Maintenance method of digital twin model for power marketing operations based on consistency constraints

Abstract

This application relates to a method for maintaining a digital twin model of electricity marketing operations based on consistency constraints. The method includes: acquiring a digital twin model corresponding to the electricity marketing operation, and monitoring data collected from at least two data sources for the electricity marketing operation; determining consistency constraint dimensions matching the electricity marketing operation based on the maintenance requirements of the digital twin model; performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimensions to obtain consistency constraint data matching the digital twin model; and using the consistency constraint data to maintain the digital twin model to obtain an updated model corresponding to the electricity marketing operation. This method can improve the prediction accuracy of the digital twin model corresponding to the electricity marketing operation.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method for maintaining a digital twin model of power marketing operations based on consistency constraints. Background Technology

[0002] With the gradual liberalization of the electricity market, electricity marketing operations are facing unprecedented challenges. Electricity marketing must not only ensure a balance between supply and demand but also achieve optimal allocation of electricity resources in a market-driven environment. Therefore, traditional electricity marketing methods can no longer meet the needs of refined management, especially when dealing with rapidly changing electricity loads, dispatching, and market demands; traditional methods struggle to make real-time and accurate dynamic adjustments.

[0003] Against this backdrop, digital twin technology has emerged. By constructing a digital twin model based on digital twin technology, the operational status of the real world can be mapped based on the digital twin model. In this way, various dynamic changes in power marketing operations can be effectively simulated, providing strong support for optimizing decision-making, reducing costs, and improving efficiency.

[0004] However, current digital twin models suffer from low prediction accuracy. Summary of the Invention

[0005] Therefore, it is necessary to provide a consistency-consistency-based digital twin model maintenance method for power marketing operations, which can improve the prediction accuracy of the digital twin model corresponding to power marketing operations, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for maintaining a digital twin model of electricity marketing operations based on consistency constraints, comprising: acquiring a digital twin model corresponding to the electricity marketing operations, and monitoring data collected from at least two data sources for the electricity marketing operations; determining consistency constraint dimensions matching the electricity marketing operations based on the maintenance requirements of the digital twin model; performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimensions to obtain consistency constraint data matching the digital twin model; and using the consistency constraint data to maintain the digital twin model to obtain an updated model corresponding to the electricity marketing operations.

[0007] In one embodiment, the consistency constraint dimension includes at least one sub-constraint dimension; consistency analysis is performed on the monitoring data corresponding to each data source based on the consistency constraint dimension to obtain consistency constraint data matching the digital twin model, including: for each sub-constraint dimension, consistency analysis is performed on the monitoring data corresponding to each data source based on the sub-constraint dimension to obtain the corresponding dimension analysis data under the sub-constraint dimension; based on the corresponding dimension analysis data under the sub-constraint dimension, the weight coefficient corresponding to the sub-constraint dimension is determined; and the weight coefficients corresponding to each sub-constraint dimension and the corresponding dimension analysis data are weighted and summed to obtain consistency constraint data matching the power marketing operation.

[0008] In one embodiment, consistency analysis is performed on the monitoring data corresponding to each data source based on the sub-constraint dimension to obtain the dimensional analysis data corresponding to the sub-constraint dimension. This includes: selecting a target data source from each data source and determining the remaining data sources other than the target data source; obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension based on the difference features between the monitoring data corresponding to the target data source and each remaining data source; taking the next data source adjacent to the target data source in each data source as the new target data source, and returning to the step of determining the remaining data sources other than the target data source in each data source; and determining the data set containing the target analysis data corresponding to each target data source under the sub-constraint dimension as the dimensional analysis data corresponding to the sub-constraint dimension according to the order of the target data sources.

[0009] In one embodiment, the sub-constraint dimension includes a data consistency dimension; the method further includes: obtaining the covariance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources, the covariance being used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources; based on the difference features between the monitoring data corresponding to the target data source and each of the remaining data sources, obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension, including: obtaining a first standard deviation matching the monitoring data corresponding to the target data source and a second standard deviation matching the monitoring data corresponding to the remaining data sources; and obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension based on each covariance, the first standard deviation, and each second standard deviation corresponding to the target data source.

[0010] In one embodiment, the sub-constraint dimension includes a time consistency dimension, and the monitoring data includes multiple sub-data. The method further includes: dividing the detection time window of the target data source to obtain multiple sub-detection times; for each sub-detection time, obtaining the data difference between the sub-data of the remaining data sources at the sub-detection time and the sub-data of the target data source at the sub-detection time; the data difference is used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources; based on the difference features between the monitoring data corresponding to the target data source and each remaining data source, obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension, including: obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension based on the number of sub-detection times corresponding to the target data source and the data differences corresponding to each sub-detection time.

[0011] In one embodiment, the sub-constraint dimension includes a spatial consistency dimension; the method further includes: obtaining the data distance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources, the data distance being used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources; and obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension based on the difference features between the monitoring data corresponding to the target data source and each of the remaining data sources, including: obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension based on the data distances corresponding to the target data source and the number of data sources of at least two data sources.

[0012] In one embodiment, the dimensional analysis data includes target analysis data corresponding to each target data source. Determining the weight coefficients corresponding to the sub-constraint dimensions based on the dimensional analysis data corresponding to the sub-constraint dimensions includes: normalizing each target analysis data corresponding to the sub-constraint dimensions to obtain target normalized data corresponding to each target analysis data; for each target analysis data, obtaining the entropy value corresponding to the target analysis data based on the target normalized data and the number of data sources; obtaining the sub-coefficients corresponding to each target analysis data under the sub-constraint dimensions based on the maximum entropy value among the entropy values ​​corresponding to each target analysis data and the entropy values ​​corresponding to each target analysis data; and obtaining the weight coefficients corresponding to the sub-constraint dimensions based on the sub-coefficients corresponding to each target analysis data under the sub-constraint dimensions.

[0013] Secondly, this application provides a device for maintaining a digital twin model of power marketing operations based on consistency constraints. The device includes: an acquisition module for acquiring a digital twin model corresponding to the power marketing operation and monitoring data collected from at least two data sources for the power marketing operation; a determination module for determining a consistency constraint dimension matching the power marketing operation based on the maintenance requirements of the digital twin model; a processing module for performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimension to obtain consistency constraint data matching the digital twin model; and a maintenance module for maintaining the digital twin model using the consistency constraint data to obtain an updated model corresponding to the power marketing operation.

[0014] Thirdly, this application also provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring a digital twin model corresponding to the power marketing operation, and monitoring data collected from at least two data sources for the power marketing operation; determining a consistency constraint dimension matching the power marketing operation based on the maintenance requirements of the digital twin model; performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimension to obtain consistency constraint data matching the digital twin model; and maintaining the digital twin model using the consistency constraint data to obtain an updated model corresponding to the power marketing operation.

