CN117614992A - Edge decision method and system for engineering remote monitoring - Google Patents
Edge decision method and system for engineering remote monitoring Download PDFInfo
- Publication number
- CN117614992A CN117614992A CN202311765190.1A CN202311765190A CN117614992A CN 117614992 A CN117614992 A CN 117614992A CN 202311765190 A CN202311765190 A CN 202311765190A CN 117614992 A CN117614992 A CN 117614992A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- edge processing
- decision
- target
- processing nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 166
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 224
- 239000008358 core component Substances 0.000 claims abstract description 44
- 238000012806 monitoring device Methods 0.000 claims abstract description 32
- 230000004044 response Effects 0.000 claims abstract description 15
- 238000010276 construction Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims description 44
- 230000003993 interaction Effects 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 13
- 230000001360 synchronised effect Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 17
- 238000013528 artificial neural network Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 239000000306 component Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000009430 construction management Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000000586 desensitisation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000407 epitaxy Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0894—Policy-based network configuration management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application discloses an edge decision method and system for engineering remote monitoring, and relates to the technical field of remote monitoring, wherein the method comprises the steps of reading a monitoring point configuration table of a target engineering project and determining core components of each point monitoring device; reading a data operation processing center arranged in an engineering supervision system, covering a plurality of layers of edge processing nodes based on function difference, wherein the nodes can be interacted; matching a group of edge processing nodes of the target layer, and determining monitoring decision data; real-time construction monitoring is carried out based on the monitoring decision data, and the real-time monitoring data is returned to the edge processing nodes of the two groups of target layers which are determined based on the nearby distance matching of the decision task; processing decision tasks based on the edge processing nodes of the two groups of target layers, and determining task execution strategies; and transmitting the task execution strategy back to the engineering supervision system for strategy downloading and implementation response. Thereby achieving the technical effects of reducing the monitoring decision delay, having good network adaptability and reducing the data security risk.
Description
Technical Field
The invention relates to the technical field of remote monitoring, in particular to an edge decision method and an edge decision system for engineering remote monitoring.
Background
Engineering remote monitoring refers to monitoring the running state of an engineering site in real time through equipment such as a sensor, a camera and the like, and collecting related data. For monitoring and management of worksites, equipment or other engineering projects. Engineering remote monitoring combines cloud computing to perform data processing and analysis, and assists in decision making and provides real-time feedback. The existing technology based on the cloud computing server has the technical problems of poor timeliness of monitoring decision, high network connection requirement and data security risk.
Disclosure of Invention
The application aims to provide an edge decision method and system for engineering remote monitoring. The method and the device are used for solving the technical problems of poor monitoring decision timeliness, high network connection requirement and data security risk in the prior art.
In view of the above technical problems, the present application provides an edge decision method and system for engineering remote monitoring.
In a first aspect, the present application provides an edge decision method for engineering remote monitoring, where the method includes:
reading a monitoring point configuration table of a target engineering project, and determining a core component of each point monitoring device, wherein the core component comprises an image sensor and a digital processing chip;
the method comprises the steps of reading a data operation processing center of a target engineering area, wherein the data operation processing center is deployed in an engineering supervision system, covers a plurality of layers of edge processing nodes based on function difference, and can realize information interaction between the nodes;
aiming at the monitoring point configuration table and the core component, matching a group of edge processing nodes of a target layer to carry out monitoring equipment control decision based on project planning, and determining monitoring decision data, wherein the edge processing nodes of the target layer belong to the multi-layer edge processing nodes;
real-time construction monitoring is carried out based on the monitoring decision data, and the real-time monitoring data is returned to edge processing nodes of two groups of target layers based on decision tasks, wherein the edge processing nodes are determined based on nearby distance matching;
processing the decision task based on the edge processing nodes of the two groups of target layers, and determining a task execution strategy;
and the task execution strategy is returned to the engineering supervision system to carry out strategy downloading and implementation response.
In a second aspect, the present application further provides an edge decision system for engineering remote monitoring, where the system includes:
the monitoring module is used for reading a monitoring point configuration table of a target engineering project and determining a core component of each point monitoring device, wherein the core component comprises an image sensor and a digital processing chip;
the processing center interaction module is used for reading a data operation processing center of the target engineering area, wherein the data operation processing center is deployed in an engineering supervision system, covers multi-layer edge processing nodes based on function difference, and can realize information interaction between the nodes;
the matching decision module is used for matching a group of edge processing nodes of the target layer with the core component according to the monitoring point configuration table to carry out a monitoring equipment control decision based on project planning, and determining monitoring decision data, wherein the edge processing nodes of the group of target layers belong to the multi-layer edge processing nodes;
the monitoring feedback module is used for carrying out real-time construction monitoring based on the monitoring decision data and returning the real-time monitoring data to edge processing nodes of two groups of target layers based on decision tasks, wherein the edge processing nodes are determined based on nearby distance matching;
the policy decision module is used for processing the decision task based on the edge processing nodes of the two groups of target layers and determining a task execution policy;
and the feedback execution module is used for transmitting the task execution strategy back to the engineering supervision system for strategy release and implementation response.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the method comprises the steps of reading a monitoring point configuration table of a target engineering project, and determining core components of each point monitoring device, wherein the core components comprise an image sensor and a digital processing chip; the data operation processing center of the target engineering area is read, wherein the data operation processing center is deployed in an engineering supervision system, covers a plurality of layers of edge processing nodes based on function difference, and can realize information interaction between the nodes; aiming at the monitoring point configuration table and the core component, matching a group of edge processing nodes of the target layer to carry out a monitoring equipment control decision based on project planning, and determining monitoring decision data, wherein the edge processing nodes of the target layer belong to a plurality of layers of edge processing nodes; real-time construction monitoring is carried out based on the monitoring decision data, and the real-time monitoring data is returned to edge processing nodes of two groups of target layers based on decision tasks, wherein the edge processing nodes are determined based on nearby distance matching; processing decision tasks based on the edge processing nodes of the two groups of target layers, and determining task execution strategies; and transmitting the task execution strategy back to the engineering supervision system for strategy downloading and implementation response. Thereby achieving the technical effects of reducing the monitoring decision delay, having good network adaptability and reducing the data security risk.
