Reservoir safety monitoring method based on edge calculation

Abstract

The invention discloses a reservoir safety monitoring method based on edge calculation, and particularly relates to the technical field of hydraulic engineering safety monitoring. According to the method, the reservoir geographic grid model is constructed and the static environment parameters are pre-calculated, so that an objective and uniform data base is established for evaluation, a quantifiable index system covering three dimensions of monitoring perception, data timeliness and cost effectiveness is established, and accurate calculation logic is defined for each dimension; different layout schemes are converted into a group of calculable coefficients, and finally a comprehensive and comparable comprehensive efficiency index is generated through weighted fusion, so that quantitative sorting of advantages and disadvantages of the schemes is realized, subjectivity and randomness of decision making are greatly reduced, and scheme comparison and selection are based on basis, scientific and transparent.

Description

Technical Field

[0001] This invention relates to the field of water conservancy project safety monitoring technology, and more specifically, to a reservoir safety monitoring method based on edge computing. Background Technology

[0002] In the field of water conservancy project safety, reservoirs, as core infrastructure for water resource regulation and flood control, are directly related to the safety of life and property and the balance of the ecological environment in downstream areas. With the rapid iteration of new-generation information technologies such as the Internet of Things and edge computing, edge computing-based reservoir safety monitoring methods are gradually replacing traditional monitoring modes and becoming the mainstream of industry development. By deploying edge computing nodes on-site at reservoirs, the local real-time processing, analysis, and early warning of monitoring data can be achieved, which not only significantly reduces the load pressure on cloud data processing but also effectively shortens data transmission latency, providing technical support for rapid response to reservoir emergencies.

[0003] However, existing reservoir safety monitoring methods still have the following shortcomings in terms of the deployment of edge nodes:

[0004] Firstly, the deployment of nodes lacks a scientific and quantitative evaluation system. Traditional solutions rely heavily on the experience and judgment of technical personnel, and do not adequately consider key factors such as the geographical environment and risk distribution of the reservoir area. This can easily lead to monitoring blind spots in high-risk areas or substandard signal coverage in key locations, making it impossible to form a comprehensive and high-precision monitoring network.

[0005] Secondly, there is a lack of effective evaluation standards for the timeliness of data transmission. The existing solutions do not systematically calculate the link transmission delay, processing delay and the link throughput capacity during the flood peak period. Under extreme hydrological conditions, data congestion and packet loss are likely to occur, resulting in the failure to deliver early warning information in a timely manner and missing the best opportunity for response.

[0006] Third, the balance between cost and benefit is difficult to control. Some solutions overemphasize monitoring coverage while neglecting deployment and maintenance costs, resulting in a waste of resources. Other solutions sacrifice monitoring performance to reduce costs, failing to meet the actual needs of long-term reservoir safety monitoring.

[0007] The lack of a unified benchmark for comparing the advantages and disadvantages of different deployment schemes makes it difficult to flexibly select suitable schemes based on the actual priorities of the project, which brings great subjectivity and uncertainty to engineering decisions.

[0008] To address this, a reservoir safety monitoring method based on edge computing has been developed. Summary of the Invention

[0009] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a reservoir safety monitoring method based on edge computing.

[0010] To achieve the above objectives, the present invention provides the following technical solution:

[0011] A reservoir safety monitoring method based on edge computing includes:

[0012] S1: Divide the reservoir area into geographic grids, construct a high-precision geographic grid model, and pre-calculate and store a set of static environmental parameters for each geographic grid unit;

[0013] Static environmental parameters include pre-marked key points and pre-input risk scores for the mesh;

[0014] S2: Deployment scheme is defined as ;

[0015] S3: Overlay the deployment scheme S with the static environmental parameters for analysis. Through simulation calculation, output multi-dimensional evaluation parameters. After processing the multi-dimensional evaluation parameters using pre-edited processing logic, construct a multi-dimensional coefficient set.

[0016] S4: After processing the multi-dimensional coefficient set using weighted fusion logic, a comprehensive performance index is generated for each scheme; based on the comprehensive performance index, the ranking results of all deployment schemes are output and then input into a pre-edited report template to generate a visual evaluation report;

[0017] S5: Based on the comprehensive effectiveness index of all deployment schemes, select the scheme with the highest comprehensive effectiveness index from the visualization evaluation report as the reservoir monitoring scheme.

