line of the cluster, and the Euclidean distance between the power consumption curves of other days and the center line is calculated. The calculation formula is:

[0109]

[0110] In the formula, are the data points of the time series of electricity consumption curves in other days, The data points are the cluster center lines.

[0111] The Euclidean distance of the curve is used for clustering. The objective function is to minimize the sum of square errors of the Euclidean distance within the cluster. The calculation formula is:

[0112]

[0113] Then, the center line of the cluster is updated, and the new center line is the average power consumption curve within the cluster. The K-means algorithm can effectively divide the daily power consumption curve into K clusters, and the curves in each cluster are as similar as possible, while the curves between different clusters are as different as possible.

[0114] Based on the above scheme, the target electric load distribution information is screened after the curve distribution, which improves the accuracy of extracting the distribution change characteristics of each feature type.

[0115] Optionally, based on the electricity consumption change characteristics of each building structure type, the sub-building electricity consumption structure information of each building structure type and the change correspondence between the electricity load change characteristics of each building structure type are identified, including: for each building structure type, based on the sub-historical electricity consumption data of the building structure type, the historical building electricity consumption structure information of the building structure type is identified; based on the distribution change characteristics of each characteristic type of the building structure type and the historical building electricity consumption structure information of the building structure type, the sub-change correspondence between the historical building electricity consumption structure information of the building structure type and the distribution change characteristics of each characteristic type is identified; and the sub-change correspondence between the historical building electricity consumption structure information of the building structure type and the distribution change characteristics of all characteristic types is used as the change correspondence between the sub-building electricity consumption structure information of the building structure type and the electricity load change characteristics of the building structure type.

[0116] In this embodiment, the terminal identifies the historical building electricity structure information of the building structure type based on the sub-historical electricity consumption data of the building structure type for each building structure type. Then, based on the distribution change characteristics of each feature type of the building structure type and the historical building electricity structure information of the building structure type, the terminal identifies the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of each feature type. Finally, the terminal uses the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of all feature types as the change correspondence between the sub-building electricity structure information of the building structure type and the electricity load change characteristics of the building structure type. Among them, the method of identifying each sub-change correspondence is to identify the sub-change correspondence between the historical building electricity structure information of each building structure type and the distribution change characteristics of each feature type through the trained XGB algorithm.

[0117] Based on the above scheme, by identifying the historical building electricity structure information of each building structure type and the sub-change correspondence between the distribution change characteristics of each characteristic type, the sub-building electricity structure information of the building structure type and the change correspondence between the electricity load change characteristics of the building structure type are determined, thereby improving the comprehensiveness and accuracy of the identification.

[0118] Optionally, based on the change correspondence, the power consumption process of each building structure type is simulated through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type to obtain the simulated power load information of each building structure type, and based on the simulated power load information of all building structure types, the predicted power load information of the target building complex is determined, including: obtaining the power consumption structure change strategy of each building structure type, and identifying the simulated power consumption structure information corresponding to each power consumption structure change strategy; for each building structure type, based on the power consumption prediction model corresponding to the building structure type and the change correspondence corresponding to the building structure type, through the building structure type The simulated power consumption structure information of each type is obtained by simulating the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information, and the simulated power load information corresponding to each simulated power consumption structure information of the building structure type is obtained; the simulated power load information corresponding to each simulated power consumption structure information of the building structure type is split into sub-simulated power load information of each building structure in each simulated power consumption structure information corresponding to the building structure type; the sub-simulated power load information of all building structures in each simulated power consumption structure information is distributed and arranged according to the position information of each building structure in the target building complex, and the predicted power load information of the target building complex in each simulated power consumption structure information is obtained.

[0119] In this embodiment, the terminal obtains the power structure change strategy of each building structure type, and identifies each simulated power structure information corresponding to each power structure change strategy. The simulated power structure information includes the structural data parameters of the building structure type of each building structure of each building structure type and the simulated power environment data of the power environment type of each building structure. That is, when identifying each simulated power structure information, the power environment data of each power environment type is adjusted respectively by the single variable method to obtain each simulated power environment data of the power environment type of the building structure.

[0120] For each building structure type, the terminal simulates the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information through each simulated power consumption structure information of the building structure type, based on the power consumption prediction model corresponding to the building structure type and the corresponding change correspondence relationship of the building structure type, to obtain the simulated power load information corresponding to each simulated power consumption structure information of the building structure type. The specific process of obtaining the simulated power load information is to first simulate the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information through the power consumption prediction model corresponding to the building structure type, predict the simulated daily power consumption of each building structure, and then identify the simulated power load information corresponding to each simulated power consumption structure information of the building structure type through the simulated daily power consumption of each building structure of the building structure type and the corresponding change relationship of the building structure type.