[0015] Fourthly, this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the following steps: acquiring a digital twin model corresponding to the power marketing operation, and monitoring data collected from at least two data sources for the power marketing operation; determining a consistency constraint dimension matching the power marketing operation based on the maintenance requirements of the digital twin model; performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimension to obtain consistency constraint data matching the digital twin model; and maintaining the digital twin model using the consistency constraint data to obtain an updated model corresponding to the power marketing operation.

[0016] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps: acquiring a digital twin model corresponding to power marketing operations, and monitoring data collected from at least two data sources for power marketing operations; determining consistency constraint dimensions matching the power marketing operations based on the maintenance requirements of the digital twin model; performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimensions to obtain consistency constraint data matching the digital twin model; and maintaining the digital twin model using the consistency constraint data to obtain an updated model corresponding to the power marketing operations.

[0017] The aforementioned method for maintaining a digital twin model of power marketing operations based on consistency constraints involves acquiring a digital twin model corresponding to the power marketing operations and monitoring data collected from at least two data sources for each operation. Based on the maintenance requirements of the digital twin model, it determines the consistency constraint dimensions that match the power marketing operations. Then, it performs consistency analysis on the monitoring data corresponding to each data source based on these consistency constraint dimensions to obtain consistency constraint data matching the digital twin model. This consistency constraint data is then used to maintain the digital twin model, resulting in an updated model for the power marketing operations. Therefore, by adjusting the parameters of the digital twin model corresponding to the power marketing operations based on the feedback from the data corrected for consistency constraints, the fidelity between the model and the actual power system state can be ensured. This allows the digital twin model to adapt to dynamic changes in the power system and improves the prediction accuracy of the digital twin model in power marketing operations. Attached Figure Description

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a flowchart illustrating a method for maintaining a digital twin model of electricity marketing operations based on consistency constraints in one embodiment.

[0020] Figure 2 This is a flowchart illustrating the process of performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimension in one embodiment to obtain consistency constraint data that matches the digital twin model.

[0021] Figure 3 This is a flowchart illustrating the process of performing consistency analysis on monitoring data corresponding to each data source based on sub-constraint dimensions in one embodiment to obtain dimensional analysis data corresponding to the sub-constraint dimensions.

[0022] Figure 4 This is a flowchart illustrating the process of determining the weight coefficients corresponding to sub-constraint dimensions based on dimensional analysis data under the sub-constraint dimensions in one embodiment.

[0023] Figure 5 This is a flowchart illustrating a method for maintaining a digital twin model of electricity marketing operations based on consistency constraints, as described in another embodiment.

[0024] Figure 6This is a structural block diagram of a digital twin model maintenance device for electricity marketing operations based on consistency constraints in one embodiment;

[0025] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. Detailed Implementation

[0026] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0027] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0029] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0030] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0031] Existing digital twin models are generally based on historical data and fixed algorithms for modeling and prediction. With the dynamic changes in the electricity market, existing models often cannot adjust parameters in a timely manner, resulting in a gradual increase in prediction errors. This makes existing technologies lack sufficient flexibility and adaptability in dealing with fluctuations in electricity load and changes in market demand.

[0032] In addition, the data used to train existing digital twin models mostly comes from different sources. These data may be inconsistent due to differences in collection methods, data formats, or transmission processes, resulting in low model accuracy. Because no effective solutions have been provided for this data inconsistency problem, the models cannot reflect the state of the real world in real time and accurately, which affects the decision-making efficiency of electricity marketing operations.

[0033] Current methods for continuously calibrating digital twin models lead to a decline in accuracy over long-term use. While incremental learning can improve accuracy, it fails to address the consistency constraints of the data used for training, resulting in low stability and reliability in complex environments. Furthermore, existing calibration methods often require complex calculations on large datasets, leading to long system response times and failing to meet the real-time and efficiency requirements of power marketing operations. In large-scale power systems, slow update speeds and high computational resource consumption often prevent real-time scheduling and forecasting tasks from being completed.

[0034] In view of this, this application provides a method for maintaining a digital twin model of power marketing operations based on consistency constraints. This method can be applied to a server in a maintenance system. Specifically, the server is used to acquire the digital twin model corresponding to the power marketing operation, as well as monitoring data collected from at least two data sources for the power marketing operation. Based on the maintenance requirements of the digital twin model, it determines the consistency constraint dimensions that match the power marketing operation, and performs consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimensions to obtain consistency constraint data that matches the digital twin model. Then, the consistency constraint data is used to maintain the digital twin model to obtain an updated model corresponding to the power marketing operation.

[0035] The server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0036] In one embodiment, such as Figure 1 As shown, a method for maintaining a digital twin model of electricity marketing operations based on consistency constraints is provided. Taking the application of this method to a server in a maintenance system as an example, the method includes the following steps:

[0037] S102, acquire the digital twin model corresponding to the electricity marketing operation, as well as the monitoring data collected from at least two data sources for the electricity marketing operation.

[0038] The digital twin model corresponding to electricity marketing operations is used to simulate these operations. The data content used to train the digital twin model varies depending on the specific electricity marketing operation. For example, if electricity marketing operations represent load forecasting, the corresponding data may include historical electricity load data; if electricity marketing operations represent electricity price analysis, the corresponding data may include electricity market transaction data and user electricity consumption data.

[0039] Here, "data source" refers to the equipment used to collect data required for electricity marketing operations. Data sources include, but are not limited to, sensors, metering equipment, and telemetry equipment. For example, data required for electricity marketing operations can be collected from the power system.

[0040] In some embodiments, monitoring data may include power load data. Power load data refers to the power demand data at various load points in the power system, including but not limited to: instantaneous load power, peak and valley electricity consumption data, historical load curves, and regional load data.

[0041] In some embodiments, monitoring data may include power grid status data. Power grid status data is used to reflect the operating status of the power system's power network, including voltage, frequency, power factor, network topology, etc.

[0042] In one embodiment, the monitoring data may include equipment operating status data of electrical equipment in the power system. Equipment operating status data reflects the health status of the electrical equipment and includes, but is not limited to: equipment temperature, equipment vibration data, operating time, fault alarm information, and maintenance record data.

[0043] S104, Based on the maintenance requirements of the digital twin model, determine the consistency constraint dimensions that match the power marketing operations.

[0044] In this embodiment, maintenance requirements are used to characterize the model optimization requirements of the digital twin model. Consistency constraint dimensions refer to the dimensions considered when optimizing the digital twin model. Consistency constraint dimensions include at least one sub-consistency dimension, which may include, but is not limited to, format consistency dimension, data consistency dimension, temporal consistency dimension, and spatial consistency dimension.

