Distribution line intelligent monitoring system and method based on Internet of Things
Through the intelligent monitoring system based on the Internet of Things, the coordinated work of data acquisition equipment and computing processing terminals is solved, and the processing speed reduction caused by large data volume or complex computing tasks in the existing technology is realized, real-time monitoring of distribution lines and Fault warning improves the reliability and stability of power supply.
Patent Information
- Application Number
- CN202411137730.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-12
AI Technical Summary
When the data volume is large or the calculation tasks are complex, the processing speed of existing distribution line monitoring systems will decrease, which will not meet the requirements of real-time monitoring and rapid response, resulting in delays in fault prediction and positioning time, which may lead to the expansion of faults or greater losses.
Adopt an intelligent monitoring system based on the Internet of Things, through the collaboration between data acquisition equipment and application servers and computing processing terminals, intelligent scheduling and resource optimization of data processing tasks are realized, ensuring that emergency tasks are given priority, and pre-stored fault detection and location and predictive models to perform efficient data processing.
Real-time monitoring and fault warning of distribution lines is realized, the reliability and stability of power supply is improved, the efficiency and accuracy of fault handling is ensured, the possibility of fault occurrence is reduced, and the distribution of different scales and complexities is adapted to Grid demand.
Smart Images

Figure CN118944303A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power distribution line monitoring, and in particular to an intelligent power distribution line monitoring system and method based on the Internet of Things. Background Art
[0002] In the power system, the failure of distribution lines is a complex and changeable problem. In addition to the common single-phase line break fault, which usually causes zero-sequence current abnormality and triggers the action of protection devices, there is another more significant and common fault type, which is the overcurrent quick-break trip. The occurrence of this kind of fault is often accompanied by serious consequences, such as equipment damage, power supply interruption, etc., which poses a serious threat to the stability and reliability of the power system.
[0003] The current intelligent monitoring methods of distribution networks generally rely on centralized computing and processing to predict or locate faults through model training. Although this method has played an important role in improving the efficiency and accuracy of fault handling, the centralized processing method also has a series of problems, which are gradually emerging in practical applications.
[0004] The centralized computing method places extremely high demands on the data transmission network. With the development of smart grids, the scale of distribution networks continues to expand, and the amount of data that needs to be transmitted has also increased dramatically. If the bandwidth of the data transmission network is insufficient or the stability is poor, it will lead to data transmission delays, losses or errors, which will affect the accuracy of model training and the effectiveness of fault prediction. This will not only weaken the performance of the system, but may also pose a potential threat to the stable operation of the power system. In the centralized computing mode, the central server needs to process massive data from various distribution network nodes and perform complex model training and calculations. If the amount of data is too large or the computing task is too complex, the processing speed will decrease and cannot meet the requirements of real-time monitoring and rapid response. This will increase the time delay of fault prediction and location, which may lead to the expansion of faults or cause greater losses. Summary of the invention
[0005] In order to solve the problem that in the existing processing method, if the data volume is too large or the calculation task is too complicated, the processing speed will be reduced and the requirements of real-time monitoring and rapid response cannot be met, the present invention provides a distribution line intelligent monitoring system and method based on the Internet of Things.
[0006] In a first aspect, the technical solution of the present invention provides an intelligent monitoring system for power distribution lines based on the Internet of Things, including a data acquisition device, the data acquisition device is connected to an application server, and the application server is connected to a plurality of computing and processing terminals; The data acquisition device includes a data collector and a data acquisition terminal in the distribution line connected to the data collector for collecting the running status of the distribution line; the data collector obtains the collected data of the data acquisition terminal and transmits the obtained data to the application server; The collected data include system operation status data and line equipment data, including overhead wires, lightning arresters, pole switches, etc.; The application server generates data processing tasks according to the configuration information set by the user, creates and maintains a task queue, wherein the configuration information includes several processing judgments for distribution network status fault detection and positioning based on the collected data; the task queue includes several data processing tasks sorted according to the set conditions; the data processing task includes a task ID and a task type; the data to be processed corresponding to the task ID is stored in the database of the application server; the application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; and sends the task and task data to the target computing and processing terminal, receives the calculation results returned by the target computing and processing terminal, and sends the calculation results and the corresponding collected data to the storage server; After receiving the issued task and the corresponding task data, the computing and processing terminal processes the data based on the task type and returns the processing result to the application server.