The foregoing description is merely an overview of the technical solutions of the present application, and may be implemented according to the content of the specification, so that the technical means of the present application can be more clearly explained, and the following specific embodiments of the present application are given for more understanding of the above and other objects, features and advantages of the present application.
Drawings
Embodiments of the invention and the following brief description are described with reference to the drawings, in which:
FIG. 1 is a schematic flow chart of an edge decision method for engineering remote monitoring;
FIG. 2 is a schematic flow chart of a multi-layer edge processing node based on functional differences covered in an edge decision method for engineering remote monitoring;
fig. 3 is a schematic structural diagram of an edge decision system for engineering remote monitoring in the present application.
Reference numerals illustrate: the system comprises a monitoring module 11, a processing center interaction module 12, a matching decision module 13, a monitoring feedback module 14, a strategy decision module 15 and a feedback execution module 16.
Detailed Description
The edge decision method and the system for engineering remote monitoring solve the technical problems of poor timeliness of monitoring decision, high network connection requirement and data security risk in the prior art.
In order to solve the above problems, the technical embodiment adopts the following overall concept:
firstly, reading a monitoring point configuration table of a target engineering project, and determining core components of each monitoring device, wherein the core components comprise an image sensor and a digital processing chip; then, a data operation processing center of the target engineering area is searched, the center is positioned in an engineering supervision system and covers a plurality of layers of edge processing nodes, and the nodes are arranged according to the function level difference and can mutually perform information interaction; and then, matching a group of target layer edge processing nodes suitable for project planning according to the monitoring point configuration table and the core component, and making a control decision of the monitoring equipment to form monitoring decision data. The group of target layer edge processing nodes cover a plurality of layers and belong to a plurality of layers of edge processing nodes in the data operation processing center; further, real-time construction monitoring is implemented based on the monitoring decision data, the real-time monitoring data is transmitted back to a second group of target layer edge processing nodes based on decision tasks, and the nodes are determined according to nearby distance matching; then, the decision task is executed by the second group of target layer edge processing nodes, and a task execution strategy is determined; and finally, sending the task execution strategy back to the engineering supervision system, implementing response and downloading execution. Thereby achieving the technical effects of reducing the monitoring decision delay, having good network adaptability and reducing the data security risk.
In order to better understand the foregoing technical solutions, the following detailed description will be given with reference to the accompanying drawings and specific embodiments, and it should be noted that the described embodiments are only some examples of the present application, and not all examples of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present invention are shown.
Example 1
As shown in fig. 1, the present application provides an edge decision method for engineering remote monitoring, which includes:
s100: reading a monitoring point configuration table of a target engineering project, and determining a core component of each point monitoring device, wherein the core component comprises an image sensor and a digital processing chip;
the monitoring point configuration table contains configuration information of monitoring points of the target engineering project and is obtained through interaction with a monitoring management scheme of the target engineering project. Specifically, the information contained in the monitoring point configuration table includes information such as the position of the monitoring point, the type of the monitoring device, the type of the sensor, the digital processing chip and the like. By reading the monitoring point configuration table of the target engineering project, the layout characteristics and the monitoring equipment characteristics of the monitoring system of the target engineering project can be obtained, and the subsequent edge processing node distribution based on the characteristics of the target engineering project is facilitated.
Further, the step of reading the configuration table of the monitoring points of the target engineering project and determining the core component of the monitoring equipment of each point comprises the following steps:
the monitoring point configuration table comprises the spatial distribution of multi-point monitoring equipment configured in an engineering area;
determining core component parameters aiming at each point monitoring device, wherein the core component parameters at least comprise the degree of freedom of regulation and control based on the number of sensor lines, the multiple of an outer lens, the wide view angle and the focal length;
and carrying out mapping identification of the core component parameters and the multipoint monitoring equipment.
Optionally, determining the core components of the monitoring device, in particular the image sensor and the digital processing chip, involves obtaining the hardware composition of the monitoring device. The image sensor is used for converting a scene light signal into an electric signal through photoelectric conversion, capturing a scene image, and the digital processing chip is used for processing and encoding acquired image data. The digital processing chip is used for collecting, preprocessing, enhancing, encoding and other processes of the digital image. Processing the electric signal based on the digital processing chip comprises the following steps: white balance, exposure control, color correction, image coding, etc. The method has the advantages of providing high-quality image output, ensuring the stability of the image under different illumination conditions, controlling the image volume and facilitating the processing and transmission. These two components are the core of the monitoring device, with a critical impact on image quality and processing performance.
Optionally, after the monitoring point configuration table is read, the camera model, the sensor model and the digital processing chip model of each monitoring point are identified according to the information in the table, the technical specification and the performance characteristics of the monitoring equipment are determined based on the model information interaction monitoring equipment specification, and the core component parameters are obtained, so that a foundation is provided for further analysis and optimization of the monitoring system.