[0045] Among them, the format consistency dimension is used to characterize the analysis of monitoring data from the data format dimension, the data consistency dimension is used to characterize the analysis of monitoring data from the data content dimension, the time consistency dimension is used to characterize the analysis of monitoring data from the data collection time dimension, and the spatial consistency dimension is used to characterize the analysis of monitoring data from the data spatial dimension.

[0046] In this embodiment, the method for determining the maintenance requirements of the digital twin model based on the maintenance requirements of the digital twin model and the consistency constraint dimension that matches the power marketing operation is not limited.

[0047] In one implementation, when the usage time of the digital twin model reaches a preset duration, it is determined that the digital twin model meets maintenance requirements. Based on the mapping relationship between usage time and sub-constraint dimensions, and the usage time of the digital twin model, consistency constraint dimensions that match electricity marketing operations are determined. The longer the usage time, the more sub-constraint dimensions are required.

[0048] In one embodiment, when the error between the input data of the digital twin model and the predicted data of the digital twin model based on the input data exceeds a preset threshold, the digital twin model is determined to meet the maintenance requirements; the preset sub-constraint dimensions configured for the maintenance requirements are determined as consistency constraint dimensions that match the power marketing operations. For example, the preset sub-constraint dimensions may include data consistency dimensions, spatial consistency dimensions, and temporal consistency dimensions, or other settings may be used.

[0049] S106. Based on the consistency constraint dimension, perform consistency analysis on the monitoring data corresponding to each data source to obtain consistency constraint data that matches the digital twin model.

[0050] Among them, the consistency constraint dimension is used to ensure that data collected from different data sources can meet certain consistency requirements when input into the digital twin model, preventing model prediction errors caused by inconsistencies between data sources and improving data collaboration among multiple data sources.

[0051] The consistency constraint dimension can include at least one sub-constraint dimension. Consistency analysis is performed on the monitoring data corresponding to each data source based on the consistency constraint dimension, and there is no limit to the way to obtain consistency constraint data that matches the digital twin model.

[0052] In one implementation, for each sub-constraint dimension, based on the mapping relationship between the sub-constraint dimension and the preset analysis strategy, the preset analysis strategy that matches the sub-constraint dimension corresponding to the power marketing operation is determined as the target strategy for the power marketing operation under the sub-constraint dimension; the target strategy corresponding to the sub-constraint dimension is used to perform consistency analysis on the monitoring data corresponding to each data source to obtain the dimension analysis results corresponding to the sub-constraint dimension; based on the dimension analysis results corresponding to each sub-constraint dimension, consistent constraint data matching the digital twin model is obtained.

[0053] In some embodiments, the monitoring data corresponding to each data source can be preprocessed to obtain preprocessed data for each data source. For each data source, the preprocessed data is used as the monitoring data for the new data source, and consistency analysis is performed on the monitoring data corresponding to each data source based on the consistency constraint dimension to obtain consistency constraint data that matches the digital twin model. In other words, the consistency analysis process based on the consistency constraint dimension is performed only after the monitoring data corresponding to each data source has been preprocessed.

[0054] In some cases, data preprocessing includes noise suppression and data normalization. In some embodiments, a Kalman filter can be used to suppress noise in the monitoring data to filter out interference from external environmental factors on the acquisition results. In some embodiments, Z-score normalization can be used to normalize the monitoring data to eliminate dimensional differences.

[0055] S108, use consistency constraint data to maintain the digital twin model and obtain the updated model corresponding to the power marketing operation.

[0056] The updated model refers to the model after the digital twin model has been maintained (i.e., updated). The application of the updated model is not limited. For example, it can be used for load forecasting and electricity price analysis.

[0057] In some embodiments, the incremental learning method is invoked to update the parameters of the digital twin model using consistency constraint data, thereby obtaining an updated model corresponding to the power marketing operation.

[0058] For example, the parameters of a digital twin model can be represented as a mapping function. , This represents the various parameters in the digital twin model, where X is the consistency constraint data. The output of the digital twin model for X. This represents the actual output corresponding to X. The parameters of the digital twin model are dynamically updated using an incremental learning method, allowing it to gradually adapt to new data.

[0059] Specifically, by adjusting the parameters To minimize the model output Compared with actual output The error between them The specific update formula is as follows:

[0060]

[0061] in, The update step size is used to control the learning rate. The loss function can be the mean squared error, or other types of loss functions can be used. loss function Adjusting parameters The gradient.

[0062] For example, taking mean squared error as the loss function, it satisfies:

[0063]

[0064] The gradient vector, composed of the partial derivatives of all parameters, can be obtained from the loss function. The gradient vector satisfies:

[0065]

[0066] Therefore, all parameters of the digital twin model can be updated synchronously to satisfy:

[0067]

[0068] based on Figure 1 The process involves acquiring a digital twin model corresponding to electricity marketing operations and monitoring data collected from at least two data sources for these operations. Based on the maintenance requirements of the digital twin model, a consistency constraint dimension matching the electricity marketing operations is determined. Consistency analysis is then performed on the monitoring data from each data source based on this constraint dimension to obtain consistency constraint data matching the digital twin model. This consistency constraint data is then used to maintain the digital twin model, resulting in an updated model for the electricity marketing operations. By adjusting the parameters of the digital twin model corresponding to the electricity marketing operations based on the feedback from the data corrected for consistency constraints, the fidelity between the model and the actual power system state can be ensured. This allows the digital twin model to adapt to dynamic changes in the power system and improves its predictive accuracy in electricity marketing operations.

[0069] In one embodiment, the consistency constraint dimension includes at least one sub-constraint dimension. For example, the implementation method of performing consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimension to obtain consistency constraint data matching the digital twin model (i.e., S106) can be as follows: Figure 2 As shown, it includes the following steps:

[0070] S202, for each sub-constraint dimension, perform consistency analysis on the monitoring data corresponding to each data source based on the sub-constraint dimension to obtain the corresponding dimension analysis data under the sub-constraint dimension.

[0071] For example, based on the mapping relationship between sub-constraint dimensions and preset analysis strategies, the preset analysis strategy that matches the sub-constraint dimension corresponding to the power marketing operation can be determined as the target strategy under the sub-constraint dimension; based on the target strategy under the sub-constraint dimension, consistency analysis is performed on the monitoring data corresponding to each data source to obtain the dimension analysis data under the sub-constraint dimension.

[0072] S204, Based on the dimensional analysis data corresponding to the sub-constraint dimension, determine the weight coefficients corresponding to the sub-constraint dimension.

[0073] There are no restrictions on the method for determining the weight coefficients of the sub-constraint dimensions based on the dimensional analysis data corresponding to the sub-constraint dimensions.