[0121] Afterwards, the terminal splits the simulated power load information corresponding to each simulated power structure information of the building structure type into sub-simulated power load information of each building structure in each simulated power structure information corresponding to the building structure type. Finally, the terminal distributes and arranges the sub-simulated power load information of all building structures in each simulated power structure information according to the position information of each building structure in the target building complex, and obtains the predicted power load information of the target building complex in each simulated power structure information. Among them, in each simulated power structure information of each building structure type, except that the structural data parameters of the building structure type of each building structure of the building structure type are different, the simulated power environment data of the power environment type of each building structure of each building structure type is the same.

[0122] Based on the above scheme, the power load simulation of regional building complexes can be realized by combining the analyzed sub-building power structure information of each building structure type and the corresponding relationship between the power load change characteristics of each building structure type. The module integrates data acquisition and transmission interfaces, can monitor the environmental conditions inside and outside the building and the status of power equipment in real time, and conducts real-time analysis and processing through the data processing unit to ensure the real-time and accuracy of load simulation.

[0123] This application also provides an example of simulation identification of building power load, such as Figure 6 As shown, the specific processing process includes the following steps:

[0124] Step S601, obtaining historical electricity consumption data of the target building complex and building complex electricity consumption structure information of the target building complex.

[0125] Step S602: split the target building complex into various building structures, and identify the building structure type of each building structure in the building structure diagram of the target building complex.

[0126] Step S603, split the building complex electricity structure information into sub-building electricity structure information corresponding to each building structure, and summarize the sub-building electricity structure information corresponding to each building structure according to each building structure type to obtain the building electricity structure information of each building structure type.

[0127] Step S604: for each building structure type, split the building electricity structure information of the building structure type into building structure data of each structure type and electricity environment data of each electricity environment type.

[0128] Step S605 , performing data cleaning processing on the building structure data of each structure type and the power environment data of each power environment type to obtain the structure parameter value of each structure type and the power environment parameter value of each power environment type.

[0129] Step S606: Based on the structural parameter values ​​of each structural type and the power consumption environment parameter values ​​of each power consumption environment type, a power consumption prediction model of the building structure type is constructed through a prediction model building strategy.

[0130] Step S607: split the historical electricity consumption data into sub-historical electricity consumption data corresponding to each building structure type.

[0131] Step S608: for each building structure type, data distribution processing is performed on the sub-historical power consumption data of the building structure type to obtain power load distribution information of the building structure type.

[0132] Step S609, filtering the target power load distribution information in the power load distribution information through the distribution screening strategy, and extracting the distribution change characteristics of each characteristic type in the target power load distribution information through the distribution feature extraction network.

[0133] Step S610: Using the distribution change characteristics of each characteristic type as the power load change characteristics of each building structure type.

[0134] Step S611 , for each building structure type, based on the sub-historical electricity usage data of the building structure type, identifying the historical building electricity usage structure information of the building structure type.

[0135] Step S612, based on the distribution change characteristics of each characteristic type of the building structure type and the historical building electricity structure information of the building structure type, identify the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of each characteristic type.

[0136] Step S613, taking the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of all feature types as the change correspondence between the sub-building electricity structure information of the building structure type and the electricity load change characteristics of the building structure type.

[0137] Step S614, obtaining the power consumption structure change strategy of each building structure type, and identifying each simulated power consumption structure information corresponding to each power consumption structure change strategy.

[0138] Step S615, for each building structure type, based on the power consumption prediction model corresponding to the building structure type and the corresponding change correspondence of the building structure type, through each simulated power consumption structure information of the building structure type, the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information is simulated to obtain the simulated power load information corresponding to each simulated power consumption structure information of the building structure type.

[0139] Step S616, splitting the simulated power load information corresponding to each simulated power structure information of the building structure type into sub-simulated power load information of each building structure in each simulated power structure information corresponding to the building structure type.

[0140] Step S617, distribute and arrange the sub-simulation power load information of all building structures in each simulation power load structure information according to the position information of each building structure in the target building complex, and obtain the predicted power load information of the target building complex in each simulation power load structure information.

[0141] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0142] Based on the same inventive concept, the embodiment of the present application also provides a device for simulating and identifying building power loads for implementing the method for simulating and identifying building power loads mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more simulating and identifying devices for building power loads provided below can refer to the limitations of the method for simulating and identifying building power loads above, and will not be repeated here.