Optionally, the spatial distribution of the multi-point monitoring device in the engineering area includes the installation point position, the installation height and the sensor orientation of the monitoring device. Illustratively, the components of the monitoring device include: lens group, sensor, digital processing chip, buffer memory, support and steering mechanism. The corresponding core component parameters are the number of sensor lines, the multiple of the outer lens, the wide view angle and the regulation degree of freedom of focal length. Such as the number of sensor pixels, the optical zoom magnification range, the view angle adjustable range, and the focal length range. In addition, the specificity of the characteristics of the monitoring equipment is based, and the sensitivity range, the aperture size, the HDR support, the multi-frame synthesis and the like are also included.
After the parameters of the core component are determined, mapping identification is carried out on the parameters and the multipoint monitoring equipment. Such identification is used to track and manage the various monitoring points so that the performance and characteristics of each device can be more readily understood throughout the monitoring system. And meanwhile, the subsequent maintenance and optimization work is facilitated.
S200: the method comprises the steps of reading a data operation processing center of a target engineering area, wherein the data operation processing center is deployed in an engineering supervision system, covers a plurality of layers of edge processing nodes based on function difference, and can realize information interaction between the nodes;
optionally, the data operation processing center of the target engineering area is a remote operation processing center constructed based on the principle of edge computing technology, the data operation processing center is connected with a plurality of edge processing nodes, and the plurality of edge processing nodes can perform data transmission and information interaction through data connection. The data operation processing center is embedded in the engineering supervision system and is used for carrying out operation processing such as engineering supervision task analysis, node matching, task splitting, multi-node cooperative processing and the like based on the characteristics of engineering projects.
Further, as shown in fig. 2, the data operation processing center covers a multi-layer edge processing node based on functional variability, and the steps include:
configuring and determining a layer of edge processing nodes for a first processing function, wherein the layer of edge processing nodes comprises at least one distributed node;
configuring and determining an N-layer edge processing node aiming at an N-th processing function;
and based on the functional correlation, correlating the one-layer edge processing node to the N-layer edge processing nodes, and determining the multi-layer edge processing node as the data operation processing center.
Optionally, the multi-layer edge processing node is adapted to different tasks and functions according to the functional differences. The above functional differences are embodied as computing power, storage power, network power, etc. of the edge processing node.
Alternatively, the computing power may be divided into general computing power represented by CPU and high performance computing power represented by GPU, and the commonly used unit of measure is the number of floating point operations (FLOPS) performed per second, specifically including double precision (FP 64), single precision (FP 32), and half precision (FP 16). The data storage capacity is determined by three aspects of storage capacity, storage performance and storage safety. Network capacity is comprehensively measured by network bandwidth, network delay and network packet loss rate. Higher network quality means faster data exchange and may have more processing power.
Optionally, based on the processing function, the edge processing nodes are subjected to matching screening, the N-layer edge processing nodes are configured and determined, and the edge processing nodes with different characteristics are applicable to different processing functions. For an image processing task, selecting an edge processing node configured with a GPU for accelerating image processing based on the size of image data and processing parameter requirements, and generating a layer of edge processing nodes.
Further, consider the functional dependencies between different edge processing nodes. Some functions may need a plurality of nodes to cooperate, so that cooperation is realized based on the functions, the association relation between the edge processing nodes of different layers is defined, the smooth data communication between the association nodes is ensured, and then the multi-layer edge processing nodes are obtained. The multi-layer edge processing nodes are in an interpenetrating fusion state of the N-layer edge processing nodes.
Further, based on the functional correlation, the multi-layer edge processing node is determined by associating the layer of edge processing nodes up to the N-layer edge processing node, and the steps further include:
the functional correlation comprises synchronous correlation and asynchronous correlation, and a difference correlation mode is configured;
combining the distinguishing association mode, and carrying out association from the one-layer edge processing node to the N-layer edge processing node by taking the sequence position based on the functional correlation as a constraint;
based on a nearby principle, the matching association between each point monitoring device and the multi-layer edge processing node is established and used as the configured data operation processing center.
Optionally, multiple edge processing nodes work cooperatively, involving parallel processing, data sharing, or other forms of cooperation. Thereby enabling synchronous correlation and asynchronous correlation between the edge processing nodes. Illustratively, tasks that need to be performed synchronously on multiple edge nodes determine synchronization dependencies among the multiple edge nodes, such as split parallel processing of large data volume computing tasks. The association mode corresponding to the synchronous correlation is established based on a synchronous mechanism, so that each node can work cooperatively when executing tasks, such as synchronous communication or shared memory. Tasks that may be performed independently or require sequential execution determine asynchronous dependencies between multiple edge nodes. The output of the previous task step is transferred by the step upstream node to the step downstream node by the edge processing node with asynchronous dependencies. The method is realized by establishing a proper communication mechanism based on an association mode of asynchronous correlation. Including message queues, event triggers, publish-subscribe models, etc. The edge nodes communicate asynchronously through these mechanisms without having to wait for other nodes to complete tasks.
Optionally, combining a differential association mode, and carrying out association from one layer of edge processing nodes to N layers of edge processing nodes by taking the sequence of the functional correlation as a constraint; in the association establishment process, for a certain layer or n layers of edge processing nodes which are not involved, the bypass is established to carry out the overrun association of the edge processing nodes, so that a plurality of node association paths are formed. Wherein N is a positive integer and N is less than N; the number of path layers m of the plurality of node-associated paths is less than or equal to N.