[0018] Specifically, the specific definition logic of the S2 deployment scheme;

[0019] N: The set of nodes to be deployed, each node It includes its geographic coordinates and node type; where i is the node number.

[0020] L: The set of planned communication links between nodes, each link Define the node it connects to, where j is the link number.

[0021] Specifically, the multi-dimensional evaluation parameters in S3 include:

[0022] The multi-dimensional evaluation parameters include monitoring coverage and perception quality, data flow timeliness, and cost-benefit analysis.

[0023] Specifically, the multi-dimensional coefficient set in S3 includes coverage perception coefficient, data timeliness coefficient, and cost-effectiveness coefficient;

[0024] The monitoring coverage and perception quality dimensions include spatial coverage and key area coverage. Based on spatial coverage and key area coverage, the coverage perception coefficients are obtained after processing and multi-dimensional coefficient set.

[0025] The data flow timeliness dimension includes the overall average latency and throughput evaluation value. Based on the overall average latency and throughput evaluation value, the data timeliness coefficient is obtained after processing in a multi-dimensional coefficient set.

[0026] The cost-benefit comprehensive dimension includes comprehensive cost and risk coverage cost. Based on comprehensive cost and risk coverage cost, a cost-benefit coefficient with multi-dimensional coefficient set is obtained after processing.

[0027] Specifically, the calculation logic for the coverage perception coefficient;

[0028] For each geographic grid cell in the reservoir area, the pre-input risk score of the grid is extracted and compared with the preset static risk score threshold. Grid cells with scores higher than the threshold are marked as high-risk grid cells.

[0029] Obtain nodes within deployment scheme S Effective communication range, node identification The high-risk grid cells covered by the effective communication range are integrated, and the high-risk grid cells covered by all nodes are combined to obtain the set of high-risk coverage cells for the current deployment scheme S. ;

[0030] Set up high-risk coverage units and set The spatial coverage of the layout scheme S is obtained by calculating the ratio of the number of grid cells; where the set This represents all high-risk grid cells within the reservoir area;

[0031] Extract the pre-marked key points of each group of reservoirs; for each node in the deployment scheme S... The signal strength at the key point P in the reservoir is obtained.

[0032] Summarize the signal intensity sequence of all nodes at key point P, and extract the maximum value as the optimal signal intensity of the key point;

[0033] The best signal strength is compared with the preset signal strength threshold. If the best signal strength of key point P is higher than the signal strength threshold, it means that key point P has high-quality coverage.

[0034] After comparing the best signal strength of all key points, the number of key points with high-quality coverage is counted, and their proportion in the total number of key points is calculated as the coverage of key parts.

[0035] Extract the spatial coverage and key area coverage of deployment scheme S, and output the coverage perception coefficient of deployment scheme S after comprehensive processing.

[0036] Specifically, the calculation logic for the data timeliness coefficient;

[0037] For each link in the communication link set of deployment scheme S, Latency is divided into transmission latency and processing latency;

[0038] Transmission delay Through formula The calculation yielded the result, where Let be the physical distance of the j-th link segment on the path of the i-th sensor. Let j be the signal propagation speed of the j-th link segment. Let J be the average queuing delay of the j-th link segment;

[0039] Each link The processing time of each node is statistically analyzed and summed to obtain the processing latency;

[0040] Each link After summing the transmission delay and processing delay, for each link The summed values ​​are averaged to obtain the overall average delay of deployment scheme S.

[0041] Predefine the flow matrix for all sensors during peak flood periods;

[0042] Based on the routing strategy, the traffic of each node is loaded onto the network topology, and the routing path for each link is calculated. The aggregated traffic that needs to be carried; that is, by comparing the average packet size with the link The result is obtained by multiplying the packet arrival rates;

[0043] For each link The link utilization rate is obtained by calculating the ratio of aggregated traffic to the designed bandwidth.

[0044] Traverse each link The highest link utilization rate is identified as the throughput evaluation value of deployment scheme S;

[0045] Extract the overall average latency and throughput evaluation values ​​of deployment scheme S, and output the data timeliness coefficient of deployment scheme S after comprehensive processing.

