Power transformation intelligent service model management method and system based on internet-of-things management platform

Abstract

The invention discloses a power transformation intelligent service model management method and system based on an internet-of-things management platform. The method comprises the steps that a first-stage transformer substation intelligent patrol system model is transmitted to a second stage based on first-stage artificial intelligence'two libraries and one platform '; issuing the transformer substation intelligent patrol system model to an Internet of Things management platform based on second-level artificial intelligence "two libraries and one platform"; the Internet of Things management platform provides an HTTP Restful interface service to push a message to the MQS; an SDK access specification is provided; and based on the MQS message, the third-stage transformer substation intelligent patrol system pulls a transformer substation intelligent patrol system model from the Internet of Things management platform, deploys the model in the third-stage transformer substation intelligent patrol system, and carries out local intelligent patrol task processing on the transformer substation. According to the method, data sharing and reference of three-level model data are realized, collaborative learning and common iterative updating of multi-level models are realized, the accuracy and real-time iterative updating of the models are improved, and constantly changing business requirements are met.

Description

Technical Field

[0001] The present invention relates to the technical field of substations, and in particular to a substation intelligent service model management method and system based on an Internet of Things management platform. Background Art

[0002] Under the severe situation of rapid growth in substation scale, increasingly complex external environment and relatively insufficient personnel, the large-scale application of intelligent substation inspection can greatly improve the efficiency and accuracy of inspection, reduce labor costs and risk management costs, and further improve the operating efficiency and operation and maintenance quality of power grid companies.

[0003] The current substation model has low accuracy, recall rate, precision and other indicators and low generalization ability, resulting in low model practicality and inability to meet the application needs of substation intelligent patrol scenarios. It is urgent to improve the model optimization system, implement regular iteration of the algorithm model, improve the accuracy of the substation algorithm model, and quickly improve the model's practicality. Summary of the invention

[0004] In view of the problems existing in the above-mentioned prior art, the present invention provides a substation intelligent service model management method and system based on the Internet of Things management platform. The technical solution is as follows: In a first aspect, a method for managing a substation intelligent service model based on an IoT management platform is provided, the method comprising the following steps: Based on the first-level artificial intelligence "two libraries and one platform", the first-level substation intelligent inspection system model is transmitted to the second level; Based on the second-level artificial intelligence "two databases and one platform", the substation intelligent inspection system model is sent to the IoT management platform through the HTTP Restful protocol; The IoT management platform provides HTTP Restful interface service to push messages to MQS and SDK access specifications. Based on MQS messages, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, deploys the model within the third-level substation intelligent patrol system, and performs local intelligent patrol task processing in the substation.

[0005] In some implementations, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform based on the MQS message, including: Obtain the parameters of the latest version of the substation intelligent patrol system model sent to the IoT management platform at the first level, including the multi-dimensional technical parameters, performance index parameters, and functional parameters of the model; Based on the comparison of the parameters of the substation intelligent patrol system model deployed inside the current third-level substation intelligent patrol system, it is determined whether it is necessary to pull the substation intelligent patrol system model to the Internet of Things management platform.

[0006] In some embodiments, after pulling the substation intelligent patrol system model from the Internet of Things management platform, the performance indicators of the current model are tested based on local sample data. If the performance indicators do not meet the standards, a message is sent to the second level, and the second level updates the substation intelligent patrol system model based on the collected third-level local sample data.