Optionally, based on a nearby principle, according to a plurality of node association paths from one layer of edge processing nodes to N layers of edge processing nodes, selecting an edge processing node closest to each layer of edge processing nodes, and establishing matching association between each point monitoring device and multiple layers of edge processing nodes as the configured data operation processing center. Wherein the distance between edge processing nodes is based on network topology, physical distance, or other relevance metrics. Illustratively, the matching association of each point monitoring device with the multi-layer edge processing node is established based on a path planning algorithm, such as Dijkstra algorithm or a-x algorithm.
Optionally, the established matching association is stored, a matching relation table is constructed, and the matching relation table records each monitoring device and multiple edge nodes matched by each monitoring device task. The matching relation table is configured in the data operation processing center, so that data can be effectively transmitted from the monitoring equipment to the nearest edge processing nodes and coordinated among the multi-layer edge processing nodes when processing tasks.
Optionally, a dynamic adjustment mechanism is applied, and node distances are re-evaluated and matching relationships are adjusted according to real-time conditions of edge processing nodes when the system is running, so as to cope with changes of network topology or workload. Exemplary include offline of a portion of the edge processing nodes, new addition of edge processing nodes, change of edge processing node connection paths, and the like.
S300: aiming at the monitoring point configuration table and the core component, matching a group of edge processing nodes of a target layer to carry out monitoring equipment control decision based on project planning, and determining monitoring decision data, wherein the edge processing nodes of the target layer belong to the multi-layer edge processing nodes;
the edge processing nodes of the set of target layers are used for executing monitoring equipment control decisions, wherein the monitoring equipment control decisions are realized through analysis project planning. Illustratively, core components of each monitoring point are matched to corresponding edge processing nodes according to information in the monitoring point configuration table. And then taking a supervision plan of the target engineering project as a decision input feature, taking monitoring decision data as a decision output feature, and taking historical monitoring decision data and a historical project plan as sample data to carry out control decision of the monitoring equipment. Wherein the optional decision model comprises a matching optimization model, a neural network model, an analytic hierarchy model or a decision tree model, and the like.
The monitoring decision data comprise monitoring parameter configuration, data transmission strategies, task allocation, data processing modes and the like. The monitoring decision data specifies specific operations for performing the incident monitoring acquisition on each monitoring device. To data in the form of configuration files, task lists, etc.
S400: real-time construction monitoring is carried out based on the monitoring decision data, and the real-time monitoring data is returned to edge processing nodes of two groups of target layers based on decision tasks, wherein the edge processing nodes are determined based on nearby distance matching;
optionally, the real-time construction monitoring is performed based on the monitoring decision data, the monitoring decision data is analyzed and is sent to each point monitoring device in a split mode, and each point monitoring device is controlled to obtain the real-time monitoring data of the target project scene, wherein the real-time monitoring data comprises static construction image data and dynamic image data. Further, according to the collection characteristics of the monitoring device, the real-time monitoring data can be further divided into white light image data, point cloud image data, infrared image data and the like.
Optionally, the edge processing nodes of the two groups of target layers based on the decision task are edge processing nodes of the target layer closest to the target engineering project, which are determined based on the nearby distance matching. The set of nodes includes edge processing nodes at different layers. The determined metrics of the nodes include consideration of network topology and physical distance between the edge processing nodes and the monitoring points. The edge processing node is used for carrying out monitoring decision and construction management based on the returned real-time monitoring data.
Optionally, the real-time monitoring data is transmitted to the edge processing node of the selected target layer by using a network communication mechanism. The security and reliability of transmission are ensured by introducing methods of encrypted transmission, integrity verification, data desensitization and the like.
Further, after the edge processing node determines based on the nearby distance matching, the steps further include:
counting the real-time idle computing power configuration of each node in the edge processing nodes;
judging whether the real-time idle computing power configuration meets the processing computing power requirement, and if not, generating a node extension instruction;
and along with the receiving of the node extension instruction, carrying out the forward extension of the same-layer edge processing node based on a nearby principle, and determining the compensation edge processing node.
Optionally, after determining the edge processing nodes of the two groups of target layers based on the decision task, each edge processing node in the group of edge processing nodes is interacted, and real-time idle computing power configuration of each edge processing node is counted, wherein the real-time idle computing power configuration comprises available resources in aspects of CPU, memory, storage and the like. And comparing the real-time idle calculation power configuration with the calculation power requirement of the current task. If the current real-time idle computing power cannot meet the task demand, generating a node extension instruction, wherein the instruction comprises information of which edge processing nodes are extended and the resource demand of the extension. The node extension instruction is used for indicating the engineering supervision system and the data operation processing center to carry out the same-layer edge processing node extension. The same-layer edge processing nodes are edge processing nodes which are positioned at the same layer as the nodes which are configured to meet the calculation force requirements of the current task by real-time idle calculation force. Illustratively, an edge processing node which meets the requirement of epitaxial resources and is closest to the edge processing node in the same layer is selected, and forward selection is performed to meet the requirement of calculation power.
Optionally, after the new node is added to the edge processing nodes of the two groups of target layers, the real-time update and discrimination of the real-time idle computing power configuration are performed based on the steps, so that the resource configuration meets the computing power requirement. The system state is monitored in real time, task demands are responded in time, and system resources are balanced through epitaxy and forward extension. Ensuring a full-scale configuration of the processing forces. The use of the proximity principle helps to reduce communication delay and improve efficiency.
