193 results about "Node deployment" patented technology

The invention relates to an intrusion detection method based on cross-domain security management and a shared behavior model. The method comprises the following steps: acquiring multi-dimensional original data according to a preset cross-domain data acquisition rule and multi-domain node deployment; performing compliance, integrity and format matching degree verification on the original data, shielding sensitive information by using a dynamic desensitization technology based on a verification result, converting a heterogeneous data format, filtering missing field abnormal data, and obtaining compliance data; the method comprises the following steps: extracting a multi-dimensional feature set of user cross-domain access, constructing a shared behavior feature vector through weighted calculation, constructing a reference behavior model library in combination with a cross-domain security policy, and screening out intrusion behaviors and feature deviation data through feature comparison and behavior deviation calculation; according to the method, cross-domain security audit logs are fused for correlation analysis, intrusion behavior types and risk levels are judged by means of a Bayesian network model, differential security response strategies are generated and executed, and cross-domain intrusion detection and protection are achieved.

The invention relates to an underwater wireless sensor network path sensing routing method based on deep reinforcement learning, which comprises the following steps that: firstly, a node constructs and periodically updates a transmission preference model based on local and neighbor node interaction information; secondly, deploying a deep reinforcement learning model at each underwater sensor node to perform distributed routing strategy learning; and finally, generating a global guide vector by the sink node according to the routing path information of the received data packet, reversely spreading the global guide vector to the source node, fusing the global guide vector with a local transmission preference vector of the node to generate a guide reward, optimizing the deep reinforcement learning model, and updating a routing strategy. According to the method, the problems of difference and complexity of underwater transmission tasks can be solved, and the network data transmission efficiency and the overall service quality are improved in combination with local preference and global guidance while the node online learning is kept to adapt to the dynamic underwater environment.

The invention relates to the technical field of smart city public safety, in particular to an urban gas pipeline leakage risk intelligent early warning and positioning method and device.Firstly, a digital twinborn construction and dynamic coupling module constructs and drives a virtual image of a gas pipe network, then, a multi-modal data acquisition and fusion module comprehensively senses the state of the pipe network, and finally, the leakage risk of the gas pipeline is monitored. The intelligent early warning and positioning decision module realizes a core intelligent algorithm; a cloud-edge-end collaborative architecture is adopted, and a terminal sensor is responsible for data acquisition; the edge computing node is deployed in a regional pressure regulating station and is used for carrying out primary data processing and local real-time alarming; the cloud center deploys a digital twin platform and a core AI algorithm model, and performs big data analysis, simulation deduction and global decision. Compared with the prior art, the method can realize early and accurate identification and prediction of gas leakage and potential risks (such as abnormal stress) of the pipeline.

The invention discloses a multi-device and multi-language synchronous translation device and method based on a block chain and double AIs, and relates to the technical field of intelligent translation and edge computing, the device comprises a translation machine terminal, an edge computing node and a cloud server which form an end-edge-cloud three-level collaborative architecture, a translator terminal collects voice and lip shape information through a multi-mode sensing module, performs preliminary recognition by means of an edge lightweight AI unit, and realizes safe and rapid networking based on a block chain identity unit and an NFC touch networking unit. The edge computing node deploys a block chain group management module, a semantic collaborative optimization module and a local cache retransmission module, and is responsible for multi-language translation, semantic optimization and reliable distribution. The cloud server realizes global model training and term library management; according to the method, low-delay and high-accuracy multi-device synchronous interactive translation is realized through device authentication, voice recognition, edge optimization, multi-language parallel translation and adaptive transmission, and the translation efficiency and security in a multi-user and multi-language scene are remarkably improved.

The invention discloses a mobile 5G fused cross-domain resource scheduling system, and belongs to the technical field of cross-domain resource scheduling. Comprising a service feature intelligent sensing module, a multi-domain network topology dynamic sensing module, an intelligent resource slice evolution arrangement module, a cross-domain protocol intelligent adaptation conversion module, a data flow intelligent optimization scheduling module, a network loop risk prediction self-healing module and a security cooperative defense module. According to the method, lightweight probes are deployed at edge computing nodes, link states, loads and delay indexes are collected in real time, occupation of excessive CPU or memory resources is avoided, network nodes and links are represented as graph structures, edge weights are dynamically adjusted, real-time and accurate sensing of the network states is achieved, node overload risks are predicted in combination with an ARIMA model, potential problems are found in advance, and the method has the advantages of being high in reliability and high in reliability. Therefore, timely and accurate network state input is provided for intelligent resource slice arrangement, network changes can be responded more quickly and efficiently, and the overall system performance and stability are improved.

