Edge device collaborative optimization method and device based on water level prediction and medium

Abstract

The invention discloses a water level prediction-based edge device collaborative optimization method, device and medium, and the method comprises the steps: carrying out the hydrological dynamic prediction analysis of real-time river reach monitoring data, so as to obtain a hydrological prediction parameter matrix; performing edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; based on the optimal edge device combination data, an edge device deployment instruction set is determined through edge device virtual deployment verification; according to the edge device deployment instruction set, through edge device real-time operation monitoring, a real-time monitoring data stream for the edge device is obtained; performing equipment monitoring effect analysis on the real-time monitoring data stream, and determining edge equipment collaborative optimization parameters; and on the basis of the equipment performance library, an edge equipment collaborative optimization strategy is obtained through equipment configuration strategy iteration. According to the method, the technical problem that in the prior art, the deployment prediction effect of the hydrometric station edge equipment is poor is solved.

Description

Technical Field

[0001] This application relates to the field of digital water conservancy technology, and particularly to a method, device and medium for collaborative optimization of edge devices based on water level prediction. Background Art

[0002] In recent years, with the frequent occurrence of global climate change and extreme hydrological events, the importance of hydrological monitoring in flood control and disaster reduction, water resources management and other fields has become increasingly prominent. Traditional hydrological monitoring systems mainly rely on fixed-configured sensor devices and manual experience to formulate measurement plans. Although they can meet the basic data collection requirements, in the face of complex scenarios such as sudden floods and heavy rains, problems such as lagging equipment deployment and low resource scheduling efficiency often lead to incomplete or untimely data acquisition, thus affecting the early deployment of water conservancy edge devices.

[0003] In the prior art, some methods attempt to plan monitoring tasks in advance through hydrological prediction models, or use Internet of Things technology to achieve remote device control. Since device selection and deployment highly rely on manual experience and cannot dynamically adjust the device combination according to real-time hydrological changes, the deployment strategy for water conservancy edge devices still cannot meet the actual device requirements of water level stations in multiple different river reaches. Because the locations of hydrological stations are usually far from urban areas and it is not easy to store devices, it is necessary to dynamically optimize the device deployment strategies for different hydrological environments and different river reaches. Summary of the Invention

[0004] Embodiments of this application provide a method, device and medium for collaborative optimization of edge devices based on water level prediction, which solve the technical problem of poor prediction effect of edge device deployment in hydrological stations in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for collaborative optimization of edge devices based on water level prediction, which is characterized in that the method includes: obtaining real-time river reach monitoring data, and performing hydrological dynamic prediction analysis on the real-time river reach monitoring data to obtain a hydrological prediction parameter matrix; performing edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; based on the optimal edge device combination data, determining an edge device deployment instruction set through virtual deployment verification of edge devices; according to the edge device deployment instruction set, obtaining a real-time monitoring data stream for edge devices through real-time operation monitoring of edge devices; performing device monitoring effect analysis on the real-time monitoring data stream to determine edge device collaborative optimization parameters; feeding back the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtaining an edge device collaborative optimization strategy through iterative device configuration strategies.

[0006] In an implementation manner of the present application, hydrological dynamic prediction analysis is performed on real-time river section monitoring data to obtain a hydrological prediction parameter matrix, which specifically includes: performing spatio-temporal alignment processing on the real-time river section monitoring data to obtain a standardized monitoring data set; wherein, the real-time river section monitoring data includes: hydrological monitoring data, meteorological monitoring data, and terrain monitoring data; based on the standardized monitoring data set, determining river section basic water flow characteristic data through basic water flow characteristic analysis; obtaining delayed sequence monitoring data of the real-time river section monitoring data, and according to the delayed sequence monitoring data and the river section basic water flow characteristic data, obtaining a hydrological prediction parameter matrix through dynamic water level correction of spatio-temporal graph neural fusion.

