Electric power engineering construction state real-time monitoring method, system, equipment and medium

Abstract

The invention relates to the technical field of power construction monitoring. The invention provides an electric power engineering construction state real-time monitoring method, system and device and a medium, and the method comprises the steps: collecting the load state and communication delay data of each node through an edge computing node network, and generating node load state data and a communication delay distribution map; calculating a time sequence compensation parameter according to the communication delay distribution map, and generating a time sequence synchronization data stream; task scheduling is executed based on the dynamic resource pre-allocation strategy and the time sequence synchronization data flow, and an optimized resource allocation strategy is generated; and according to the optimized resource allocation strategy and the construction state monitoring data, generating a collaborative efficiency evaluation result, so as to solve the problems of resource overload, data time sequence deviation accumulation and collaborative control failure, and improve the construction efficiency and the data synchronization precision.

Description

Technical Field

[0001] This invention relates to the field of power construction monitoring technology, and in particular to a method, system, equipment and medium for real-time monitoring of the construction status of power engineering projects. Background Technology

[0002] With the rapid development of smart grids and new power facilities, the complexity and safety requirements of power engineering construction are increasing. Real-time monitoring technology of construction status, as a core means to ensure project efficiency and prevent equipment failures, has become a key link in the intelligent transformation of power engineering.

[0003] However, the relevant power engineering monitoring technologies have the following problems: centralized resource allocation methods rely on static task priority division, which cannot respond to dynamic load changes at key construction nodes, leading to resource overload and task scheduling failure at high-load nodes; communication delay compensation mechanisms do not integrate dynamic modeling of time-series distribution characteristics, resulting in the accumulation of time-series deviations between vibration signals and hoisting operation data; and the monitoring system lacks a closed-loop feedback mechanism for resource strategies and efficiency, making it difficult to achieve adaptive collaborative optimization of the construction process. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, system, equipment and medium for real-time monitoring of the construction status of power engineering to address the above-mentioned technical problems, so as to solve the problems of resource overload, data timing deviation accumulation and collaborative control failure, and improve construction efficiency and data synchronization accuracy.

[0005] Firstly, this application provides a method for real-time monitoring of the construction status of power engineering projects, the method comprising:

[0006] By collecting load status and communication latency data of each node through the edge computing node network, node load status data and communication latency distribution map are generated;

[0007] Based on node load status data and the priority of tasks at key nodes in the construction phase, a dynamic resource pre-allocation strategy is generated.

[0008] Calculate timing compensation parameters based on the communication delay distribution map, and generate a timing synchronization data stream;

[0009] Based on the dynamic resource pre-allocation strategy and the time-series synchronized data stream, task scheduling is performed to generate an optimized resource allocation strategy;

[0010] Based on the optimized resource allocation strategy and construction status monitoring data, a collaborative efficiency assessment result is generated and fed back to the edge computing node network. The construction status monitoring data includes vibration signal data, hoisting operation record data, and environmental monitoring data.

[0011] Furthermore, based on node load status data and the prioritization of tasks at key nodes during the construction phase, a dynamic resource pre-allocation strategy is generated, including:

[0012] Identify the key node types in the current construction phase and generate a priority task list based on construction schedule constraints;

[0013] First-level load nodes are selected based on node load status data, and a mapping relationship between first-level load nodes and priority tasks is established to generate an initial resource pre-allocation strategy.

[0014] Based on the dynamic changes of key nodes in the construction phase, conflict prediction and handling are performed on the initial resource pre-allocation strategy to generate a dynamic resource pre-allocation strategy.

[0015] Furthermore, identify the key node types in the current construction phase, and generate a priority task list based on construction schedule constraints, including:

[0016] Based on the construction phase division model, identify the key node types of the current construction phase and generate key node type labels;

[0017] Obtain construction schedule constraints, perform conflict detection and handling between key node type labels and construction schedule constraints, and generate dynamic weight adjustment parameters.

[0018] The key nodes are prioritized based on the dynamic weight adjustment parameters to generate a priority task list.

[0019] Furthermore, based on the optimized resource allocation strategy and construction status monitoring data, a collaborative performance evaluation result is generated and fed back to the edge computing node network, including:

[0020] Collect task completion time, resource utilization rate and time sequence alignment error data corresponding to the optimized resource allocation strategy, perform multi-dimensional performance fusion processing, and generate collaborative performance evaluation indicators.

[0021] Root cause analysis is performed on parameters in the collaborative effectiveness evaluation indicators that do not reach the preset threshold, and optimization suggestion data is generated.

[0022] The optimization suggestions are fed back to the node load level label generation module and the time series compensation parameter calculation module. Based on the optimization suggestions, the node load level classification rules and the time series compensation parameter calculation logic are dynamically adjusted, triggering dynamic updates of the parameters of the edge computing node network.