The invention relates to an AI Agent-based production equipment edge computing decision dynamic adjustment method and system, and the method comprises the steps: obtaining real-time operation data comprising equipment state parameters, production environment parameters and edge computing node computing resource use data through an AI Agent suitable for the deployment of a production equipment edge computing node; performing feature extraction on the data to obtain a multi-dimensional feature set, inputting the multi-dimensional feature set into a pre-training decision model, generating an initial decision result, generating an equipment operation instruction according to multi-aspect accurate information, executing actual operation, and realizing dynamic adjustment of a production decision; according to the scheme, the decision-making efficiency, accuracy and adaptability of industrial equipment production can be improved, and then the production efficiency of industrial production equipment is improved.

The invention discloses a performance monitoring system and method for expansion and upgrading of a big data platform, and relates to the technical field of big data analysis. According to the performance monitoring system and method, key information of newly-added Web servers is collected to form a standardized configuration data set, and node deployment normalization and cluster compatibility in the expansion stage are improved; operating load logs before capacity expansion are directionally pulled and screened, and a historical cluster server operating load set is constructed through structural analysis; first dynamic weight configuration is completed by combining two types of load sets, the cache types of the Web servers are distinguished according to cache configuration identifiers, and secondary weight adjustment is performed on the shared distributed cache Web servers based on the hit rate, so that the defects of existing weight configuration are overcome, accurate weight adaptation is realized, the cache hit rate is increased, the frequency of requesting to penetrate through a database is reduced, and the service life of the Web servers is prolonged. The database load is reduced, the response delay is shortened, resource imbalance and service instability are avoided, and the performance of platform expansion upgrading operation is guaranteed.

The invention relates to the technical field of traffic flow state sensing, and discloses a multi-mode road network traffic flow state real-time sensing and complementing method. Comprising the following steps of S1, an edge node deployment and reference calibration stage, S2, a lightweight multi-modal data acquisition stage, S3, an edge end real-time preprocessing stage, S4, a dynamic reliability weight fusion stage, S5, a sparse region completion stage and S6, a cloud iterative optimization stage. The system further comprises the following modules and components: an edge node deployment and reference calibration module, a lightweight multi-modal data acquisition module, an edge end real-time preprocessing module, a dynamic reliability weight fusion module, a sparse region completion module and a cloud iterative optimization module. The objective of the invention is to solve the problems that existing traffic flow state sensing mostly depends on sensing equipment of a single type, traffic flow data acquisition requirements in different scenes are difficult to consider, and data dimensions are incomplete due to equipment limitation.

The invention relates to the technical field of data circulation and data security, and discloses a digital ecological data market circulation system, comprising: a data provider node deployed with a federated learning client and used for locally training a model by using original data, generating an encrypted intermediate result and managing a corresponding data asset voucher; the data demand side node is deployed with a federated learning coordination server and is used for defining a federated learning task, distributing an initial model and aggregating intermediate results from each data provider node to update a global model; the data element circulation method comprises the following steps of data capitalization and voucher generation, federal learning and process evidence storage, under-chain credible contribution degree evaluation and intelligent contract driven settlement. Compared with the prior art, the method has the advantages that the leakage risk is completely eradicated from the root of technology, a dynamic and accurate value evaluation and distribution system is achieved, a credible environment which is traceable in the whole process and transparent in rule is constructed, and the mobility and financial attributes of data assets are improved.