[0007] In an implementation manner of the present application, edge device combination optimization is performed on the hydrological prediction parameter matrix to obtain optimal edge device combination data, which specifically includes: performing risk threshold analysis on the hydrological prediction parameter matrix to determine the risk prediction level; based on the risk prediction level, obtaining a preliminary device requirement list through multi-level edge device mapping; performing multi-objective optimization analysis on the preliminary device requirement list to obtain a candidate device combination list; wherein, the objectives of the multi-objective optimization analysis include: device accuracy, deployment requirements, and device transportation distance; according to the candidate device combination list, obtaining optimal edge device combination data through device efficiency collaborative evaluation.

[0008] In an implementation manner of the present application, based on the optimal edge device combination data, edge device virtual deployment verification is performed to determine an edge device deployment instruction set, which specifically includes: performing device scheduling analysis on the optimal edge device combination data to obtain an edge device scheduling list; wherein, the device scheduling analysis includes: device inventory analysis and inventory location analysis; based on the edge device scheduling list, determining edge device deployment feasibility parameters through virtual deployment verification of digital twin; integrating deployment rules for the edge device deployment feasibility parameters to determine an edge device deployment instruction set.

[0009] In an implementation manner of the present application, according to the edge device deployment instruction set, edge device real-time operation monitoring is performed to obtain a real-time monitoring data stream for edge device use, which specifically includes: performing edge node instruction control on the edge device deployment instruction set to determine a target edge device wake-up instruction; waking up the target edge device through the target edge device wake-up instruction, and performing instant status switching analysis on the target edge device to obtain the instant working status of the edge device; performing real-time operation monitoring on the instant working status of the edge device to obtain a real-time monitoring data stream for edge device use.

[0010] In one implementation of the present application, device monitoring effect analysis is performed on the real-time monitoring data stream to determine the edge device collaborative optimization parameters, which specifically includes: performing abnormal parameter monitoring on the real-time monitoring data stream to obtain a device abnormal data report; and determining the edge device collaborative optimization parameters based on the device abnormal data report through predictive weight redistribution.

[0011] In one implementation of the present application, based on the device performance library, an edge device collaborative optimization strategy is obtained through iterative device configuration strategy, which specifically includes: determining an iteration threshold through iterative accuracy threshold analysis, and based on the iteration threshold, performing iterative device configuration strategy on the device performance library to obtain an edge device collaborative optimization strategy.

[0012] In one implementation of the present application, after obtaining the edge device collaborative optimization strategy based on the device performance library through iterative device configuration strategy, the method further includes: updating the edge device collaborative optimization strategy to a preset device configuration strategy library, and based on the device configuration strategy library, obtaining the edge device configuration strategy of the updated water level station through water level station data update; performing basic device requirement analysis on the edge device configuration strategy of the updated water level station to determine the initial device configuration strategy of the updated water level station.

[0013] In a second aspect, an embodiment of the present application further provides an edge device collaborative optimization device based on water level prediction, which is characterized in that the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: obtain real-time river section monitoring data, and perform hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix; perform edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; determine an edge device deployment instruction set based on the optimal edge device combination data through edge device virtual deployment verification; obtain the real-time monitoring data stream of the edge device through edge device real-time operation monitoring according to the edge device deployment instruction set; perform device monitoring effect analysis on the real-time monitoring data stream to determine the edge device collaborative optimization parameters; feedback the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtain an edge device collaborative optimization strategy through iterative device configuration strategy.

[0014] In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium for collaborative optimization of edge devices based on water level prediction, storing computer-executable instructions, characterized in that the computer-executable instructions are set to: obtain real-time river section monitoring data, and perform hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix; perform edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; based on the optimal edge device combination data, determine an edge device deployment instruction set through edge device virtual deployment verification; according to the edge device deployment instruction set, obtain a real-time monitoring data stream for edge devices through real-time operation monitoring of edge devices; perform device monitoring effect analysis on the real-time monitoring data stream to determine edge device collaborative optimization parameters; feedback the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtain an edge device collaborative optimization strategy through device configuration strategy iteration.