[0023] Furthermore, for parameters in the collaborative effectiveness evaluation indicators that fail to reach the preset threshold, root cause analysis is performed to generate optimization suggestion data, including:

[0024] The collaborative effectiveness evaluation indicators are classified according to the preset effectiveness threshold, and parameter deviation types are generated.

[0025] A construction phase correlation analysis was performed on the resource utilization deviation item in the parameter deviation type to generate resource allocation optimization suggestions;

[0026] Perform a compensation parameter correlation analysis on the timing alignment error deviation item in the parameter deviation type to generate timing compensation optimization suggestions;

[0027] Integrate resource allocation optimization suggestions with time-series compensation optimization suggestions to generate optimization suggestion data.

[0028] Furthermore, timing compensation parameters are calculated based on the communication delay distribution map to generate a timing synchronization data stream, including:

[0029] Delay distribution density features are extracted from the communication delay distribution map, and offset correction is performed on the delay distribution density features based on the dynamic characteristics of the construction scenario to generate dynamic time-series offsets.

[0030] By superimposing construction scenario weight parameters on dynamic temporal offsets, multimodal temporal compensation parameters are generated.

[0031] Multimodal time-series compensation parameters are loaded onto the vibration signal data and hoisting operation record data in the construction status monitoring data, respectively, and a time-series synchronous data stream is generated through segmented interpolation correction processing.

[0032] Furthermore, by collecting load status and communication latency data of each node through the edge computing node network, node load status data and communication latency distribution maps are generated, including:

[0033] Data on GPU utilization, memory usage, and task queue length are collected by edge nodes deployed at the tower base, hoisting area, and control room.

[0034] The GPU utilization, memory usage and task queue length data are classified and aggregated to generate node load status data, which includes three load level labels.

[0035] The system measures the data transmission delay between nodes, performs distribution density analysis based on the delay time, and generates a communication delay distribution map.

[0036] Secondly, this application also provides a real-time monitoring system for the construction status of power engineering projects, the system comprising:

[0037] The data mapping module is used to collect load status and communication latency data of each node through the edge computing node network, and generate node load status data and communication latency distribution maps.

[0038] The dynamic pre-allocation module is used to prioritize tasks based on node load status data and key nodes in the construction phase, and generate dynamic resource pre-allocation strategies.

[0039] The timing compensation module is used to calculate timing compensation parameters based on the communication delay distribution map and generate a timing synchronization data stream;

[0040] The scheduling optimization module is used to perform task scheduling based on dynamic resource pre-allocation strategy and time-series synchronous data stream, and generate an optimized resource allocation strategy.

[0041] The performance feedback module is used to generate collaborative performance evaluation results based on the optimized resource allocation strategy and construction status monitoring data, and to feed the collaborative performance evaluation results back to the edge computing node network. The construction status monitoring data includes vibration signal data, hoisting operation record data and environmental monitoring data.

[0042] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods in the first aspect of this application.

[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods in the first aspect of this application.

[0044] The technical solution provided in this application includes the following technical effects: It provides a method, system, equipment, and medium for real-time monitoring of the construction status of power engineering projects. The method includes: collecting load status and communication delay data of each node through an edge computing node network to generate node load status data and communication delay distribution maps; prioritizing tasks based on node load status data and key nodes in the construction phase to generate a dynamic resource pre-allocation strategy; calculating timing compensation parameters based on the communication delay distribution map to generate a timing synchronization data stream; executing task scheduling based on the dynamic resource pre-allocation strategy and the timing synchronization data stream to generate an optimized resource allocation strategy; generating a collaborative efficiency evaluation result based on the optimized resource allocation strategy and construction status monitoring data, and feeding the collaborative efficiency evaluation result back to the edge computing node network. The construction status monitoring data includes vibration signal data, hoisting operation record data, and environmental monitoring data, to solve problems such as resource overload, accumulation of data timing deviations, and collaborative control failures, thereby improving construction efficiency and data synchronization accuracy. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A flowchart of a method for real-time monitoring of the construction status of a power engineering project, as described in one embodiment of the present invention;

[0047] Figure 2 A flowchart of a dynamic resource pre-allocation strategy based on node load status data and key nodes in the construction phase, in one embodiment of the present invention;

[0048] Figure 3 This is a structural diagram of a real-time monitoring system for the construction status of a power engineering project, according to one embodiment of the present invention. Detailed Implementation

[0049] To make the above-mentioned objects, features, and advantages of this application more apparent and understandable, the specific implementation methods of this application will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0050] like Figure 1 As shown, this application provides a method for real-time monitoring of the construction status of power engineering projects, the method comprising:

[0051] S101: Collect load status and communication latency data of each node through the edge computing node network, and generate node load status data and communication latency distribution map.