The invention provides an intelligent operation and maintenance method and system for an industrial computing network, electronic equipment and a storage medium, and the method comprises the steps: deploying computing power agents at heterogeneous computing power nodes to obtain operation and maintenance events in a unified manner, and carrying out the centralized root cause analysis of the operation and maintenance events through a cloud end, so as to match an operation and maintenance strategy, the method comprises the following steps: acquiring an operation and maintenance strategy library, issuing the operation and maintenance strategy to a corresponding computing power agent for execution and feeding back a result, and finally performing closed-loop updating on the operation and maintenance strategy library and an artificial intelligence model based on a complete event case, thereby realizing unified perception of heterogeneous dispersed computing power nodes through the computing power agent, and solving the problem that unified management and monitoring are difficult due to resource dispersion; through automatic root cause analysis and strategy matching, a fault root cause can be rapidly and accurately positioned and an operation and maintenance scheme can be generated so that serious dependence on artificial experience can be eliminated and fault processing time can be substantially shortened. Through continuous optimization of a closed-loop learning mechanism, the operation and maintenance automation level is greatly improved, and high availability and stability of an industrial computing network are guaranteed.

The invention relates to a virtual consistency multi-node message passing interface expansion method, device and equipment. The method comprises the following steps: deploying a distributed file system client at each computing node of a multi-node cluster, creating a unified virtual directory mounting point, transparently converting a file operation request under the unified virtual directory mounting point into a corresponding network protocol, and docking a global unified data storage pool, the unified virtual directory mounting point is used for providing consistent file views for all the computing nodes; pointing a file read-write path prefix of the message passing interface process to the unified virtual directory mounting point; and in response to the received user operation request, allocating computing nodes to the user operation request, ensuring that all the allocated computing nodes are mounted to the distributed file system, and starting a message passing interface process. By adopting the method, the consistency of the cross-node file view can be solved from the system level on the premise of not changing the communication logic.

The invention relates to the technical field of wireless sensor networks, in particular to a heterogeneous wireless sensor network coverage method for a mountain new energy construction site, which comprises the following steps of: constructing a three-dimensional mountain monitoring area, inputting related parameters and establishing a multi-target optimization model taking the non-coverage rate, the reciprocal of the connectivity rate and the minimum total energy consumption as targets; initializing a dung beetle population, dividing the dung beetle population into four classes, obtaining an initial coverage scheme, and screening a non-dominated coverage scheme solution set for storage; iteratively updating the positions of various types of dung beetles based on a multi-target dung beetle optimization algorithm; the current coverage scheme and the archive set are combined, the archive set is updated after non-dominated sorting, and dense solutions are discarded to guarantee diversity when the scale is over-scale; and outputting a solution set after the maximum number of iterations is reached, and selecting a target scheme to complete node deployment. The method is adaptive to complex mountain scenes, network coverage and communication quality are improved, energy consumption is reduced, local optimum is avoided, and mountain monitoring effects of high coverage, low energy consumption and strong adaptation are achieved.

The application discloses a 6G distributed tri-polarization MIMO network parameter configuration method, and belongs to the technical field of wireless communication network optimization. The method unifies node deployment parameters, array structure parameters, tri-polarization port parameters and propagation mode parameters into the same candidate configuration and evaluation process; according to path loss, large-scale and small-scale propagation parameters, polarization impact, differential directional diagram response and near-far field propagation response, the overall network equivalent channel matrix corresponding to the candidate scheme is constructed; then, the candidate scheme is screened based on capacity, effective rank, condition number and received power, and a recommended network parameter configuration scheme is output. The method can coordinate the relationship between spatial deployment, polarization structure and propagation mode under the same framework, and improve the matching of the parameter configuration result and the actual propagation condition.

The invention discloses a node deployment method, device and equipment and a storage medium, which are applied to a vehicle, the vehicle is provided with a plurality of nodes deployed in an initial deployment mode, and a plurality of measurement points used for measuring the signal intensity of the nodes are arranged in a set range of the vehicle. The method comprises the following steps: for each measurement point, collecting the signal intensity of each node at the measurement point; determining an unqualified target measurement point from the plurality of measurement points according to the signal intensity; and performing node deployment on the vehicle again according to the target measurement point. According to the scheme, the initial node deployment effect is quantitatively analyzed by introducing a deployment evaluation mechanism based on the signal intensity of multiple measurement points, and the redeployment of the node positions is guided accordingly, so that the signal coverage quality in a vehicle setting range is effectively improved, the rationality and stability of node deployment are improved, and the vehicle safety is improved. And the problem of signal blind area or uneven coverage caused by empirical deployment is avoided.