[0015] An embodiment of the present application provides a method, device and medium for collaborative optimization of edge devices based on water level prediction. By combining hydrological prediction with the analysis of edge device deployment strategies, it solves the technical problem of poor prediction effect of edge device deployment in existing hydrological stations, realizes real-time prediction of the monitoring equipment requirements of hydrological stations in different river sections, improves the prediction effect of edge device deployment in hydrological stations, and reduces the scheduling difficulty of edge devices in hydrological stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0017] Figure 1 It is a flowchart of a method for collaborative optimization of edge devices based on water level prediction provided by an embodiment of the present application;

[0018] Figure 2 It is a schematic internal structure diagram of a device for collaborative optimization of edge devices based on water level prediction provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0020] The embodiments of the present application provide a method, device, and medium for collaborative optimization of edge devices based on water level prediction. By combining hydrological prediction with the analysis of edge device deployment strategies, the technical problem of poor prediction effect of edge device deployment in hydrological stations in the prior art is solved, the real-time prediction of the monitoring equipment requirements of hydrological stations in different river reaches is realized, the prediction effect of edge device deployment prediction in hydrological stations is improved, and the scheduling difficulty of edge devices in hydrological stations is reduced.

[0021] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0022] Figure 1 It is a flowchart of a method for collaborative optimization of edge devices based on water level prediction provided by the embodiments of the present application. As Figure 1 shown, a method for collaborative optimization of edge devices based on water level prediction provided by the embodiments of the present application specifically includes the following steps:

[0023] Step 101: Obtain real-time river reach monitoring data, and perform hydrological dynamic prediction analysis on the real-time river reach monitoring data to obtain a hydrological prediction parameter matrix.

[0024] Exemplarily, through hydrological dynamic prediction analysis of real-time river reach monitoring data, a method combining data preprocessing, shallow water solution technology for flow characteristics, and dynamic water level correction of spatio-temporal graph neural fusion is adopted to realize the construction of a hydrological prediction parameter matrix, providing a data basis for the analysis of edge device configuration in different river reaches where the water level stations are located.

[0025] Specifically, performing hydrological dynamic prediction analysis on real-time river reach monitoring data to obtain a hydrological prediction parameter matrix includes: performing spatio-temporal alignment processing on real-time river reach monitoring data to obtain a standardized monitoring data set; wherein, the real-time river reach monitoring data includes: hydrological monitoring data, meteorological monitoring data, and terrain monitoring data; based on the standardized monitoring data set, determining the basic flow characteristics data of the river reach through basic flow characteristics analysis; obtaining the delayed sequence monitoring data of the real-time river reach monitoring data, and obtaining the hydrological prediction parameter matrix through dynamic water level correction of spatio-temporal graph neural fusion according to the delayed sequence monitoring data and the basic flow characteristics data of the river reach.

[0026] In one embodiment, first, obtain real-time monitoring data, with water level, flow velocity, sediment concentration, rainfall, temperature, riverbed elevation, and cross-section shape as the main monitoring data. Perform Kalman filter denoising and spatio-temporal alignment processing on the data to generate a standardized data set.

[0027] Then, based on the terrain data in the standardized data set and the initial hydrological parameters of the river reach, calculate the basic flow characteristics by solving the shallow water equations to obtain the water level distribution and flow velocity field of the river reach.

[0028] Finally, the spatio-temporal graph neural network (ST-GNN) is used to fuse the basic water flow characteristics with the delayed sequence monitoring data of the real-time river section monitoring data. Through dynamic water level correction, a prediction parameter matrix for the next 3 hours is output.

[0029] Furthermore, according to the update of the delayed sequence monitoring data, a prediction parameter matrix is continuously generated with a 3-hour cycle.

[0030] Step 102: Optimize the edge device combination of the hydrological prediction parameter matrix to obtain the optimal edge device combination data.

[0031] Exemplarily, by optimizing the edge device combination of the hydrological prediction parameter matrix, risk threshold analysis, multi-level edge device mapping, multi-objective optimization analysis, and device efficiency collaborative evaluation are adopted to realize the edge device combination analysis of the predicted water level of the river section where the water level station is located, and the prediction effect of the edge device deployment prediction of the hydrological station is improved.