[0007] As a preferred embodiment of the technical solution of the present invention, the application server remotely accesses the Linux system of the data collector through the TELNET protocol, so that the data collector and the data acquisition terminal obtain the data of the data acquisition terminal through command operations and then send the data to the application server after analysis.
[0008] As a preferred embodiment of the technical solution of the present invention, the application server obtains information on pending tasks, the task information including task type, expected deadline and resource requirements to generate a task queue; sorts the tasks by urgency according to the expected deadline and resource requirements to obtain a sorted task queue; based on the sorted task queue, calculates the computing processing terminal corresponding to the task requirements and sends down the tasks and task data.
[0009] As a preferred embodiment of the technical solution of the present invention, the computing and processing terminal pre-stores a trained fault detection and location model and a fault prediction model; The fault detection and location model and the fault prediction model are associated with the corresponding task ID and task type respectively; After the computing and processing terminal obtains the task and corresponding task data sent by the application server, it preprocesses the task data, matches the pre-stored fault detection and positioning model and fault prediction model according to the task ID and task type, inputs the preprocessed data into the matched model, and returns the output result to the application server.
[0010] The application server generates a task queue based on the type of tasks to be processed, the expected deadline, and resource requirements, and sorts them according to a certain priority. This intelligent task scheduling method ensures that urgent tasks with high resource requirements are processed first, thereby improving the efficiency and accuracy of fault handling. The computing and processing terminal pre-stores the trained fault detection and location model and fault prediction model. When receiving a task issued by the application server, the computing and processing terminal can quickly match the corresponding model according to the task ID and task type, and perform efficient data processing. This processing method not only improves the efficiency of data processing, but also ensures the accuracy of the processing results. Through the fault prediction model, the system can predict potential risks before a fault occurs and take corresponding preventive measures in advance. This can not only reduce the possibility of a fault, but also reduce the impact of the fault on the power system and improve the reliability and stability of power supply.
[0011] As a preferred embodiment of the technical solution of the present invention, the application server communicates with the computing processing terminal to obtain the attribute information of each computing processing terminal and caches it locally; the attribute information includes the computing resource configuration of the computing processing terminal and the task ID corresponding to the pre-stored model; The application server obtains the task ID, task type, and resource requirements; according to the task type, it queries all computing processing terminals that pre-store the model corresponding to the task type from the local cache and generates a computing processing terminal set and corresponding computing resource configuration; it traverses the computing processing terminals in the access set, determines whether the current resource value of the computing processing terminal meets the resources required for the task, sets the computing processing terminal whose resources meet the resource requirements of the processing task as a candidate node and generates a candidate node list; Calculate the estimated completion time of each computing processing terminal in the list of all candidate nodes and sort them according to the time size, select the computing processing terminal with the smallest estimated completion time as the target computing processing terminal and send the task and the corresponding task data to the target computing processing terminal.
[0012] As a preferred embodiment of the technical solution of the present invention, when the application server cannot find a computing processing terminal that pre-stores a model corresponding to the task type from the local cache according to the task type, the application server sends a model creation instruction to the computing processing terminal, and when the application server receives a response message from the computing processing terminal based on the creation instruction within a set time, the computing processing terminal that sends the response message within the set time is defined as a first-class computing processing terminal; and the historical data corresponding to the creation model is sent to the first-class computing processing terminal; The first type of computing and processing terminal performs training and optimization of the neural network model based on the acquired historical data to obtain a trained fault detection and location model or a fault prediction model; inputs the preprocessed data into the trained model, and returns the output result to the application server.
