Power grid twin construction method and device, electronic equipment and computer readable medium

Abstract

This disclosure presents embodiments of a method, apparatus, electronic device, and computer-readable medium for constructing a power grid twin. One specific implementation of the method includes: generating a power grid twin skeleton based on regional environmental parameters corresponding to a target area; decomposing the power grid twin skeleton based on historical equipment parameters corresponding to the power equipment; and for each local power grid twin skeleton in at least one local power grid twin skeleton, performing the following processing steps: in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generating a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton; and binding the local power grid twin with a status monitoring strategy. This implementation effectively ensures the stable and normal operation of the power equipment.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the fields of computer technology and power grid operation monitoring, specifically to methods, apparatus, electronic devices, and computer-readable media for constructing power grid twins. Background Technology

[0002] A digital twin, also known as a digital mapping, refers to a virtual representation of the real world, including physical objects, processes, and relationships. In the field of power grid operation monitoring, since electricity is one of the most important basic energy sources, related power equipment is widely used in various industries. The detection of the operating status of power equipment is usually carried out through manual inspection.

[0003] However, manual inspection has the following technical problems:

[0004] With numerous power equipment located in complex locations, conventional manual inspection methods are inefficient and untimely, thus failing to effectively guarantee the stable and normal operation of the power equipment.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure provide methods, apparatuses, electronic devices, and computer-readable media for constructing power grid twins to address the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide a method for constructing a power grid twin. The method includes: generating a power grid twin skeleton based on regional environmental parameters corresponding to a target region, wherein the regional environmental parameters include regional spatial parameters and equipment layout parameters, the equipment layout parameters characterizing the equipment layout of power equipment located within the target region, and the power grid twin skeleton consisting of at least M skeleton anchor points and N skeleton veins; decomposing the power grid twin skeleton based on historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton; for each of the at least one local power grid twin skeletons, performing the following processing steps: in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generating a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton, wherein the real-time equipment parameters include real-time equipment attribute parameters and real-time equipment operating parameters; and binding a status monitoring strategy to the local power grid twin. Secondly, some embodiments of this disclosure provide a power grid twin construction apparatus, comprising: a generation unit configured to generate a power grid twin skeleton based on regional environmental parameters corresponding to a target region, wherein the regional environmental parameters include regional spatial parameters and equipment layout parameters, the equipment layout parameters characterizing the equipment layout of power equipment set in the target region, and the power grid twin skeleton consisting of at least M skeleton anchor points and N skeleton veins; a skeleton decomposition unit configured to decompose the power grid twin skeleton based on historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton; and an execution unit configured to perform the following processing steps for each of the at least one local power grid twin skeletons: in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generating a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton, wherein the real-time equipment parameters include real-time equipment attribute parameters and real-time equipment operating parameters; and binding a status monitoring strategy to the local power grid twin.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: the power grid twin construction method of some embodiments of this disclosure effectively ensures the stable and normal operation of power equipment. Specifically, the reason why the stable operation of power equipment cannot be effectively guaranteed is that there are many power equipment and their deployment locations are complex, and the efficiency and timeliness of conventional manual inspection methods are poor. Based on this, the power grid twin construction method of some embodiments of this disclosure first generates a power grid twin skeleton based on the regional environmental parameters corresponding to the target area. The aforementioned regional environmental parameters include: regional spatial parameters and equipment layout parameters. The aforementioned equipment layout parameters characterize the equipment layout of the power equipment set in the aforementioned target area. The aforementioned power grid twin skeleton consists of at least M skeleton anchor points and N skeleton veins. In practice, the power equipment itself or the surrounding environment of the power equipment may affect the normal operation of the power equipment. Therefore, by constructing a power grid twin skeleton, the skeleton anchor points used for power grid twin construction and the skeleton veins representing the relationship between the skeleton anchor points can be determined from the perspective of power equipment layout and the surrounding environment of the power equipment, so as to realize the construction of the twin skeleton. Secondly, based on the historical equipment parameters corresponding to the power equipment, the aforementioned power grid twin skeleton is decomposed to obtain at least one local power grid twin skeleton. For the target area (e.g., a large area requiring the construction of a power grid twin), there are often many power equipment units with complex deployment locations. If a power grid twin is constructed for all power equipment in the target area, a large amount of unnecessary data updates will occur during the data update and synchronization process, resulting in excessive computational resources and affecting the update speed. Therefore, this disclosure adaptively decomposes the power grid twin skeleton by combining the historical equipment data corresponding to the power equipment to obtain at least one local power grid twin skeleton. Next, for each local power grid twin skeleton in the above at least one local power grid twin skeleton, the following processing steps are performed: First, in response to the update of the power equipment parameters corresponding to the above local power grid twin skeleton, a local power grid twin is generated based on the real-time equipment parameters of the power equipment corresponding to the above local power grid twin skeleton and the above local power grid twin skeleton. The real-time equipment parameters include: real-time equipment attribute parameters and real-time equipment operating parameters. In practice, when equipment parameter updates are detected (especially the first update), this is used to synchronize updates between the power equipment and the local power grid twin, thereby obtaining the corresponding local power grid twin. This method combines the characteristics of data updates to achieve the construction and generation of a local twin (only for the local power grid twin), thus avoiding full updates and improving update speed. The second step is to bind the aforementioned local power grid twin with a status monitoring strategy.In practice, different local power grid twins often correspond to different electronic devices, resulting in varying anomaly monitoring strategies. Therefore, it is necessary to set appropriate status monitoring strategies and bind them to the corresponding local power grid twins to achieve automatic triggering and alarms for abnormal states. This approach effectively ensures the stable and normal operation of power equipment. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the power grid twin construction method according to the present disclosure;

