A digital twin virtual mapping method, system and storage medium

Abstract

The present invention relates to the field of data processing technology, and more specifically to a digital twin virtual time mapping method, system and storage medium. The method comprises: step S1: creating a twin model, mapping the grid layout and the rated parameters of each power-consuming device into the twin model; step S2: obtaining the historical power consumption data of each power-consuming device and obtaining the power consumption mode of each power-consuming device, and obtaining the device grouping with correlation among the power-consuming devices based on the power consumption mode of each power-consuming device in a preset time period; step S3: obtaining the power consumption probability distribution of the power-consuming device in a preset time period; step S4: updating the abnormal real-time power consumption data and normal real-time power consumption data corrected by the power-consuming device into the twin model; step S5: correcting the simulated power consumption data based on the real-time power consumption data to obtain the first virtual power consumption data. The present invention solves the problem of low accuracy in identifying abnormal data and improves the accuracy in identifying abnormal data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically to a digital twin virtual time mapping method, system and storage medium. Background Art

[0002] With the continuous advancement of technology and the continuous expansion of application scenarios, the application prospects of digital twin models in power forecasting are broad, and will make important contributions to the intelligence and sustainable development of power systems. Similar existing technologies include a Chinese patent with publication number CN118311909A, which proposes a building energy management system based on digital twins, involving the field of digital twin technology, including: a model construction module, a data acquisition module, a power consumption analysis module, a prediction simulation module and a safety warning module; the model construction module is used to establish a three-dimensional model of a building; the data acquisition module is used to collect power energy parameters; the power consumption analysis module performs directional data processing on the meter display, including a first analysis unit, a second analysis unit and a third analysis unit; the prediction simulation module constructs a building energy consumption prediction model, and predicts the energy consumption according to the prediction model to obtain the energy consumption prediction value Ny; the safety warning module selects different safety warning processing strategies for the energy consumption prediction value Ny; the present invention can also make accurate predictions in the event of emergencies, and can make emergency adjustments in time through prediction alarms. In addition, similar prior art also includes a US patent with publication number US20230350363A1, which discloses a system and method for energy supply chain management and optimization through energy virtual twins, the energy system including multiple interconnected microgrids connected to at least one macro grid. The energy system is connected to one or more cloud servers, the cloud server includes at least one processor and a memory storing computer code, when the computer code is executed by the at least one processor, a persistent virtual world system including multiple virtual objects mapped according to the real world includes at least one virtual replica of the corresponding real world element. The memory also stores a decentralized energy management system connected to the persistent virtual world system, including at least an energy control system, which is configured to digitally control the energy flow based on data received from the energy through the virtualization of reality in the persistent virtual world system. The system and energy market platform realize energy aggregation and exchange between energy-related devices. Both of the above patents realize the generation of twin models through virtual-real mapping, and use twin models to solve real problems, but neither of them considers the problem of managing device data with related relationships together during virtual-real mapping and improving data accuracy. Summary of the invention

[0003] In order to better solve the above problems, the present invention provides a digital twin virtual-real mapping method, which comprises the following steps:

[0004] Step S1: creating a twin model, mapping the grid layout in the target area and each power-consuming device in the grid and the rated parameters of the power-consuming device into the twin model according to the grid layout diagram of the target area;

[0005] Step S2: acquiring historical power consumption data of each of the power consuming devices through a storage unit, acquiring a power consumption mode of each of the power consuming devices based on the historical power consumption data, and acquiring a group of devices having a correlation with the corresponding power consumption mode among the power consuming devices based on the power consumption mode of each of the power consuming devices within a preset time period;

[0006] Step S3: obtaining a probability distribution of power consumption of each power-consuming device in the device group within a preset time period based on historical data of each power-consuming device in the device group;

[0007] Step S4: periodically collect the real-time power consumption data of the power-consuming device corresponding to each of the device groups, and determine whether the real-time power consumption data is abnormal based on the standard data of the power consumption mode corresponding to the power consumption device, the power consumption probability distribution of the power consumption mode corresponding to the power consumption device, and the real-time power consumption data of other power-consuming devices in the device group where the power-consuming device is located, and update the corrected abnormal real-time power consumption data and normal real-time power consumption data of the power-consuming device into the twin model;

[0008] Step S5: Simulate the simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period through the twin model simulation and the rated parameters of the power consuming device, and correct the simulated power consumption data based on the real-time power consumption data of the power consuming device to obtain virtual power consumption data.

[0009] As a preferred technical solution of the present invention, step S1 includes:

[0010] Step S11: creating the twin model by a creation unit, and mapping the entrance, transmission lines, transmission equipment, substation equipment and distribution equipment of the power grid into the twin model according to the positional relationship based on the power grid layout diagram of the target area;

[0011] Step S12: each of the power consuming devices in the power grid and the rated parameters of the power consuming devices are also mapped into the twin model, where the rated parameters at least include rated voltage, rated current and rated power.