[0032] Specifically, optimizing the edge device combination of the hydrological prediction parameter matrix to obtain the optimal edge device combination data includes: performing risk threshold analysis on the hydrological prediction parameter matrix to determine the risk prediction level; based on the risk prediction level, obtaining a preliminary device requirement list through multi-level edge device mapping; performing multi-objective optimization analysis on the preliminary device requirement list to obtain a candidate device combination list; where the objectives of the multi-objective optimization analysis include: device accuracy, deployment requirements, and device transportation distance; according to the candidate device combination list, obtaining the optimal edge device combination data through device efficiency collaborative evaluation.

[0033] In one embodiment, first, perform risk threshold analysis on the hydrological prediction parameter matrix to determine the risk prediction level, and associate the risk level with the device type in combination with the device matching rule library.

[0034] The high-risk river section is set with a predicted water level > 5m and a flow velocity > 2m / s. In the high-risk river section, a high-precision device combination needs to be deployed, including an acoustic Doppler current profiler (ADCP), a buoy array, and a sediment sensor.

[0035] The medium-risk river section is set with a water level of 3 - 5m and a stable flow velocity. In the medium-risk river section, a radar water level gauge, a camera, and a temperature and humidity sensor are required to meet the basic monitoring and floating object identification.

[0036] The low-risk river section is set with a water level < 3m and a gentle flow velocity. Only a pressure water level gauge and a low-power LoRa sensor are required to achieve low-cost continuous monitoring. Through the association of the above device types, a preliminary device requirement list is obtained.

[0037] Then, perform multi-objective optimization analysis on the preliminary device requirement list, and select the error rate as the key weight of the multi-objective optimization analysis.

[0038] Furthermore, the key weight for multi-objective optimization analysis is to preferentially select the deployment time in the river sections mainly affected by emergencies.

[0039] Furthermore, according to the edge device model, the key weight for multi-objective optimization analysis is to preferentially select device compatibility.

[0040] The NSGA-II algorithm is used to generate multiple groups of candidate solutions, and the candidate solutions are integrated into a candidate device combination table.

[0041] Finally, evaluate the effect of multi-device collaborative work, and simulate the monitoring effect of the candidate solutions in the target river section through the digital twin model. Score the candidate solutions according to dimensions such as accuracy, compatibility, and deployment time, and preferentially select the combination with the highest total score to obtain the optimal edge device combination data.

[0042] Step 103: Based on the optimal edge device combination data, determine the edge device deployment instruction set through edge device virtual deployment verification.

[0043] Exemplarily, through edge device virtual deployment verification, perform deployment scheduling analysis on the optimal edge device combination data. Since the optimal edge device combination data is only the optimal prediction combination of the edge devices in the river section where the water level station is located, further verification is required for the scheduling of different edge devices to avoid shortages or difficulties in scheduling at key nodes, reducing the scheduling difficulty of the edge devices of the hydrological station.

[0044] Specifically, based on the optimal edge device combination data, determine the edge device deployment instruction set through edge device virtual deployment verification, including: performing device scheduling analysis on the optimal edge device combination data to obtain an edge device scheduling list; wherein, the device scheduling analysis includes: device inventory analysis and inventory location analysis; based on the edge device scheduling list, determine the edge device deployment feasibility parameters through virtual deployment verification of the digital twin; and integrate the edge device deployment feasibility parameters to determine the edge device deployment instruction set.

[0045] In one embodiment, according to the optimal device combination scheme, retrieve the device inventory and location in the edge resource pool to generate a device scheduling list.

[0046] Load the device scheduling list in the three-dimensional hydrological twin model, simulate the deployment and detect the scheduling feasibility and deployment feasibility, and output a deployment feasibility report.

[0047] Combine the scheduling list and the feasibility report to generate a device deployment instruction set, which includes but is not limited to the GPS coordinates of the target river section, device installation parameters, and transportation path planning.