[0007] In some implementations, the second level updates the substation intelligent patrol system model based on the collected third level local sample data, including: The second-level artificial intelligence "two databases and one platform" collects the parameters of each third-level substation intelligent patrol system model, local sample data, and the performance index values ​​of the third-level substation intelligent patrol system model in the local sample data; Based on the third-level local sample data with similar performance index values ​​of the third-level substation intelligent patrol system model to the local sample data, or based on each third-level substation intelligent patrol system model and the local sample data, the local sample data is exchanged and input into the corresponding third-level substation intelligent patrol system model to determine the performance index values ​​of each third-level substation intelligent patrol system model after exchange; When the performance indicator value after the exchange is similar to the performance indicator value before the exchange, it is determined that the corresponding third-level local sample data features are similar; when the performance indicator value after the exchange is different from the performance indicator value before the exchange, it is determined that the corresponding third-level sample data features are not similar; Based on the network parameters of the third-level substation intelligent patrol system model with the best performance indicators among multiple third-level substation intelligent patrol system models with similar characteristic parameters of the third-level local sample data and the network parameters of the latest version of the substation intelligent patrol system model sent to the Internet of Things management platform from the first level, multiple third-level local sample data with similar characteristic parameters of the third-level local sample data are used as training samples to train and update the network parameters of the third-level model, and update the substation intelligent patrol system model pulled by the Internet of Things management platform.

[0008] In some embodiments, the method of using a plurality of third-level local sample data with similar characteristic parameters of the third-level local sample data as training samples includes: deleting duplicate items; Take a local sample data as a data set, perform correlation analysis on multiple sample sets, increase the information entropy of multiple sample sets by deleting related items, and re-acquire multiple sample data for training the model.

[0009] In some implementations, the power transformation intelligent service model management method based on the IoT management platform further includes the following steps: Based on the two-level artificial intelligence "two libraries and one platform", each second-level model data is uploaded to the first level to achieve unified management of high-quality model libraries; The first level updates its own model data based on the uploaded third-level model data and the first-level original model data; The first level updates its own model data based on the uploaded third level model data and the first level original model data, including: Based on the model data of each third level, test the performance of the first level sample data on each third level model; Count the first performance of the first-level sample data on each third-level model and the second performance of the first-level sample data on the first-level original model; Based on the comparison between the first performance and the second performance, determine whether to update the first-level original model data. When it is determined that the first-level original model data needs to be updated, the model data of the third-level model based on multiple first performances that meet the preset conditions is combined with the first-level original model data to update its own model data.

[0010] In some implementations, determining whether to update the first-level original model data based on a comparison between the first performance performance and the second performance performance includes: Obtain the generation time of each third-level model data uploaded to the first level at the third level; Respectively obtain the distance between the first performance performance and the second performance performance corresponding to each third-level model, wherein the performance is characterized based on multiple indicator dimensions, and the calculation of the distance includes obtaining weights for each dimension data in the performance based on preset requirements, obtaining optimized performance performance based on the weights, and calculating the distance based on the optimized performance performance; Based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data, it is determined whether to update the result of the first-level original model data.

[0011] In some implementations, the result of determining whether to update the first-level original model data based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data includes: Based on the difference vector of the feature vectors of the first performance expression and the second performance expression corresponding to each third-level model as the distance, based on the distance and the generation time of each third-level model data to form input data, input a preset analysis model, and obtain the result of whether to update the first-level original model data, specifically including: The first-level model is used as a central node, and each third-level model is used as a node connected to the central node to form a model performance graph; the node data includes the performance of the model and the generation time of the model data; based on the model performance graph, the data distribution of the distance corresponding to each third-level model is characterized; Acquire a node feature matrix and a node adjacency matrix based on the model performance graph, wherein the feature of each node in the node feature matrix is ​​determined based on the performance of the node model and the model data generation time; Based on the model performance graph, the preset graph neural network is input to obtain the result of whether the first-level original model data needs to be updated.

[0012] In some implementations, the result of determining whether to update the first-level original model data based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data includes: Obtaining the distance and model data generation time corresponding to each third-level model; Determine the influence of the model parameters of the third-level model on the result of whether to update the first-level original model data based on the generation time of the third-level model data, the longer the generation time of the third-level model is from the current time, the smaller the influence; Based on the influence of the model parameters of the third-level model on whether to update the first-level original model data, the distances corresponding to the third-level models are aggregated, and when the aggregation result is greater than a preset distance threshold, it is determined to update the first-level original model data.