[0046] Specifically, the calculation logic for the cost-benefit ratio;

[0047] Extract the estimated total cost from deployment plan S as the comprehensive cost;

[0048] The pre-input risk scores of all covered grid cells in deployment scheme S are summarized and summed to obtain the total risk coverage score of deployment scheme S.

[0049] Divide the total cost of deployment plan S by the total risk coverage score to obtain the risk coverage cost;

[0050] Extract the overall cost and risk coverage cost of deployment scheme S, and output the cost-benefit coefficient of deployment scheme S after comprehensive processing.

[0051] Specifically, in step S4, a comprehensive performance index is generated for each solution;

[0052] The coverage perception coefficient, data timeliness coefficient, and cost-effectiveness coefficient are extracted from the multi-dimensional coefficients of deployment scheme S, and after normalization, they are labeled as follows: ;

[0053] Using formula After comprehensive processing, the overall efficiency index of deployment scheme S is output. ;in The weighting coefficients are set, and + + =1; g is a preset natural constant, and is greater than 1.

[0054] Specifically, in step S5, users can adjust the weights of the multi-dimensional coefficient set based on the project focus, and then output the comprehensive performance index of all deployment schemes after adjusting the weights, and update the visual evaluation report to provide feedback to the user.

[0055] The technical effects and advantages of this invention are as follows:

[0056] (1) By constructing a reservoir geographic grid model and pre-calculating static environmental parameters, an objective and unified data base was established for the assessment. A quantifiable indicator system covering three dimensions of monitoring and perception, data timeliness, and cost-effectiveness was created. Precise calculation logic was defined for each dimension. Different deployment schemes were transformed into a set of calculable coefficients. Finally, a comprehensive and comparable comprehensive efficiency index was generated through weighted fusion. This achieved a quantitative ranking of the merits of the schemes, greatly reduced the subjectivity and arbitrariness of decision-making, and made the scheme comparison based on evidence and scientifically transparent.

[0057] (2) By supporting users to adjust the weights according to the project focus, we can avoid the waste of resources caused by excessive pursuit of coverage, and also prevent the sacrifice of monitoring performance by compressing costs. This provides an adaptation solution for reservoir monitoring projects with different needs, and achieves optimal resource allocation and maximized monitoring efficiency. Attached Figure Description

[0058] Figure 1 This is a flowchart of a reservoir safety monitoring method based on edge computing according to the present invention. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] like Figure 1 As shown, a reservoir safety monitoring method based on edge computing includes:

[0061] Constructing a reservoir environmental parameter database: Based on the reservoir digital elevation model (DEM), administrative divisions, and engineering structure, the reservoir area is divided into geographic grids, a high-precision geographic grid model is constructed, and a set of static environmental parameters is pre-calculated and stored for each geographic grid unit;

[0062] Static environmental parameters include terrain parameters (pre-marked key points, elevation, slope, and undulation), engineering proximity parameters (distance to key structures such as dams and spillways), grid pre-input risk scores (static risk scores set by experts based on geology and hydrology within the grid area), and communication environmental parameters (simulated wireless signal strength index and wired access feasibility indicators).

[0063] Input edge node deployment candidate schemes: Deployment schemes are defined as follows: ;

[0064] N: The set of nodes to be deployed, each node It includes its geographic coordinates, node type (e.g., full-function aggregation node, lightweight acquisition node, relay node) and hardware configuration (computing power, storage capacity, communication interface type, power supply type); where i is the node number;

[0065] L: The set of planned communication links between nodes, each link Define the node pairs it connects to and the planned communication technology (e.g., fiber optic, 5G, LoRa). j is the link number;

[0066] Perform multi-dimensional quantitative evaluation and analysis: Overlay the deployment scheme S with static environmental parameters, output multi-dimensional evaluation parameters through simulation calculation, and construct a multi-dimensional coefficient set after processing the multi-dimensional evaluation parameters using pre-edited processing logic;

[0067] The multi-dimensional evaluation parameters include monitoring coverage and perception quality, data flow timeliness, and cost-benefit analysis.