[0048] Step 104: According to the edge device deployment instruction set, through real-time operation monitoring of the edge device, obtain the real-time monitoring data stream for the edge device.

[0049] Exemplarily, in order to analyze the actual monitoring effect of the current edge device deployment instruction set, it is necessary to conduct real-time operation monitoring of the edge device. And in order to cope with possible emergencies in the river section, it is also necessary to instantaneously switch and monitor the real-time working state of the edge device.

[0050] Specifically, according to the edge device deployment instruction set, through real-time operation monitoring of the edge device, obtain the real-time monitoring data stream for the edge device, including: performing edge node instruction control on the edge device deployment instruction set to determine the target edge device wake-up instruction; through the target edge device wake-up instruction, wake up the target edge device, and conduct an instant state switching analysis on the target edge device to obtain the instant working state of the edge device; perform real-time operation monitoring on the instant working state of the edge device to obtain the real-time monitoring data stream for the edge device.

[0051] In one embodiment, first, remotely wake up the device through the TLS1.3 encryption protocol, dynamically calibrate the sensor through edge node instruction control. If the real-time water level > 5m, automatically control the ADCP to switch to the emergency mode.

[0052] Package the data according to the preset data encapsulation standard, attach metadata such as device ID and quality identification, and perform data backup to obtain the real-time monitoring data stream for the edge device.

[0053] Step 105: Analyze the device monitoring effect of the real-time monitoring data stream to determine the edge device collaborative optimization parameters.

[0054] Exemplarily, by analyzing the device monitoring effect of the real-time monitoring data stream, based on the real-time cooperation state of the edge device, through abnormal parameter monitoring, it is judged whether there are defects in this set of configurations under the strategy configured for the current edge device, and the strategy is optimized according to the abnormality, realizing the collaborative optimization of the edge device and improving the robustness of the edge device deployment prediction of the hydrological station.

[0055] Specifically, analyze the device monitoring effect of the real-time monitoring data stream to determine the edge device collaborative optimization parameters, including: performing abnormal parameter monitoring on the real-time monitoring data stream to obtain the device abnormal data report; based on the device abnormal data report, determine the edge device collaborative optimization parameters through predictive weight redistribution.

[0056] In one embodiment, run the Isolation Forest algorithm at the edge to identify data anomalies. Usually, in the case of rising water level and sudden increase in flow velocity, sensor drift and data loss of the edge device will occur, and an abnormal data report will be generated accordingly.

[0057] Update the device performance library and prediction weights according to the exception report, eliminate high-frequency failure devices in the policy, and change the prediction weight allocation of the current river section. Through the reallocation of prediction weights, determine the collaborative optimization parameters of edge devices.

[0058] Step 106: Feed back the collaborative optimization parameters of edge devices to the preset device performance library, and based on the device performance library, obtain the collaborative optimization strategy of edge devices through iterative device configuration strategies.

[0059] Exemplarily, through iterative device configuration strategies, the dynamic optimization of device configuration for corresponding river sections of different water level stations is realized, gradually improving the adaptability of edge device allocation and enhancing the prediction effect of the prediction of edge device deployment at hydrological stations.

[0060] Specifically, based on the device performance library, obtaining the collaborative optimization strategy of edge devices through iterative device configuration strategies includes: determining the iteration threshold through iterative accuracy threshold analysis, and based on the iteration threshold, performing iterative device configuration strategies on the device performance library to obtain the collaborative optimization strategy of edge devices.

[0061] Further, after obtaining the collaborative optimization strategy of edge devices based on the device performance library through iterative device configuration strategies, the method further includes: updating the collaborative optimization strategy of edge devices to the preset device configuration strategy library, and based on the device configuration strategy library, obtaining the edge device configuration strategy of the updated water level station through water level station data update; performing basic device requirement analysis on the edge device configuration strategy of the updated water level station to determine the initial device configuration strategy of the updated water level station.