[0014] Figure 2 This is a schematic diagram showing the positional relationships of the segmented regions in a set of segmented regions;

[0015] Figure 3 This is a schematic diagram illustrating the process of generating the affected area after the update;

[0016] Figure 4 These are schematic diagrams of structures of some embodiments of the power grid twin construction apparatus according to this disclosure;

[0017] Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0018] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0019] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0020] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0021] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0022] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0023] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] refer to Figure 1 The diagram illustrates a flow 100 of some embodiments of a power grid twin construction method according to the present disclosure. This power grid twin construction method includes the following steps:

[0025] Step 101: Generate the grid twin skeleton based on the regional environmental parameters corresponding to the target area.

[0026] In some embodiments, the execution entity (e.g., a computing device) of the power grid twin construction method can generate a power grid twin skeleton based on the regional environmental parameters corresponding to the target area. The target area can be an area with a large number of power devices deployed, from which a corresponding power grid twin is to be generated. The regional environmental parameters describe the regional geographical environment of the target area and the equipment layout of the power devices deployed within the area. These regional environmental parameters include: regional spatial parameters and equipment layout parameters. The regional spatial parameters characterize the regional geographical environment of the target area. The equipment layout parameters characterize the equipment layout of the power devices located within the target area. The power grid twin skeleton consists of at least M skeleton anchor points and N skeleton veins. M and N are both positive integers. Skeleton anchor points characterize monitoring points in the power grid twin skeleton (e.g., regional environmental monitoring points, equipment status monitoring points). Skeleton veins characterize the equipment connection relationships between power devices. For example, power devices can be transformers, circuit breakers, reactors, etc.

[0027] It should be noted that the aforementioned computing devices can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed on the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0028] Optionally, the equipment layout information may include a set of equipment description information. This equipment description information includes: equipment type, equipment location information, and equipment connection information. The equipment type represents the type of power equipment. The equipment location information represents the location where the power equipment is deployed. The equipment connection information represents the connection relationships and connection methods between the power equipment.

[0029] In some optional implementations of certain embodiments, the regional environmental parameters can be generated through the following steps:

[0030] The first step is to obtain a remote sensing map of the target area and the equipment layout parameters corresponding to the power equipment set in the target area.

[0031] In practice, when power equipment is initially deployed, its location is often measured and mapped using instruments such as total stations (electronic total stations). Specifically, the equipment layout parameters can be stored on a server. Therefore, the layout parameters of the power equipment within the target area can be retrieved from the server via wired or wireless connections. The regional remote sensing map can be the latest remote sensing image of the target area acquired through methods such as synthetic aperture radar.

[0032] The second step is to segment the remote sensing image of the region based on the regional roads within the aforementioned regional remote sensing image, thereby obtaining a set of segmented regions.

[0033] In practice, the aforementioned implementing entities can use regional roads as dividing boundaries to segment the regional remote sensing images, thereby obtaining the aforementioned set of segmented regions.

[0034] As an example, see Figure 2 The diagram shows the positional relationship of the segmented regions in the set of segmented regions. The set of segmented regions may include: segmented region A, segmented region B, segmented region C, segmented region D, segmented region E, segmented region F, segmented region G, and segmented region H.

[0035] The third step is to perform region filtering on the segmented regions in the above segmented region set based on the above device description information set, so as to obtain the first segmented region set and the second segmented region set.

[0036] The first segmented region is the segmented region obtained from image localization where the location of the power equipment within the region matches the corresponding equipment description information. The second segmented region is the segmented region obtained from image localization where the location of the power equipment within the region does not match the corresponding equipment description information.

[0037] In practice, for each segmented region in the segmentation region set, image localization and recognition of power equipment within the segmented region can be performed using a model such as YOLO (You Only Look Once). Then, position matching is performed with the equipment location information included in the equipment description information set. When the location of the power equipment within the segmented region obtained from image localization matches the corresponding equipment description information, the segmented region is determined as the first segmented region. When the location of the power equipment within the segmented region obtained from image localization does not match the corresponding equipment description information, the segmented region is determined as the second segmented region. Specifically, due to the accuracy limitations of remote sensing images and the small size of some power equipment, inaccurate image localization may occur, thus affecting the matching accuracy.

[0038] The fourth step is to generate the aforementioned regional spatial parameters based on the first set of segmented regions and the second set of segmented regions.