S500: processing the decision task based on the edge processing nodes of the two groups of target layers, and determining a task execution strategy;
optionally, decision task processing is performed based on the edge processing nodes of the two groups of target layers, and a task execution strategy is obtained, wherein the engineering supervision task execution strategy comprises: engineering progress reports, security construction reports, supervision notices, etc.
Optionally, the decision task is implemented based on neural network algorithm principle according to engineering supervision planning of the target project, and firstly, the returned real-time monitoring data is preprocessed based on the returned real-time monitoring data, including data cleaning, denoising, normalization and the like. Data quality and consistency are ensured so that the data can be used as input of the neural network. Then, a neural network architecture suitable for tasks is designed, and a proper number of layers, a proper number of nodes, a proper activation function and the like of the neural network are selected. And then, acquiring historical monitoring data and a historical task execution strategy to generate sample data. The data is divided into a training set, a verification set and a test set. Meanwhile, a definite label is defined for the supervision task so that the neural network learns and predicts the result of the task. Next, the neural network model is trained using the data of the training set. Model parameters are continuously adjusted through a back propagation algorithm, so that the model parameters can adapt to the characteristics and modes of tasks. The performance of the model is then verified using the data of the verification set. And adjusting the super parameters of the neural network according to the verification result to improve the generalization capability and the prediction accuracy of the model. And finally, evaluating the performance of the final model, and if the performance of the model meets the accuracy requirement of engineering supervision planning. The trained and verified model is embedded into the edge processing nodes of the two groups of target layers for processing decision tasks and determining task execution strategies.
S600: and the task execution strategy is returned to the engineering supervision system to carry out strategy downloading and implementation response.
Further, the steps of policy issuing and implementing response include:
based on the task execution strategy, identifying a wind control early warning strategy, wherein the wind control early warning strategy has the highest priority;
traversing an emergency plan library, and matching and determining a target emergency plan based on the wind control early warning strategy, wherein the emergency plan library is arranged in the engineering supervision system;
and carrying out implementation response of the target emergency plan based on the engineering supervision system.
The method includes the steps that policy identification is conducted on task execution policies based on policy labels, if wind control early warning policies exist in the task execution policies, the wind control early warning policies are used as the most priority execution policies, an emergency plan library is traversed, corresponding emergency plans are obtained, and target emergency plans are generated. And then, the transmission and execution are directly carried out through strategies such as remote equipment control, remote operation regulation and control and the like, so that the sending of risk events and the expansion of engineering risks are avoided to the greatest extent, and the safety of engineering projects is ensured.
Further, the method further comprises:
determining a communication network covering the target engineering area, wherein the communication network comprises a private network and the Internet and is configured with a network transmission checkpoint, and the network transmission checkpoint is configured based on transmission requirements;
combining the network transmission gateway to perform pre-detection before data transmission and determine a target transmission network;
and adjusting an actual transmission channel based on the channel state of the target transmission network.
Optionally, preferably, a private network is preferentially adopted to transmit engineering monitoring data such as real-time monitoring data, task execution policies and the like. The private line network generally provides stable and reliable connection, and is suitable for scenes with higher requirements on transmission stability; the internet provides wider coverage, and is suitable for general data transmission.
Optionally, a network transport gateway is configured in the communication network for monitoring and managing data transmissions. The network transmission gateway can set the parameters of transmission rate, priority, safety and the like so as to adapt to the data transmission requirements of different types.
Optionally, before actually performing data transmission, pre-checking before network transmission is performed, including checking whether configuration of a network transmission checkpoint meets transmission requirements, so as to ensure smooth network connection, normal operation of equipment, network protection security, and the like.
Optionally, the adjustment of the actual transmission channel is performed according to the channel state of the target transmission network. Exemplary include dynamically adjusting transmission routes, optimizing bandwidth allocation, handling network congestion, etc., to ensure efficiency and stability of data transmission.
In summary, the edge decision method for engineering remote monitoring provided by the invention has the following technical effects:
the method comprises the steps of reading a monitoring point configuration table of a target engineering project, and determining core components of each point monitoring device, wherein the core components comprise an image sensor and a digital processing chip; the data operation processing center of the target engineering area is read, wherein the data operation processing center is deployed in an engineering supervision system, covers a plurality of layers of edge processing nodes based on function difference, and can realize information interaction between the nodes; aiming at the monitoring point configuration table and the core component, matching a group of edge processing nodes of the target layer to carry out a monitoring equipment control decision based on project planning, and determining monitoring decision data, wherein the edge processing nodes of the target layer belong to a plurality of layers of edge processing nodes; real-time construction monitoring is carried out based on the monitoring decision data, and the real-time monitoring data is returned to edge processing nodes of two groups of target layers based on decision tasks, wherein the edge processing nodes are determined based on nearby distance matching; processing decision tasks based on the edge processing nodes of the two groups of target layers, and determining task execution strategies; and transmitting the task execution strategy back to the engineering supervision system for strategy downloading and implementation response. Thereby achieving the technical effects of reducing the monitoring decision delay, having good network adaptability and reducing the data security risk.