[0013] In the second aspect, a substation intelligent service model management system based on the Internet of Things management platform is provided, the system comprising: The first-level management unit is used to transmit the first-level substation intelligent inspection system model to the second level based on the first-level artificial intelligence "two libraries and one platform"; The second-level management unit is used to send the substation intelligent inspection system model to the IoT management platform through the HTTP Restful protocol based on the second-level artificial intelligence "two libraries and one platform"; The transit management unit, the IoT management platform provides HTTP Restful interface service to push messages to MQS; and provides SDK access specifications; The third-level management unit, based on MQS messages, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, and deploys the model in the third-level substation intelligent patrol system to process the local intelligent patrol tasks of the substation.

[0014] The present invention provides a substation intelligent service model management method and system based on the Internet of Things management platform, which has the following beneficial effects: based on the two-level artificial intelligence "two libraries and one platform", the first-level model is sent to the second level, and the second level sends the model to the Internet of Things management platform, and the selected model data is pushed to the third-level substation intelligent patrol system to realize model synchronization, supporting the on-site analysis and application of the algorithm model on the station side; based on the two-level artificial intelligence "two libraries and one platform", the second-level model data is uploaded to the first level, and data sharing and reference of multiple third-level station-side model data and model data of three different levels are realized, and collaborative learning and common iterative update of multi-level models are realized, thereby improving the accuracy and real-time iterative update of the model to meet the ever-changing business needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a method for managing a substation intelligent service model based on an IoT management platform provided in an embodiment of the present application; Figure 2 It is a flowchart of a method for updating a substation intelligent patrol system model based on the collected third-level local sample data at the second level in an embodiment of the present application; Figure 3 It is a flowchart of the first-level self-model updating process in the embodiment of the present application; Figure 4 It is a structural diagram of a substation intelligent service model management system based on the Internet of Things management platform in an embodiment of the present application. DETAILED DESCRIPTION

[0016] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0017] See also Figure 1 The embodiment of the present application provides a substation intelligent service model management method based on the Internet of Things management platform, comprising the following steps: Step 1: Based on the first-level artificial intelligence "two libraries and one platform", the first-level substation intelligent inspection system model is transmitted to the second level; Step 2: Based on the second-level artificial intelligence "two databases and one platform", the substation intelligent inspection system model is sent to the IoT management platform through the HTTP Restful protocol; Step 3: The IoT management platform provides HTTP Restful interface service to push messages to MQS and provides SDK access specifications; Step 4: Based on the MQS message, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, deploys the model in the third-level substation intelligent patrol system, and performs local intelligent patrol task processing in the substation.

[0018] Specifically, in the embodiment of the present application, the first level is the headquarters artificial intelligence platform, which includes a "sample library", a "model library" and an "operation platform". The "sample library" contains sample data related to the substation intelligent patrol data uploaded by all second-level platforms within the jurisdiction, and the "model library" includes at least one relevant model for realizing the substation intelligent patrol function; The second level is the scope of management under the headquarters, and the third level is the scope of management under the second level. For example, the second level is the provincial artificial intelligence platform, which also includes the provincial sample library, model library, and operation platform. The "sample library" contains sample data related to the substation intelligent patrol data uploaded by all third-level system platforms within the jurisdiction, and the "model library" includes at least one relevant model for realizing the substation intelligent patrol function; The third level is the substation end, where the substation intelligent patrol system includes a patrol host and an intelligent analysis host. The patrol host is used to summarize and manage all collected substation patrol data, including video data, audio data, and text data, etc. The intelligent analysis host is used to analyze patrol results using at least one relevant model with substation intelligent patrol function. It can be understood that the third-level system platform in this application can also be other station-end system models, which are used to provide other business services at the station end.

[0019] In the embodiment of the present application, based on the two-level artificial intelligence "two libraries and one platform", the headquarters will send the model to the provincial side, and the provincial side will send the model to the Internet of Things management platform, and push the selected model data to the substation intelligent patrol system to achieve model synchronization, supporting the on-site analysis and application of the algorithm model on the station side; based on the two-level artificial intelligence "two libraries and one platform", each provincial company will upload the model data to the headquarters to realize the unified management of high-quality model libraries.

[0020] The provincial artificial intelligence "two libraries and one platform" provides the functions of adding, deleting, and modifying the information of each substation's intelligent patrol system to realize the management of substation information; supports sending the model to the corresponding substation, and transmits the model information to the substation intelligent patrol system according to the address of the managed substation; supports model sending status monitoring, and can view the model sending status. On the IoT management platform side, register application information and create a Topic (message subscription topic), and bind the application to the Topic. The provincial artificial intelligence "two libraries and one platform" sends the model name, model OSS address, model startup command, model unique identification ID and other information to the IoT management platform-MQS through HTTP Restful. After receiving the message, the IoT management platform will store the message in the Topic bound to the application and send the message to the substation intelligent patrol system.

[0021] The substation intelligent patrol system is accessed through the JAVA-based SDK provided by the IoT management platform, and monitors messages with the same topic as the artificial intelligence "two libraries and one platform" from the IoT management platform-MQS. When the substation intelligent patrol system receives a message from the IoT management platform, it can obtain the algorithm model information with the same structure sent by the artificial intelligence "two libraries and one platform" to the IoT management platform in the message content.

[0022] In one implementation, in the above step 4, based on the MQS message, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, including the following steps: Step 41, obtaining the parameters of the latest version of the substation intelligent patrol system model sent to the IoT management platform at the first level, wherein the parameters include multi-dimensional technical parameters, performance index parameters, and functional parameters of the model; Step 42, based on the comparison of the parameters of the substation intelligent patrol system model deployed inside the current third-level substation intelligent patrol system, determine whether it is necessary to pull the substation intelligent patrol system model from the Internet of Things management platform. It can be understood that when there are differences after parameter comparison or the difference items meet the preset update conditions, it is necessary to pull the substation intelligent patrol system model from the Internet of Things management platform to update its own model data.

[0023] In one embodiment, in the above step 4, after pulling the substation intelligent patrol system model from the IoT management platform, it also includes: Step 43, testing the performance index of the current model based on the local sample data, and sending a message to the second level if the performance index does not meet the standard, and the second level updates the substation intelligent patrol system model based on the collected third level local sample data.

[0024] See also Figure 2 In one embodiment, in the above step 43, the second level updates the substation intelligent patrol system model based on the collected third level local sample data, including: Step 431, the second-level artificial intelligence "two databases and one platform" collects the parameters of each third-level substation intelligent patrol system model, local sample data, and the performance index values ​​of the third-level substation intelligent patrol system model in the local sample data; Step 432, based on the third-level local sample data of the third-level substation intelligent patrol system model having similar performance index values ​​to the local sample data or based on each third-level substation intelligent patrol system model and the local sample data, the local sample data is exchanged and inputted into the corresponding third-level substation intelligent patrol system model, and the exchanged performance index values ​​of each third-level substation intelligent patrol system model are determined; Step 433, when the performance indicator value after the exchange is similar to the performance indicator value before the exchange, it is determined that the corresponding third-level local sample data features are similar; when the performance indicator value after the exchange is different from the performance indicator value before the exchange, it is determined that the corresponding third-level sample data features are not similar; Step 434, based on the network parameters of the third-level substation intelligent patrol system model with the best performance indicators among multiple third-level substation intelligent patrol system models with similar characteristic parameters of the third-level local sample data and the network parameters of the latest version of the substation intelligent patrol system model sent to the Internet of Things management platform by the first level as a reference, and using multiple third-level local sample data with similar characteristic parameters of the third-level local sample data as training samples, train and update the network parameters of the third-level model, and update the substation intelligent patrol system model pulled by the Internet of Things management platform.

[0025] In an embodiment of the present application, by interlacing sample sets and models, it is determined whether the features of each third-level local sample data are similar, and the same model is trained together based on each third-level local sample data with similar sample features to achieve model training for a class of sample features.

[0026] The above-mentioned third-level local sample data based on the performance index value of the third-level substation intelligent patrol system model in the local sample data is similar, or based on each third-level substation intelligent patrol system model and local sample data, the local sample data is exchanged and input into the corresponding third-level substation intelligent patrol system model to determine the exchanged performance index value of each third-level substation intelligent patrol system model. Specifically, the station-end models and station-end local samples of multiple station-ends whose performance on the local sample data of each station-end model at the current moment is similar can be exchanged. The exchange process is: non-local sample data, that is, sample data of multiple other station-ends, are input into the station-end model of this station end, and the performance of the sample data of other station ends in the model of this station end is analyzed. If the performance of the sample data of other station ends in the model of this station end is consistent with or similar to the performance of the local sample data of this station end in the model of this station end, it is determined that the data characteristics of the sample data of the other station ends are similar to the local sample data of this station end.

[0027] The above-mentioned third-level local sample data based on the performance index value of the local sample data of the third-level substation intelligent patrol system model is similar to that of the local sample data, or based on each third-level substation intelligent patrol system model and the local sample data, the local sample data is exchanged and input into the corresponding third-level substation intelligent patrol system model to determine the exchanged performance index value of each third-level substation intelligent patrol system model. Specifically, the station-side models and station-side local samples of all station ends can be directly exchanged. The exchange process is: non-local sample data, that is, sample data of multiple other station ends, are input into the station-side model of this station end, and the performance of the sample data of other station ends in the station-side model is analyzed. If the performance of the sample data of other station ends in the station-side model is consistent with or similar to the performance of the local sample data of this station end in the station-side model, it is determined that the data characteristics of the sample data of the other station ends are similar to the local sample data of this station end.

[0028] In one embodiment, the above step 434, using a plurality of third-level local sample data with similar third-level local sample data characteristic parameters as training samples, includes: Step 4341, delete duplicates; Step 4342, using a local sample data as a data set, performing correlation analysis on multiple sample sets, increasing the information entropy of multiple sample sets by deleting related items, and reacquiring multiple sample data for training the model. The correlation analysis on multiple sample sets can be implemented using principal component analysis, Pearson correlation method, and other methods.

[0029] In one implementation, the substation intelligent service model management method based on the IoT management platform of the embodiment of the present application further includes: Step 5: Based on the two-level artificial intelligence "two libraries and one platform", upload each second-level model data to the first level to achieve unified management of high-quality model libraries; Step 6: The first level updates its own model data based on the uploaded third-level model data and the first-level original model data; See also Figure 3 The first level updates its own model data based on the uploaded third-level model data and the first-level original model data, including: Step 61, based on each third-level model data, testing the performance of the first-level sample data on each third-level model; Step 62, counting the first performance of the first-level sample data on each third-level model and the second performance of the first-level sample data on the first-level original model; Step 63, based on the comparison between the first performance and the second performance, determine whether to update the first-level original model data. When it is determined that the first-level original model data needs to be updated, the model data of the third-level model based on multiple first performances that meet the preset conditions is combined with the first-level original model data to update its own model data.

[0030] In the embodiment of the present application, the headquarters system platform collects and manages all the station-side model data and sample data collected by the station-side, and forms high-quality models and samples on the headquarters system platform. The headquarters system platform checks the update status of its own model in real time based on the continuously updated station-side model data, so as to realize the model data sharing and joint learning and updating of the headquarters system platform model and the station-side model, and continuously improve the intelligent service effect.

[0031] In one embodiment, in the above step 63, determining whether to update the first-level original model data based on the comparison between the first performance performance and the second performance performance includes: Step 631, obtaining the generation time of each third-level model data uploaded to the first level at the third level; Step 632, respectively obtaining the distance between the first performance and the second performance corresponding to each third-level model, wherein the performance is represented based on multiple indicator dimensions, and the calculation of the distance includes obtaining weights for each dimension data in the performance based on preset requirements, obtaining optimized performance based on the weights, and calculating the distance based on the optimized performance; Step 633: Determine whether to update the result of the first-level original model data based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data.

[0032] In the embodiment of the present application, based on the gap between the performance of each third-level model on the first-level sample data and the performance of the first-level model and the generation time of each third-level model data, it is determined whether to update the first-level original model data. It can be understood that the greater the gap between the performance of each third-level model on the first-level sample data and the performance of the first-level model, the greater the probability that the first-level original model data needs to be updated. If the generation time of the third-level model data is far away from the current time, the third-level model is less important for the decision of whether to update the first-level model. In addition, in the present application, different weight coefficients can also be set for different indicator dimensions of the performance of the model. For example, in some scenarios, it is necessary to focus more on the accuracy of model prediction, and in some scenarios, it is necessary to focus more on the speed of prediction results.

[0033] In one implementation, in step 633, determining whether to update the result of the first-level original model data based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data includes: Based on the difference vector of the feature vectors of the first performance expression and the second performance expression corresponding to each third-level model as the distance, based on the distance and the generation time of each third-level model data to form input data, input a preset analysis model, and obtain the result of whether to update the first-level original model data, specifically including: Step 63301, taking the first-level model as the central node and each third-level model as a node connected to the central node, a model performance graph is formed; the node data includes the performance of the model and the generation time of the model data; based on the model performance graph, the data distribution of the distance corresponding to each third-level model is characterized; Step 63302, obtaining a node feature matrix and a node adjacency matrix based on the model performance graph, wherein the feature of each node in the node feature matrix is ​​determined based on the performance of the node model and the model data generation time; Step 63303, based on the model performance graph input into the preset graph neural network, obtain the result of whether the first-level original model data needs to be updated.

[0034] The graph convolutional network (GCN) takes the node feature matrix H and the adjacency matrix A as input, and outputs high-dimensional node feature representation after multiple layers of convolution. Its inter-layer propagation can be expressed as: ; In the formula, f() represents the nonlinear mapping function, L is the number of hidden layers, Indicates The node feature matrix of the hidden layer output. =0, then =X, where X represents the input node feature matrix. ,in, is the adjacency matrix after adding self-connection, is the adjacency matrix The degree matrix of For each graph convolution layer, the process is to convert the adjacency matrix A and the node feature matrix After multiplication, the trainable parameter matrix Perform linear transformation, that is, inter-layer propagation can be written as: , () represents the activation function.

[0035] In an embodiment of the present application, a neural network is used to mine the data distribution of the distance corresponding to each third-level model and the relationship between the generation time of the model data and whether to update the first-level original model data. The first-level model is used as the central node, and each third-level model is used as a node connected to the central node to form a model performance graph. The node characteristics of each node on the model performance graph include the performance data of the first-level model and each third-level model, and the corresponding model data generation time, and include the difference vector information of the feature vectors of the first performance performance and the second performance performance corresponding to each third-level model, that is, the distance information. The model performance graph containing the distance information of the first performance performance and the second performance performance corresponding to each third-level model and the model data generation time data is used with a graph neural network. After node update, the hidden spatiotemporal characteristics of the input data are fully mined to obtain the decision result of whether to update the first-level original model data.

[0036] In one implementation, in step 633, determining whether to update the result of the first-level original model data based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data includes: Step 63311, obtaining the distance and model data generation time corresponding to each third-level model; Determine the influence of the model parameters of the third-level model on the result of whether to update the first-level original model data based on the generation time of the third-level model data, the longer the generation time of the third-level model is from the current time, the smaller the influence; Step 63312, based on the influence of the model parameters of the third-level model on the result of whether to update the first-level original model data, the distances corresponding to the respective third-level models are aggregated, and when the aggregation result is greater than a preset distance threshold, it is determined to update the first-level original model data.

[0037] In an embodiment of the present application, the influence of the model parameters of the third-level model on the result of whether to update the first-level original model data is determined based on the generation time of the third-level model data, and the distances corresponding to each third-level model are aggregated based on the influence. When the aggregated distance is larger, it indicates that the model parameters of each station end are more different from the first-level original model data, and the first-level original model data needs to be updated.

[0038] See also Figure 4 Based on the above method embodiment, the embodiment of the present application provides a substation intelligent service model management system based on the Internet of Things management platform, including: The first-level management unit is used to transmit the first-level substation intelligent inspection system model to the second level based on the first-level artificial intelligence "two libraries and one platform"; The second-level management unit is used to send the substation intelligent inspection system model to the IoT management platform through the HTTP Restful protocol based on the second-level artificial intelligence "two libraries and one platform"; The transit management unit, the IoT management platform provides HTTP Restful interface service to push messages to MQS; and provides SDK access specifications; The third-level management unit, based on MQS messages, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, and deploys the model in the third-level substation intelligent patrol system to process the local intelligent patrol tasks of the substation.

[0039] It should be noted that: the substation intelligent service model management system based on the Internet of Things management platform provided in this embodiment only uses the division of the above-mentioned functional units as an example when performing substation intelligent service model management. In actual applications, the above-mentioned functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. In addition, the substation intelligent service model management system based on the Internet of Things management platform provided in this embodiment and the substation intelligent service model management method embodiment based on the Internet of Things management platform provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0040] The present invention is not limited to the above-mentioned specific implementation modes. Various changes made by ordinary technicians in this field based on the above-mentioned concepts without creative work are all within the protection scope of the present invention.

Claims

1. A method for managing a substation intelligent service model based on an IoT management platform, characterized in that: The steps include: Based on the first-level artificial intelligence "two databases and one platform", the first-level substation intelligent inspection system model is transmitted to the second level; Based on the second-level artificial intelligence "two databases and one platform", the substation intelligent inspection system model is sent to the IoT management platform through the HTTP Restful protocol; The IoT management platform provides HTTP Restful interface service to push messages to MQS; And provide SDK access specifications; Based on MQS messages, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, deploys the model within the third-level substation intelligent patrol system, and performs local intelligent patrol task processing in the substation.

2. The method for managing a substation intelligent service model based on an IoT management platform according to claim 1 is characterized in that: Based on the MQS message, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, including: Obtain the parameters of the latest version of the substation intelligent patrol system model sent to the IoT management platform at the first level, including the multi-dimensional technical parameters, performance index parameters, and functional parameters of the model; Based on the comparison of the parameters of the substation intelligent patrol system model deployed inside the current third-level substation intelligent patrol system, it is determined whether it is necessary to pull the substation intelligent patrol system model to the Internet of Things management platform.

3. The method for managing a substation intelligent service model based on an IoT management platform according to claim 1 or 2, characterized in that: After pulling the substation intelligent patrol system model from the IoT management platform, the performance indicators of the current model are tested based on local sample data. If the performance indicators do not meet the standards, a message is sent to the second level. The second level updates the substation intelligent patrol system model based on the collected local sample data of the third level.

4. The method for managing a substation intelligent service model based on an IoT management platform according to claim 3 is characterized in that: The second level updates the substation intelligent patrol system model based on the collected third level local sample data, including: The second-level artificial intelligence "two databases and one platform" collects the parameters of each third-level substation intelligent patrol system model, local sample data, and the performance index values ​​of the third-level substation intelligent patrol system model in the local sample data; Based on the third-level local sample data with similar performance index values ​​of the third-level substation intelligent patrol system model to the local sample data, or based on each third-level substation intelligent patrol system model and the local sample data, the local sample data is exchanged and input into the corresponding third-level substation intelligent patrol system model to determine the performance index values ​​of each third-level substation intelligent patrol system model after exchange; When the performance indicator value after the exchange is similar to the performance indicator value before the exchange, it is determined that the corresponding third-level local sample data features are similar; when the performance indicator value after the exchange is different from the performance indicator value before the exchange, it is determined that the corresponding third-level sample data features are not similar; Based on the network parameters of the third-level substation intelligent patrol system model with the best performance indicators among multiple third-level substation intelligent patrol system models with similar characteristic parameters of the third-level local sample data and the network parameters of the latest version of the substation intelligent patrol system model sent to the Internet of Things management platform from the first level, multiple third-level local sample data with similar characteristic parameters of the third-level local sample data are used as training samples to train and update the network parameters of the third-level model, and update the substation intelligent patrol system model pulled by the Internet of Things management platform.