[0039] In practice, it includes the following sub-steps:

[0040] The first sub-step involves performing the following region precision processing steps based on the second segmented region set:

[0041] Step 1: Select the second segmentation region sequentially from the second segmentation region set as the target segmentation region.

[0042] As an example, the second segmentation region set may include: second segmentation region A, second segmentation region B, and second segmentation region C. The aforementioned execution entity may sequentially select second segmentation region A as the target segmentation region.

[0043] Step 2: Obtain supplementary images of the target segmented region.

[0044] The image resolution of the supplementary regional image is greater than that of the aforementioned regional remote sensing image. In practice, the supplementary regional image can be an image acquired from a top-down perspective by means of a drone or similar device, targeting a segmented region, and with a resolution greater than that of the regional remote sensing image.

[0045] Step 3: Based on the supplementary image of the region, optimize the region accuracy of the target segmentation region to obtain the optimized target segmentation region.

[0046] In practice, the optimized target segmentation region can be obtained by replacing local remote sensing images within the target segmentation region with region-supplemented images through image replacement and updating.

[0047] Step 4: Determine whether the location of the power equipment within the optimized target segmentation area matches the equipment description information corresponding to the power equipment.

[0048] In practice, the optimized target segmentation region can be further localized and identified using the YOLO model. Due to the increased image resolution, the location of power equipment can be more accurately determined. Based on this, the location is then matched again with the equipment location information included in the equipment description information set.

[0049] Step 5: In response to matching, the optimized target segmentation region is used as the first segmentation region and added to the above first segmentation region set.

[0050] Step 6: In response to the second segmentation region set being empty after removing the target segmentation region, the above region precision processing steps are terminated.

[0051] The second sub-step is to take the second segmentation region set after removing the target segmentation region as the second segmentation region set and then perform the above region precision processing steps again.

[0052] The third sub-step involves extracting region boundary feature points for each of the first segmented regions in the updated set of first segmented regions to generate a set of region boundary feature points.

[0053] In practice, an edge feature point extraction method based on the Sobel operator can be used to extract the boundary feature points of the first segmented region, resulting in a set of boundary feature points. In particular, considering that the boundary of the first segmented region is continuous and has a certain length, using all extracted key points as boundary feature points would result in a large number of feature points, thus affecting the structural complexity of the generated power grid twin skeleton. Therefore, after edge feature point extraction, polygon vertices (feature points) of the corresponding polygons in the first segmented region are determined as the set of boundary feature points through polygon approximation.

[0054] The fourth sub-step is to determine the set of feature points of the aforementioned region boundary as the spatial parameters of the aforementioned region.

[0055] In some optional implementations of certain embodiments, the execution entity generates a power grid twin skeleton based on regional environmental parameters corresponding to the target region, including:

[0056] The first step is to determine the set of regional boundary feature points included in the above-mentioned regional spatial parameters and the equipment location information included in the equipment description information set in the above-mentioned equipment description information set as the M skeleton anchor points included in the above-mentioned power grid twin skeleton.

[0057] In practice, the aforementioned implementing entity can use the power equipment corresponding to the regional boundary feature points and equipment location information as skeleton anchor points to obtain M skeleton anchor points.

[0058] The second step is to determine the N skeleton networks included in the above-mentioned power grid twin skeleton based on the above-mentioned M skeleton anchor points and the equipment connection information included in the equipment description information set.

[0059] In practice, in order to ensure power transmission, there are often connections between power equipment. Therefore, based on the equipment connection information, the anchor point connection relationship between the corresponding power equipment skeleton anchor points can be determined as the skeleton network.

[0060] Step 102: Based on the historical equipment parameters corresponding to the power equipment, decompose the power grid twin skeleton to obtain at least one local power grid twin skeleton.

[0061] In some embodiments, the aforementioned executing entity can decompose the power grid twin skeleton based on the historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton. The historical equipment parameters may include: equipment attribute parameters and historical equipment operating parameters. Equipment attribute parameters can characterize the equipment specifications of the power equipment. Historical equipment operating parameters can characterize the historical operating parameters of the power equipment. For example, historical equipment operating parameters may include: historical voltage curves, historical current curves, etc. Specifically, historical equipment attribute parameters can be collected by sensors installed at the power equipment. For example, historical equipment attribute parameters can be collected by displacement sensors.

[0062] In some optional implementations of certain embodiments, the aforementioned execution entity performs skeleton decomposition on the power grid twin skeleton based on the historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton, including the following steps:

[0063] The first step is to determine the anchor point importance of the corresponding power equipment's skeleton anchor point in the aforementioned power grid twin skeleton based on the historical equipment parameters.