[0013] As a preferred embodiment of the technical solution of the present invention, before issuing a task, the application server issues a task notification to the computing and processing terminal; the notification includes the task ID and the estimated execution time of the task; after the computing and processing terminal receives the task notification, it reserves a position for the task in the task waiting queue according to the estimated execution time of the task and updates the waiting time of the task waiting queue.
[0014] As a preferred embodiment of the technical solution of the present invention, after receiving the task, the computing processing terminal determines whether there is a reserved position for the task in the task waiting queue. If so, the task is inserted into the reserved position; otherwise, the task is placed at the end of the task waiting queue waiting for execution.
[0015] In a second aspect, the technical solution of the present invention also provides a distribution line intelligent monitoring method based on the Internet of Things, comprising the following steps: The data collector acquires the collected data from the data collection terminal and transmits the acquired data to the application server; The application server generates data processing tasks according to the configuration information set by the user, creates and maintains a task queue, and the data processing tasks include a task ID and a task type; and saves the to-be-processed data corresponding to the task ID in the database of the application server; the configuration information includes a number of processing judgments for distribution network status fault detection and positioning based on the collected data; the task queue includes a number of data processing tasks sorted according to the set conditions; The application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; and sends the task and task data to the target computing and processing terminal; After the computing and processing terminal obtains the task and corresponding task data sent by the application server, it pre-processes the task data, matches the pre-stored fault detection and location model and fault prediction model according to the task ID and task type, inputs the pre-processed data into the matched model, and returns the output result to the application server; Receive the calculation results returned by the target calculation processing terminal, and send the calculation results and corresponding collected data to the storage server.
[0016] As a preferred embodiment of the technical solution of the present invention, the application server remotely accesses the Linux system of the data collector through the TELNET protocol, so that the data collector and the data acquisition terminal obtain the data of the data acquisition terminal through command operations and then send the data to the application server after analysis.
[0017] As a preferred embodiment of the technical solution of the present invention, the application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; and sends the task and task data to the target computing and processing terminal. The steps include: The application server obtains information about pending tasks, including task type, expected deadline, and resource requirements to generate a task queue; sorts tasks by urgency according to expected deadline and resource requirements to obtain a sorted task queue; based on the sorted task queue, calculates the computing processing terminal corresponding to the task requirements and sends tasks and task data.
[0018] As a preferred embodiment of the technical solution of the present invention, the method further comprises: the application server communicates with the computing processing terminal to obtain attribute information of each computing processing terminal and caches it locally; the attribute information includes computing resource configuration of the computing processing terminal and task ID corresponding to the pre-stored model; The application server obtains the task ID, task type, and resource requirements; according to the task type, it queries all computing processing terminals that pre-store the model corresponding to the task type from the local cache and generates a computing processing terminal set and corresponding computing resource configuration; it traverses the computing processing terminals in the access set, determines whether the current resource value of the computing processing terminal meets the resources required for the task, sets the computing processing terminal whose resources meet the resource requirements of the processing task as a candidate node and generates a candidate node list; Calculate the estimated completion time of each computing processing terminal in the list of all candidate nodes and sort them according to the time size, select the computing processing terminal with the smallest estimated completion time as the target computing processing terminal and send the task and the corresponding task data to the target computing processing terminal.
[0019] As a preferred embodiment of the technical solution of the present invention, the method further includes: when the application server cannot find a computing processing terminal that pre-stores a model corresponding to the task type from the local cache according to the task type, issuing a model creation instruction to the computing processing terminal, and when receiving a response message based on the creation instruction from the computing processing terminal within a set time, defining the computing processing terminal that sends the response message within the set time as a first-class computing processing terminal; and sending the historical data corresponding to the creation model to the first-class computing processing terminal; The first type of computing and processing terminal performs training and optimization of the neural network model based on the acquired historical data to obtain a trained fault detection and location model or a fault prediction model; inputs the preprocessed data into the trained model, and returns the output result to the application server.