5. The method for managing a substation intelligent service model based on an IoT management platform according to claim 4 is characterized in that: The method of using a plurality of third-level local sample data with similar third-level local sample data characteristic parameters as training samples includes: Remove duplicates; Take a local sample data as a data set, perform correlation analysis on multiple sample sets, increase the information entropy of multiple sample sets by deleting related items, and re-acquire multiple sample data for training the model.

6. The method for managing a substation intelligent service model based on an IoT management platform according to claim 1, characterized in that: The method further comprises: Based on the two-level artificial intelligence "two libraries and one platform", each second-level model data is uploaded to the first level to achieve unified management of high-quality model libraries; The first level updates its own model data based on the uploaded third-level model data and the first-level original model data; The first level updates its own model data based on the uploaded third level model data and the first level original model data, including: Based on the model data of each third level, test the performance of the first level sample data on each third level model; Count the first performance of the first-level sample data on each third-level model and the second performance of the first-level sample data on the first-level original model; Based on the comparison between the first performance and the second performance, determine whether to update the first-level original model data. When it is determined that the first-level original model data needs to be updated, the model data of the third-level model based on multiple first performances that meet the preset conditions is combined with the first-level original model data to update its own model data.

7. The method for managing a substation intelligent service model based on an IoT management platform according to claim 6 is characterized in that: The determining whether to update the first-level original model data based on the comparison between the first performance performance and the second performance performance includes: Obtain the generation time of each third-level model data uploaded to the first level at the third level; Respectively obtain the distance between the first performance performance and the second performance performance corresponding to each third-level model, wherein the performance is characterized based on multiple indicator dimensions, and the calculation of the distance includes obtaining weights for each dimension data in the performance based on preset requirements, obtaining optimized performance performance based on the weights, and calculating the distance based on the optimized performance performance; Based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data, it is determined whether to update the result of the first-level original model data.

8. The method for managing a substation intelligent service model based on an IoT management platform according to claim 7 is characterized in that: The result of determining whether to update the first-level original model data based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data includes: Based on the difference vector of the feature vectors of the first performance expression and the second performance expression corresponding to each third-level model as the distance, based on the distance and the generation time of each third-level model data to form input data, input a preset analysis model, and obtain the result of whether to update the first-level original model data, specifically including: The first-level model is used as a central node, and each third-level model is used as a node connected to the central node to form a model performance graph; the node data includes the performance of the model and the generation time of the model data; based on the model performance graph, the data distribution of the distance corresponding to each third-level model is characterized; Acquire a node feature matrix and a node adjacency matrix based on the model performance graph, wherein the feature of each node in the node feature matrix is ​​determined based on the performance of the node model and the model data generation time; Based on the model performance graph, the preset graph neural network is input to obtain the result of whether the first-level original model data needs to be updated.

9. The method for managing a substation intelligent service model based on an IoT management platform according to claim 7, characterized in that: The result of determining whether to update the first-level original model data based on the data distribution of the distances corresponding to each third-level model and the generation time of the model data includes: Obtaining the distance and model data generation time corresponding to each third-level model; Determine the influence of the model parameters of the third-level model on the result of whether to update the first-level original model data based on the generation time of the third-level model data, the longer the generation time of the third-level model is from the current time, the smaller the influence; Based on the influence of the model parameters of the third-level model on whether to update the first-level original model data, the distances corresponding to the third-level models are aggregated, and when the aggregation result is greater than a preset distance threshold, it is determined to update the first-level original model data.

10. A substation intelligent service model management system based on the Internet of Things management platform, characterized in that: include: The first-level management unit is used to transmit the first-level substation intelligent inspection system model to the second level based on the first-level artificial intelligence "two libraries and one platform"; The second-level management unit is used to send the substation intelligent patrol system model to the IoT management platform through the HTTP Restful protocol based on the second-level artificial intelligence "two libraries and one platform"; The transit management unit, the IoT management platform provides HTTP Restful interface service to push messages to MQS; And provide SDK access specifications; The third-level management unit, based on MQS messages, the third-level substation intelligent patrol system pulls the substation intelligent patrol system model from the IoT management platform, and deploys the model in the third-level substation intelligent patrol system to process the local intelligent patrol tasks of the substation.

Images