[0064] In practice, the importance of power equipment within a target area is determined by combining its specifications and historical operating parameters during operation. Specifically, based on electricity demand and future planning, power equipment that meets these needs is often selected during the deployment phase. Therefore, the importance of anchor points is determined by combining historical equipment parameters, including equipment attribute parameters and historical operating parameters, to assess the impact of the corresponding equipment's backbone anchor points on the target area's electricity consumption. This disclosure considers that historical equipment operating parameters are time-series data with temporal characteristics, and also takes into account the large amount of historical operating parameter data for a large number of power equipment. Therefore, a minLSTM backbone network is used to extract features from historical equipment operating parameters to generate corresponding operating labels. Then, the operating labels and equipment attribute parameters are used to construct a JSON-formatted descriptive text for the power equipment. An ALBERT model is used for text feature extraction, and finally, a multi-classifier is used to output the corresponding anchor point importance.

[0065] The second step involves performing the following skeleton decomposition steps for each of the M skeleton anchor points mentioned above, which corresponds to an anchor point importance:

[0066] The first sub-step involves determining the affected area based on the importance of the aforementioned skeleton anchor points, centered on them.

[0067] In practice, since the M skeleton anchor points include skeleton anchor points corresponding to power equipment and skeleton anchor points corresponding to region boundaries, only the skeleton anchor points corresponding to power equipment have anchor point importance. Specifically, the anchor point importance is used as the region radius coefficient to determine the initial region radius. Wherein, the initial region radius = base region radius × region radius coefficient. Combining this with the initial region radius will yield a circular region centered on the skeleton anchor points, which serves as the influence region.

[0068] The second sub-step involves updating the affected region based on the skeleton anchor points around the region boundary, resulting in the updated affected region.

[0069] As an example, see Figure 3 The diagram illustrates the process of generating the updated affected region. However, the circular region (affected region) often doesn't accurately reflect the actual application scenario. Therefore, further, the distance between each skeleton anchor point outside the circular region in the set of M skeleton anchor points and the boundary of the circular region is calculated. When the distance is less than a preset threshold, the skeleton anchor point is selected as a candidate skeleton anchor point, resulting in a candidate skeleton anchor point set. Finally, the closed region enclosed by the candidate skeleton anchor point set is taken as the updated affected region.

[0070] The third sub-step involves generating a local power grid twin skeleton based on the skeleton anchor points and skeleton network within the updated affected area.

[0071] The local power grid twin skeleton includes the skeleton anchor points within the updated region and the skeleton network between the skeleton anchor points within the updated region.

[0072] The aforementioned content, "in some optional implementations of some embodiments," serves as an inventive point of this disclosure. By combining historical equipment parameters corresponding to the power equipment, the importance of anchor points is dynamically determined, and an updated impact area tailored to the actual application scenario is generated based on the anchor point importance. This constructs a local power grid twin skeleton containing power equipment as its core, facilitating more targeted condition monitoring in the future.

[0073] Step 103: For each local power grid twin skeleton in at least one local power grid twin skeleton, perform the following processing steps:

[0074] Step 1031: In response to the update of the power equipment parameters corresponding to the local power grid twin skeleton, generate a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton.

[0075] In some embodiments, the aforementioned execution entity can, in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generate a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton. In practice, since the power equipment corresponding to the local power grid twin skeleton is known, it can be achieved by grouping devices and setting parameter listeners on the electronic devices corresponding to the local power grid twin skeleton to monitor whether the power equipment corresponding to the local power grid twin skeleton has updated its parameters. Specifically, the local power grid twin can be obtained by hard-binding the real-time equipment parameters corresponding to the power equipment to the local power grid twin. In practice, the real-time equipment parameters may include: real-time operating parameters corresponding to the power equipment and sensor parameters collected by sensors used to monitor changes in the regional environment. The real-time operating parameters characterize the real-time operating status of the power equipment. Furthermore, at the skeleton anchor points corresponding to the local power grid twin but not to the power equipment, i.e., the skeleton anchor points corresponding to the regional edge feature points of the first segmented region, sensors such as displacement sensors and flooding sensors can be set to detect changes in the regional environment of the first segmented region corresponding to the local power grid twin, serving as sensor parameters. When the environment changes, it is synchronized with the local power grid twin. This method can effectively monitor changes in the regional environment of the area where power equipment is installed, enabling early detection of anomalies.

[0076] In some optional implementations of certain embodiments, the execution entity, in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generates a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton, including:

[0077] The first step is to extract parameter features from the above real-time device parameters to generate device parameter features.

[0078] In practice, real-time equipment parameters consist of two parts: real-time operating parameters corresponding to the power equipment and sensor parameters collected by sensors. This disclosure considers that both parts are time-series signals, but with different signal dimensions, and that these two parts are not generated synchronously in real time. Therefore, triggers are set for these two parts of the parameters, and the corresponding time-series feature extractors are activated through these triggers to extract features from the corresponding real-time operating parameters or sensor parameters, thus obtaining the equipment parameter features. Specifically, the time-series feature extractor uses a minLSTM as the backbone network. In particular, different time-series feature extractors are used for different parameters, and transfer learning is used to train the models between different time-series feature extractors. This reduces network computational and training costs.

[0079] The second step is to determine the importance of the parameters based on the aforementioned equipment parameter characteristics.