[0074] In one implementation, for the dimensional analysis data corresponding to the sub-constraint dimension, a first preset coefficient matching the dimensional analysis data is obtained; based on the mapping relationship between the sub-constraint dimension and the preset coefficient, the preset coefficient matching the sub-constraint dimension corresponding to the power marketing operation can be determined as the second preset coefficient; based on the first preset coefficient and the second preset coefficient, the weight coefficient corresponding to the sub-constraint dimension is determined.

[0075] In some cases, the average of the first and second preset coefficients can be used as the weight coefficient corresponding to the sub-constraint dimension. Alternatively, the maximum value of the first and second preset coefficients can be used as the weight coefficient corresponding to the sub-constraint dimension.

[0076] S206, weighted summation is performed on the weight coefficients and dimensional analysis data corresponding to each sub-constraint dimension to obtain consistent constraint data that matches the power marketing operation.

[0077] for example, This represents data with consistency constraints. This represents monitoring data from different data sources. Taking consistency constraints, including data consistency, time consistency, and spatial consistency, as an example... satisfy:

[0078]

[0079] in, This represents the weight coefficient corresponding to the sub-constraint dimension being a data consistency dimension. This indicates the dimensional analysis results when the sub-constraint dimension is a data consistency dimension. This represents the weight coefficient corresponding to the sub-constraint dimension being the time consistency dimension. This indicates the dimensional analysis results when the sub-constraint dimension is a time consistency dimension. This represents the weight coefficient corresponding to the sub-constraint dimension being the spatial consistency dimension. This indicates the dimensional analysis results when the sub-constraint dimension is a spatial consistency dimension.

[0080] It should be understood that Used to characterize the correlation results between data sources Used to characterize the time consistency results between data sources Used to characterize spatial consistency results between data sources.

[0081] based on Figure 2 The content shown is obtained by weighting and summing the weight coefficients and dimensional analysis data corresponding to each sub-constraint dimension to obtain consistent constraint data that matches the power marketing operation. Thus, by comprehensively considering each constraint dimension, the consistency of data analysis between data sources can be improved, and the model prediction accuracy can be further enhanced.

[0082] In one embodiment, the implementation method of performing consistency analysis on the monitoring data corresponding to each data source based on the sub-constraint dimension to obtain the dimensional analysis data corresponding to the sub-constraint dimension (i.e., S202) can be as follows: Figure 3 As shown, it includes the following steps:

[0083] S302, Select the target data source from the data sources, and determine the remaining data sources other than the target data source.

[0084] For example, the target data source can be selected from the data sources in the order they appear. For instance, the first data source can be designated as the target data source, and all other data sources can be designated as the remaining data sources; the second data source can be designated as the target data source, and all other data sources can be designated as the remaining data sources, and so on.

[0085] S304. Based on the differences between the monitoring data corresponding to the target data source and each remaining data source, obtain the target analysis data corresponding to the target data source under the sub-constraint dimension.

[0086] There are no restrictions on the method of obtaining the target analysis data corresponding to the target data source under the sub-constraint dimension, based on the difference characteristics between the monitoring data corresponding to the target data source and each remaining data source.

[0087] In one implementation, for each remaining data source, the data difference between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources is taken as the difference feature between the monitoring data corresponding to the target data source and the remaining data sources respectively; the set of data differences representing each difference feature is determined as the target analysis data corresponding to the target data source under the sub-constraint dimension.

[0088] S306, take the next data source adjacent to the target data source in each data source as the new target data source, and return the steps for determining each remaining data source in each data source other than the target data source.

[0089] S308, according to the order of the target data sources, determine the data set containing the target analysis data corresponding to each target data source under the sub-constraint dimension as the dimensional analysis data corresponding to the sub-constraint dimension.

[0090] based on Figure 3 The content shown demonstrates that by comparing the target data source with other remaining data sources, the target analysis data corresponding to the target data source under the sub-constraint dimension can be obtained, which can improve the analysis accuracy and further improve the model training accuracy.

[0091] In one embodiment, the sub-constraint dimension includes a data consistency dimension. For example, obtaining the target analysis data (i.e., S304) corresponding to the target data source under the sub-constraint dimension based on the difference characteristics between the monitoring data corresponding to the target data source and each remaining data source may include the following steps:

[0092] S11, obtain the covariance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources. The covariance is used to characterize the difference between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources.

[0093] For example, if the monitoring data includes multiple sub-data, then based on the multiple sub-data corresponding to the target data source and the multiple sub-data corresponding to the remaining data sources, the covariance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources can be obtained.

[0094] S12, obtain the first standard deviation that matches the monitoring data corresponding to the target data source, and the second standard deviation that matches the monitoring data corresponding to the remaining data sources.

[0095] For example, if the monitoring data includes multiple sub-data, then a first standard deviation matching the monitoring data corresponding to the target data source can be obtained based on the multiple sub-data corresponding to the target data source; similarly, a second standard deviation matching the monitoring data corresponding to the remaining data sources can be obtained.

[0096] S13. Based on the covariance, first standard deviation and second standard deviation of the target data source, obtain the target analysis data corresponding to the target data source under the sub-constraint dimension.

[0097] For example, if the sub-constraint dimension includes a data consistency dimension, then the target analysis data corresponding to the target data source under the data consistency dimension satisfies:

[0098]

[0099] Where N represents the number of data sources, This indicates the monitoring data corresponding to the target data source. This represents the target analysis data corresponding to the target data source under the data consistency dimension. This indicates the monitoring data corresponding to the remaining data sources. This represents the covariance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources. This represents the first standard deviation of the monitoring data that matches the target data source. This represents the second standard deviation that matches the monitoring data corresponding to the remaining data sources.

[0100] Furthermore, for each target data source, by combining the target analysis data corresponding to each target data source, we can obtain the dimensional analysis data corresponding to the data consistency dimension.

[0101] for example, This indicates the dimensional analysis results corresponding to the data consistency dimension. satisfy:

[0102]

[0103] Based on the content shown in S11-S13, by considering the covariance and standard deviation between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources, the accuracy of data analysis can be improved from the perspective of data consistency, and the accuracy of model maintenance can be further improved.

[0104] In one embodiment, the sub-constraint dimension includes a time consistency dimension. For example, obtaining the target analysis data (i.e., S304) corresponding to the target data source under the sub-constraint dimension based on the difference characteristics between the monitoring data corresponding to the target data source and each remaining data source may include the following steps:

[0105] S21, divide the detection time window of the target data source to obtain multiple sub-detection times.

[0106] The detection time windows for different target data sources can be the same or different.

[0107] For example, if the monitoring data includes multiple sub-data, then the latest collection time and the earliest collection time are determined based on the collection time of each of the multiple sub-data corresponding to the target data source; and the detection time window is determined based on the time interval between the latest collection time and the earliest collection time.