[0143] In an exemplary embodiment, Figure 7 As shown, a simulation identification device for building power load is provided, including: an acquisition module 710, a splitting module 720, an identification module 730 and a determination module 740, wherein:

[0144] The acquisition module 710 is used to acquire the historical power consumption data of the target building group and the building group power consumption structure information of the target building group, and split the building group power consumption structure information into building power consumption structure information of each building structure type;

[0145] The splitting module 720 is used to construct a power consumption prediction model for each building structure type based on the building power consumption structure information of each building structure type, and split the historical power consumption data into sub-historical power consumption data corresponding to each building structure type;

[0146] The identification module 730 is used to identify the power load change characteristics of each building structure type based on the sub-historical power consumption data corresponding to each building structure type, and identify the change correspondence between the sub-building power consumption structure information of each building structure type and the power load change characteristics of each building structure type based on the power consumption change characteristics of each building structure type;

[0147] Determination module 740 is used to simulate the power consumption process of each building structure type based on the change correspondence, through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type, to obtain the simulated power load information of each building structure type, and determine the predicted power load information of the target building complex based on the simulated power load information of all building structure types.

[0148] Optionally, the acquisition module 710 is specifically configured to:

[0149] Splitting the target building complex into individual building structures, and identifying the building structure type of each building structure in the building structure diagram of the target building complex;

[0150] The electricity consumption structure information of the building complex is split into sub-building electricity consumption structure information corresponding to each building structure, and the sub-building electricity consumption structure information corresponding to each building structure is aggregated according to each building structure type to obtain the building electricity consumption structure information of each building structure type.

[0151] Optionally, the splitting module 720 is specifically used to:

[0152] For each building structure type, splitting the building power structure information of the building structure type into building structure data of each structure type and power environment data of each power environment type;

[0153] Performing data cleaning processing on the building structure data of each of the structural types and the power environment data of each of the power environment types to obtain the structural parameter values ​​of each of the structural types and the power environment parameter values ​​of each of the power environment types;

[0154] Based on the structural parameter values ​​of each of the structural types and the power consumption environment parameter values ​​of each of the power consumption environment types, a power consumption prediction model of the building structure type is constructed through a prediction model building strategy.

[0155] Optionally, the identification module 730 is specifically configured to:

[0156] For each building structure type, performing data distribution processing on the sub-historical power consumption data of the building structure type to obtain power load distribution information of the building structure type;

[0157] Filter the target power load distribution information in the power load distribution information through a distribution screening strategy, and respectively extract the distribution change characteristics of each feature type in the target power load distribution information through a distribution feature extraction network;

[0158] The distribution change characteristics of each characteristic type are used as the power load change characteristics of each building structure type.

[0159] Optionally, the identification module 730 is specifically configured to:

[0160] For each building structure type, based on the sub-historical electricity consumption data based on the building structure type, identifying the historical building electricity consumption structure information of the building structure type;

[0161] Based on the distribution change characteristics of each characteristic type of the building structure type and the historical building electricity structure information of the building structure type, identifying the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of each characteristic type;

[0162] The sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of all feature types is used as the change correspondence between the sub-building electricity structure information of the building structure type and the electricity load change characteristics of the building structure type.

[0163] Optionally, the determining module 740 is specifically configured to:

[0164] Acquire the power consumption structure change strategy of each of the building structure types, and identify each simulated power consumption structure information corresponding to each power consumption structure change strategy;

[0165] For each building structure type, based on the power consumption prediction model corresponding to the building structure type and the corresponding change correspondence relationship of the building structure type, through each simulated power consumption structure information of the building structure type, the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information is simulated to obtain the simulated power load information corresponding to each simulated power consumption structure information of the building structure type;

[0166] Splitting the simulated power load information corresponding to each simulated power structure information of the building structure type into sub-simulated power load information of each building structure in each simulated power structure information corresponding to the building structure type;

[0167] The sub-simulated power load information of all building structures in each simulated power structure information is distributed and arranged according to the position information of each building structure in the target building complex to obtain the predicted power load information of the target building complex in each simulated power structure information.

[0168] Each module in the above-mentioned simulation identification device for building power load can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0169] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a simulation identification method for building power load is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0170] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0171] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0172] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0173] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0176] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A simulation identification method for building power load, characterized in that: The method comprises: Acquire historical electricity consumption data of a target building complex and building complex electricity consumption structure information of the target building complex, and split the building complex electricity consumption structure information into building electricity consumption structure information of each building structure type; Based on the building electricity consumption structure information of each building structure type, construct an electricity consumption prediction model for each building structure type, and split the historical electricity consumption data into sub-historical electricity consumption data corresponding to each building structure type; Based on the sub-historical electricity consumption data corresponding to each building structure type, identifying the electricity load change characteristics of each building structure type, and based on the electricity consumption change characteristics of each building structure type, identifying the change correspondence between the sub-building electricity consumption structure information of each building structure type and the electricity load change characteristics of each building structure type; Based on the change correspondence, the power consumption process of each building structure type is simulated through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type to obtain the simulated power load information of each building structure type, and based on the simulated power load information of all building structure types, the predicted power load information of the target building complex is determined.