The invention relates to the technical field of wireless communication, in particular to an ad hoc network transmission method suitable for a field environment, which comprises the following steps: S1, heterogeneous network architecture design: network nodes are deployed in a non-signal area and are responsible for data acquisition and Mesh relay transmission; the gateway nodes are deployed at the boundary of a signal area and are responsible for 4G / LoRa protocol conversion and cloud forwarding, and each node has the capability of automatically identifying the signal intensity of the current environment; and S3, an intelligent transmission mechanism is adopted, in the starting stage, after the nodes are powered on, cellular network signals are automatically detected, and according to the signal strength, the roles of the network nodes and the competitive gateway nodes are autonomously determined. An autonomous relay transmission mechanism based on the Mesh network is constructed, the network reliability is improved, autonomous roaming and multi-path transmission of the nodes are achieved, the communication success rate in a severe environment is improved, energy consumption distribution is optimized, and the situation that specific nodes deplete energy too early is avoided through dynamic role distribution.

The invention relates to the technical field of virtual power grid coordination control, in particular to a distributed virtual power grid multi-source self-adaptive power coordination control method, which comprises the following steps: S1, deploying a sensor network at each node of a distributed virtual power grid, and installing voltage, current and frequency sensors and load monitoring equipment at key positions of the power grid, the Internet of Things technology is adopted, data collected by a sensor are transmitted to a data processing center in real time, a complete multi-source data collection and transmission system is constructed, and basic data are provided for subsequent analysis and prediction; s2, after the data processing center receives the original data, cleaning preprocessing is carried out firstly, a threshold value is set through a statistical method to remove abnormal data, and noise is removed through a filtering algorithm, and the problems that an existing distributed virtual power grid power coordination control method is low in prediction accuracy, cannot provide a reliable basis for power coordination control, and is poor in prediction accuracy can be effectively solved. And the energy utilization efficiency and the stability of the power grid are poor.

The invention relates to the technical field of honeypot trapping networks, in particular to a transverse movement attack path analysis method and system based on a virtualized trapping network. The method comprises the steps that system logs of N network nodes in the virtualized trapping network are collected regularly, honeypot servers are deployed in all the network nodes in the virtualized trapping network, and N is an integer larger than or equal to 1; updating the constructed attack path according to the association degree between the system log of the Nth network node and the constructed attack path; traversing the system logs of the N network nodes until the system logs collected in the current period are processed. According to the method, all the log data in all the nodes in the virtualized trapping network are integrated, and a complete and comprehensive attack graph is established, so that comprehensive analysis of cross-system and cross-device behaviors of attackers is realized, and the depth and accuracy of existing analysis are improved.

The invention discloses a computing power network resource credible scheduling method based on cloud network security fusion, and relates to the technical field of cloud computing and network security. Aiming at the problems of low resource utilization rate, insufficient security isolation, lack of credibility evaluation and the like in the existing computing power scheduling, a computing power network architecture containing a distributed security resource pool is constructed, and various security services are deployed through security nodes and serve as trust agents to provide security resource support and credibility evaluation basis for computing power task scheduling. According to the method, node state information is collected through state monitoring modules deployed at all nodes; the node credibility is calculated through a credibility evaluation module on the dispatching center and the security node; and the task scheduling module is used for realizing target node optimization and security service link optimization by utilizing a hierarchical deep Q network (Hierarchical Deep Q-Network) model on the basis of the node state information and the credibility result. According to the method, efficient task scheduling can be guaranteed, meanwhile, a user-defined security policy is supported, malicious nodes are effectively identified, and the security of a computing power network is improved.

This invention provides a method for early warning and self-healing of material blockages on production lines that integrates the Internet of Things (IoT). It relates to the fields of industrial intelligent manufacturing and automation technology. The method involves deploying multiple types of sensors at key equipment nodes on the production line to collect multi-source heterogeneous data. This data is then transmitted to edge computing nodes for preprocessing, outputting a multimodal feature dataset. A production line blockage early warning model is constructed based on this multimodal fusion deep learning network model. Blockage monitoring is performed using this model. Based on the monitoring results, corresponding self-healing strategies are executed, generating control commands that are sent to the production line actuators. The entire chain of data for each early warning and self-healing event, along with its final result labels, is collected to form a feedback dataset. This dataset is then used for periodic incremental training and optimization of the production line blockage early warning model. This invention achieves early warning and autonomous handling of blockages, improving production continuity and intelligence.

The invention relates to the technical field of electric power automation, and particularly discloses a spare power automatic switching control method and system based on an artificial intelligence Internet of Things, and the method comprises the steps: node deployment and initialization, data collection and preprocessing, edge reasoning, cloud fusion, decision control and closed-loop monitoring. According to the scheme, the lightweight intelligent models are deployed at the edge nodes, local real-time fault prediction and confidence evaluation are realized, the cloud realizes fault-tolerant fusion under communication abnormity according to the confidence of each edge node, the influence of single-point communication abnormity on the overall spare power automatic switching judgment of the system is effectively avoided, and the adaptability is relatively high; probabilistic risk assessment and expectation return modeling are introduced to realize quantitative decision-making of control actions, flexibility and adaptivity of a spare power automatic switching strategy are effectively improved through dynamic optimization response to system risks, edge nodes and a cloud end carry out online learning to effectively adapt to operation environment changes of an Internet of Things communication network, and the reliability of a spare power automatic switching system is improved. And the fault tolerance and robustness of the system are enhanced.

A network slice deployment and reconfiguration method includes: deploying virtual nodes in each network slice sequentially; if the deployment of the current virtual node in the current network slice fails, identifying the congested physical node causing the failure, and selecting the congested physical node with the highest congestion as the current congested physical node; selecting the network slice with the lowest importance that was successfully deployed as the current successfully deployed network slice; for the current congested physical node, if the currently successfully deployed network slice is reconfigurable, reconfiguring the currently successfully deployed network slice and redeploying the current virtual node of the current network slice; otherwise, selecting the next successfully deployed network slice as the current successfully deployed network slice and returning to the reconfigurability determination step; if there is no next successfully deployed network slice, selecting the next congested physical node as the current congested physical node and returning to the reconfigurability determination step; if there is no reconfigurable successfully deployed network slice for each congested physical node, rejecting the deployment of the current network slice.

The application discloses a kind of distributed reservation systems and methods for multi-resource cooperation, comprising: transaction manager, at least two resource managers, lock manager, transaction log module and workflow controller;Transaction manager coordinates each resource manager through two-phase commit 2PC protocol, realizes the atomicity execution of cross-node shadow and summary table update;Lock manager adopts read-write lock separation mechanism to resolve concurrent conflict, and handles deadlock problem through timeout detection and active unlocking strategy;Transaction log module is based on prewrite log mechanism Complete record shadow and summary table linkage operation details, provide reliable support for fault recovery and transaction rollback;Workflow controller encapsulates distributed call details, realizes service survival real-time detection and automatic reconnection function.The application has high expansibility, strong consistency, high concurrent adaptation capability and perfect exception fault-tolerant mechanism, and can be widely applied to travel service scene of multi-node deployment.

The invention belongs to the technical field of big data customer information matching, and discloses an intelligent customer information matching method based on big data, which comprises the following steps of: firstly, establishing a scene customer behavior semantic dictionary according to three groups of new customers, high-value customers and loss early-warning customers, and determining behavior label mapping rules of different customer types; for example, the browsing duration of a new customer exceeds 3 minutes, the consultation frequency exceeds 2, the behavior is defined as a high-intention behavior, the semantic dictionary is dynamically updated every 24 hours based on cross-platform semantic conflict feedback, and the cross-platform data semantic standard is unified; secondly, screening weak association features by adopting a mutual information and customer value double-weight algorithm, setting weights according to customer value differences, and preferentially retaining features with higher association degree with customer demands to generate structured feature vectors; and finally, deploying a preprocessing effect verification module at an edge computing node, performing field secondary labeling, null interpolation complementation and time format unification operation on the data, and improving the data standardization level.

The application relates to the technical field of artificial intelligence, and particularly discloses a complex neural network multi-node deployment method based on semantic communication, which comprises the following steps: obtaining a complex neural network, training the complex neural network to obtain a trained complex neural network; evaluating the maximum sub-model size that can be borne by each computing power node; splitting the trained complex neural network into multiple sub-models according to the maximum sub-model size that can be borne by each computing power node, and dispersively deploying the multiple sub-models on each computing power node; constructing a high-entropy semantic communication link between adjacent computing power nodes, logically connecting the dispersively deployed multiple sub-models according to a data flow transmission path to form a complete distributed large model; and performing inference on the distributed large model. The application solves the problem of distributed deployment of a large-scale neural network under the condition of insufficient computing power of a single node, and provides a feasible technical path for intelligent shuttling, emergence and on-demand allocation.

The invention relates to a development machine packaging method and system in a K8S cluster, which is characterized in that development machine resources are defined based on CRD and a controller, configuration information is described, and automatic life cycle management is realized in combination with operators; cRD is deployed in a host cluster, and is synchronized to K8S space of each tenant through an exclusive synchronizer; an SSH access path is opened by means of node port type service resources and an exclusive layer 4 forwarding entry; a public network IP path is automatically allocated by using the load balancer type service resources in combination with a metal load balancer component; remote access and safety control of the Zhu service are realized through a gateway, a signature verification mechanism and a domain name system analysis function of list monitoring; and deploying an exclusive daemon process set at each host node.

The invention relates to the technical field of power system automation and electric energy quality control, in particular to an electric energy quality optimization control method and system based on distributed collaborative decision. The method comprises the following steps: deploying synchronous phasor measurement units and corresponding edge intelligent decision nodes at a plurality of nodes of a power grid, and constructing a distributed network; each node calculates an electric energy quality characteristic index based on local data; dynamic role negotiation is carried out through local communication, and a leading controller is determined; the dominant controller fuses strategies and confidence information of local and adjacent nodes to generate a cooperative control strategy; and finally, equipment such as a static var generator and an active power filter is controlled to perform coordinated execution. Through a decentralized collaborative decision-making mechanism, the defects that centralized control is slow in response and low in reliability are overcome, rapid self-adaptive treatment on voltage sag, harmonic waves and other problems is achieved, and the response speed, the treatment success rate and the system robustness are remarkably improved.

A node deployment method for time difference positioning and direction finding of internal and external field targets, which takes the weighted sum of the average positioning accuracy improvement of the internal field area positioning and the average direction finding accuracy improvement of the external field area as the objective function of the station deployment optimization, takes the wireless sensor sensing capability as the constraint condition, improves the coverage rate of the internal field area, and deploys the distributed nodes for time difference positioning and direction finding of internal and external field targets; after the optimization deployment of the application, in the case of the change of the external field target source position and RDOA measurement error, the average positioning accuracy of the internal field area, the average direction finding accuracy of the external field target, and the coverage rate performance of the internal field area are all significantly improved, which improves the coverage range of the wireless sensor network while taking into account the internal field target positioning and external field target direction finding of the key area.

The invention relates to the technical field of power monitoring and adjustment, and discloses a three-phase unbalance degree monitoring and adjustment integrated method fused with edge computing, comprising the following steps: S1, deploying edge computing nodes; s2, acquiring three-phase voltage, current and active power data of the power distribution network through the power distribution terminal; s3, calculating a three-phase unbalance degree; s4, carrying out edge side real-time analysis and threshold judgment; s5, generating a dynamic adjustment strategy; and S6, adjusting instruction execution and feedback. According to the technical architecture of edge calculation enabling, dynamic adaptation optimization and hierarchical cooperative control, multi-dimensional improvement of monitoring precision, adjustment efficiency, operation economy and system collaboration is achieved for the pain points of three-phase unbalance monitoring lagging, extensive adjustment, low resource utilization rate and the like of a traditional power distribution network.

The invention relates to the technical field of photovoltaic power generation, and discloses a photovoltaic power generation anomaly detection method and device and a storage medium, and the method comprises the steps: generating standardized time series data, calculating nonlinear entropy and energy entropy features, constructing a mixed feature space, and outputting an optimized feature set through an attention mechanism; inputting the optimized feature set into a neural network model, training the model through a simulation sample generated by a digital twin system and a real sample, and migrating the model to a lightweight student model through knowledge distillation; a student model is deployed at an edge computing node for real-time anomaly analysis, parameters are updated by using a federal learning strategy aggregation model, and an anomaly judgment threshold is dynamically adjusted; an abnormal analysis result is fed back to a cloud end to be compared with digital twinborn simulation, and a feature extraction strategy and model parameters are adjusted through an optimization algorithm and a reinforcement learning framework. According to the method, the detection precision of the lightweight model in a complex environment is improved, and the contradiction between limited edge computing resources and high real-time requirements is solved.