[0108] In some cases, the acquisition time window, consisting of the time interval between the latest and earliest acquisition times, can be defined as the detection time window. Alternatively, a portion of the acquisition time window can be defined as the detection time window, meaning the acquisition time window includes the detection time window.

[0109] S22, for each sub-detection time, obtain the data difference between the sub-data of the remaining data source at the sub-detection time and the sub-data of the target data source at the sub-detection time; the data difference is used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data source.

[0110] For example, data differences can be characterized as data discrepancies.

[0111] S23. Based on the number of sub-detection times corresponding to the target data source and the differences in data at each sub-detection time, obtain the target analysis data corresponding to the target data source under the sub-constraint dimension.

[0112] For example, the sub-constraint dimension includes a time consistency dimension, under which the target analysis data corresponding to the target data source satisfies:

[0113]

[0114] Where T represents the number of sub-detection times corresponding to the target data source. This represents the target analysis data corresponding to the target data source under the time consistency dimension. This represents the data difference between the sub-data from the remaining data source at sub-detection time t and the sub-data from the target data source at sub-detection time t.

[0115] Furthermore, for each target data source, by combining the target analysis data corresponding to each target data source, we can obtain the corresponding dimensional analysis data under the time consistency dimension.

[0116] for example, This indicates the dimensional analysis results corresponding to the time consistency dimension. satisfy:

[0117]

[0118] Based on the content shown in S21-S23, by analyzing the data differences between the sub-data of the remaining data source at the sub-detection time and the sub-data of the target data source at the sub-detection time, the accuracy of analysis can be improved from the perspective of time consistency, and the accuracy of model maintenance can be further improved.

[0119] In one embodiment, the sub-constraint dimension includes a spatial consistency dimension. For example, obtaining the target analysis data (i.e., S304) corresponding to the target data source under the sub-constraint dimension based on the difference characteristics between the monitoring data corresponding to the target data source and each remaining data source may include the following steps:

[0120] S31, obtain the data distance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources. The data distance is used to characterize the difference between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources.

[0121] Data distance can refer to Euclidean distance or other types of spatial distance.

[0122] S32, based on the data distances corresponding to the target data source and the number of data sources of at least two data sources, obtain the target analysis data corresponding to the target data source under the sub-constraint dimension.

[0123] For example, taking Euclidean distance as the data distance, the sub-constraint dimensions include spatial consistency dimension. Under the spatial consistency dimension, the target analysis data corresponding to the target data source satisfies:

[0124]

[0125] in, This represents the target analysis data corresponding to the target data source under the spatial consistency dimension. This represents the Euclidean distance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources.

[0126] Furthermore, for each target data source, by combining the target analysis data corresponding to each target data source, we can obtain the dimensional analysis data corresponding to the spatial consistency dimension.

[0127] for example, The result of the dimensional analysis corresponding to the spatial consistency dimension is then... satisfy:

[0128]

[0129] Based on the content shown in S31-S32, by using the data distance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources, the accuracy of data analysis can be improved from the perspective of spatial consistency, and the accuracy of model maintenance can be further improved.

[0130] It should be understood that in the collaborative work of multiple data sources, the importance and reliability of different data sources may change dynamically. Therefore, it is necessary to dynamically adjust the weights of data relevance, temporal consistency and spatial consistency, that is, the weight coefficients corresponding to different sub-constraint dimensions, to ensure coordination in the model.

[0131] Specifically, this application can use the entropy weight method for dynamic weight adjustment. The entropy weight method can effectively quantify the information content of each data source and dynamically adjust the weights according to the amount of information. Information entropy is an indicator that measures the uncertainty of information. The higher the information entropy, the more uncertain the information content of the data source, and its weight should be smaller; conversely, data sources with lower information entropy contain more deterministic information, and their weights should be larger.

[0132] In one embodiment, the dimensional analysis data includes target analysis data corresponding to each target data source. For example, the method for determining the weight coefficients (i.e., S204) corresponding to the sub-constraint dimensions based on the dimensional analysis data under each sub-constraint dimension can be as follows: Figure 4 As shown, it includes the following steps:

[0133] S402, normalize the target analysis data corresponding to each target under the sub-constraint dimension to obtain the target normalized data corresponding to each target analysis data.

[0134] For example, taking the data consistency dimension as an example of a sub-constraint dimension, Indicates the target data source under the data consistency dimension. For the corresponding target analysis data, the target normalized data corresponding to the target analysis data under the data consistency dimension satisfies:

[0135]

[0136] For example, taking the sub-constraint dimension including the time consistency dimension as an example, Indicates the target data source under the time consistency dimension. The corresponding target analysis data, under the time consistency dimension, satisfies the following:

[0137]

[0138] For example, taking the sub-constraint dimension including the spatial consistency dimension as an example, Target data source under the dimension of spatial consistency The corresponding target analysis data, under the spatial consistency dimension, satisfies the following:

[0139]

[0140] S404: For each target analysis data, based on the target normalized data corresponding to the target analysis data and the number of data sources, obtain the entropy value corresponding to the target analysis data.

[0141] For example, taking the data consistency dimension as an example of a sub-constraint dimension, Indicates the target data source under the data consistency dimension. Corresponding target analysis data, This represents the target normalized data corresponding to the target analysis data under the data consistency dimension, and then the entropy value corresponding to the target analysis data under the data consistency dimension. satisfy:

[0142]

[0143] Where k is a constant, and k satisfies: This is to ensure the normalization of entropy.

[0144] For example, taking the sub-constraint dimension including the time consistency dimension as an example, Indicates the target data source under the time consistency dimension. Corresponding target analysis data, Let represent the target normalized data corresponding to the target analysis data under the time consistency dimension. Then, the target normalized data corresponding to the target analysis data under the time consistency dimension satisfies:

[0145]

[0146] For example, taking the sub-constraint dimension including the spatial consistency dimension as an example, Target data source under the dimension of spatial consistency Corresponding target analysis data, Let represent the target normalized data corresponding to the target analysis data under the spatial consistency dimension. Then, the target normalized data corresponding to the target analysis data under the spatial consistency dimension satisfies:

[0147]

[0148] S406. Based on the maximum entropy value among the entropy values ​​corresponding to each target analysis data, and the entropy values ​​corresponding to each target analysis data, obtain the sub-coefficients corresponding to each target analysis data under the sub-constraint dimension.

[0149] For example, taking the data consistency dimension as an example, the sub-coefficients corresponding to the target analysis data under the data consistency dimension satisfy:

[0150]

[0151] in, Indicates the target data source under the data consistency dimension. Corresponding target analysis data, This indicates the target analysis data under the data consistency dimension. The corresponding entropy value, This represents the maximum entropy value among the entropy values ​​corresponding to each target analysis data under the data consistency dimension. This indicates the target analysis data under the data consistency dimension. The corresponding sub-coefficients.