2. The method according to claim 1, characterized in that The step of splitting the building complex power consumption structure information into building power consumption structure information of each building structure type includes: Splitting the target building complex into individual building structures, and identifying the building structure type of each building structure in the building structure diagram of the target building complex; The electricity consumption structure information of the building complex is split into sub-building electricity consumption structure information corresponding to each building structure, and the sub-building electricity consumption structure information corresponding to each building structure is aggregated according to each building structure type to obtain the building electricity consumption structure information of each building structure type.

3. The method according to claim 2, characterized in that The step of constructing a power consumption prediction model for each building structure type based on the building power consumption structure information of each building structure type includes: For each building structure type, splitting the building power structure information of the building structure type into building structure data of each structure type and power environment data of each power environment type; Performing data cleaning processing on the building structure data of each of the structural types and the power environment data of each of the power environment types to obtain the structural parameter values ​​of each of the structural types and the power environment parameter values ​​of each of the power environment types; Based on the structural parameter values ​​of each of the structural types and the power consumption environment parameter values ​​of each of the power consumption environment types, a power consumption prediction model of the building structure type is constructed through a prediction model building strategy.

4. The method according to claim 1, characterized in that The identifying the power load change characteristics of each building structure type based on the sub-historical power consumption data corresponding to each building structure type includes: For each building structure type, performing data distribution processing on the sub-historical power consumption data of the building structure type to obtain power load distribution information of the building structure type; Filter the target power load distribution information in the power load distribution information through a distribution screening strategy, and respectively extract the distribution change characteristics of each feature type in the target power load distribution information through a distribution feature extraction network; The distribution change characteristics of each characteristic type are used as the power load change characteristics of each building structure type.

5. The method according to claim 4, characterized in that The identifying the corresponding relationship between the sub-building power structure information of each building structure type and the power load change characteristics of each building structure type based on the power consumption change characteristics of each building structure type includes: For each building structure type, based on the sub-historical electricity consumption data based on the building structure type, identifying the historical building electricity consumption structure information of the building structure type; Based on the distribution change characteristics of each characteristic type of the building structure type and the historical building electricity structure information of the building structure type, identifying the sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of each characteristic type; The sub-change correspondence between the historical building electricity structure information of the building structure type and the distribution change characteristics of all feature types is used as the change correspondence between the sub-building electricity structure information of the building structure type and the electricity load change characteristics of the building structure type.

6. The method according to claim 1, characterized in that Based on the change correspondence, the power consumption process of each building structure type is simulated through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type to obtain the simulated power load information of each building structure type, and based on the simulated power load information of all building structure types, the predicted power load information of the target building complex is determined, including: Acquire the power consumption structure change strategy of each of the building structure types, and identify each simulated power consumption structure information corresponding to each power consumption structure change strategy; For each building structure type, based on the power consumption prediction model corresponding to the building structure type and the corresponding change correspondence relationship of the building structure type, through each simulated power consumption structure information of the building structure type, the power consumption process of each building structure corresponding to the building structure type in each simulated power consumption structure information is simulated to obtain the simulated power load information corresponding to each simulated power consumption structure information of the building structure type; Splitting the simulated power load information corresponding to each simulated power structure information of the building structure type into sub-simulated power load information of each building structure in each simulated power structure information corresponding to the building structure type; The sub-simulated power load information of all building structures in each simulated power structure information is distributed and arranged according to the position information of each building structure in the target building complex to obtain the predicted power load information of the target building complex in each simulated power structure information.

7. A simulation identification device for building power load, characterized in that: The device comprises: An acquisition module, used to acquire historical electricity consumption data of a target building complex and building electricity consumption structure information of the target building complex, and split the building electricity consumption structure information into building electricity consumption structure information of each building structure type; A splitting module, for constructing a power consumption prediction model for each building structure type based on the building power consumption structure information of each building structure type, and splitting the historical power consumption data into sub-historical power consumption data corresponding to each building structure type; An identification module is used to identify the power load change characteristics of each building structure type based on the sub-historical power consumption data corresponding to each building structure type, and based on the power consumption change characteristics of each building structure type, identify the change correspondence between the sub-building power consumption structure information of each building structure type and the power load change characteristics of each building structure type; A determination module is used to simulate the power consumption process of each building structure type based on the change correspondence, through the power consumption prediction model of each building structure type and the power consumption structure change strategy of each building structure type, to obtain the simulated power load information of each building structure type, and determine the predicted power load information of the target building complex based on the simulated power load information of all building structure types.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images