Example 2
Based on the same concept as the edge decision method for engineering remote monitoring in the embodiment, as shown in fig. 3, the application further provides an edge decision system for engineering remote monitoring, where the system includes:
the monitoring module 11 is used for reading a monitoring point configuration table of a target engineering project and determining a core component of each point monitoring device, wherein the core component comprises an image sensor and a digital processing chip;
the processing center interaction module 12 is used for reading a data operation processing center of the target engineering area, wherein the data operation processing center is deployed in an engineering supervision system, covers a plurality of layers of edge processing nodes based on function difference, and can realize information interaction between the nodes;
the matching decision module 13 is configured to match a set of edge processing nodes of a target layer with the core component according to the monitoring point configuration table to perform a monitoring device control decision based on project planning, and determine monitoring decision data, where the edge processing nodes of the set of target layers belong to the multi-layer edge processing nodes;
the monitoring feedback module 14 is configured to perform real-time construction monitoring based on the monitoring decision data, and transmit the real-time monitoring data back to edge processing nodes of two groups of target layers based on decision tasks, where the edge processing nodes are determined based on nearby distance matching;
the policy decision module 15 is configured to determine a task execution policy based on processing the decision task by the edge processing nodes of the two groups of target layers;
and the feedback execution module 16 is used for transmitting the task execution strategy back to the engineering supervision system for strategy downloading and implementation response.
Further, the monitoring module 11 further includes:
the parameter acquisition unit is used for determining core component parameters aiming at each point monitoring device, wherein the core component parameters at least comprise the degree of freedom of regulation and control based on the number of sensor lines, the multiple of an outer lens, the wide view angle and the focal length;
and the mapping identification unit is used for carrying out mapping identification on the core component parameter and the multipoint monitoring equipment.
Further, the processing center interaction module 12 further includes:
a processing node configuration unit, configured to configure and determine a layer of edge processing nodes for a first processing function, where the layer of edge processing nodes includes at least one distributed node;
the updating configuration unit is used for configuring and determining N-layer edge processing nodes aiming at the Nth processing function;
and the correlation unit is used for correlating the one-layer edge processing node to the N-layer edge processing nodes based on the functional correlation, and determining the multi-layer edge processing node as the data operation processing center.
Further, the method further comprises the following steps:
a functional correlation unit, wherein the functional correlation comprises synchronous correlation and asynchronous correlation, and a difference correlation mode is configured;
the node association unit is used for associating the one-layer edge processing node to the N-layer edge processing node by taking the sequence position based on the functional correlation as a constraint in combination with the distinguishing association mode;
and the node matching association unit is used for establishing the matching association between the monitoring equipment of each point and the multi-layer edge processing node based on the nearby principle and taking the matching association as the configured data operation processing center.
Further, the monitoring feedback module 14 further includes:
the computing power monitoring unit is used for counting the real-time idle computing power configuration of each node in the edge processing nodes;
the computing force judging unit is used for judging whether the real-time idle computing force configuration meets the processing computing force requirement or not, and if not, generating a node extension instruction;
and the extension compensation unit is used for carrying out the forward extension of the same-layer edge processing node along with the receiving of the node extension instruction based on the nearby principle and determining the compensation edge processing node.
Further, the feedback execution module 16 further includes:
the wind control early warning unit is used for identifying a wind control early warning strategy based on the task execution strategy, wherein the wind control early warning strategy has the highest priority;
the plan matching unit is used for traversing an emergency plan library and matching and determining a target emergency plan based on the wind control early warning strategy, wherein the emergency plan library is arranged in the engineering supervision system;
and the response unit is used for responding to implementation of the target emergency plan based on the engineering supervision system.
Further, the system further comprises:
a communication network acquisition unit, configured to determine a communication network covering the target engineering area, where the communication network includes a private network and the internet, and is configured with a network transmission checkpoint, where the network transmission checkpoint is configured based on a transmission requirement;
the pre-detection unit is used for combining the network transmission gateway to perform pre-detection before data transmission and determine a target transmission network;
and the channel adjusting unit is used for adjusting the actual transmission channel based on the channel state of the target transmission network.
It should be understood that the embodiments mentioned in this specification focus on the differences from other embodiments, and the specific embodiment in the first embodiment is equally applicable to an edge decision system for engineering remote monitoring described in the second embodiment, which is not further developed herein for brevity of description.
It should be understood that the embodiments disclosed herein and the foregoing description may enable one skilled in the art to utilize the present application. While the present application is not limited to the above-mentioned embodiments, obvious modifications, combinations, and substitutions of the embodiments mentioned in the present application are also included in the scope of protection of the present application.
Claims (8)
1. An edge decision method for engineering remote monitoring, which is characterized by comprising the following steps:
reading a monitoring point configuration table of a target engineering project, and determining a core component of each point monitoring device, wherein the core component comprises an image sensor and a digital processing chip;
the method comprises the steps of reading a data operation processing center of a target engineering area, wherein the data operation processing center is deployed in an engineering supervision system, covers a plurality of layers of edge processing nodes based on function difference, and can realize information interaction between the nodes;
aiming at the monitoring point configuration table and the core component, matching a group of edge processing nodes of a target layer to carry out monitoring equipment control decision based on project planning, and determining monitoring decision data, wherein the edge processing nodes of the target layer belong to the multi-layer edge processing nodes;
real-time construction monitoring is carried out based on the monitoring decision data, and the real-time monitoring data is returned to edge processing nodes of two groups of target layers based on decision tasks, wherein the edge processing nodes are determined based on nearby distance matching;
processing the decision task based on the edge processing nodes of the two groups of target layers, and determining a task execution strategy;
and the task execution strategy is returned to the engineering supervision system to carry out strategy downloading and implementation response.
2. The method of claim 1, characterized in that the method comprises:
determining a communication network covering the target engineering area, wherein the communication network comprises a private network and the Internet and is configured with a network transmission checkpoint, and the network transmission checkpoint is configured based on transmission requirements;
combining the network transmission gateway to perform pre-detection before data transmission and determine a target transmission network;
and adjusting an actual transmission channel based on the channel state of the target transmission network.