[0152] For example, taking the sub-constraint dimension including the time consistency dimension as an example, the sub-coefficients corresponding to the target analysis data under the time consistency dimension satisfy:

[0153]

[0154] in, Indicates the target data source under the time consistency dimension. Corresponding target analysis data, Data representing target analysis under the dimension of time consistency The corresponding entropy value, This represents the maximum entropy value among the entropy values ​​corresponding to each target analysis data under the time consistency dimension. Data representing target analysis under the dimension of time consistency The corresponding sub-coefficients.

[0155] For example, taking the spatial consistency dimension as an example, the sub-coefficients corresponding to the target analysis data under the spatial consistency dimension satisfy:

[0156]

[0157] in, Target data source under the dimension of spatial consistency Corresponding target analysis data, Target analysis data under the dimension of spatial consistency The corresponding entropy value, This represents the maximum entropy value among the entropy values ​​corresponding to each target analysis data under the spatial consistency dimension. Target analysis data under the dimension of spatial consistency The corresponding sub-coefficients.

[0158] S408: Based on the sub-coefficients corresponding to the target analysis data under each sub-constraint dimension, obtain the weight coefficients corresponding to the sub-constraint dimension.

[0159] For example, by combining the sub-coefficients corresponding to the target analysis data under each sub-constraint dimension, the weight coefficients corresponding to the sub-constraint dimension can be obtained.

[0160] For example, by weighting the sub-coefficients corresponding to each target analysis data under the sub-constraint dimension and the target analysis data under the sub-constraint dimension, the data processing results under the sub-constraint dimension can be obtained; by summing the data processing results corresponding to each sub-constraint dimension, consistent constraint data matching the digital twin model can be obtained.

[0161] based on Figure 4 The content shown demonstrates that by determining the weight coefficients corresponding to the sub-constraint dimensions from an entropy perspective, the accuracy of determining the weight coefficients can be improved, which in turn can enhance the maintenance accuracy of the digital twin model.

[0162] In conjunction with the above, in one embodiment, such as Figure 5 As shown, a method for maintaining a digital twin model of electricity marketing operations based on consistency constraints is provided. Taking the application of this method to a server in a maintenance system as an example, the method may include the following steps:

[0163] S502, acquire the digital twin model corresponding to the electricity marketing operation, and the monitoring data collected from at least two data sources for the electricity marketing operation.

[0164] S504, based on the maintenance requirements of the digital twin model, determines the consistency constraint dimensions that match the electricity marketing operations.

[0165] For example, consistency constraint dimensions include data consistency, time consistency, and spatial consistency.

[0166] S506, Select the target data source from the data sources, and determine the remaining data sources other than the target data source.

[0167] S508, based on the differences between the monitoring data corresponding to the target data source and each remaining data source, obtain the target analysis data corresponding to the target data source under the data consistency dimension, the target analysis data corresponding to the target data source under the time consistency dimension, and the target analysis data corresponding to the target data source under the spatial consistency dimension.

[0168] For example, for each remaining data source, the covariance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources is obtained; the first standard deviation matching the monitoring data corresponding to the target data source and the second standard deviation matching the monitoring data corresponding to the remaining data sources are obtained; based on each covariance, the first standard deviation and each second standard deviation corresponding to the target data source, the target analysis data corresponding to the target data source under the data consistency dimension is obtained.

[0169] For example, the detection time window of the target data source is divided to obtain multiple sub-detection times; for each sub-detection time, the data difference between the sub-data of the remaining data source at the sub-detection time and the sub-data of the target data source at the sub-detection time is obtained; based on the number of sub-detection times corresponding to the target data source and the data differences corresponding to each sub-detection time, the target analysis data corresponding to the target data source under the time consistency dimension is obtained.

[0170] For example, for each remaining data source, the data distance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources is obtained; based on the data distances corresponding to the target data source and the number of data sources of at least two data sources, the target analysis data corresponding to the target data source under the spatial consistency dimension is obtained.

[0171] S510, take the next data source adjacent to the target data source in each data source as the new target data source, and return the steps for determining each remaining data source in each data source other than the target data source.

[0172] S512, based on the target analysis data corresponding to each target data source under the data consistency dimension, obtain the corresponding dimension analysis data under the data consistency dimension.

[0173] S514, Analyze the data based on the corresponding dimensions under the data consistency dimension, and determine the weight coefficients corresponding to the data consistency dimension.

[0174] S516, based on the target analysis data corresponding to each target data source under the time consistency dimension, obtain the corresponding dimension analysis data under the time consistency dimension.

[0175] S518, based on the dimensional analysis data corresponding to the time consistency dimension, determine the weight coefficients corresponding to the time consistency dimension.

[0176] S520 obtains the corresponding dimensional analysis data under the spatial consistency dimension based on the target analysis data corresponding to each target data source under the spatial consistency dimension.

[0177] S522, based on the dimensional analysis data corresponding to the spatial consistency dimension, determine the weight coefficients corresponding to the spatial consistency dimension.

[0178] S524, the dimensional analysis data corresponding to the data consistency dimension, the dimensional analysis data corresponding to the time consistency dimension, and the dimensional analysis data corresponding to the spatial consistency dimension are weighted and summed with the weight coefficients corresponding to the data consistency dimension, the time consistency dimension, and the spatial consistency dimension, respectively, to obtain consistency constraint data that matches the digital twin model.

[0179] S526 uses consistency constraint data to maintain the digital twin model and obtains the updated model corresponding to the power marketing operation.

[0180] The specific content of S502-S526 can be found in the aforementioned description.

[0181] As can be seen from the above, the method provided in this application solves the problems of existing technologies in power marketing operations by introducing consistency constraints. It ensures the consistency and synergy of information from different data sources during model calibration, avoiding increased model errors due to data inconsistency. Therefore, it effectively resolves the contradiction between diverse data sources and real-time feedback, enabling the optimization of model accuracy and stability while ensuring data consistency. This improves the efficiency and effectiveness of power marketing operations, providing more reliable technical support for the efficient operation of power marketing.

[0182] Furthermore, by calibrating the model based on monitoring data collected from at least two data sources for electricity marketing operations, the parameters of the digital twin model can be automatically adjusted according to real-time changes in electricity marketing operations. This flexible dynamic adjustment mechanism allows the model to continuously adapt to external changes such as electricity load and market demand, maintaining the model's continuous effectiveness and accuracy. Moreover, it enables the digital twin model in electricity marketing operations to be accurately calibrated when facing complex power networks, thereby improving the model's predictive accuracy. Compared with existing technologies, this application can maintain high model accuracy and stability in more complex and dynamic environments.