[0052] Specifically, data is collected through a constructed network of edge computing nodes. This includes each node in the edge computing node network collecting its own load status information and communication latency data between nodes. The load status information covers multi-dimensional data such as the usage of computing resources, the occupancy of storage resources, and the length of task processing queues, to comprehensively reflect the node's operating load status; the communication latency data is obtained by measuring the time required for data transmission between different nodes, and is used to analyze the communication efficiency and latency characteristics between nodes.

[0053] Subsequently, the collected load status data is classified and aggregated to generate node load status data that can characterize the load level of each node. At the same time, based on the communication delay data, a distribution density analysis is performed to generate a communication delay distribution map that intuitively shows the communication delay between nodes, providing basic data support and basis for subsequent resource allocation and task scheduling.

[0054] S102: Based on node load status data and the priority of tasks for key nodes in the construction phase, a dynamic resource pre-allocation strategy is generated.

[0055] Specifically, this involves in-depth analysis of node load status data, combined with the identification and segmentation of key nodes in the current power engineering construction phase. By assessing the importance and urgency of each key node in the current construction progress, the priority order of tasks is determined. Based on the load capacity of the nodes, high-priority tasks are rationally allocated to nodes with stronger load capacity, generating an initial resource pre-allocation plan. Subsequently, based on the dynamic changes of key nodes during construction, the initial plan is adjusted and optimized to ensure that resource allocation can adapt to real-time changes in the construction phase, generating a dynamic resource pre-allocation strategy to achieve efficient resource utilization and rational task scheduling, thereby improving the collaborative efficiency of power engineering construction.

[0056] S103: Calculate timing compensation parameters based on the communication delay distribution map and generate a timing synchronization data stream.

[0057] Specifically, the density features of the delay distribution are extracted from the communication delay distribution map, reflecting the distribution of communication delay across different nodes. Based on the dynamic characteristics of power engineering construction scenarios, the extracted delay distribution density features are subjected to offset correction processing to generate dynamic time-series offsets to adapt to changes in communication delay during construction. These dynamic time-series offsets are combined with weight parameters of the construction scenario to generate multimodal time-series compensation parameters, which integrate the importance of communication delay and the construction scenario. Subsequently, these multimodal time-series compensation parameters are applied to vibration signal data and hoisting operation record data from construction status monitoring data. Through piecewise interpolation correction processing, time-series compensation is performed on these data to generate a time-synchronized data stream, ensuring data consistency and accuracy across different nodes.

[0058] S104: Based on the dynamic resource pre-allocation strategy and the time-series synchronous data stream, execute task scheduling to generate an optimized resource allocation strategy.

[0059] Specifically, the initial resource allocation for each task is determined based on a dynamic resource pre-allocation strategy, clarifying the tasks each node is responsible for executing and the corresponding resource allocation. Simultaneously, by combining time-series synchronized data streams, the order and timing of task execution are ensured to match the communication latency characteristics, avoiding task execution chaos or resource waste due to timing issues.

[0060] During task scheduling, the task execution status and resource usage of each node are monitored in real time. The initial resource allocation is dynamically adjusted based on the actual execution progress and changes in demand. For example, if the task execution progress of a node is ahead of schedule or delayed, or if there are temporary peaks or troughs in resource usage, resources are promptly allocated from nodes with sufficient resources to nodes with limited resources, ensuring that all tasks can be executed smoothly and efficiently.

[0061] Given the unique and uncertain nature of power engineering construction, an emergency resource allocation mechanism is established. In the event of emergencies or abnormal events, resources are rapidly reallocated to prioritize the execution of critical tasks while minimizing the impact on other tasks. This generates a more rational, efficient, and adaptive optimized resource allocation strategy within complex construction environments, thereby improving the overall collaborative efficiency and resource utilization of the power engineering construction process.

[0062] S105: Based on the optimized resource allocation strategy and construction status monitoring data, generate collaborative efficiency evaluation results and feed them back to the edge computing node network. Construction status monitoring data includes vibration signal data, hoisting operation record data, and environmental monitoring data.

[0063] Specifically, the optimized resource allocation strategy is combined with construction status monitoring data. This data encompasses multi-dimensional information, including vibration signal data, hoisting operation records, and environmental monitoring data. Through comprehensive analysis of this data, the execution status and resource utilization efficiency of each stage of the construction process are evaluated, generating a collaborative effectiveness evaluation index. This index reflects the rationality of resource use, task execution efficiency, and the degree of collaboration between different stages during the construction process from multiple perspectives.