[0068] The dimensions of monitoring coverage and perceived quality include spatial coverage and coverage of key areas;

[0069] Based on spatial coverage and coverage of key areas, the coverage perception coefficients are obtained after processing, which are a multi-dimensional coefficient set.

[0070] Specifically:

[0071] For each geographic grid cell in the reservoir area, the pre-input risk score of the grid is extracted and compared with the preset static risk score threshold. Grid cells with scores higher than the threshold are marked as high-risk grid cells.

[0072] Obtain nodes within deployment scheme S Effective communication range, node identification The high-risk grid cells covered by the effective communication range are integrated, and the high-risk grid cells covered by all nodes are combined to obtain the set of high-risk coverage cells for the current deployment scheme S. ;

[0073] Additional explanation: When conducting high-risk coverage unit aggregation... During integration, identical grids are removed. That is, if two groups of nodes cover the same high-risk grid cell, one group is retained after deduplication to avoid duplicates in subsequent statistical counts.

[0074] Set up high-risk coverage units and set The spatial coverage of the layout scheme S is obtained by calculating the ratio of the number of grid cells; where the set This represents all high-risk grid cells within the reservoir area;

[0075] Ideally, spatial coverage is 100%, with all high-risk areas within the monitoring network.

[0076] Low spatial coverage indicates the existence of high-risk "monitoring blind spots," and the priority of the assessment plan should be reduced.

[0077] Extract pre-marked key points of each reservoir from the terrain parameters; such as key parts such as the dam crest, spillway inlet, and high-risk landslide points.

[0078] For each node in the deployment scheme S , obtain the signal strength at the key point P in the reservoir; P is the number of the key point;

[0079] The signal strength calculation logic is performed using the logarithmic distance path loss model as an example:

[0080] Calculate the spatial straight-line distance d between the node and the key point:

[0081] ;in( , , ) represents the node coordinates, ( , , () represents the coordinates of the key points;

[0082] Calculate path loss based on d: ;in This is the set reference distance; This represents the path loss during propagation at the reference distance; if d < Then directly take d. .

[0083] Then node Signal strength at key point P in the reservoir ;in For the receiving antenna gain of the key point monitoring equipment, Inherent losses (such as cable losses and equipment interface losses). This refers to the transmit power of the edge node, which is the original power of the node's signal transmission source. This represents the transmit antenna gain of the edge node.

[0084] Summarize the signal intensity sequence of all nodes at key point P, and extract the maximum value as the optimal signal intensity of the key point;

[0085] The optimal signal strength is compared with the preset signal strength threshold. If the optimal signal strength of key point P is higher than the signal strength threshold, it means that key point P has high-quality coverage, indicating that high-quality signals can be obtained at key point.

[0086] After comparing the best signal strength of all key points, the number of key points with high-quality coverage is counted, and their proportion in the total number of key points is calculated as the coverage of key parts.

[0087] Extract the spatial coverage and key area coverage of deployment scheme S, and output the coverage perception coefficient of deployment scheme S after comprehensive processing.

[0088] This involves setting weighting coefficients for spatial coverage and key area coverage, multiplying the spatial coverage and key area coverage by their respective weighting coefficients, and then summing them to obtain the coverage perception coefficient.

[0089] Data stream timeliness dimensions include overall average latency and throughput assessment values;

[0090] Based on the overall average latency and throughput evaluation values, the data timeliness coefficient is obtained after processing through a multi-dimensional coefficient set.

[0091] Establish the affiliation of each sensor: determine the corresponding edge node (i.e. the direct communication node of the sensor) and the networking path from the edge node to the aggregation center (such as edge node → regional gateway → aggregation center, or edge node directly connected to the aggregation center), forming a complete "sensor-edge node-aggregation center" transmission link topology.

[0092] For each link in the communication link set of deployment scheme S, Latency is divided into transmission latency and processing latency;

[0093] Transmission delay Through formula The calculation yielded the result, where Let be the physical distance of the j-th link segment on the path of the i-th sensor. Let j be the signal propagation speed of the j-th link segment. The average queuing delay of the j-th link segment is estimated through simulation or a link utilization model. For example, the queuing delay corresponding to the link utilization u is... , This refers to the data packet transmission duration.

[0094] Each link The processing time of each node is statistically analyzed and summed to obtain the processing latency;

[0095] Each link After summing the transmission delay and processing delay, for each link The summed values ​​are averaged to obtain the overall average delay of deployment scheme S.

[0096] Predefine the flow matrix for all sensors during peak flood periods;

[0097] Based on the routing strategy, the traffic of each node is loaded onto the network topology, and the routing path for each link is calculated. The aggregated traffic that needs to be carried; that is, by comparing the average packet size with the link The result is obtained by multiplying the packet arrival rates; where the link... The data packet arrival rate is an estimated or measured value during peak periods;

[0098] For each link The link utilization rate is obtained by calculating the ratio of aggregated traffic to the designed bandwidth.

[0099] Record the design bandwidth of all communication links in the scheme, and clarify the carrying capacity of each link (e.g., a gateway link needs to carry forwarded data from 3 edge nodes).

[0100] Traverse each link The highest link utilization rate is identified as the throughput evaluation value of deployment scheme S;

[0101] Additional note: A throughput assessment value of <1 indicates that the network bandwidth has a margin of safety even during peak periods.

[0102] Throughput assessment value ≈ 1: The bandwidth just meets the peak demand, with no waste but also no buffering, and traffic needs to be strictly controlled;

[0103] Throughput assessment value > 1: A bottleneck exists, the link will be overloaded, resulting in severe queuing delay and packet loss.

[0104] Extract the overall average latency and throughput evaluation values ​​of deployment scheme S, and output the data timeliness coefficient of deployment scheme S after comprehensive processing;

[0105] That is, after normalizing the overall average latency and throughput evaluation values, the overall average latency and throughput evaluation values ​​are multiplied by the corresponding weight coefficients, and then summed to obtain the coverage perception coefficient.

[0106] The overall cost-benefit dimension includes total cost and risk coverage cost;

[0107] Based on the comprehensive cost and risk coverage cost, a cost-benefit coefficient with a multi-dimensional coefficient set is obtained after processing.

[0108] The estimated total cost is extracted from deployment plan S as the comprehensive cost; the estimated total cost is the deployment cost (hardware, installation, civil engineering) and operation and maintenance cost (energy, communication fees) for each node; the operation and maintenance cost is estimated according to the operation and maintenance period;

[0109] The cost covers the hardware procurement, on-site installation, and supporting civil engineering of the nodes, as well as subsequent energy consumption, communication fees, equipment maintenance, etc., but does not include the overall construction cost of the aggregation center and cloud platform (only for individual edge nodes).

[0110] The annual operation and maintenance cost is calculated in "calendar year". If the full life cycle cost needs to be calculated, the cycle can be extended according to the design life of each node (such as 5-8 years).

[0111] The pre-input risk scores of all covered grid cells in deployment scheme S are summarized and summed to obtain the total risk coverage score of deployment scheme S.

[0112] Divide the total cost of deployment plan S by the total risk coverage score to obtain the risk coverage cost;

[0113] Extract the overall cost and risk coverage cost of deployment scheme S, and output the cost-benefit coefficient of deployment scheme S after comprehensive processing;

[0114] That is, after normalizing the comprehensive cost and risk coverage cost, the comprehensive cost and risk coverage cost are multiplied by the corresponding weighting coefficients, and then summed to obtain the cost-benefit coefficient.

[0115] Generate a visual evaluation report: After comprehensively processing the multi-dimensional coefficient set using weighted fusion logic, a comprehensive performance index is generated for each solution; the weights can be configured by the user according to the project's priorities (such as greater security or greater cost). Based on the comprehensive performance index, the ranking results of all deployment solutions are output, and then input into a pre-edited report template to generate a visual evaluation report;

[0116] Specifically:

[0117] The coverage perception coefficient, data timeliness coefficient, and cost-effectiveness coefficient are extracted from the multi-dimensional coefficients of deployment scheme S, and after normalization, they are labeled as follows: ;

[0118] Using formula After comprehensive processing, the overall efficiency index of deployment scheme S is output. ;in The weighting coefficients are set, and + + =1; g is a preset natural constant, and is greater than 1.

[0119] Traditional deployment scheme evaluation relies heavily on experience-based judgment, which suffers from strong subjectivity and inconsistent standards. The comprehensive effectiveness index normalizes and weights the indicators of the three core dimensions of coverage perception, data timeliness, and cost-effectiveness, transforming the qualitative merits of the scheme into quantitative numerical results, and providing a unified comparison benchmark for different deployment schemes (such as schemes with different numbers of nodes and different network topologies).

[0120] For example, Option A may have a high coverage perception coefficient but a low cost-effectiveness coefficient, while Option S or Option S may have outstanding data timeliness but have blind spots in coverage. The comprehensive effectiveness index can be used to intuitively sort the options, helping decision-makers to quickly identify the optimal option for Option S that balances safety and cost or Option S that prioritizes monitoring timeliness, thus avoiding decision-making bias.

[0121] Reservoir monitoring scheme determination: Based on the comprehensive effectiveness index of all deployment schemes, users selectively choose the reservoir monitoring scheme with the highest comprehensive effectiveness index from the visualization evaluation report;

[0122] Users can adjust the weights of the multi-dimensional coefficient set based on the project focus, and then output the comprehensive performance index of all deployment schemes after adjusting the weights, and update the visual evaluation report to provide feedback to the user.

[0123] For example, initially The values ​​are set to 0.4, 0.3, and 0.3 respectively. If the user needs to focus on cost, the values ​​can be adjusted to 0.3, 0.3, and 0.4. The specific values ​​are based on user customization.

[0124] The above formulas are all dimensionless calculations. Dimensionless calculations can be performed using various methods such as standardization, which will not be elaborated here. The formulas are derived from software simulations based on a large amount of collected data, and the preset parameters in the formulas can be set by those skilled in the art according to the actual situation.

[0125] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, ATA hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0126] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply 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 embodiments of this application.

[0127] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0131] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable ATA hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A reservoir safety monitoring method based on edge computing, characterized in that, include: S1: Divide the reservoir area into geographic grids, construct a high-precision geographic grid model, and pre-calculate and store a set of static environmental parameters for each geographic grid unit; Static environmental parameters include pre-marked key points and pre-input risk scores for the mesh; S2: Deployment scheme is defined as ; S3: Overlay the deployment scheme S with the static environmental parameters for analysis. Through simulation calculation, output multi-dimensional evaluation parameters. After processing the multi-dimensional evaluation parameters using pre-edited processing logic, construct a multi-dimensional coefficient set. S4: After comprehensively processing the multi-dimensional coefficient set using weighted fusion logic, a comprehensive performance index is generated for each scheme; after outputting the ranking results of all deployment schemes based on the comprehensive performance index, the results are input into a pre-edited report template to generate a visual evaluation report; S5: Based on the comprehensive effectiveness index of all deployment schemes, select the scheme with the highest comprehensive effectiveness index from the visualization evaluation report as the reservoir monitoring scheme.

2. The reservoir safety monitoring method based on edge computing according to claim 1, characterized in that: The specific definition logic of the S2 deployment scheme; N: The set of nodes to be deployed, each node Includes its geographic coordinates and node type; Where i is the node number; L: The set of planned communication links between nodes, each link Define the node it connects to, where j is the link number.

3. The reservoir safety monitoring method based on edge computing according to claim 1, characterized in that: The multi-dimensional evaluation parameters in S3 specifically include: The multi-dimensional evaluation parameters include monitoring coverage and perception quality, data flow timeliness, and cost-benefit analysis.

4. The reservoir safety monitoring method based on edge computing according to claim 3, characterized in that: The multi-dimensional coefficient set in S3 specifically includes coverage perception coefficient, data timeliness coefficient, and cost-effectiveness coefficient; The monitoring coverage and perception quality dimensions include spatial coverage and key area coverage. Based on spatial coverage and key area coverage, the coverage perception coefficients are obtained after processing and multi-dimensional coefficient set. The data flow timeliness dimension includes the overall average latency and throughput evaluation value. Based on the overall average latency and throughput evaluation value, the data timeliness coefficient is obtained after processing in a multi-dimensional coefficient set. The cost-benefit comprehensive dimension includes comprehensive cost and risk coverage cost. Based on comprehensive cost and risk coverage cost, a cost-benefit coefficient with multi-dimensional coefficient set is obtained after processing.

5. The reservoir safety monitoring method based on edge computing according to claim 4, characterized in that: The specific calculation logic of the coverage perception coefficient; For each geographic grid cell in the reservoir area, the pre-input risk score of the grid is extracted and compared with the preset static risk score threshold. Grid cells with scores higher than the threshold are marked as high-risk grid cells. Obtain nodes within deployment scheme S Effective communication range, node identification The high-risk grid cells covered by the effective communication range are integrated, and the high-risk grid cells covered by all nodes are combined to obtain the set of high-risk coverage cells for the current deployment scheme S. ; Set up high-risk coverage units and set The spatial coverage of the layout scheme S is obtained by calculating the ratio of the number of grid cells; where the set This represents all high-risk grid cells within the reservoir area; Extract the pre-marked key points of each group of reservoirs; For each node in the deployment scheme S The signal strength at the key point P in the reservoir is obtained. Summarize the signal intensity sequence of all nodes at key point P, and extract the maximum value as the optimal signal intensity of the key point; The best signal strength is compared with the preset signal strength threshold. If the best signal strength of key point P is higher than the signal strength threshold, it means that key point P has high-quality coverage. After comparing the best signal strength of all key points, the number of key points with high-quality coverage is counted, and their proportion in the total number of key points is calculated as the coverage of key parts. Extract the spatial coverage and key area coverage of deployment scheme S, and output the coverage perception coefficient of deployment scheme S after comprehensive processing.

6. The reservoir safety monitoring method based on edge computing according to claim 4, characterized in that: The specific calculation logic of the data timeliness coefficient; For each link in the communication link set of deployment scheme S, Latency is divided into transmission latency and processing latency; Transmission delay Through formula The calculation yielded the result, where Let be the physical distance of the j-th link segment on the path of the i-th sensor. Let j be the signal propagation speed of the j-th link segment. Let J be the average queuing delay of the j-th link segment; Each link The processing time of each node is statistically analyzed and summed to obtain the processing latency; Each link After summing the transmission delay and processing delay, for each link The summed values ​​are averaged to obtain the overall average delay of deployment scheme S. Predefine the flow matrix for all sensors during peak flood periods; Based on the routing strategy, the traffic of each node is loaded onto the network topology, and the routing path for each link is calculated. The aggregated traffic that needs to be carried; that is, by comparing the average packet size with the link The result is obtained by multiplying the packet arrival rates; For each link The link utilization rate is obtained by calculating the ratio of aggregated traffic to the designed bandwidth. Traverse each link The highest link utilization rate is identified as the throughput evaluation value of deployment scheme S; Extract the overall average latency and throughput evaluation values ​​of deployment scheme S, and output the data timeliness coefficient of deployment scheme S after comprehensive processing.

7. The reservoir safety monitoring method based on edge computing according to claim 4, characterized in that: The specific calculation logic of the cost-benefit ratio; Extract the estimated total cost from deployment plan S as the comprehensive cost; The pre-input risk scores of all covered grid cells in deployment scheme S are summarized and summed to obtain the total risk coverage score of deployment scheme S. Divide the total cost of deployment plan S by the total risk coverage score to obtain the risk coverage cost; Extract the overall cost and risk coverage cost of deployment scheme S, and output the cost-benefit coefficient of deployment scheme S after comprehensive processing.

8. The reservoir safety monitoring method based on edge computing according to claim 4, characterized in that: In step S4, a comprehensive performance index is generated for each scheme; The coverage perception coefficient, data timeliness coefficient, and cost-effectiveness coefficient are extracted from the multi-dimensional coefficients of deployment scheme S, and after normalization, they are labeled as follows: ; Using formula After comprehensive processing, the overall performance index of deployment scheme S is output. ;in The weighting coefficients are set, and + + =1; g is a preset natural constant, and is greater than 1.

9. The reservoir safety monitoring method based on edge computing according to claim 1, characterized in that: In step S5, users can adjust the weights of the multi-dimensional coefficient set based on the project focus, and then output the comprehensive performance index of all deployment schemes after adjusting the weights, and update the visual evaluation report to provide feedback to the user.

Images