[0020] As a preferred embodiment of the technical solution of the present invention, the method also includes: before issuing the task, the application server issues a task notification to the computing and processing terminal; the notification includes the task ID and the estimated execution time of the task; after the computing and processing terminal receives the task notification, it reserves a position for the task in the task waiting queue according to the estimated execution time of the task and updates the waiting time of the task waiting queue.
[0021] As a preferred embodiment of the technical solution of the present invention, the method also includes: after the computing processing terminal receives the task, it determines whether there is a reserved position for the task in the task waiting queue. If so, the task is inserted into the reserved position; otherwise, the task is placed at the end of the task waiting queue waiting for execution.
[0022] It can be seen from the above technical solutions that the present invention has the following advantages: the system can collect the operating data of the distribution line in real time, and through the collaborative processing of the application server and the computing and processing terminal, it can realize real-time monitoring of the distribution network status and fault warning, thereby improving the reliability and stability of power supply. The application server intelligently assigns tasks to appropriate computing and processing terminals according to the status of the computing and processing terminals and the characteristics of the data processing tasks, thereby realizing the rational use of resources and efficient execution of tasks. The system can accurately locate the fault point by configuring the processing judgment of the distribution network status fault detection and positioning based on the collected data through configuration information settings, and provides strong support for fault handling. After receiving the task, the computing and processing terminal can perform efficient data processing based on the task type, and return the processing results to the application server, thereby improving the efficiency and accuracy of data processing.
[0023] The system has good scalability and can increase the number of data acquisition devices and computing terminals according to actual needs, while supporting user-defined configuration information and processing logic. This allows the system to adapt to distribution networks of different sizes and complexities and meet different monitoring needs.
[0024] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0026] Figure 1 is a schematic block diagram of a system according to an embodiment of the present invention.
[0027] Figure 2 is a schematic flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION
[0028] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0029] like Figure 1 As shown, an embodiment of the present invention provides an intelligent monitoring system for power distribution lines based on the Internet of Things, including a data acquisition device, the data acquisition device is connected to an application server, and the application server is connected to a plurality of computing and processing terminals; The data acquisition device includes a data collector and a data acquisition terminal in the distribution line connected to the data collector for collecting the running status of the distribution line; the data collector obtains the collected data of the data acquisition terminal and transmits the obtained data to the application server; The collected data include system operation status data and line equipment data, including overhead wires, lightning arresters, pole switches, etc.; The application server generates data processing tasks according to the configuration information set by the user, creates and maintains a task queue, wherein the configuration information includes several processing judgments for distribution network status fault detection and positioning based on the collected data; the task queue includes several data processing tasks sorted according to the set conditions; the data processing task includes a task ID and a task type; the data to be processed corresponding to the task ID is stored in the database of the application server; the application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; and sends the task and task data to the target computing and processing terminal, receives the calculation results returned by the target computing and processing terminal, and sends the calculation results and the corresponding collected data to the storage server; After receiving the issued task and the corresponding task data, the computing and processing terminal processes the data based on the task type and returns the processing result to the application server.
[0030] In the embodiment of the present invention, the application server remotely accesses the Linux system of the data collector through the TELNET protocol, so that the data collector and the data collection terminal obtain the data of the data collection terminal through command operation and then send it to the application server after analysis.
[0031] In some embodiments, an application server obtains information about pending tasks, where the task information includes task type, expected deadline, and resource requirements to generate a task queue; the tasks are sorted by urgency according to the expected deadline and resource requirements to obtain a sorted task queue; based on the sorted task queue, a computing processing terminal corresponding to the task requirements is calculated and tasks and task data are issued.
[0032] In some embodiments, the computing and processing terminal pre-stores a trained fault detection and location model and a fault prediction model; The fault detection and location model and the fault prediction model are associated with the corresponding task ID and task type respectively; After the computing and processing terminal obtains the task and corresponding task data sent by the application server, it preprocesses the task data, matches the pre-stored fault detection and positioning model and fault prediction model according to the task ID and task type, inputs the preprocessed data into the matched model, and returns the output result to the application server.
[0033] It should be noted that the models pre-stored in the computing and processing terminal or that need to be created are all models trained using existing technologies.
[0034] The application server generates a task queue based on the type of tasks to be processed, the expected deadline, and resource requirements, and sorts them according to a certain priority. This intelligent task scheduling method ensures that urgent tasks with high resource requirements are processed first, thereby improving the efficiency and accuracy of fault handling. The computing and processing terminal pre-stores the trained fault detection and location model and fault prediction model. When receiving a task issued by the application server, the computing and processing terminal can quickly match the corresponding model according to the task ID and task type, and perform efficient data processing. This processing method not only improves the efficiency of data processing, but also ensures the accuracy of the processing results. Through the fault prediction model, the system can predict potential risks before a fault occurs and take corresponding preventive measures in advance. This can not only reduce the possibility of a fault, but also reduce the impact of the fault on the power system and improve the reliability and stability of power supply.
[0035] In some embodiments, the application server communicates with the computing processing terminal to obtain attribute information of each computing processing terminal and caches it locally; the attribute information includes computing resource configuration of the computing processing terminal and a task ID corresponding to a pre-stored model; The application server obtains the task ID, task type, and resource requirements; according to the task type, it queries all computing processing terminals that pre-store the model corresponding to the task type from the local cache and generates a computing processing terminal set and corresponding computing resource configuration; it traverses the computing processing terminals in the access set, determines whether the current resource value of the computing processing terminal meets the resources required for the task, sets the computing processing terminal whose resources meet the resource requirements of the processing task as a candidate node and generates a candidate node list; Calculate the estimated completion time of each computing processing terminal in the list of all candidate nodes and sort them according to the time size, select the computing processing terminal with the smallest estimated completion time as the target computing processing terminal and send the task and the corresponding task data to the target computing processing terminal.
[0036] In the embodiment of the present invention, when calculating the estimated completion time of each computing and processing terminal in the list of all candidate nodes to execute a task, the estimated completion time Ti of executing task i is composed of the time Si when the application processor obtains the state of the computing and processing terminal, the delay Pi of sending the task to the computing and processing terminal, the waiting delay Wi of the task in the task waiting queue of the computing and processing terminal, the specific task execution time Ki of the computing and processing terminal to execute the task, and the transmission delay Fi of returning the task execution result to the application server, that is: Ti=Si+Pi+Wi+Ki+Fi; The delay Pi for sending the task to the computing processing terminal is the sum of the propagation delay and the transmission delay. The propagation delay is determined by the number of routing hops on the communication link, and the transmission delay is determined by the minimum bandwidth on the communication link.
[0037] The waiting delay Wi of a task in the task waiting queue of the computing processing terminal is calculated by summing the estimated execution time of each waiting task in the queue and adding the estimated remaining processing time of the currently executing task. The specific task execution time Ki of the task executed by the computing processing terminal is determined by the size of the processed data Yi and the CPU computing power; Ki=C*Yi / CPU computing power; The transmission delay Fi of returning the task execution result to the application server is determined by the propagation delay.
[0038] In some embodiments, when the application server cannot find a computing processing terminal that pre-stores a model corresponding to the task type from the local cache according to the task type, the application server sends a model creation instruction to the computing processing terminal, and when the application server receives a response message from the computing processing terminal based on the creation instruction within a set time, the computing processing terminal that sends the response message within the set time is defined as a first-class computing processing terminal; and the historical data corresponding to the creation model is sent to the first-class computing processing terminal; The first type of computing and processing terminal performs training and optimization of the neural network model based on the acquired historical data to obtain a trained fault detection and location model or a fault prediction model; inputs the preprocessed data into the trained model, and returns the output result to the application server.
[0039] In some embodiments, before issuing a task, the application server issues a task notification to the computing and processing terminal; the notification includes the task ID and the estimated execution time of the task; after receiving the task notification, the computing and processing terminal reserves a position for the task in the task waiting queue according to the estimated execution time of the task and updates the waiting time of the task waiting queue.
[0040] Correspondingly, after receiving the task, the computing processing terminal determines whether there is a reserved position for the task in the task waiting queue. If so, the task is inserted into the reserved position; otherwise, the task is placed at the end of the task waiting queue to wait for execution.
[0041] like Figure 2 As shown, the embodiment of the present invention also provides a distribution line intelligent monitoring method based on the Internet of Things, comprising the following steps: Step 1: The data collector obtains the collected data from the data collection terminal and transmits the obtained data to the application server; Step 2: The application server generates a data processing task according to the configuration information set by the user, creates and maintains a task queue, and the data processing task includes a task ID and a task type; and saves the to-be-processed data corresponding to the task ID in the database of the application server; the configuration information includes a number of processing judgments for distribution network status fault detection and positioning based on the collected data; the task queue includes a number of data processing tasks sorted according to the set conditions; Step 3: The application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; and sends the task and task data to the target computing and processing terminal; Step 4: After the computing terminal obtains the task and corresponding task data sent by the application server, it pre-processes the task data, matches the pre-stored fault detection and location model and fault prediction model according to the task ID and task type, inputs the pre-processed data into the matched model, and returns the output result to the application server; Step 5: Receive the calculation results returned by the target calculation processing terminal, and send the calculation results and corresponding collected data to the storage server.
[0042] In the embodiment of the present invention, the application server remotely accesses the Linux system of the data collector through the TELNET protocol, so that the data collector and the data collection terminal obtain the data of the data collection terminal through command operation and then send it to the application server after analysis.
[0043] In some embodiments, an application server obtains information about pending tasks, where the task information includes task type, expected deadline, and resource requirements to generate a task queue; the tasks are sorted by urgency according to the expected deadline and resource requirements to obtain a sorted task queue; based on the sorted task queue, a computing processing terminal corresponding to the task requirements is calculated and tasks and task data are issued.
[0044] In some embodiments, the application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; and sends the task and task data to the target computing and processing terminal. The steps include: The application server communicates with the computing and processing terminal to obtain the attribute information of each computing and processing terminal and caches it locally; the attribute information includes the computing resource configuration of the computing and processing terminal and the task ID corresponding to the pre-stored model; The application server obtains the task ID, task type, and resource requirements; according to the task type, it queries all computing processing terminals that pre-store the model corresponding to the task type from the local cache and generates a computing processing terminal set and corresponding computing resource configuration; it traverses the computing processing terminals in the access set, determines whether the current resource value of the computing processing terminal meets the resources required for the task, sets the computing processing terminal whose resources meet the resource requirements of the processing task as a candidate node and generates a candidate node list; Calculate the estimated completion time of each computing processing terminal in the list of all candidate nodes and sort them according to the time size, select the computing processing terminal with the smallest estimated completion time as the target computing processing terminal and send the task and the corresponding task data to the target computing processing terminal.
[0045] In some embodiments, the method further includes: when the application server cannot find a computing processing terminal that pre-stores a model corresponding to the task type from the local cache according to the task type, issuing a model creation instruction to the computing processing terminal, and when receiving a response message based on the creation instruction from the computing processing terminal within a set time, defining the computing processing terminal that sends the response message within the set time as a first-category computing processing terminal; and sending the historical data corresponding to the creation model to the first-category computing processing terminal; The first type of computing and processing terminal performs training and optimization of the neural network model based on the acquired historical data to obtain a trained fault detection and location model or a fault prediction model; inputs the preprocessed data into the trained model, and returns the output result to the application server.
[0046] In some embodiments, the method also includes: before issuing the task, the application server issues a task notification to the computing and processing terminal; the notification includes the task ID and the estimated execution time of the task; after the computing and processing terminal receives the task notification, it reserves a position for the task in the task waiting queue according to the estimated execution time of the task and updates the waiting time of the task waiting queue.
[0047] In some embodiments, the method further includes: after the computing processing terminal receives the task, determining whether there is a reserved position for the task in the task waiting queue, and if so, inserting the task into the reserved position, otherwise placing the task at the end of the task waiting queue waiting for execution.
[0048] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0049] An embodiment of the intelligent monitoring method for distribution lines based on the Internet of Things provided in an embodiment of the present invention belongs to the same inventive concept as the intelligent monitoring system for distribution lines based on the Internet of Things in the above-mentioned embodiments. For details not fully described in the embodiment of the intelligent monitoring method for distribution lines based on the Internet of Things, reference can be made to the embodiment of the intelligent monitoring system for distribution lines based on the Internet of Things.
[0050] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.
Claims
1. An intelligent monitoring system for power distribution lines based on the Internet of Things, characterized in that: It includes a data acquisition device, the data acquisition device is connected to an application server, and the application server is connected to a plurality of computing and processing terminals; The data acquisition equipment includes a data acquisition device and a data acquisition terminal in the distribution line connected to the data acquisition device for collecting the operation status of the distribution line; The data collector acquires the collected data from the data collection terminal and transmits the acquired data to the application server; The application server generates data processing tasks according to the configuration information set by the user, creates and maintains a task queue, wherein the configuration information includes several processing judgments for distribution network status fault detection and positioning based on the collected data; the task queue includes several data processing tasks sorted according to the set conditions; the data processing task includes a task ID and a task type; the data to be processed corresponding to the task ID is stored in the database of the application server; the application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; And send the task and task data to the target computing and processing terminal, receive the calculation results returned by the target computing and processing terminal, and send the calculation results and corresponding collected data to the storage server; After receiving the issued task and the corresponding task data, the computing and processing terminal processes the data based on the task type and returns the processing result to the application server.
2. The power distribution line intelligent monitoring system based on the Internet of Things according to claim 1 is characterized in that: The application server remotely accesses the Linux system of the data collector through the TELNET protocol, so that the data collector and the data acquisition terminal obtain the data from the data acquisition terminal through command operations and send it to the application server after analysis.
3. The power distribution line intelligent monitoring system based on the Internet of Things according to claim 2 is characterized in that: The application server obtains information about pending tasks, including task type, expected deadline, and resource requirements to generate a task queue; sorts tasks by urgency according to expected deadline and resource requirements to obtain a sorted task queue; based on the sorted task queue, calculates the computing processing terminal corresponding to the task requirements and sends tasks and task data.
4. The power distribution line intelligent monitoring system based on the Internet of Things according to claim 3 is characterized in that: The computing and processing terminal pre-stores the trained fault detection and location model and fault prediction model; The fault detection and location model and the fault prediction model are associated with the corresponding task ID and task type respectively; After the computing and processing terminal obtains the task and corresponding task data sent by the application server, it preprocesses the task data, matches the pre-stored fault detection and positioning model and fault prediction model according to the task ID and task type, inputs the preprocessed data into the matched model, and returns the output result to the application server.
5. The power distribution line intelligent monitoring system based on the Internet of Things according to any one of claims 1 to 4, characterized in that: The application server communicates with the computing and processing terminal to obtain the attribute information of each computing and processing terminal and caches it locally; The attribute information includes the computing resource configuration of the computing processing terminal and the task ID corresponding to the pre-stored model; The application server obtains the task ID, task type, and resource requirements; according to the task type, it queries all computing processing terminals that pre-store the model corresponding to the task type from the local cache and generates a computing processing terminal set and corresponding computing resource configuration; it traverses the computing processing terminals in the access set, determines whether the current resource value of the computing processing terminal meets the resources required for the task, sets the computing processing terminal whose resources meet the resource requirements of the processing task as a candidate node and generates a candidate node list; Calculate the estimated completion time of each computing processing terminal in the list of all candidate nodes and sort them according to the time size, select the computing processing terminal with the smallest estimated completion time as the target computing processing terminal and send the task and the corresponding task data to the target computing processing terminal.