[0012] As a preferred technical solution of the present invention, step S2 includes:

[0013] Step S21: acquiring historical power consumption data corresponding to each power consuming device through a storage unit, wherein the historical power consumption data is time series data, obtaining multiple power consumption modes of each of the power consuming devices based on the historical power consumption data based on a clustering algorithm, and obtaining a central value and a data range of each of the power consumption modes, wherein a difference between the central values ​​corresponding to any two different power consumption modes is greater than a first threshold;

[0014] Step S22: analyzing the correlation between the power consumption modes of different power consuming devices within a preset time period, and dividing the power consuming devices into a plurality of device groups according to the correlation, wherein the corresponding power consumption modes of the power consuming devices in the same device group are correlated with each other;

[0015] Step S23: Divide the remaining power-consuming devices that have not been divided into device groups into multiple sub-power consumption modes corresponding to each power consumption mode, obtain the device group with the highest timing power consumption trend correlation with each sub-power consumption mode among all the device groups as the first group, and add the remaining power-consuming devices and the sub-power consumption modes to the first group.

[0016] As a preferred technical solution of the present invention, step S4 includes:

[0017] Step S41: obtaining a power consumption value range with a probability less than a set value according to the power consumption probability distribution of the power consuming devices in each device group within the preset time period, and taking the power consumption value range of the power consuming devices as an abnormal power consumption value range;

[0018] Step S42: periodically acquiring the first real-time power consumption data of each of the power-consuming devices within the preset time period, and comparing the first real-time power consumption data with the standard power consumption data corresponding to the power consumption mode of the power-consuming device and acquiring a difference; when the difference is less than a set difference, the real-time power consumption data is normal; otherwise, when the difference is greater than or equal to the set difference or the first real-time power consumption data falls within the corresponding abnormal power consumption value range, acquiring the second real-time power consumption data of other power-consuming devices in the power-consuming device group to which the power-consuming device belongs;

[0019] Step S43: When the second real-time power consumption data corresponding to the other power-consuming devices are all normal, the first real-time power consumption data is abnormal, and the first real-time power consumption data is corrected according to the correlation between the first real-time power consumption data and the other power-consuming devices in the power-consuming device group, and the corrected or normal first real-time power consumption data is sent to the twin model.

[0020] As a preferred technical solution of the present invention, the step S43 further includes:

[0021] When the second real-time power consumption data corresponding to the other power consuming devices are not all normal, the first real-time power consumption device is taken as the first device, and a first power consumption data set consisting of multiple third real-time power consumption data of the first device in a first time period after the collection time corresponding to the first real-time power consumption data is obtained, the abnormal second real-time power consumption data corresponds to the other power consuming devices as the second device, and a second power consumption data set consisting of multiple fourth real-time power consumption data of the second device in the first time period is obtained, the first power consumption data set is compared with each power consumption mode of the first power consuming device, and a power consumption mode having a similarity with the first power consumption data set greater than a set similarity is obtained as the first mode. Similarly, a power consumption mode having a similarity with the second power consumption data set greater than the set similarity is obtained as the second mode, the first mode and the second mode are respectively added to the first mode set and the second mode set corresponding to the first device and the second device in the preset time period, and step S2 is repeated to re-acquire the third group and the fourth group corresponding to the first device and the second device respectively, and the first real-time power consumption data and the first power consumption data set of the first device and the second real-time power consumption data and the second power consumption data set of the second device are respectively sent to the twin model.

[0022] As a preferred technical solution of the present invention, step S3 includes:

[0023] Based on the power consumption pattern of each of the power-consuming devices in the device group within the preset time period, and reading the historical data corresponding to the power consumption pattern from the storage unit, the value probability of each power consumption data in the power consumption pattern is obtained through a data statistical algorithm, and the power consumption probability distribution of the power consumption pattern is obtained based on the value probability.

[0024] As a preferred technical solution of the present invention, step S5 includes:

[0025] The simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period is simulated by the twin model simulation and the rated parameters of the power consuming device, and the power factor of the power consuming device corresponding to the rated parameters is adjusted so that the difference between the simulated power consumption data and the real-time power consumption data is less than the set difference.

[0026] The present invention provides a digital twin virtual-reality mapping system, which is used to implement the above method, and the system includes:

[0027] A creation unit, configured to create a twin model, and map the grid layout in the target area and each power-consuming device in the grid and the rated parameters of the power-consuming device into the twin model according to the grid layout diagram of the target area;

[0028] A storage unit, used to store historical power consumption data of each of the power consuming devices;

[0029] A grouping unit, configured to obtain a power consumption mode of each of the power consuming devices based on the historical power consumption data, obtain a device group having a relevant relationship with the corresponding power consumption mode among the power consuming devices based on the power consumption mode of each of the power consuming devices within a preset time period, and obtain a probability distribution of power consumption of the power consuming devices within a preset time period based on the historical data of each of the power consuming devices in the device group;

[0030] The calculation unit is configured to: periodically collect the real-time power consumption data of the power-consuming device corresponding to each of the device groups, and determine whether the real-time power consumption data is abnormal based on the standard data of the power consumption mode corresponding to the power consumption device, the power consumption probability distribution of the power consumption mode corresponding to the power consumption device, and the real-time power consumption data of other power-consuming devices in the device group where the power-consuming device is located, and update the corrected abnormal real-time power consumption data and normal real-time power consumption data of the power-consuming device into the twin model;

[0031] A simulation unit is used to simulate the simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period through the twin model simulation and the rated parameters of the power consuming device, and to correct the simulated power consumption data based on the real-time power consumption data of the power consuming device to obtain virtual power consumption data.