[0062] The above is the method embodiment proposed in this application. Based on the same inventive concept, the embodiments of this application also provide a collaborative optimization device for edge devices based on water level prediction, and its structure is as Figure 2 shown.

[0063] Figure 2 FIG. is a schematic internal structure diagram of a collaborative optimization device for edge devices based on water level prediction provided by an embodiment of this application. As Figure 2 shown, the device includes:

[0064] At least one processor 201;

[0065] And a memory 202 communicatively connected to at least one processor;

[0066] Wherein, the memory 202 stores instructions executable by at least one processor, and the instructions are executed by at least one processor 201 so that at least one processor 201 can:

[0067] Obtain real-time river section monitoring data, and conduct hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix; perform edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; based on the optimal edge device combination data, determine the edge device deployment instruction set through edge device virtual deployment verification; according to the edge device deployment instruction set, obtain the real-time monitoring data stream for edge devices through real-time operation monitoring of edge devices; conduct device monitoring effect analysis on the real-time monitoring data stream to determine the edge device collaborative optimization parameters; feedback the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtain the edge device collaborative optimization strategy through device configuration strategy iteration.

[0068] Some embodiments of the present application provide a Figure 1 non-volatile computer storage medium for edge device collaborative optimization based on water level prediction, storing computer-executable instructions, and the computer-executable instructions are set as:

[0069] Obtain real-time river section monitoring data, and conduct hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix; perform edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; based on the optimal edge device combination data, determine the edge device deployment instruction set through edge device virtual deployment verification; according to the edge device deployment instruction set, obtain the real-time monitoring data stream for edge devices through real-time operation monitoring of edge devices; conduct device monitoring effect analysis on the real-time monitoring data stream to determine the edge device collaborative optimization parameters; feedback the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtain the edge device collaborative optimization strategy through device configuration strategy iteration.

[0070] Each embodiment in the present application is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments. In particular, for the embodiments of Internet of Things devices and media, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0071] The systems and media provided by the embodiments of the present application correspond one-to-one with the methods. Therefore, the systems and media also have beneficial technical effects similar to those of their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be elaborated here.

[0072] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0073] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0074] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0076] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0077] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0078] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0079] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0080] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. An edge device collaborative optimization method based on water level prediction, characterized in that The method includes: Obtaining real-time river section monitoring data, and performing hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix; Performing edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; Based on the optimal edge device combination data, determining an edge device deployment instruction set through edge device virtual deployment verification; According to the edge device deployment instruction set, obtaining a real-time monitoring data stream for edge devices through real-time operation monitoring of edge devices; Performing device monitoring effect analysis on the real-time monitoring data stream to determine edge device collaborative optimization parameters; Feeding back the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtaining an edge device collaborative optimization strategy through device configuration strategy iteration.

2. The collaborative optimization method for edge devices based on water level prediction according to claim 1, characterized in that Performing hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix, specifically including: Performing spatio-temporal alignment processing on the real-time river section monitoring data to obtain a standardized monitoring data set; wherein, the real-time river section monitoring data includes: hydrological monitoring data, meteorological monitoring data, and terrain monitoring data; Based on the standardized monitoring data set, determining river section basic water flow characteristic data through basic water flow characteristic analysis; Obtaining delay sequence monitoring data of the real-time river section monitoring data, and based on the delay sequence monitoring data and the river section basic water flow characteristic data, obtaining the hydrological prediction parameter matrix through dynamic water level correction of spatio-temporal graph neural fusion.

3. A method for collaborative optimization of edge devices based on water level prediction according to claim 1, characterized in that Performing edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data, specifically including: Performing risk threshold analysis on the hydrological prediction parameter matrix to determine a risk prediction level; Based on the risk prediction level, obtaining a preliminary device requirement list through multi-level edge device mapping; Performing multi-objective optimization analysis on the preliminary device requirement list to obtain a candidate device combination list; wherein, the objectives of the multi-objective optimization analysis include: device accuracy, deployment requirements, and device transportation distance; According to the candidate device combination list, obtaining the optimal edge device combination data through device efficiency collaborative evaluation.