[0064] Subsequently, a thorough root cause analysis was conducted on parameters that failed to meet the preset performance standards to identify the specific reasons for insufficient performance. Based on the root cause analysis results, targeted optimization suggestions were generated to guide subsequent resource allocation and task scheduling adjustments. These optimization suggestions were then fed back to relevant modules in the edge computing node network, such as the node load level label generation module and the time-series compensation parameter calculation module, to dynamically adjust the node load level classification rules and time-series compensation parameter calculation logic according to the suggestions, thereby achieving continuous optimization and improvement of the construction process.

[0065] One embodiment of this application provides a method for real-time monitoring of the construction status of power engineering projects, comprising: collecting load status and communication delay data of each node through an edge computing node network to generate node load status data and communication delay distribution maps; prioritizing tasks based on node load status data and key nodes in the construction phase to generate a dynamic resource pre-allocation strategy; calculating timing compensation parameters according to the communication delay distribution map to generate a timing synchronization data stream; executing task scheduling based on the dynamic resource pre-allocation strategy and the timing synchronization data stream to generate an optimized resource allocation strategy; generating a collaborative performance evaluation result based on the optimized resource allocation strategy and construction status monitoring data, and feeding the collaborative performance evaluation result back to the edge computing node network. The construction status monitoring data includes vibration signal data, hoisting operation record data, and environmental monitoring data to solve problems such as resource overload, accumulation of data timing deviations, and collaborative control failures, thereby improving construction efficiency and data synchronization accuracy.

[0066] like Figure 2 As shown, based on node load status data and the prioritization of tasks at key nodes during the construction phase, a dynamic resource pre-allocation strategy is generated, including:

[0067] S201: Identify the key node types in the current construction phase and generate a priority task list based on construction schedule constraints;

[0068] S202: Filter first-level load nodes based on node load status data, establish a mapping relationship between first-level load nodes and priority tasks, and generate an initial resource pre-allocation strategy;

[0069] S203: Based on the dynamic changes of key nodes in the construction phase, conflict prediction and processing are performed on the initial resource pre-allocation strategy to generate a dynamic resource pre-allocation strategy.

[0070] Specifically, the key node types of the current construction stage are identified through a construction phase segmentation model, generating corresponding key node type labels. Conflict detection processing is then performed on these labels in conjunction with construction schedule constraints, generating dynamic weight adjustment parameters. These parameters are then used to prioritize key nodes, generating a priority task list. Based on node load status data, nodes meeting the first-level load standard are selected, and a mapping relationship is established between these first-level load nodes and priority tasks, generating an initial resource pre-allocation strategy. Based on the dynamic changing characteristics of key nodes in the construction stage, conflict prediction processing is performed on the initial resource pre-allocation strategy to identify and resolve existing resource allocation conflicts, generating a dynamic resource pre-allocation strategy to ensure that resource allocation can adapt to the dynamic changes in the construction process.

[0071] Furthermore, identify the key node types in the current construction phase, and generate a priority task list based on construction schedule constraints, including:

[0072] Based on the construction phase division model, identify the key node types of the current construction phase and generate key node type labels;

[0073] Obtain construction schedule constraints, perform conflict detection and handling between key node type labels and construction schedule constraints, and generate dynamic weight adjustment parameters.

[0074] The key nodes are prioritized based on the dynamic weight adjustment parameters to generate a priority task list.

[0075] Specifically, the current construction phase is identified using a construction phase segmentation model, key node types are extracted, and corresponding labels are generated for each key node type to facilitate subsequent processing and differentiation. Next, construction schedule constraints are obtained, including time limits, task dependencies, and resource availability limitations. The extracted key node type labels are cross-referenced with the construction schedule constraints, and conflict detection is performed to identify potential conflict points. Based on the severity and scope of the conflicts, dynamic weight adjustment parameters are generated, reflecting the relative importance and urgency of each key node under the current construction schedule. Based on these dynamic weight adjustment parameters, a specific ranking algorithm is used to prioritize key nodes, ensuring that key nodes with higher weights are given priority in resource allocation and task scheduling. This generates a more reasonable and efficient priority task list, providing scientific guidance for subsequent resource allocation and construction management.

[0076] Furthermore, based on the optimized resource allocation strategy and construction status monitoring data, a collaborative performance evaluation result is generated and fed back to the edge computing node network, including:

[0077] Collect task completion time, resource utilization rate and time sequence alignment error data corresponding to the optimized resource allocation strategy, perform multi-dimensional performance fusion processing, and generate collaborative performance evaluation indicators.

[0078] Root cause analysis is performed on parameters in the collaborative effectiveness evaluation indicators that do not reach the preset threshold, and optimization suggestion data is generated.

[0079] The optimization suggestions are fed back to the node load level label generation module and the time series compensation parameter calculation module. Based on the optimization suggestions, the node load level classification rules and the time series compensation parameter calculation logic are dynamically adjusted, triggering dynamic updates of the parameters of the edge computing node network.