[0080] In practice, since the two sets of parameters mentioned above are not generated synchronously in real time, the feature dimension of the collected device parameter features may be W×H. Here, the output dimension of each temporal feature extractor is 1×H, and W represents the parameter features corresponding to the two sets of parameters generated at the same time, with W being the variable. Therefore, when determining parameter importance based on the aforementioned device parameter features, a network structure of convolutional neural network + SPP (Spatial Pyramid Pooling) network + multi-classifier is used to generate parameter importance.

[0081] The third step is to determine the parameter update frequency based on the parameter importance and the pre-built parameter update decision tree.

[0082] In practice, parameter update decision trees determine the intervals corresponding to parameter importance and thus map the corresponding parameter update frequency.

[0083] The fourth step involves synchronizing the real-time equipment parameters of the power equipment corresponding to the aforementioned local power grid twin skeleton with the aforementioned local power grid twin skeleton based on the parameter importance and parameter update frequency corresponding to the real-time equipment parameters, in order to generate the aforementioned local power grid twin.

[0084] In practice, real-time equipment parameters are added to corresponding update queues based on their importance, and these parameters are periodically synchronized to the local grid twin at intervals defined by the parameter update frequency. This method allows for dynamic adjustment of parameter importance and update frequency based on data characteristics, reducing the data update pressure on the local grid twin compared to real-time synchronization. Specifically, once the local grid twin is generated, new real-time equipment parameters are directly synchronized to it.

[0085] Step 1032: Bind the status monitoring strategy to the local power grid twin.

[0086] In practice, the aforementioned implementing entities can bind status monitoring strategies to the local power grid twin. These status monitoring strategies can be pre-configured and automatically triggered when anomalies occur in the electrical equipment corresponding to the local power grid twin and in the surrounding environment. In practice, the status monitoring strategies can be hard-coded and bound to the local power grid twin.

[0087] In some optional implementations of certain embodiments, the aforementioned execution entity binds a state monitoring strategy to the local power grid twin, including the following steps:

[0088] The first step is to select the device monitoring strategies that meet the selection criteria from at least one device monitoring strategy, and use them as the target device monitoring strategies to obtain the target device monitoring strategy set.

[0089] At least one of the aforementioned equipment monitoring policies is extracted by the target terminal from the equipment monitoring policy pool. The selection criteria are: the equipment monitoring policy must be able to be triggered based on the equipment status of the power equipment corresponding to the aforementioned local power grid twin skeleton. The target terminal is an authorized terminal with twin control permissions. For example, the equipment monitoring policy could be "monitoring the current changes of power equipment, and issuing an early warning when the real-time current exceeds a preset current value."

[0090] The second step is to generate a policy certificate corresponding to each target device monitoring policy in the above target device monitoring policy set.

[0091] The policy certificate includes: authorization period, policy lifespan, policy identifier, policy authorization object identifier, and signature algorithm type. In practice, a policy certificate retrieval request can be sent to the authorized node to obtain the policy certificate for the target device monitoring policy. The policy identifier represents the target device monitoring policy. The policy authorization object identifier represents the node identifier of the authorized node. The policy lifespan represents the validity period of the corresponding target device monitoring policy.

[0092] The third step is to generate a status monitoring policy based on the above set of target device monitoring policies and the policy certificates corresponding to the target device monitoring policies.

[0093] In practice, a status monitoring strategy consists of a set of monitoring strategies for the target device and the corresponding policy certificates for the monitoring strategies of the target device. When the policy certificate is valid, the corresponding monitoring strategy for the target device is in a usable state.

[0094] The fourth step is to distribute the aforementioned status monitoring strategy to the power equipment corresponding to the aforementioned local power grid twin skeleton, and simultaneously soft-bind the aforementioned status monitoring strategy and the aforementioned local power grid twin.

[0095] In practice, soft binding allows for flexible adjustments to monitoring strategies based on changing monitoring needs, thereby improving monitoring robustness.

[0096] Optionally, after binding the state monitoring strategy to the aforementioned local power grid twin, the method further includes:

[0097] The first step is to publish the aforementioned local power grid twin to the target terminal in response to successful binding.

[0098] The target terminal mentioned above is a trusted terminal with twin control permissions. This allows for real-time monitoring of power equipment and its surrounding environment through the trusted terminal in conjunction with the local power grid twin.

[0099] The second step is to send a binding error message to the target terminal in response to the binding failure.