6. The power distribution line intelligent monitoring system based on the Internet of Things according to claim 5 is characterized in that: When the application server cannot find a computing processing terminal that has pre-stored a model corresponding to the task type from the local cache according to the task type, it sends a model creation instruction to the computing processing terminal, and when the application server receives response information from the computing processing terminal based on the creation instruction within a set time, the computing processing terminal that sends the response information within the set time is defined as a first-category computing processing terminal; and sending the historical data corresponding to the created model to the first type of computing and processing terminal; The first type of computing and processing terminal performs training and optimization of the neural network model based on the acquired historical data to obtain a trained fault detection and location model or a fault prediction model; The preprocessed data is fed into the trained model and the output is returned to the application server.
7. The power distribution line intelligent monitoring system based on the Internet of Things according to claim 6 is characterized in that: Before sending a task, the application server sends a task notification to the computing and processing terminal; the notification includes the task ID and the estimated execution time of the task; after receiving the task notification, the computing and processing terminal reserves a position for the task in the task waiting queue according to the estimated execution time of the task and updates the waiting time of the task waiting queue.
8. The power distribution line intelligent monitoring system based on the Internet of Things according to claim 7 is characterized in that: After receiving the task, the computing processing terminal determines whether there is a reserved position for the task in the task waiting queue. If so, the task is inserted into the reserved position; otherwise, the task is placed at the end of the task waiting queue to wait for execution.
9. An intelligent monitoring method for power distribution lines based on the Internet of Things, characterized in that: The steps include: The data collector acquires the collected data from the data collection terminal and transmits the acquired data to the application server; The application server generates data processing tasks according to the configuration information set by the user, creates and maintains a task queue, and the data processing tasks include a task ID and a task type; and saves the to-be-processed data corresponding to the task ID in the database of the application server; the configuration information includes a number of processing judgments for distribution network status fault detection and positioning based on the collected data; the task queue includes a number of data processing tasks sorted according to the set conditions; The application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; And send the task and task data to the target computing and processing terminal; After the computing and processing terminal obtains the task and corresponding task data sent by the application server, it pre-processes the task data, matches the pre-stored fault detection and location model and fault prediction model according to the task ID and task type, inputs the pre-processed data into the matched model, and returns the output result to the application server; Receive the calculation results returned by the target calculation processing terminal, and send the calculation results and corresponding collected data to the storage server.
10. The method for intelligent monitoring of power distribution lines based on the Internet of Things according to claim 9, characterized in that: The application server obtains the status of the computing and processing terminal and calculates and confirms the execution terminal of each task based on the obtained information, that is, the target computing and processing terminal; The steps of sending the task and task data to the target computing and processing terminal include: The application server communicates with the computing and processing terminal to obtain the attribute information of each computing and processing terminal and caches it locally; the attribute information includes the computing resource configuration of the computing and processing terminal and the task ID corresponding to the pre-stored model; The application server obtains the task ID, task type, and resource requirements; according to the task type, it queries all computing processing terminals that pre-store the model corresponding to the task type from the local cache and generates a computing processing terminal set and corresponding computing resource configuration; it traverses the computing processing terminals in the access set, determines whether the current resource value of the computing processing terminal meets the resources required for the task, sets the computing processing terminal whose resources meet the resource requirements of the processing task as a candidate node and generates a candidate node list; Calculate the estimated completion time of each computing processing terminal in the list of all candidate nodes and sort them according to the time size, select the computing processing terminal with the smallest estimated completion time as the target computing processing terminal; send the task and the corresponding task data to the target computing processing terminal.