[0032] The present invention provides a computer storage medium, wherein the storage medium stores program instructions, wherein when the program instructions are executed, the device where the storage medium is located is controlled to execute the above method.

[0033] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0034] The present invention creates the above-mentioned twin model, maps the power grid layout in the target area and each power-consuming device and rated parameters in the power grid to the above-mentioned twin model according to the power grid layout diagram of the target area, thereby realizing physical mapping of the power grid. The present invention also uses the historical power consumption data of the above-mentioned power-consuming devices and obtains all power consumption patterns of each of the above-mentioned power-consuming devices based on the clustering window through a clustering algorithm, thereby obtaining the correlation between the power consumption patterns corresponding to different power-consuming devices within a preset time period, and divides the power-consuming devices with the above-mentioned correlation into the same device group, and also divides the power consumption patterns of power-consuming devices whose power consumption patterns are not correlated with the power consumption patterns of other power-consuming devices into the above-mentioned multiple sub-power consumption patterns, and compares the sub-power consumption patterns with the power consumption patterns of the power-consuming devices in each of the above-mentioned device groups corresponding to the above-mentioned sub-power consumption pattern time period. By comparison, a first group closest to the above-mentioned sub-power consumption pattern is obtained, and the above-mentioned remaining power consuming devices and the corresponding sub-power consumption patterns are added to the above-mentioned first group, so as to facilitate group management, and judge the abnormality of the power consumption data according to the correlation between the power consuming devices, and obtain the power consumption probability distribution of the power consuming devices within a preset time period based on the historical data of each power consuming device in the above-mentioned device group, and judge whether the real-time power consumption data is abnormal based on the standard data of the power consumption pattern corresponding to the power consumption pattern of the power consuming device, the power consumption probability distribution of the power consumption pattern corresponding to the power consuming device and the real-time power consumption data of other power consuming devices in the device group where the power consuming device is located. Not only can it be accurately identified whether the first real-time power consumption data is abnormal, but also the above-mentioned first real-time power consumption data can be corrected. The mutual cooperation of the above-mentioned technical solutions improves the accuracy of identifying abnormal data. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a digital twin virtual-reality mapping method of the present invention;

[0036] Figure 2 This is a digital twin virtual-reality mapping structure diagram of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0038] The present invention provides a digital twin virtual-real mapping method, such as Figure 1 As shown, the method comprises the following steps:

[0039] Step S1: creating a twin model, mapping the grid layout in the target area and each power-consuming device in the grid and the rated parameters of the power-consuming device into the twin model according to the grid layout diagram of the target area;

[0040] Specifically, by creating a twin model of the target area, which can be a building or a factory, the grid entrance, transmission lines, transmission equipment, substation equipment and distribution equipment are mapped to the twin model according to their positional relationship. At the same time, each power-consuming device is mapped into the twin model to realize the physical mapping of the power grid. The rated parameters of the power-consuming devices are further mapped into the twin model, laying the foundation for correcting the simulated power consumption data by adjusting the rated parameters.

[0041] Step S2: acquiring historical power consumption data of each of the power consuming devices through a storage unit, acquiring a power consumption mode of each of the power consuming devices based on the historical power consumption data, and acquiring a group of devices having a correlation with the corresponding power consumption mode among the power consuming devices based on the power consumption mode of each of the power consuming devices within a preset time period;

[0042] Specifically, by using the historical power consumption data of the power-consuming devices and obtaining all the power consumption patterns of each of the power-consuming devices based on the clustering window through the clustering algorithm, it is convenient to obtain the correlation between the power consumption patterns of the power-consuming devices within a preset time period, and by analyzing the correlation between the power consumption patterns of different power-consuming devices within the preset time period, wherein the preset time period is a working day or a holiday, and the power-consuming devices with the above correlation are divided into the same device group, and the power consumption patterns of the power-consuming devices whose power consumption patterns are not correlated with the power consumption patterns of other power-consuming devices are divided into a plurality of the above sub-power consumption patterns, and the sub-power consumption patterns are compared with the power consumption patterns of the power-consuming devices in each of the above-mentioned device groups corresponding to the above-mentioned sub-power consumption pattern time period, to obtain a first group closest to the above-mentioned sub-power consumption pattern, and add the above-mentioned other power-consuming devices and the corresponding sub-power consumption patterns to the above-mentioned first group. Through the above-mentioned technical solution, device groups with correlation are obtained, which is convenient for group management, and the abnormality of power consumption data is judged according to the correlation between the power-consuming devices.

[0043] Step S3: obtaining a probability distribution of power consumption of each power-consuming device in the device group within a preset time period based on historical data of each power-consuming device in the device group;

[0044] Specifically, the above technical solution can obtain the power consumption probability distribution of each power consuming device corresponding to the power consumption mode within the above preset time period, and then determine whether the power consumption mode of the above power consuming device has changed or whether the data is abnormal through the above power consumption probability distribution, thereby improving the recognition accuracy of abnormal data.

[0045] Step S4: periodically collect the real-time power consumption data of the power-consuming device corresponding to each of the device groups, and determine whether the real-time power consumption data is abnormal based on the standard data of the power consumption mode corresponding to the power consumption device, the power consumption probability distribution of the power consumption mode corresponding to the power consumption device, and the real-time power consumption data of other power-consuming devices in the device group where the power-consuming device is located, and update the corrected abnormal real-time power consumption data and normal real-time power consumption data of the power-consuming device into the twin model;

[0046] Specifically, through the above-mentioned power consumption probability distribution of each of the above-mentioned power-consuming devices within the above-mentioned preset time period, the above-mentioned abnormal power consumption value range with the above-mentioned probability less than the set value is obtained, so as to lay a foundation for further judging the abnormality of the first real-time power consumption data collected in real time based on the above-mentioned abnormal power consumption value range, by periodically obtaining the above-mentioned first real-time power consumption data of each of the above-mentioned power-consuming devices, wherein the real-time power consumption data of the above-mentioned power-consuming devices include the above-mentioned first real-time power consumption data, and comparing the above-mentioned first real-time power consumption data with the standard data of the above-mentioned power-consuming devices corresponding to the above-mentioned power consumption mode within the preset time, wherein the collection time of the above-mentioned first real-time power consumption data is consistent with the time corresponding to the above-mentioned standard data in the above-mentioned power consumption mode, when the difference between the two is less than the set difference, the above-mentioned first real-time power consumption data is considered to be normal, and when the above-mentioned difference is greater than the above-mentioned set difference or the above-mentioned first real-time power consumption data falls into the above-mentioned abnormal power consumption value range, it cannot be judged that the above-mentioned first real-time power consumption data is caused by the change of the power consumption mode of the above-mentioned power-consuming device. Whether the first real-time power consumption data deviates from the standard data or the collected first real-time power consumption data is abnormal, therefore, it is necessary to judge whether the first real-time power consumption data is abnormal through the second real-time power consumption data of other power-consuming devices in the same device group, wherein the real-time power consumption data of the other power-consuming devices include the second real-time power consumption data. When the second real-time power consumption data corresponding to the other power-consuming devices are normal, since the power consumption modes of the power-consuming devices in the same device group have a correlation, when the deviation between the first real-time power consumption data and the standard power consumption data is large or falls within the abnormal power consumption value range, and the corresponding second real-time power consumption data of other power-consuming devices are normal, the first real-time power consumption data is abnormal, and is corrected through the above-mentioned correlation between the other power-consuming devices, and the corrected or normal first real-time power consumption data is updated to the twin model. Through the above-mentioned technical solution, not only can it be accurately identified whether the first real-time power consumption data is abnormal, but also the first real-time power consumption data can be corrected.

[0047] Step S5: Simulate the simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period through the twin model simulation and the rated parameters of the power consuming device, and correct the simulated power consumption data based on the real-time power consumption data of the power consuming device to obtain virtual power consumption data.

[0048] Specifically, since the working power of the above-mentioned power consuming devices is different in different power consumption modes, and since the rated parameters of the power consuming devices are fixed, the size of the active power can be adjusted by adjusting the virtual power factor of the above-mentioned power consuming devices, thereby adjusting the size of the simulated power consumption data. Through the above-mentioned technical solution, accurate virtual power consumption data can be obtained.

[0049] Furthermore, the step S1 comprises:

[0050] Step S11: creating the twin model by a creation unit, and mapping the entrance, transmission lines, transmission equipment, substation equipment and distribution equipment of the power grid into the twin model according to the positional relationship based on the power grid layout diagram of the target area;

[0051] Step S12: each of the power consuming devices in the power grid and the rated parameters of the power consuming devices are also mapped into the twin model, where the rated parameters at least include rated voltage, rated current and rated power.

[0052] Specifically, by creating the above-mentioned twin model, and mapping the above-mentioned power grid entrance, transmission lines, transmission equipment, substation equipment and distribution equipment into the above-mentioned twin model according to the positional relationship, and mapping each power-consuming device into the above-mentioned twin model, the physical mapping of the power grid is realized, and the above-mentioned rated parameters of the above-mentioned power-consuming devices are further mapped into the above-mentioned twin model, laying the foundation for correcting the simulated power consumption data by adjusting the rated parameters.

[0053] Furthermore, the step S2 comprises:

[0054] Step S21: acquiring historical power consumption data corresponding to each power consuming device through a storage unit, wherein the historical power consumption data is time series data, obtaining multiple power consumption modes of each of the power consuming devices based on the historical power consumption data based on a clustering algorithm, and obtaining a central value and a data range of each of the power consumption modes, wherein a difference between the central values ​​corresponding to any two different power consumption modes is greater than a first threshold;

[0055] Specifically, through the historical power consumption data of the above-mentioned power-consuming devices and the above-mentioned clustering algorithm based on the clustering window, multiple power consumption modes of each of the above-mentioned power-consuming devices are obtained, that is, the power consumption at different times and the changing trend within the preset time, wherein the above-mentioned clustering window is 24 hours, and the central value and data range of each of the above-mentioned power consumption modes are also obtained, and the difference between the central values ​​of any two different power consumption modes is greater than the above-mentioned first threshold, so as to distinguish the above-mentioned power consumption modes. Through the above-mentioned technical solution, all power consumption modes of each of the above-mentioned power-consuming devices are obtained, so as to facilitate the acquisition of the correlation between the power consumption modes of the power-consuming devices within the preset time period.

[0056] Step S22: analyzing the correlation between the power consumption modes of different power consuming devices within a preset time period, and dividing the power consuming devices into a plurality of device groups according to the correlation, wherein the corresponding power consumption modes of the power consuming devices in the same device group are correlated with each other;

[0057] Step S23: Divide the remaining power-consuming devices that have not been divided into device groups into multiple sub-power consumption modes corresponding to each power consumption mode, obtain the device group with the highest timing power consumption trend correlation with each sub-power consumption mode among all the device groups as the first group, and add the remaining power-consuming devices and the sub-power consumption modes to the first group.

[0058] Specifically, by analyzing the correlation between the power consumption patterns corresponding to different power consuming devices within a preset time period, wherein the preset time period is a working day or a holiday, and dividing the power consuming devices with the above correlation into the same device group, the power consumption patterns of the power consuming devices whose power consumption patterns are not correlated with the power consumption patterns of other power consuming devices are divided into a plurality of the above sub-power consumption patterns, and the sub-power consumption patterns are compared with the power consumption patterns of the power consuming devices in each of the above-mentioned device groups corresponding to the above-mentioned sub-power consumption pattern time period, a first group closest to the above-mentioned sub-power consumption pattern is obtained, and the above-mentioned remaining power consuming devices and the corresponding sub-power consumption patterns are added to the above-mentioned first group. Through the above-mentioned technical solution, a device group with a correlation is obtained, thereby facilitating group management, and judging the abnormality of the power consumption data based on the correlation between the power consuming devices.

[0059] Furthermore, the step S4 comprises:

[0060] Step S41: obtaining a power consumption value range with a probability less than a set value according to the power consumption probability distribution of the power consuming devices in each device group within the preset time period, and taking the power consumption value range of the power consuming devices as an abnormal power consumption value range;

[0061] Specifically, through the above-mentioned power consumption probability distribution of each of the above-mentioned power-consuming devices within the above-mentioned preset time period, the abnormal power consumption value range with the above-mentioned probability less than the set value is obtained. Through the above-mentioned technical scheme, the abnormal power consumption value range of each power-consuming device in each device group within the above-mentioned preset time period can be obtained, laying a foundation for further judging the abnormality of the first real-time power consumption data collected in real time based on the above-mentioned abnormal power consumption value range.

[0062] Step S42: periodically acquiring the first real-time power consumption data of each of the power consuming devices within the preset time period, and comparing the first real-time power consumption data with the standard power consumption data corresponding to the power consumption mode of the power consuming device and acquiring a difference; when the difference is less than a set difference, the first real-time power consumption data is normal; otherwise, when the difference is greater than or equal to the set difference or the first real-time power consumption data falls within the corresponding abnormal power consumption value range, acquiring the second real-time power consumption data of other power consuming devices in the power consuming device group to which the power consuming device belongs;

[0063] Specifically, by periodically acquiring the above-mentioned first real-time power consumption data of each of the above-mentioned power-consuming devices, and comparing the above-mentioned first real-time power consumption data with the standard data of the above-mentioned power-consuming devices corresponding to the above-mentioned power consumption mode within a preset time, wherein the collection time of the above-mentioned first real-time power consumption data is consistent with the time corresponding to the above-mentioned standard data in the above-mentioned power consumption mode, when the difference between the two is less than the set difference, the above-mentioned first real-time power consumption data is considered to be normal, and when the above-mentioned difference is greater than the above-mentioned set difference or the above-mentioned first real-time power consumption data falls within the above-mentioned abnormal power consumption value range, it cannot be determined whether the above-mentioned first real-time power consumption data deviates from the above-mentioned standard data due to the change in the power consumption mode of the above-mentioned power-consuming device or the collected first real-time power consumption data is abnormal. Therefore, it is necessary to determine whether the above-mentioned first real-time power consumption data is abnormal through the second real-time power consumption data of other power-consuming devices in the same device group.

[0064] Step S43: When the second real-time power consumption data corresponding to the other power-consuming devices are all normal, the first real-time power consumption data is abnormal, and the first real-time power consumption data is corrected through the correlation between the power consumption mode of the power-consuming device and the power consumption modes of other power-consuming devices in the device group, and the corrected or normal first real-time power consumption data is sent to the twin model.

[0065] Specifically, when the above-mentioned second real-time power consumption data corresponding to the above-mentioned other power-consuming devices are all normal, since the power consumption modes of the power-consuming devices in the same device group are correlated, therefore, when the deviation between the first real-time power consumption data and the standard power consumption data is large or falls into the abnormal power consumption value range, and the corresponding second real-time power consumption data of other power-consuming devices are all normal, the first real-time power consumption data is abnormal, and is corrected through the above-mentioned correlation between the above-mentioned other power-consuming devices, for example: correlation coefficient, and at the same time, the above-mentioned corrected or normal first real-time power consumption data is updated to the above-mentioned twin model. Through the above-mentioned technical solution, not only can it be accurately identified whether the first real-time power consumption data is abnormal, but also the above-mentioned first real-time power consumption data can be corrected.

[0066] Furthermore, the step S43 further includes:

[0067] When the second real-time power consumption data corresponding to the other power consuming devices are not all normal, the first real-time power consumption device is taken as the first device, and a first power consumption data set consisting of multiple third real-time power consumption data of the first device in a first time period after the collection time corresponding to the first real-time power consumption data is obtained, the abnormal second real-time power consumption data corresponds to the other power consuming devices as the second device, and a second power consumption data set consisting of multiple fourth real-time power consumption data of the second device in the first time period is obtained, the first power consumption data set is compared with each power consumption mode of the first power consuming device, and a power consumption mode having a similarity with the first power consumption data set greater than a set similarity is obtained as the first mode. Similarly, a power consumption mode having a similarity with the second power consumption data set greater than the set similarity is obtained as the second mode, the first mode and the second mode are respectively added to the first mode set and the second mode set corresponding to the first device and the second device in the preset time period, and step S2 is repeated to re-acquire the third group and the fourth group corresponding to the first device and the second device respectively, and the first real-time power consumption data and the first power consumption data set of the first device and the second real-time power consumption data and the second power consumption data set of the second device are respectively sent to the twin model.

[0068] Specifically, when the second real-time power consumption data corresponding to other power-consuming devices in the device group to which the above-mentioned power-consuming device belongs are not all normal, that is, not every second real-time power consumption data has a difference with the corresponding standard data within the preset difference range, at this time, it may be that the external environment has changed so that the power consumption mode of some power-consuming devices has changed. Therefore, through the first power consumption data set of the above-mentioned first device in the first time period after the above-mentioned first real-time power consumption data collection time and the above-mentioned second power consumption data set of the above-mentioned second device in the second time period, wherein the above-mentioned real-time power consumption data of the above-mentioned power-consuming device includes the above-mentioned third real-time power consumption data, and the real-time power consumption data of the above-mentioned other power-consuming devices includes the above-mentioned fourth power consumption data, the power consumption of the above-mentioned first device and the above-mentioned second device and the change of power consumption over time are obtained. The trend is then identified, and the current first mode and second mode of the first device and the second device are respectively identified. Since the power consumption modes of the first device and the second device have changed, the power consumption modes of the first device and the second device and other power-consuming devices in their device group may no longer have a correlation. Therefore, by repeating the above step S2, the first group and the second group that are respectively correlated with the above-mentioned first device and the above-mentioned second device are re-acquired. When the above-mentioned first device or the above-mentioned second device cannot match the above-mentioned first mode and the above-mentioned second mode, it means that the first device or the second device has a fault. Therefore, an alarm message is sent to the above-mentioned twin model. Through the above-mentioned technical solution, the device grouping can be re-acquired when the power consumption mode of the power-consuming device changes.

[0069] Furthermore, the step S3 comprises:

[0070] Based on the power consumption pattern of each of the power-consuming devices in the device group within the preset time period, and reading the historical data corresponding to the power consumption pattern from the storage unit, the value probability of each power consumption data in the power consumption pattern is obtained through a data statistical algorithm, and the power consumption probability distribution of the power consumption pattern is obtained based on the value probability.

[0071] Specifically, the above technical solution can obtain the power consumption probability distribution of each power consuming device corresponding to the power consumption mode within the above preset time period, that is, the power consumption probability distribution within the preset time, and then judge whether the power consumption mode of the above power consuming device has changed or whether the data is abnormal through the above power consumption probability distribution, thereby improving the recognition accuracy of abnormal data.

[0072] Furthermore, the step S5 comprises:

[0073] The simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period is simulated by the twin model simulation and the rated parameters of the power consuming device. When the difference between the simulated power consumption data and the real-time power consumption data received by the twin model is greater than the set difference, the simulated power consumption data is corrected by adjusting the virtual power factor corresponding to the power consuming device to obtain the virtual power consumption data, so that the difference between the virtual power consumption data and the real-time power consumption data is less than or equal to the set difference, wherein the simulated power consumption data is the product of the rated power and the virtual power factor.

[0074] Specifically, since the working power of the above-mentioned power consuming devices is different in different power consumption modes, and since the rated parameters of the power consuming devices are fixed, the size of the active power can be adjusted by adjusting the virtual power factor of the above-mentioned power consuming devices, thereby adjusting the size of the simulated power consumption data. Through the above-mentioned technical solution, accurate virtual power consumption data can be obtained.

[0075] The present invention also provides a digital twin virtual-real mapping system, which is used to implement the above method, such as Figure 2 As shown, the system comprises:

[0076] A creation unit, configured to create a twin model, and map the grid layout in the target area and the rated parameters of each power-consuming device in the grid to the twin model according to the grid layout diagram of the target area;

[0077] A storage unit, used to store historical power consumption data of each of the power consuming devices;

[0078] A grouping unit, configured to obtain a power consumption mode of each of the power consuming devices based on the historical power consumption data, obtain a device group having a relevant relationship with the corresponding power consumption mode among the power consuming devices based on the power consumption mode of each of the power consuming devices within a preset time period, and obtain a probability distribution of power consumption of the power consuming devices within a preset time period based on the historical data of each of the power consuming devices in the device group;

[0079] The calculation unit is configured to: periodically collect the real-time power consumption data of the power-consuming device corresponding to each of the device groups, and determine whether the real-time power consumption data is abnormal based on the standard data of the power consumption mode corresponding to the power consumption device, the power consumption probability distribution of the power consumption mode corresponding to the power consumption device, and the real-time power consumption data of other power-consuming devices in the device group where the power-consuming device is located, and update the corrected abnormal real-time power consumption data and normal real-time power consumption data of the power-consuming device into the twin model;

[0080] A simulation unit is used to simulate the simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period through the twin model simulation and the rated parameters of the power consuming device, and to correct the simulated power consumption data based on the real-time power consumption data of the power consuming device to obtain virtual power consumption data.