[0100] The above-described embodiments of this disclosure have the following beneficial effects: the power grid twin construction method of some embodiments of this disclosure effectively ensures the stable and normal operation of power equipment. Specifically, the reason why the stable operation of power equipment cannot be effectively guaranteed is that there are many power equipment and their deployment locations are complex, and the efficiency and timeliness of conventional manual inspection methods are poor. Based on this, the power grid twin construction method of some embodiments of this disclosure first generates a power grid twin skeleton based on the regional environmental parameters corresponding to the target area. The aforementioned regional environmental parameters include: regional spatial parameters and equipment layout parameters. The aforementioned equipment layout parameters characterize the equipment layout of the power equipment set in the aforementioned target area. The aforementioned power grid twin skeleton consists of at least M skeleton anchor points and N skeleton veins. In practice, the power equipment itself or the surrounding environment of the power equipment may affect the normal operation of the power equipment. Therefore, by constructing a power grid twin skeleton, the skeleton anchor points used for power grid twin construction and the skeleton veins representing the relationship between the skeleton anchor points can be determined from the perspective of power equipment layout and the surrounding environment of the power equipment, so as to realize the construction of the twin skeleton. Secondly, based on the historical equipment parameters corresponding to the power equipment, the aforementioned power grid twin skeleton is decomposed to obtain at least one local power grid twin skeleton. For the target area (e.g., a large area requiring the construction of a power grid twin), there are often many power equipment units with complex deployment locations. If a power grid twin is constructed for all power equipment in the target area, a large amount of unnecessary data updates will occur during the data update and synchronization process, resulting in excessive computational resources and affecting the update speed. Therefore, this disclosure adaptively decomposes the power grid twin skeleton by combining the historical equipment data corresponding to the power equipment to obtain at least one local power grid twin skeleton. Next, for each local power grid twin skeleton in the above at least one local power grid twin skeleton, the following processing steps are performed: First, in response to the update of the power equipment parameters corresponding to the above local power grid twin skeleton, a local power grid twin is generated based on the real-time equipment parameters of the power equipment corresponding to the above local power grid twin skeleton and the above local power grid twin skeleton. The real-time equipment parameters include: real-time equipment attribute parameters and real-time equipment operating parameters. In practice, when equipment parameter updates are detected (especially the first update), this is used to synchronize updates between the power equipment and the local power grid twin, thereby obtaining the corresponding local power grid twin. This method combines the characteristics of data updates to achieve the construction and generation of a local twin (only for the local power grid twin), thus avoiding full updates and improving update speed. The second step is to bind the aforementioned local power grid twin with a status monitoring strategy.In practice, different local power grid twins often correspond to different electronic devices, resulting in varying anomaly monitoring strategies. Therefore, it is necessary to set appropriate status monitoring strategies and bind them to the corresponding local power grid twins to achieve automatic triggering and alarms for abnormal states. This approach effectively ensures the stable and normal operation of power equipment.

[0101] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a power grid twin construction device, which are similar to... Figure 1 Corresponding to the method embodiments shown, this power grid twin construction device can be specifically applied to various electronic devices.

[0102] like Figure 4 As shown, in some embodiments, the power grid twin construction apparatus 400 includes: a generation unit 401, a skeleton decomposition unit 402, and an execution unit 403. The generation unit 401 is configured to generate a power grid twin skeleton based on the regional environmental parameters corresponding to the target area. The regional environmental parameters include regional spatial parameters and equipment layout parameters. The equipment layout parameters characterize the equipment layout of the power equipment located within the target area. The power grid twin skeleton consists of at least M skeleton anchor points and N skeleton veins. The skeleton decomposition unit 402 is configured to decompose the power grid twin skeleton based on the historical equipment parameters corresponding to the power equipment, obtaining at least one local power grid twin skeleton. The execution unit 403 is configured to perform the following processing steps for each of the at least one local power grid twin skeletons: in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generate a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton. The real-time equipment parameters include real-time equipment attribute parameters and real-time equipment operating parameters. Bind a status monitoring strategy to the local power grid twin.

[0103] It is understandable that the units described in the power grid twin construction device 400 are related to the reference Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the power grid twin construction device 400 and the units contained therein, and will not be repeated here.

[0104] The following is for reference. Figure 5 It illustrates a schematic diagram of the structure of an electronic device (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. Figure 5The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of this disclosure. Figure 5 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the methods described above. The processor provides computational and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the execution of the computer program in the non-volatile storage medium; when executed by the processor, the computer program causes the processor to perform any of the methods described above. The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0105] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0106] In one embodiment, the processor is configured to run a computer program stored in a memory to perform the following steps: generating a power grid twin skeleton based on regional environmental parameters corresponding to a target region, wherein the regional environmental parameters include regional spatial parameters and equipment layout parameters, the equipment layout parameters characterizing the equipment layout of power equipment located within the target region, and the power grid twin skeleton consisting of at least M skeleton anchor points and N skeleton veins; decomposing the power grid twin skeleton based on historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton; for each of the at least one local power grid twin skeletons, performing the following processing steps: in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generating a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton, wherein the real-time equipment parameters include real-time equipment attribute parameters and real-time equipment operating parameters; and binding a status monitoring strategy to the local power grid twin.

[0107] This disclosure also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to the various embodiments of the methods described above.