[0080] Specifically, key data such as task completion time, resource utilization rate, and time-series alignment error corresponding to the optimized resource allocation strategy are obtained. By comprehensively integrating and processing this multi-dimensional data, a collaborative performance evaluation index that comprehensively reflects the effectiveness of construction status monitoring and resource allocation is generated. This evaluation index covers multiple aspects, including task execution efficiency, resource utilization rationality, and data time-series consistency, providing a quantitative basis for subsequent optimization.

[0081] For parameters in the collaborative performance evaluation indicators that failed to meet preset thresholds, a detailed root cause analysis was conducted. These substandard parameters were categorized to identify the fundamental reasons for low performance. Based on the root cause analysis results, specific optimization suggestions were generated, including adjustments to resource allocation, optimization strategies for task scheduling, and improvements to data synchronization.

[0082] Subsequently, the optimization suggestions are fed back to the node load level label generation module and the timing compensation parameter calculation module in the edge computing node network. Based on these suggestions, the node load level classification rules and timing compensation parameter calculation logic are dynamically adjusted to adapt to dynamic changes during construction. This process triggers the dynamic parameter update mechanism of the edge computing node network, continuously optimizing its resource allocation and task scheduling strategies based on real-time feedback, thereby achieving efficient collaboration and continuous optimization in the power engineering construction process.

[0083] Furthermore, for parameters in the collaborative effectiveness evaluation indicators that fail to reach the preset threshold, root cause analysis is performed to generate optimization suggestion data, including:

[0084] The collaborative effectiveness evaluation indicators are classified according to the preset effectiveness threshold, and parameter deviation types are generated.

[0085] A construction phase correlation analysis was performed on the resource utilization deviation item in the parameter deviation type to generate resource allocation optimization suggestions;

[0086] Perform a compensation parameter correlation analysis on the timing alignment error deviation item in the parameter deviation type to generate timing compensation optimization suggestions;

[0087] Integrate resource allocation optimization suggestions with time-series compensation optimization suggestions to generate optimization suggestion data.

[0088] Specifically, collaborative performance evaluation indicators are categorized based on preset performance thresholds to identify the types of parameter deviations. For deviations in resource utilization, their correlation with different construction stages is analyzed in depth. Based on factors such as construction progress, task complexity, and the rationality of resource allocation, optimization suggestions aimed at improving resource utilization efficiency are generated, such as adjusting resource allocation ratios and optimizing task execution order.

[0089] Based on the timing alignment error deviation term, the correlation between compensation parameters and the dynamic characteristics of actual construction scenarios is analyzed. Combining factors such as communication latency, data transmission stability, and construction operation rhythm, optimization suggestions for improving timing synchronization are generated. Subsequently, by integrating resource allocation optimization suggestions and timing compensation optimization suggestions, an optimization suggestion dataset is constructed to ensure that the above suggestions can work synergistically to effectively improve the overall efficiency of power engineering construction status monitoring and resource management, providing a scientific basis for subsequent system optimization and decision adjustments.

[0090] Furthermore, timing compensation parameters are calculated based on the communication delay distribution map to generate a timing synchronization data stream, including:

[0091] Delay distribution density features are extracted from the communication delay distribution map, and offset correction is performed on the delay distribution density features based on the dynamic characteristics of the construction scenario to generate dynamic time-series offsets.

[0092] By superimposing construction scenario weight parameters on dynamic temporal offsets, multimodal temporal compensation parameters are generated.

[0093] Multimodal time-series compensation parameters are loaded onto the vibration signal data and hoisting operation record data in the construction status monitoring data, respectively, and a time-series synchronous data stream is generated through segmented interpolation correction processing.

[0094] Specifically, delay distribution density features are extracted from the communication delay distribution map. These features reflect the concentration trend and distribution of communication delays across different nodes. Based on the dynamic characteristics of power engineering construction scenarios, such as changes in node positions and fluctuations in communication load during construction, the extracted delay distribution density features are subjected to offset correction processing to obtain dynamic time-series offsets, which more accurately reflect the actual communication delay situation.

[0095] By combining dynamic time offset with construction scenario weight parameters, which involve multiple factors such as node importance, task urgency, and communication link stability, a multimodal time compensation parameter is generated by comprehensively considering the above factors. This parameter can provide differentiated time compensation for data streams with different characteristics.

[0096] Subsequently, the aforementioned multimodal time-series compensation parameters were applied to the vibration signal data and hoisting operation record data from the construction status monitoring data, respectively. Since these data have different acquisition frequencies and time-series characteristics, a piecewise interpolation correction method was used to adjust and supplement the data in terms of time sequence, ensuring data consistency and synchronization in the time dimension, generating a time-synchronized data stream, and providing reliable data support for subsequent construction status analysis and decision-making.

[0097] Furthermore, by collecting load status and communication latency data of each node through the edge computing node network, node load status data and communication latency distribution maps are generated, including:

[0098] Data on GPU utilization, memory usage, and task queue length are collected by edge nodes deployed at the tower base, hoisting area, and control room.

[0099] The GPU utilization, memory usage and task queue length data are classified and aggregated to generate node load status data, which includes three load level labels.

[0100] The system measures the data transmission delay between nodes, performs distribution density analysis based on the delay time, and generates a communication delay distribution map.

[0101] Specifically, edge computing nodes are deployed in key areas of power engineering construction sites, such as tower foundations, hoisting areas, and control rooms. These nodes are used to collect key indicator data reflecting the node's load status in real time, including GPU utilization, memory usage, and task queue length. These indicators comprehensively depict the node's load status from three dimensions: computing resource usage, storage resource usage, and task processing load.

[0102] The collected GPU utilization, memory usage, and task queue length data are categorized and aggregated. Based on a preset load level classification standard, the processed data is integrated to generate node load status data with three load level labels, achieving clear classification and identification of the load level of each node.

[0103] Raw communication delay data is obtained by measuring the data transmission delay between nodes. Further, distribution density analysis is performed on this delay data, and statistical analysis methods are used to determine the distribution characteristics of communication delay in different intervals. This generates a communication delay distribution map that visually represents the communication delay between nodes, providing fundamental data support for subsequent timing compensation and task scheduling optimization.

[0104] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0105] In one embodiment, such as Figure 3 As shown, this application also provides a real-time monitoring system 300 for the construction status of power engineering projects, the system 300 comprising:

[0106] The data mapping module 301 is used to collect load status and communication delay data of each node through the edge computing node network, and generate node load status data and communication delay distribution map.

[0107] The dynamic pre-allocation module 302 is used to generate a dynamic resource pre-allocation strategy based on node load status data and the priority of tasks at key nodes in the construction phase.

[0108] Timing compensation module 303 is used to calculate timing compensation parameters based on the communication delay distribution map and generate timing synchronization data stream;

[0109] The scheduling optimization module 304 is used to perform task scheduling based on the dynamic resource pre-allocation strategy and the time-series synchronous data stream, and generate an optimized resource allocation strategy.

[0110] The efficiency feedback module 305 is used to generate collaborative efficiency evaluation results based on the optimized resource allocation strategy and construction status monitoring data, and to feed the collaborative efficiency evaluation results back to the edge computing node network. The construction status monitoring data includes vibration signal data, hoisting operation record data and environmental monitoring data.

[0111] Specifically, the data mapping module 301 collects real-time load status data of each node through edge computing nodes deployed in key locations such as the tower base, hoisting area, and control room. This data includes indicators such as GPU utilization, memory usage, and task queue length. The module then classifies and aggregates this data to generate node load status data with three load level labels. Simultaneously, it measures the data transmission latency between nodes and generates a communication latency distribution map after distribution density analysis, providing basic data support for subsequent modules.

[0112] Based on the aforementioned node load status data and the current key node classification in the construction phase, the dynamic pre-allocation module 302, combined with construction schedule constraints, uses a specific algorithm to identify key node types and generate a priority task list. By filtering nodes that meet the load requirements and establishing a mapping relationship with priority tasks, an initial resource pre-allocation strategy is generated. Furthermore, based on the dynamic changes in key nodes during the construction phase, the initial strategy is subject to conflict prediction and adjustment to generate a dynamic resource pre-allocation strategy, ensuring the rationality and adaptability of resource allocation.

[0113] The timing compensation module 303 uses the communication delay distribution map as a basis, extracts the delay distribution density features, and combines them with the dynamic characteristics of the construction scenario to correct the offset and generate a dynamic timing offset. This offset is combined with the construction scenario weight parameters to generate multimodal timing compensation parameters, which are then loaded into the vibration signal data and hoisting operation record data respectively. Piecewise interpolation correction processing is used to generate a timing synchronization data stream to ensure the timing consistency of the monitoring data.

[0114] The scheduling optimization module 304 utilizes a dynamic resource pre-allocation strategy and time-series synchronized data streams to perform task scheduling. Based on real-time task execution status and resource usage, it dynamically adjusts resource allocation to ensure tasks are executed efficiently according to priority, and generates optimized resource allocation strategies to improve resource utilization and task execution efficiency.