[0081] The present invention also provides a computer storage medium, wherein the storage medium stores program instructions, wherein when the program instructions are executed, the device where the storage medium is located is controlled to execute the above method.

[0082] In summary, the present invention creates the above-mentioned twin model, maps the power grid layout in the target area and each power-consuming device and rated parameters in the power grid to the above-mentioned twin model according to the power grid layout diagram of the target area, thereby realizing the physical mapping of the power grid. The present invention also uses the historical power consumption data of the above-mentioned power-consuming devices and obtains all power consumption patterns of each of the above-mentioned power-consuming devices based on the clustering window through a clustering algorithm, thereby obtaining the correlation between the power consumption patterns corresponding to different power-consuming devices within a preset time period, and divides the power-consuming devices with the above-mentioned correlation into the same device group, and also divides the power consumption patterns of power-consuming devices whose power consumption patterns are not correlated with the power consumption patterns of other power-consuming devices into the above-mentioned sub-power consumption patterns, and compares the sub-power consumption patterns with the power consumption patterns of the power-consuming devices in each of the above-mentioned device groups corresponding to the above-mentioned sub-power consumption pattern time period part. A comparison is made to obtain a first group that is closest to the above-mentioned sub-power consumption pattern, and the above-mentioned remaining power-consuming devices and the corresponding sub-power consumption patterns are added to the above-mentioned first group, so as to facilitate group management, and judge the abnormality of the power consumption data according to the correlation between the power-consuming devices, and also obtain the power consumption probability distribution of the power consuming devices within a preset time period based on the historical data of each power-consuming device in the above-mentioned device group, and judge whether the real-time power consumption data is abnormal based on the standard data of the power consumption pattern corresponding to the power consumption pattern of the power-consuming device, the power consumption probability distribution of the power consumption pattern corresponding to the power consumption pattern of the power-consuming device and the real-time power consumption data of other power-consuming devices in the device group where the power-consuming device is located. Not only can it be accurately identified whether the first real-time power consumption data is abnormal, but also the above-mentioned first real-time power consumption data can be corrected. The mutual cooperation of the above-mentioned technical solutions improves the accuracy of identifying abnormal data.

[0083] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0084] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0085] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A digital twin virtual-real mapping method, characterized in that: The method comprises the following steps: Step S1: creating a twin model, mapping the grid layout in the target area and each power-consuming device in the grid and the rated parameters of the power-consuming device into the twin model according to the grid layout diagram of the target area; Step S2: acquiring historical power consumption data of each of the power consuming devices through a storage unit, acquiring a power consumption mode of each of the power consuming devices based on the historical power consumption data, and acquiring a group of devices having a correlation with the corresponding power consumption mode among the power consuming devices based on the power consumption mode of each of the power consuming devices within a preset time period; Step S3: obtaining a probability distribution of power consumption of each power-consuming device in the device group within a preset time period based on historical data of each power-consuming device in the device group; Step S4: periodically collect the real-time power consumption data of the power-consuming device corresponding to each of the device groups, and determine whether the real-time power consumption data is abnormal based on the standard data of the power consumption mode corresponding to the power consumption device, the power consumption probability distribution of the power consumption mode corresponding to the power consumption device, and the real-time power consumption data of other power-consuming devices in the device group where the power-consuming device is located, and update the corrected abnormal real-time power consumption data and normal real-time power consumption data of the power-consuming device into the twin model; Step S5: Simulate the simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period through the twin model simulation and the rated parameters of the power consuming device, and correct the simulated power consumption data based on the real-time power consumption data of the power consuming device to obtain virtual power consumption data.

2. The method according to claim 1, characterized in that The step S1 comprises: Step S11: creating the twin model by a creation unit, and mapping the entrance, transmission lines, transmission equipment, substation equipment and distribution equipment of the power grid into the twin model according to the positional relationship based on the power grid layout diagram of the target area; Step S12: each of the power consuming devices in the power grid and the rated parameters of the power consuming devices are also mapped into the twin model, where the rated parameters at least include rated voltage, rated current and rated power.