3. The method of claim 1, wherein the monitoring points configuration table of the target engineering project is read and the core components of the point monitoring device are determined, the method comprising:
the monitoring point configuration table comprises the spatial distribution of multi-point monitoring equipment configured in an engineering area;
determining core component parameters aiming at each point monitoring device, wherein the core component parameters at least comprise the degree of freedom of regulation and control based on the number of sensor lines, the multiple of an outer lens, the wide view angle and the focal length;
and carrying out mapping identification of the core component parameters and the multipoint monitoring equipment.
4. The method of claim 1, wherein the data operation processing center is overlaid with a multi-layer edge processing node based on functional variability, the method comprising:
configuring and determining a layer of edge processing nodes for a first processing function, wherein the layer of edge processing nodes comprises at least one distributed node;
configuring and determining an N-layer edge processing node aiming at an N-th processing function;
and based on the functional correlation, correlating the one-layer edge processing node to the N-layer edge processing nodes, and determining the multi-layer edge processing node as the data operation processing center.
5. The method of claim 4, wherein the multi-tier edge processing node is determined by associating the one-tier edge processing node up to the N-tier edge processing node based on a functional dependency, the method comprising:
the functional correlation comprises synchronous correlation and asynchronous correlation, and a difference correlation mode is configured;
combining the distinguishing association mode, and carrying out association from the one-layer edge processing node to the N-layer edge processing node by taking the sequence position based on the functional correlation as a constraint;
based on a nearby principle, the matching association between each point monitoring device and the multi-layer edge processing node is established and used as the configured data operation processing center.
6. The method of claim 1, wherein after the edge processing node determines based on the close range match, the method comprises:
counting the real-time idle computing power configuration of each node in the edge processing nodes;
judging whether the real-time idle computing power configuration meets the processing computing power requirement, and if not, generating a node extension instruction;
and along with the receiving of the node extension instruction, carrying out the forward extension of the same-layer edge processing node based on a nearby principle, and determining the compensation edge processing node.
7. The method of claim 1, wherein policy down and enforcement responses are performed, the method comprising:
based on the task execution strategy, identifying a wind control early warning strategy, wherein the wind control early warning strategy has the highest priority;
traversing an emergency plan library, and matching and determining a target emergency plan based on the wind control early warning strategy, wherein the emergency plan library is arranged in the engineering supervision system;
and carrying out implementation response of the target emergency plan based on the engineering supervision system.
8. An edge decision system for engineering remote monitoring, the system comprising:
the monitoring module is used for reading a monitoring point configuration table of a target engineering project and determining a core component of each point monitoring device, wherein the core component comprises an image sensor and a digital processing chip;
the processing center interaction module is used for reading a data operation processing center of the target engineering area, wherein the data operation processing center is deployed in an engineering supervision system, covers multi-layer edge processing nodes based on function difference, and can realize information interaction between the nodes;
the matching decision module is used for matching a group of edge processing nodes of the target layer with the core component according to the monitoring point configuration table to carry out a monitoring equipment control decision based on project planning, and determining monitoring decision data, wherein the edge processing nodes of the group of target layers belong to the multi-layer edge processing nodes;
the monitoring feedback module is used for carrying out real-time construction monitoring based on the monitoring decision data and returning the real-time monitoring data to edge processing nodes of two groups of target layers based on decision tasks, wherein the edge processing nodes are determined based on nearby distance matching;
the policy decision module is used for processing the decision task based on the edge processing nodes of the two groups of target layers and determining a task execution policy;
and the feedback execution module is used for transmitting the task execution strategy back to the engineering supervision system for strategy release and implementation response.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311765190.1A CN117614992B (en) | 2023-12-21 | 2023-12-21 | Edge decision method and system for engineering remote monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311765190.1A CN117614992B (en) | 2023-12-21 | 2023-12-21 | Edge decision method and system for engineering remote monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117614992A true CN117614992A (en) | 2024-02-27 |
| CN117614992B CN117614992B (en) | 2024-06-25 |
Family
ID=89956281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311765190.1A Active CN117614992B (en) | 2023-12-21 | 2023-12-21 | Edge decision method and system for engineering remote monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117614992B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210096911A1 (en) * | 2020-08-17 | 2021-04-01 | Essence Information Technology Co., Ltd | Fine granularity real-time supervision system based on edge computing |
| KR20210085609A (en) * | 2019-12-31 | 2021-07-08 | 이노뎁 주식회사 | video surveillance system by use of core VMS and edge VMS in mobile edge computing |