4. A method for collaborative optimization of edge devices based on water level prediction according to claim 1, characterized in that, Based on the optimal edge device combination data, determining an edge device deployment instruction set through edge device virtual deployment verification, specifically including: Performing device scheduling analysis on the optimal edge device combination data to obtain an edge device scheduling list; wherein, the device scheduling analysis includes: device inventory analysis and inventory location analysis; Based on the edge device scheduling list, determining edge device deployment feasibility parameters through virtual deployment verification of digital twin; Integrating deployment rules for the edge device deployment feasibility parameters to determine an edge device deployment instruction set.

5. A collaborative optimization method for edge devices based on water level prediction according to claim 1, wherein According to the edge device deployment instruction set, obtaining a real-time monitoring data stream for edge devices through real-time operation monitoring of edge devices, specifically including: Performing edge node instruction control on the edge device deployment instruction set to determine a target edge device wake-up instruction; Wake up the target edge device through the target edge device wake-up instruction, and perform an instant status switch analysis on the target edge device to obtain the instant working status of the edge device; Perform real-time operation monitoring on the instant working status of the edge device to obtain the real-time monitoring data stream for the edge device.

6. The collaborative optimization method for edge devices based on water level prediction according to claim 1, characterized in that Perform device monitoring effect analysis on the real-time monitoring data stream to determine the edge device collaborative optimization parameters, specifically including: Perform abnormal parameter monitoring on the real-time monitoring data stream to obtain a device abnormal data report; Based on the device abnormal data report, determine the edge device collaborative optimization parameters through predictive weight redistribution.

7. A collaborative optimization method for edge devices based on water level prediction according to claim 1, characterized in that, Based on the device performance library, obtain the edge device collaborative optimization strategy through device configuration strategy iteration, specifically including: Determine the iteration threshold through iteration accuracy threshold analysis, and based on the iteration threshold, perform device configuration strategy iteration on the device performance library to obtain the edge device collaborative optimization strategy.

8. A collaborative optimization method for edge devices based on water level prediction according to claim 1, characterized in that, After obtaining the edge device collaborative optimization strategy through device configuration strategy iteration based on the device performance library, the method further includes: Update the edge device collaborative optimization strategy to a preset device configuration strategy library, and based on the device configuration strategy library, obtain the edge device configuration strategy for the updated water level station through water level station data update; Perform basic device requirement analysis on the edge device configuration strategy for the updated water level station to determine the initial device configuration strategy for the updated water level station.

9. An edge device collaborative optimization device based on water level prediction, characterized in that, The device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: Obtain real-time river section monitoring data, and perform hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix; Perform edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; Based on the optimal edge device combination data, determine the edge device deployment instruction set through edge device virtual deployment verification; According to the edge device deployment instruction set, obtain the real-time monitoring data stream for the edge device through edge device real-time operation monitoring; Perform device monitoring effect analysis on the real-time monitoring data stream to determine the edge device collaborative optimization parameters; Feed back the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtain the edge device collaborative optimization strategy through device configuration strategy iteration.

10. A non-volatile computer storage medium for collaborative optimization of edge devices based on water level prediction, storing computer-executable instructions, characterized in that, The computer-executable instructions are set to: Obtain real-time river section monitoring data, and perform hydrological dynamic prediction analysis on the real-time river section monitoring data to obtain a hydrological prediction parameter matrix; Perform edge device combination optimization on the hydrological prediction parameter matrix to obtain optimal edge device combination data; Based on the optimal edge device combination data, determine the edge device deployment instruction set through edge device virtual deployment verification; According to the edge device deployment instruction set, obtain the real-time monitoring data stream for the edge device through edge device real-time operation monitoring; Analyze the device monitoring effect on the real-time monitoring data stream to determine the edge device collaborative optimization parameters; Feed back the edge device collaborative optimization parameters to a preset device performance library, and based on the device performance library, obtain an edge device collaborative optimization strategy through iterative device configuration policies.

Images