[0108] The aforementioned computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. Alternatively, the aforementioned computer-readable storage medium may be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0109] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0110] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for constructing a power grid twin, characterized in that, include: Based on the regional environmental parameters corresponding to the target area, a power grid twin skeleton is generated. The regional environmental parameters include regional spatial parameters and equipment layout parameters. The equipment layout parameters characterize the equipment layout of the power equipment set in the target area. The power grid twin skeleton consists of at least M skeleton anchor points and N skeleton veins. The equipment layout parameters include a set of equipment description information, which includes equipment type, equipment location information, and equipment connection information. Based on the historical equipment parameters corresponding to the power equipment, the power grid twin skeleton is decomposed to obtain at least one local power grid twin skeleton. The historical equipment parameters include: equipment attribute parameters and historical equipment operating parameters. The equipment attribute parameters represent the equipment specifications of the power equipment, and the historical equipment operating parameters represent the historical operating parameters of the power equipment. For each local power grid twin skeleton in the at least one local power grid twin skeleton, the following processing steps are performed: In response to the update of the power equipment parameters corresponding to the local power grid twin skeleton, a local power grid twin is generated based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton. The real-time equipment parameters include: real-time equipment attribute parameters and real-time equipment operating parameters. The local power grid twin is bound to a status monitoring strategy. The step of generating a local power grid twin in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton, includes: Parameter features are extracted from the real-time device parameters to generate device parameter features; The importance of the parameters is determined based on the characteristics of the equipment parameters; The parameter update frequency is determined based on the parameter importance and the pre-built parameter update decision tree; Based on the importance and update frequency of the real-time equipment parameters, the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton are synchronized with the local power grid twin skeleton to generate the local power grid twin. The step of generating a power grid twin skeleton based on the regional environmental parameters corresponding to the target area includes: The set of regional boundary feature points included in the regional spatial parameters and the equipment location information included in the equipment description information set are determined as the M skeleton anchor points included in the power grid twin skeleton; Based on the M skeleton anchor points and the device connection information included in the device description information set, the N skeleton veins comprising the power grid twin skeleton are determined. The step of decomposing the power grid twin skeleton based on the historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton includes: Based on the historical equipment parameters corresponding to the power equipment, the anchor importance of the corresponding skeleton anchor points in the power grid twin skeleton is determined, including: using minLSTM as the backbone network to extract features from the historical equipment operating parameters to generate operating labels corresponding to the historical equipment operating parameters; constructing a JSON-formatted descriptive text for the power equipment using the operating labels and equipment attribute parameters; extracting text features using the ALBERT model; and finally outputting the corresponding anchor importance through a multi-classifier. For each of the M skeleton anchor points that corresponds to an anchor point importance, perform the following skeleton decomposition steps: Centered on the skeleton anchor point, the influence area is determined according to the importance of the corresponding anchor point, including: using the anchor point importance as the area radius coefficient to determine the initial area radius, where the initial area radius = base area radius × area radius coefficient; and combining the initial area radius to obtain a circular area centered on the skeleton anchor point, which is the influence area. Based on the skeleton anchor points around the boundary of the affected area, the affected area is updated to obtain the updated affected area. This includes: calculating the distance between each skeleton anchor point in the set of M skeleton anchor points located outside the circular area and the boundary of the circular area; when the distance is less than a preset threshold, the skeleton anchor point is used as a candidate skeleton anchor point to obtain a set of candidate skeleton anchor points; and the closed area enclosed by the set of candidate skeleton anchor points is used as the updated affected area. Based on the updated skeleton anchor points and skeleton network within the affected area, a local power grid twin skeleton is generated.

2. The method according to claim 1, characterized in that, The method further includes: In response to successful binding, the local power grid twin is published to the target terminal, wherein the target terminal is an authorized terminal with twin control permissions; In response to the binding failure, a binding error message is sent to the target terminal.

3. The method according to claim 2, characterized in that, The regional environmental parameters are generated through the following steps: Obtain a regional remote sensing map of the target area and the equipment layout parameters corresponding to the power equipment set in the target area; Based on the regional roads within the remote sensing image of the region, the remote sensing image of the region is segmented to obtain a set of segmented regions; Based on the set of device description information, the segmented regions in the set of segmented regions are filtered to obtain a first set of segmented regions and a second set of segmented regions. The first segmented region is a segmented region obtained by image localization in which the device location of the power equipment contained in the region matches the device description information corresponding to the power equipment. The second segmented region is a segmented region obtained by image localization in which the device location of the power equipment contained in the region does not match the device description information corresponding to the power equipment. The regional spatial parameters are generated based on the first set of segmented regions and the second set of segmented regions.

4. The method according to claim 3, characterized in that, The step of generating the region spatial parameters based on the first segmented region set and the second segmented region set includes: Based on the second segmented region set, perform the following region precision processing steps: Select the second segmentation regions sequentially from the second segmentation region set as the target segmentation regions; Obtain a supplementary image of the target segmented region, wherein the image resolution of the supplementary image is greater than the image resolution of the remote sensing image of the region; Based on the supplementary image of the region, the region segmentation region is optimized for regional accuracy to obtain the optimized target segmentation region; Determine whether the location of the power equipment within the optimized target segmentation area matches the equipment description information corresponding to the power equipment; In response to the matching, the optimized target segmentation region is used as the first segmentation region and added to the first segmentation region set; The region precision processing step ends when the second set of segmented regions to be removed from the target segmented region is empty. In response to the fact that the second segmentation region set after removing the target segmentation region is not empty, the second segmentation region set after removing the target segmentation region is used as the second segmentation region set, and the region precision processing step is executed again. For each of the first segmented regions in the updated set of first segmented regions, extract the region boundary feature points to generate a set of region boundary feature points. The set of feature points representing the region boundary is determined as the spatial parameters of the region.