[0115] The efficiency feedback module 305 integrates optimized resource allocation strategies with construction status monitoring data, including vibration signals, hoisting operation records, and environmental monitoring data, to perform multi-dimensional efficiency fusion processing and generate collaborative efficiency evaluation indicators. Root cause analysis is conducted on parameters that do not reach preset thresholds, generating optimization suggestions. These suggestions are then fed back to the node load level label generation module and the time-series compensation parameter calculation module, triggering dynamic parameter updates in the edge computing node network. This achieves continuous optimization and efficient collaborative management of the construction process.

[0116] The dynamic pre-allocation module 302 is also used for:

[0117] Identify the key node types in the current construction phase and generate a priority task list based on construction schedule constraints;

[0118] First-level load nodes are selected based on node load status data, and a mapping relationship between first-level load nodes and priority tasks is established to generate an initial resource pre-allocation strategy.

[0119] Based on the dynamic changes of key nodes in the construction phase, conflict prediction and handling are performed on the initial resource pre-allocation strategy to generate a dynamic resource pre-allocation strategy.

[0120] The dynamic pre-allocation module 302 is also used for:

[0121] Based on the construction phase division model, identify the key node types of the current construction phase and generate key node type labels;

[0122] Obtain construction schedule constraints, perform conflict detection and handling between key node type labels and construction schedule constraints, and generate dynamic weight adjustment parameters.

[0123] The key nodes are prioritized based on the dynamic weight adjustment parameters to generate a priority task list.

[0124] The performance feedback module 305 is also used for:

[0125] Collect task completion time, resource utilization rate and time sequence alignment error data corresponding to the optimized resource allocation strategy, perform multi-dimensional performance fusion processing, and generate collaborative performance evaluation indicators.

[0126] Root cause analysis is performed on parameters in the collaborative effectiveness evaluation indicators that do not reach the preset threshold, and optimization suggestion data is generated.

[0127] The optimization suggestions are fed back to the node load level label generation module and the time series compensation parameter calculation module. Based on the optimization suggestions, the node load level classification rules and the time series compensation parameter calculation logic are dynamically adjusted, triggering dynamic updates of the parameters of the edge computing node network.

[0128] The performance feedback module 305 is also used for:

[0129] The collaborative effectiveness evaluation indicators are classified according to the preset effectiveness threshold, and parameter deviation types are generated.

[0130] A construction phase correlation analysis was performed on the resource utilization deviation item in the parameter deviation type to generate resource allocation optimization suggestions;

[0131] Perform a compensation parameter correlation analysis on the timing alignment error deviation item in the parameter deviation type to generate timing compensation optimization suggestions;

[0132] Integrate resource allocation optimization suggestions with time-series compensation optimization suggestions to generate optimization suggestion data.

[0133] The timing compensation module 303 is also used for:

[0134] Delay distribution density features are extracted from the communication delay distribution map, and offset correction is performed on the delay distribution density features based on the dynamic characteristics of the construction scenario to generate dynamic time-series offsets.

[0135] By superimposing construction scenario weight parameters on dynamic temporal offsets, multimodal temporal compensation parameters are generated.

[0136] Multimodal time-series compensation parameters are loaded onto the vibration signal data and hoisting operation record data in the construction status monitoring data, respectively, and a time-series synchronous data stream is generated through segmented interpolation correction processing.

[0137] Data mapping module 301 is also used for:

[0138] Data on GPU utilization, memory usage, and task queue length are collected by edge nodes deployed at the tower base, hoisting area, and control room.

[0139] The GPU utilization, memory usage and task queue length data are classified and aggregated to generate node load status data, which includes three load level labels.

[0140] The system measures the data transmission delay between nodes, performs distribution density analysis based on the delay time, and generates a communication delay distribution map.

[0141] In one embodiment, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0142] In one embodiment, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0143] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0144] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for real-time monitoring of the construction status of power engineering projects, characterized in that, The method includes: By collecting load status and communication latency data of each node through the edge computing node network, node load status data and communication latency distribution map are generated; Based on the node load status data and the task priority division of key nodes in the construction phase, a dynamic resource pre-allocation strategy is generated. Calculate timing compensation parameters based on the communication delay distribution map, and generate a timing synchronization data stream; Based on the dynamic resource pre-allocation strategy and the time-series synchronous data stream, task scheduling is performed to generate an optimized resource allocation strategy. Based on the optimized resource allocation strategy and construction status monitoring data, a collaborative efficiency evaluation result is generated and fed back to the edge computing node network. The construction status monitoring data includes vibration signal data, hoisting operation record data, and environmental monitoring data.

2. The method for real-time monitoring of construction status of power engineering according to claim 1, characterized in that, The step of prioritizing tasks based on the node load status data and key nodes in the construction phase, and generating a dynamic resource pre-allocation strategy, includes: Identify the key node types in the current construction phase and generate a priority task list based on construction schedule constraints; Based on the node load status data, first-level load nodes are selected, and a mapping relationship between the first-level load nodes and priority tasks is established to generate an initial resource pre-allocation strategy. Based on the dynamic change characteristics of the key nodes in the construction phase, conflict prediction processing is performed on the initial resource pre-allocation strategy to generate the dynamic resource pre-allocation strategy.

3. The method for real-time monitoring of construction status of power engineering according to claim 2, characterized in that, The process of identifying the key node types of the current construction phase and generating a priority task list based on construction schedule constraints includes: Based on the construction phase division model, identify the key node types of the current construction phase and generate key node type labels; Obtain construction progress constraints, perform conflict detection and processing on the key node type labels and construction progress constraints, and generate dynamic weight adjustment parameters. The key nodes are prioritized according to the dynamic weight adjustment parameters to generate the priority task list.

4. The method for real-time monitoring of construction status of power engineering according to claim 1, characterized in that, The step of generating a collaborative performance evaluation result based on the optimized resource allocation strategy and construction status monitoring data, and feeding the collaborative performance evaluation result back to the edge computing node network, includes: Collect task completion time, resource utilization rate and time sequence alignment error data corresponding to the optimized resource allocation strategy, perform multi-dimensional performance fusion processing, and generate collaborative performance evaluation indicators. Root cause analysis is performed on parameters in the collaborative effectiveness evaluation indicators that do not reach the preset threshold, and optimization suggestion data is generated. The optimization suggestion data is fed back to the node load level label generation module and the time series compensation parameter calculation module. The node load level classification rules and time series compensation parameter calculation logic are dynamically adjusted according to the optimization suggestion data, triggering the dynamic update of the parameters of the edge computing node network.

5. The method for real-time monitoring of construction status of power engineering according to claim 4, characterized in that, The step of performing root cause analysis on parameters in the collaborative effectiveness evaluation indicators that do not reach the preset threshold, and generating optimization suggestion data, includes: The collaborative performance evaluation indicators are classified according to a preset performance threshold to generate parameter deviation types. A construction phase correlation analysis is performed on the resource utilization deviation item in the parameter deviation type to generate resource allocation optimization suggestions; Perform a compensation parameter correlation analysis on the timing alignment error deviation item in the parameter deviation type to generate timing compensation optimization suggestions; The resource allocation optimization suggestions and the timing compensation optimization suggestions are integrated to generate the optimization suggestion data.

6. The method for real-time monitoring of construction status of power engineering according to claim 1, characterized in that, The step of calculating timing compensation parameters based on the communication delay distribution map and generating a timing synchronization data stream includes: Delay distribution density features are extracted from the communication delay distribution map, and offset correction processing is performed on the delay distribution density features based on the dynamic characteristics of the construction scenario to generate dynamic time-series offset. The construction scenario weight parameters are superimposed on the dynamic temporal offset to generate multimodal temporal compensation parameters; The multimodal timing compensation parameters are loaded onto the vibration signal data and hoisting operation record data in the construction status monitoring data, respectively, and the timing synchronization data stream is generated through segmented interpolation correction processing.

7. The method for real-time monitoring of the construction status of power engineering according to claim 1, characterized in that, The process of collecting load status and communication latency data of each node through an edge computing node network to generate node load status data and communication latency distribution maps includes: Data on GPU utilization, memory usage, and task queue length are collected by edge nodes deployed at the tower base, hoisting area, and control room. The GPU utilization, memory usage, and task queue length data are classified and aggregated to generate the node load status data, which includes three load level labels. The data transmission delay between nodes is measured, and a distribution density analysis is performed based on the delay time to generate the communication delay distribution map.

8. A real-time monitoring system for the construction status of power engineering projects, characterized in that, The system includes: The data mapping module is used to collect load status and communication latency data of each node through the edge computing node network, and generate node load status data and communication latency distribution maps. The dynamic pre-allocation module is used to generate a dynamic resource pre-allocation strategy based on the node load status data and the task priority division of key nodes in the construction phase. The timing compensation module is used to calculate timing compensation parameters based on the communication delay distribution map and generate a timing synchronization data stream; The scheduling optimization module is used to perform task scheduling based on the dynamic resource pre-allocation strategy and the time-series synchronous data stream, and generate an optimized resource allocation strategy. The efficiency feedback module is used to generate a collaborative efficiency evaluation result based on the optimized resource allocation strategy and construction status monitoring data, and to feed the collaborative efficiency evaluation result back to the edge computing node network. The construction status monitoring data includes vibration signal data, hoisting operation record data and environmental monitoring data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the real-time monitoring method for the construction status of a power engineering project as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the real-time monitoring method for the construction status of a power engineering project as described in any one of claims 1 to 7.

Images