[0183] In summary, compared with existing digital twin models used in power marketing operations, the method provided in this application addresses several key issues. Firstly, existing technologies suffer from decreased accuracy in digital twin models due to inconsistencies or errors in data from multiple sources, failing to accurately reflect the actual operating status of the power system. Secondly, this application, through a consistency constraint mechanism, ensures that data from different data sources (such as power load, grid status, and equipment status) meets consistency requirements when input into the digital twin model, avoiding the accuracy degradation caused by inconsistencies between data sources. This consistency constraint mechanism enables effective coordination among multiple data sources within the model, resolving model distortion caused by data inconsistency and improving model stability and accuracy. Furthermore, by introducing a consistency constraint dimension and entropy weighting, the influence of different data sources can be effectively adjusted, ensuring the consistency of the model's input data and improving the model's predictive accuracy in power marketing operations.

[0184] Secondly, existing digital twin models often cannot adapt to changes in the power system in real time. However, this application introduces an incremental learning strategy, which can correct the parameters of the digital twin model based on real-time error feedback. This ensures the fidelity between the model and the actual power system state, keeping them consistent with the actual system state. This effectively reduces prediction errors and enables the model to adapt to dynamic changes in the power system, improving the prediction accuracy of the digital twin model in power marketing operations and the accuracy and reliability of power dispatch.

[0185] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0186] Based on the same inventive concept, this application also provides a device for maintaining a digital twin model of power marketing operations based on consistency constraints, which is used to implement the aforementioned method for maintaining a digital twin model of power marketing operations based on consistency constraints. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for maintaining a digital twin model of power marketing operations based on consistency constraints provided below can be found in the limitations of the method for maintaining a digital twin model of power marketing operations based on consistency constraints described above, and will not be repeated here.

[0187] In one exemplary embodiment, such as Figure 6 As shown, a device for maintaining a digital twin model of power marketing operations based on consistency constraints is provided, including: an acquisition module 602, a determination module 604, a processing module 606, and a maintenance module 608. The acquisition module 602 is used to acquire the digital twin model corresponding to the power marketing operation, and monitoring data collected from at least two data sources for the power marketing operation. The determination module 604 is used to determine the consistency constraint dimensions matching the power marketing operation based on the maintenance requirements of the digital twin model. The processing module 606 is used to perform consistency analysis on the monitoring data corresponding to each data source based on the consistency constraint dimensions to obtain consistency constraint data matching the digital twin model. The maintenance module 608 is used to maintain the digital twin model using the consistency constraint data to obtain an updated model corresponding to the power marketing operation.

[0188] In one embodiment, the consistency constraint dimension includes at least one sub-constraint dimension; the processing module 606 is further configured to: for each sub-constraint dimension, perform consistency analysis on the monitoring data corresponding to each data source based on the sub-constraint dimension to obtain the corresponding dimension analysis data under the sub-constraint dimension; determine the weight coefficient corresponding to the sub-constraint dimension based on the corresponding dimension analysis data under the sub-constraint dimension; and perform weighted summation on the weight coefficients and the corresponding dimension analysis data of each sub-constraint dimension to obtain consistency constraint data that matches the power marketing operation.

[0189] In one embodiment, the processing module 606 is further configured to: select a target data source from each data source, and determine each remaining data source other than the target data source; obtain target analysis data corresponding to the target data source under the sub-constraint dimension based on the difference features between the monitoring data corresponding to the target data source and each remaining data source; take the next data source adjacent to the target data source in each data source as the new target data source, and return the step of determining each remaining data source other than the target data source in each data source; and determine the data set containing the target analysis data corresponding to each target data source under the sub-constraint dimension as the dimension analysis data corresponding to the sub-constraint dimension according to the order of the target data sources.

[0190] In one embodiment, the sub-constraint dimension includes a data consistency dimension; the processing module 606 is further configured to: obtain the covariance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources, wherein the covariance is used to characterize the difference between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources; obtain a first standard deviation matching the monitoring data corresponding to the target data source and a second standard deviation matching the monitoring data corresponding to the remaining data sources; and obtain the target analysis data corresponding to the target data source under the sub-constraint dimension based on the covariance, the first standard deviation and the second standard deviation corresponding to the target data source.

[0191] In one embodiment, the sub-constraint dimension includes a time consistency dimension, and the monitoring data includes multiple sub-data. The processing module 606 is further configured to: divide the detection time window of the target data source to obtain multiple sub-detection times; for each sub-detection time, obtain the data difference between the sub-data of the remaining data source at the sub-detection time and the sub-data of the target data source at the sub-detection time; the data difference is used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources; based on the number of sub-detection times corresponding to the target data source and the data differences corresponding to each sub-detection time, obtain the target analysis data corresponding to the target data source under the sub-constraint dimension.

[0192] In one embodiment, the sub-constraint dimension includes a spatial consistency dimension; the processing module 606 is further configured to: obtain the data distance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources, wherein the data distance is used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources; and obtain the target analysis data corresponding to the target data source under the sub-constraint dimension based on the data distances corresponding to the target data source and the number of data sources of at least two data sources.

[0193] In one embodiment, the dimensional analysis data includes target analysis data corresponding to each target data source; the processing module 606 is further configured to: normalize each target analysis data corresponding to the sub-constraint dimension to obtain target normalized data corresponding to each target analysis data; for each target analysis data, based on the target normalized data corresponding to the target analysis data and the number of data sources, obtain the entropy value corresponding to the target analysis data; based on the maximum entropy value among the entropy values ​​corresponding to each target analysis data and the entropy values ​​corresponding to each target analysis data, obtain the sub-coefficients corresponding to each target analysis data under the sub-constraint dimension; and based on the sub-coefficients corresponding to each target analysis data under the sub-constraint dimension, obtain the weight coefficients corresponding to the sub-constraint dimension.

[0194] The modules in the aforementioned power marketing operation digital twin model maintenance device based on consistency constraints can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0195] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores monitoring data and other data corresponding to various data sources. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for maintaining a digital twin model of power marketing operations based on consistency constraints.

[0196] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0197] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0198] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0199] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0200] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0201] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0202] The technical features of the above embodiments can be combined arbitrarily. In order 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 application.

[0203] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for maintaining a digital twin model of electricity marketing operations based on consistency constraints, characterized in that, The method includes: Obtain a digital twin model corresponding to the electricity marketing operation, as well as monitoring data collected from at least two data sources for the electricity marketing operation; Based on the maintenance requirements of the digital twin model, determine the consistency constraint dimensions that match the electricity marketing operations; Based on the consistency constraint dimension, a consistency analysis is performed on the monitoring data corresponding to each of the data sources to obtain consistency constraint data that matches the digital twin model; The consistency constraint data is used to maintain the digital twin model to obtain the updated model corresponding to the electricity marketing operation; The consistency constraint dimension includes at least one sub-constraint dimension; the step of performing consistency analysis on the monitoring data corresponding to each of the data sources based on the consistency constraint dimension to obtain consistency constraint data matching the digital twin model includes: For each of the sub-constraint dimensions, a target data source is selected from each of the data sources, and the remaining data sources other than the target data source are determined from each of the data sources. Based on the differences between the monitoring data corresponding to the target data source and each of the remaining data sources, the target analysis data corresponding to the target data source under the sub-constraint dimension is obtained. The next data source adjacent to the target data source in each of the data sources is taken as the new target data source, and the step of determining each remaining data source other than the target data source is returned; According to the order of the target data sources, the data set containing the target analysis data corresponding to each of the target data sources under the sub-constraint dimension is determined as the dimension analysis data corresponding to the sub-constraint dimension; Based on the dimensional analysis data corresponding to the sub-constraint dimension, determine the weight coefficients corresponding to the sub-constraint dimension; The weight coefficients corresponding to each of the sub-constraint dimensions and the dimensional analysis data corresponding to each of the sub-constraint dimensions are weighted and summed to obtain consistency constraint data that matches the digital twin model.

2. The method according to claim 1, characterized in that, The sub-constraint dimension includes a data consistency dimension; the method further includes: Obtain the covariance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources. The covariance is used to characterize the difference between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources. The step of obtaining target analysis data corresponding to the target data source under the sub-constraint dimension based on the difference features between the monitoring data corresponding to the target data source and each of the remaining data sources includes: Obtain a first standard deviation that matches the monitoring data corresponding to the target data source, and a second standard deviation that matches the monitoring data corresponding to the remaining data sources; Based on the covariance, the first standard deviation, and the second standard deviation corresponding to the target data source, the target analysis data corresponding to the target data source under the sub-constraint dimension is obtained.

3. The method according to claim 1, characterized in that, The sub-constraint dimension includes the time consistency dimension, and the monitoring data includes multiple sub-data. The method further includes: The detection time window of the target data source is divided to obtain multiple sub-detection times; For each sub-detection time, the data difference between the sub-data of the remaining data source and the sub-data of the target data source at the sub-detection time is obtained; the data difference is used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data source. The step of obtaining target analysis data corresponding to the target data source under the sub-constraint dimension based on the difference features between the monitoring data corresponding to the target data source and each of the remaining data sources includes: Based on the number of sub-detection times corresponding to the target data source and the data differences corresponding to each sub-detection time, the target analysis data corresponding to the target data source under the sub-constraint dimension is obtained.

4. The method according to claim 1, characterized in that, The sub-constraint dimension includes a spatial consistency dimension; the method further includes: The data distance between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources is obtained, and the data distance is used to characterize the difference features between the monitoring data corresponding to the target data source and the monitoring data corresponding to the remaining data sources; The step of obtaining target analysis data corresponding to the target data source under the sub-constraint dimension based on the difference features between the monitoring data corresponding to the target data source and each of the remaining data sources includes: Based on the data distances corresponding to the target data source and the number of data sources of the at least two data sources, the target analysis data corresponding to the target data source under the sub-constraint dimension is obtained.

5. The method according to claim 1, characterized in that, The dimensional analysis data includes target analysis data corresponding to each of the target data sources; The step of determining the weight coefficients corresponding to the sub-constraint dimension based on the dimensional analysis data corresponding to the sub-constraint dimension includes: Normalize the target analysis data corresponding to each of the sub-constraint dimensions to obtain target normalized data corresponding to each target analysis data. For each target analysis data, based on the target normalized data corresponding to the target analysis data and the number of data sources, the entropy value corresponding to the target analysis data is obtained; Based on the maximum entropy value among the entropy values ​​corresponding to each of the target analysis data, and the entropy value corresponding to each of the target analysis data, the sub-coefficients corresponding to each of the target analysis data under the sub-constraint dimension are obtained. Based on the sub-coefficients corresponding to the target analysis data under each sub-constraint dimension, the weight coefficients corresponding to the sub-constraint dimension are obtained.

6. The method according to claim 1, characterized in that, The method further includes: When the usage time of the digital twin model reaches a preset time, it is determined that the digital twin model meets the maintenance requirements; Based on the mapping relationship between usage duration and sub-constraint dimensions, and the usage duration of the digital twin model, a consistency constraint dimension matching the electricity marketing operation is determined.

7. The method according to claim 1, characterized in that, The consistency constraint dimension includes at least one sub-constraint dimension, and the method further includes: For each of the sub-constraint dimensions, based on the mapping relationship between the sub-constraint dimensions and the preset analysis strategies, the preset analysis strategy that matches the sub-constraint dimension corresponding to the power marketing operation is determined as the target strategy of the power marketing operation under the sub-constraint dimension. The target strategy corresponding to the sub-constraint dimension is used to perform consistency analysis on the monitoring data corresponding to each of the data sources to obtain the dimension analysis results corresponding to the sub-constraint dimension. Based on the dimensional analysis results corresponding to each of the sub-constraint dimensions, consistency constraint data matching the digital twin model is obtained.

8. A maintenance device for a digital twin model of electricity marketing operations based on consistency constraints, characterized in that, The device includes: The acquisition module is used to acquire the digital twin model corresponding to the power marketing operation, as well as the monitoring data collected by at least two data sources for the power marketing operation. The determination module is used to determine the consistency constraint dimensions that match the power marketing operation based on the maintenance requirements of the digital twin model. The processing module is used to perform consistency analysis on the monitoring data corresponding to each of the data sources based on the consistency constraint dimension, and obtain consistency constraint data that matches the digital twin model. The maintenance module is used to maintain the digital twin model using the consistency constraint data to obtain the updated model corresponding to the power marketing operation. The consistency constraint dimension includes at least one sub-constraint dimension. The processing module is further configured to: select a target data source from each of the data sources for each sub-constraint dimension; determine the remaining data sources in each of the data sources other than the target data source; obtain target analysis data corresponding to the target data source under the sub-constraint dimension based on the difference features between the monitoring data corresponding to the target data source and each of the remaining data sources; take the next data source adjacent to the target data source in each of the data sources as a new target data source and return the step of determining the remaining data sources in each of the data sources other than the target data source; determine the data set containing the target analysis data corresponding to each of the target data sources under the sub-constraint dimension as the dimension analysis data corresponding to the sub-constraint dimension according to the order of the target data sources; determine the weight coefficient corresponding to the sub-constraint dimension based on the dimension analysis data corresponding to the sub-constraint dimension; and perform weighted summation processing on the weight coefficients corresponding to each of the sub-constraint dimensions and the dimension analysis data corresponding to each of the sub-constraint dimensions to obtain consistency constraint data matching the digital twin model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images