5. The method according to claim 4, characterized in that, The binding of the state monitoring strategy to the local power grid twin includes: From at least one device monitoring strategy, a device monitoring strategy that meets the screening criteria is selected as the target device monitoring strategy to obtain a set of target device monitoring strategies. The at least one device monitoring strategy is extracted by the target terminal from the device monitoring strategy pool. The screening criteria is that the device monitoring strategy can be triggered according to the device status of the power equipment corresponding to the local power grid twin skeleton. For each target device monitoring policy in the target device monitoring policy set, a policy certificate corresponding to the target device monitoring policy is generated. The policy certificate includes: authorization time, policy lifespan, policy identifier, policy authorization object identifier, and signature algorithm type. Based on the target device monitoring policy set and the policy certificate corresponding to the target device monitoring policy, a status monitoring policy is generated; The status monitoring strategy is distributed to the power equipment corresponding to the local power grid twin skeleton, and the status monitoring strategy and the local power grid twin are soft-bound simultaneously.

6. A device for constructing a power grid twin, characterized in that, include: The generation unit is configured to generate a power grid twin skeleton based on the regional environmental parameters corresponding to the target area. The regional environmental parameters include regional spatial parameters and equipment layout parameters. The equipment layout parameters characterize the equipment layout of the power equipment set in the target area. The power grid twin skeleton consists of at least M skeleton anchor points and N skeleton veins. The equipment layout parameters include a set of equipment description information, which includes equipment type, equipment location information, and equipment connection information. The skeleton decomposition unit is configured to decompose the power grid twin skeleton according to the historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton. The historical equipment parameters include: equipment attribute parameters and historical equipment operating parameters. The equipment attribute parameters represent the equipment specifications of the power equipment, and the historical equipment operating parameters represent the historical operating parameters of the power equipment. An execution unit is configured to perform the following processing steps for each local power grid twin skeleton in the at least one local power grid twin skeleton: in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, generate a local power grid twin based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton, wherein the real-time equipment parameters include: real-time equipment attribute parameters and real-time equipment operating parameters; and bind a status monitoring strategy to the local power grid twin. The step of generating a local power grid twin in response to an update of the power equipment parameters corresponding to the local power grid twin skeleton, based on the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton and the local power grid twin skeleton, includes: Parameter features are extracted from the real-time device parameters to generate device parameter features; The importance of the parameters is determined based on the characteristics of the equipment parameters; The parameter update frequency is determined based on the parameter importance and the pre-built parameter update decision tree; Based on the importance and update frequency of the real-time equipment parameters, the real-time equipment parameters of the power equipment corresponding to the local power grid twin skeleton are synchronized with the local power grid twin skeleton to generate the local power grid twin. The step of generating a power grid twin skeleton based on the regional environmental parameters corresponding to the target area includes: The set of regional boundary feature points included in the regional spatial parameters and the equipment location information included in the equipment description information set are determined as the M skeleton anchor points included in the power grid twin skeleton; Based on the M skeleton anchor points and the device connection information included in the device description information set, the N skeleton veins comprising the power grid twin skeleton are determined. The step of decomposing the power grid twin skeleton based on the historical equipment parameters corresponding to the power equipment to obtain at least one local power grid twin skeleton includes: Based on the historical equipment parameters corresponding to the power equipment, the anchor importance of the corresponding skeleton anchor points in the power grid twin skeleton is determined, including: using minLSTM as the backbone network to extract features from the historical equipment operating parameters to generate operating labels corresponding to the historical equipment operating parameters; constructing a JSON-formatted descriptive text for the power equipment using the operating labels and equipment attribute parameters; extracting text features using the ALBERT model; and finally outputting the corresponding anchor importance through a multi-classifier. For each of the M skeleton anchor points that corresponds to an anchor point importance, perform the following skeleton decomposition steps: Centered on the skeleton anchor point, the influence area is determined according to the importance of the corresponding anchor point, including: using the anchor point importance as the area radius coefficient to determine the initial area radius, where the initial area radius = base area radius × area radius coefficient; and combining the initial area radius to obtain a circular area centered on the skeleton anchor point, which is the influence area. Based on the skeleton anchor points around the boundary of the affected area, the affected area is updated to obtain the updated affected area. This includes: calculating the distance between each skeleton anchor point in the set of M skeleton anchor points located outside the circular area and the boundary of the circular area; when the distance is less than a preset threshold, the skeleton anchor point is used as a candidate skeleton anchor point to obtain a set of candidate skeleton anchor points; and the closed area enclosed by the set of candidate skeleton anchor points is used as the updated affected area. Based on the updated skeleton anchor points and skeleton network within the affected area, a local power grid twin skeleton is generated.

7. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

Images