3. The method according to claim 1, characterized in that The step S2 comprises: Step S21: acquiring historical power consumption data corresponding to each power consuming device through a storage unit, wherein the historical power consumption data is time series data, obtaining multiple power consumption modes of each of the power consuming devices based on the historical power consumption data based on a clustering algorithm, and obtaining a central value and a data range of each of the power consumption modes, wherein a difference between the central values ​​corresponding to any two different power consumption modes is greater than a first threshold; Step S22: analyzing the correlation between the power consumption modes of different power consuming devices within a preset time period, and dividing the power consuming devices into a plurality of device groups according to the correlation, wherein the corresponding power consumption modes of the power consuming devices in the same device group are correlated with each other; Step S23: Divide the remaining power-consuming devices that have not been divided into device groups into multiple sub-power consumption modes corresponding to each power consumption mode, obtain the device group with the highest timing power consumption trend correlation with each sub-power consumption mode among all the device groups as the first group, and add the remaining power-consuming devices and the sub-power consumption modes to the first group.

4. The method according to claim 3, characterized in that The step S4 comprises: Step S41: obtaining a power consumption value range with a probability less than a set value according to the power consumption probability distribution of the power consuming devices in each device group within the preset time period, and taking the power consumption value range of the power consuming devices as an abnormal power consumption value range; Step S42: periodically acquiring the first real-time power consumption data of each of the power-consuming devices within the preset time period, and comparing the first real-time power consumption data with the standard power consumption data corresponding to the power consumption mode of the power-consuming device and acquiring a difference; when the difference is less than a set difference, the real-time power consumption data is normal; otherwise, when the difference is greater than or equal to the set difference or the first real-time power consumption data falls within the corresponding abnormal power consumption value range, acquiring the second real-time power consumption data of other power-consuming devices in the power-consuming device group to which the power-consuming device belongs; Step S43: When the second real-time power consumption data corresponding to the other power-consuming devices are all normal, the first real-time power consumption data is abnormal, and the first real-time power consumption data is corrected according to the correlation between the first real-time power consumption data and the other power-consuming devices in the power-consuming device group, and the corrected or normal first real-time power consumption data is sent to the twin model.

5. The method according to claim 4, characterized in that The step S43 further includes: When the second real-time power consumption data corresponding to the other power consuming devices are not all normal, the first real-time power consumption device is used as the first device, and a first power consumption data set consisting of multiple third real-time power consumption data of the first device in a first time period after the collection time corresponding to the first real-time power consumption data is obtained, and the abnormal second real-time power consumption data corresponds to the other power consuming devices as the second device, and a second power consumption data set consisting of multiple fourth real-time power consumption data of the second device in the first time period is obtained, and the first power consumption data set is compared with each power consumption mode of the first power consuming device, and a power consumption mode having a similarity with the first power consumption data set greater than a set similarity is obtained as the first mode. Similarly, a power consumption mode having a similarity with the second power consumption data set greater than the set similarity is obtained as the second mode, and the first mode and the second mode are respectively added to the first mode set and the second mode set corresponding to the first device and the second device in the preset time period, and step S2 is repeated to re-acquire the third group and the fourth group corresponding to the first device and the second device, respectively, and the first real-time power consumption data and the first power consumption data set of the first device and the second real-time power consumption data and the second power consumption data set of the second device are respectively sent to the twin model.

6. The method according to claim 1, characterized in that The step S3 comprises: Based on the power consumption pattern of each of the power-consuming devices in the device group within the preset time period, and reading the historical data corresponding to the power consumption pattern from the storage unit, the value probability of each power consumption data in the power consumption pattern is obtained through a data statistical algorithm, and the power consumption probability distribution of the power consumption pattern is obtained based on the value probability.

7. The method according to claim 1, characterized in that The step S5 comprises: The simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period is simulated by the twin model simulation and the rated parameters of the power consuming device, and the power factor of the power consuming device corresponding to the rated parameters is adjusted so that the difference between the simulated power consumption data and the real-time power consumption data is less than the set difference.

8. A digital twin virtual-reality mapping system, the system being used to implement the method according to any one of claims 1 to 7, characterized in that: The system comprises: A creation unit, configured to create a twin model, and map the grid layout in the target area and each power-consuming device in the grid and the rated parameters of the power-consuming device into the twin model according to the grid layout diagram of the target area; A storage unit, used to store historical power consumption data of each of the power consuming devices; A grouping unit, configured to obtain a power consumption mode of each of the power consuming devices based on the historical power consumption data, obtain a device group having a relevant relationship with the corresponding power consumption mode among the power consuming devices based on the power consumption mode of each of the power consuming devices within a preset time period, and obtain a probability distribution of power consumption of the power consuming devices within a preset time period based on the historical data of each of the power consuming devices in the device group; The calculation unit is configured to: periodically collect the real-time power consumption data of the power-consuming device corresponding to each of the device groups, and determine whether the real-time power consumption data is abnormal based on the standard data of the power consumption mode corresponding to the power consumption device, the power consumption probability distribution of the power consumption mode corresponding to the power consumption device, and the real-time power consumption data of other power-consuming devices in the device group where the power-consuming device is located, and update the corrected abnormal real-time power consumption data and normal real-time power consumption data of the power-consuming device into the twin model; A simulation unit is used to simulate the simulated power consumption data of the power consuming device corresponding to the power consumption mode within the preset time period through the twin model simulation and the rated parameters of the power consuming device, and to correct the simulated power consumption data based on the real-time power consumption data of the power consuming device to obtain virtual power consumption data.

9. A computer storage medium, characterized in that: The storage medium stores program instructions, wherein when the program instructions are executed, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images