| WO2021190482A1 (en) * | 2020-03-27 | 2021-09-30 | 中国移动通信有限公司研究院 | Computing power processing network system and computing power processing method |
| CN114091944A (en) * | 2021-11-27 | 2022-02-25 | 国网山东省电力公司电力科学研究院 | Cloud-end-coordinated distribution network engineering field operation analysis decision system |
| CN114301911A (en) * | 2021-12-17 | 2022-04-08 | 杭州谐云科技有限公司 | Task management method and system based on edge-edge cooperation |
| US20220201555A1 (en) * | 2020-12-21 | 2022-06-23 | Quanta Cloud Technology Inc. | Method And System For Maximizing Uplink Bandwidth In A Communication System |
| WO2022189601A1 (en) * | 2021-03-10 | 2022-09-15 | Schreder S.A. | Network system with sensor configuration model update |
| CN115376063A (en) * | 2022-08-04 | 2022-11-22 | 安徽南瑞继远电网技术有限公司 | Intelligent anti-error method based on cloud edge cooperation and image recognition |
| CN116527843A (en) * | 2023-03-29 | 2023-08-01 | 五冶集团上海有限公司 | Building site safety monitoring system and monitoring method based on building site core |
| CN116739389A (en) * | 2023-08-14 | 2023-09-12 | 广东创能科技股份有限公司 | Smart city management method and system based on cloud computing |
| CN116777713A (en) * | 2023-08-24 | 2023-09-19 | 湖南天成新宇网络科技有限公司 | Intelligent park safety management method and system based on data analysis |
| CN116909737A (en) * | 2023-07-14 | 2023-10-20 | 海南科技职业大学 | Port safety monitoring edge computing task unloading scheduling method based on deep learning |
| CN117041290A (en) * | 2023-08-08 | 2023-11-10 | 广州融新智能科技有限公司 | Intelligent traffic data interaction method, platform and system |
-
2023
- 2023-12-21 CN CN202311765190.1A patent/CN117614992B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210085609A (en) * | 2019-12-31 | 2021-07-08 | 이노뎁 주식회사 | video surveillance system by use of core VMS and edge VMS in mobile edge computing |
| WO2021190482A1 (en) * | 2020-03-27 | 2021-09-30 | 中国移动通信有限公司研究院 | Computing power processing network system and computing power processing method |
| US20210096911A1 (en) * | 2020-08-17 | 2021-04-01 | Essence Information Technology Co., Ltd | Fine granularity real-time supervision system based on edge computing |
| US20220201555A1 (en) * | 2020-12-21 | 2022-06-23 | Quanta Cloud Technology Inc. | Method And System For Maximizing Uplink Bandwidth In A Communication System |
| WO2022189601A1 (en) * | 2021-03-10 | 2022-09-15 | Schreder S.A. | Network system with sensor configuration model update |
| CN114091944A (en) * | 2021-11-27 | 2022-02-25 | 国网山东省电力公司电力科学研究院 | Cloud-end-coordinated distribution network engineering field operation analysis decision system |
| CN114301911A (en) * | 2021-12-17 | 2022-04-08 | 杭州谐云科技有限公司 | Task management method and system based on edge-edge cooperation |
| CN115376063A (en) * | 2022-08-04 | 2022-11-22 | 安徽南瑞继远电网技术有限公司 | Intelligent anti-error method based on cloud edge cooperation and image recognition |
| CN116527843A (en) * | 2023-03-29 | 2023-08-01 | 五冶集团上海有限公司 | Building site safety monitoring system and monitoring method based on building site core |
| CN116909737A (en) * | 2023-07-14 | 2023-10-20 | 海南科技职业大学 | Port safety monitoring edge computing task unloading scheduling method based on deep learning |
| CN117041290A (en) * | 2023-08-08 | 2023-11-10 | 广州融新智能科技有限公司 | Intelligent traffic data interaction method, platform and system |
| CN116739389A (en) * | 2023-08-14 | 2023-09-12 | 广东创能科技股份有限公司 | Smart city management method and system based on cloud computing |
| CN116777713A (en) * | 2023-08-24 | 2023-09-19 | 湖南天成新宇网络科技有限公司 | Intelligent park safety management method and system based on data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117614992B (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11132224B2 (en) | Fine granularity real-time supervision system based on edge computing | |
| CN112087522B (en) | Edge cloud collaborative flow arrangement system for industrial robot data processing | |
| Khriji et al. | Design and implementation of a cloud-based event-driven architecture for real-time data processing in wireless sensor networks | |
| CN110022230B (en) | Deep reinforcement learning-based service chain parallel deployment method and device | |
| CN115051926A (en) | Digital twin architecture, model evaluation system and model operation method | |
| Lai et al. | Development of smart cities with fog computing and internet of things | |
| CN114760669B (en) | Flow prediction-based route decision method and system | |
| Wang et al. | FLOWPROPHET: Generic and accurate traffic prediction for data-parallel cluster computing | |
| Lyu et al. | Cooperative computing anytime, anywhere: Ubiquitous fog services | |
| EP2520069B1 (en) | Managing session data of a composite service session in a communication network | |
| CN113763713B (en) | Road network bottleneck road section excavation and management method and device | |
| CN117290668B (en) | Big data processing method and system based on industrial Internet platform | |
| CN117614992B (en) | Edge decision method and system for engineering remote monitoring | |
| Cenggoro et al. | Dynamic bandwidth management based on traffic prediction using Deep Long Short Term Memory | |
| CN116994443A (en) | Intelligent traffic signal unified optimization control system and method based on cloud management and cloud control | |
| KR102569442B1 (en) | Method adnd Aparatus of Resource Usage Prediction in Service Function | |
| Tang et al. | Application of sensor-cloud systems: smart traffic control | |
| CN115277789A (en) | Safety protection system and method for cascade hydropower station | |
| CN103702445A (en) | Body and inference rule of task combination in WSN (wireless sensor network) semantic communication | |
| CN110087031B (en) | Task allocation method facing cooperative sensing | |
| CN110855507B (en) | Unmanned data network interaction method based on software definition | |
| Jafarizadeh et al. | Performance analysis of processing load distribution in camera networks for multi-target tracking | |
| WO2018216828A1 (en) | Energy big data management system and method therefor | |
| Xu et al. | Optimizing the cost-performance tradeoff for coflows across geo-distributed datacenters | |
| CN115622932B (en) | Calculation power scheduling method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |