116 results about "Network clustering" patented technology

The invention discloses an electric power, traffic and communication network collaborative electric power recovery method and system and a medium, and the method comprises the steps: inputting three-network comprehensive data of a target region into a deep classification-clustering model to obtain a three-network clustering result, and carrying out the calculation to generate a three-network node coupling tensor; determining a fault node set of the power network, and quantifying the cross-network influence of fault nodes by using a three-network node coupling tensor; based on the cross-network influence of the fault node, a chain risk value is obtained, and thus the weak level of the fault node is obtained; based on the weak grade of the fault node and the cross-network influence of the fault node on the traffic congestion rate and the communication delay, constructing a three-network cooperative power recovery model, and solving to obtain an optimal power recovery strategy; performing power recovery on the target area based on the power recovery optimal strategy; the power can be recovered through cooperation of power, traffic and the communication network, the recovery difficulty is small, the efficiency is high, and power failure economic losses and first-aid repair resource waste are reduced.

An embodiment method for managing at least one vehicle network including at least one electronic control unit (ECU) among a plurality of ECUs in a vehicle network management apparatus is provided, which may include, based on information of at least one default partial network cluster including at least one ECU among the plurality of ECUs according to at least one default partial network function provided by default in a mapping database, configuring a new partial network cluster by adding an ECU according to user customization to the at least one default partial network cluster, and storing information of the new partial network cluster in the mapping database.

The invention discloses a storage battery real-time monitoring method based on edge calculation, and the method comprises the following steps: S1, collecting multi-source operation parameters of a storage battery, and constructing an operation parameter set; s2, processing the operation parameter set to generate a standardized state vector; s3, on the basis of a micro neural network model, generating graph structure reasoning characteristics are fused; s4, performing global search on a connection structure between the sub-network clusters by adopting a spider-now-monkey optimization algorithm, and updating the structure configuration of the micro neural network model; s5, on the basis of the graph structure reasoning features and the optimized sparse connection structure, forming a monitoring judgment result; s6, performing edge response control according to a monitoring judgment result, and generating a response record; and S7, based on the response record and the monitoring determination result, completing edge side dynamic optimization of the miniature neural network model. Sparse neural clusters and edge reasoning are adopted, and real-time monitoring and dynamic optimization control of the state of the storage battery are achieved.

The invention relates to the technical field of academic network processing, and particularly discloses an academic network clustering method based on graph structure perception, which comprises the following steps: preprocessing an academic network and constructing a data set; based on the constructed data set, extracting features of the academic network through an enhanced graph auto-encoder, and constructing a reconstruction loss function; periodically updating an adjacent matrix of the academic network through a graph weight updating mechanism, and obtaining an optimal feature representation; a self-supervision mechanism is introduced, clustering soft distribution and auxiliary target distribution are obtained based on the obtained optimal feature representation, and a clustering loss function is determined; and integrating the reconstruction loss function and the clustering loss function, iteratively optimizing parameters of the structure perception depth map clustering model, and obtaining a clustering result after the parameters of the structure perception depth map clustering model are updated. The invention aims to solve the problems of intensive calculation and insufficient edge reliability in the existing academic network clustering method, and improve the efficiency and accuracy of the academic network clustering algorithm.

The present invention provides a geophysical identification method for mid-deep undercompacted low-velocity mudstone. By statistically analyzing data, representative P-wave velocity, S-wave velocity, and density of low-velocity mudstone and gas-bearing sandstone in well logging data are obtained. Combining geological information, a theoretical model of the superimposed relationship between low-velocity mudstone and gas-bearing sandstone is designed, and convolution forward modeling and prestack forward modeling are carried out on it. The post-stack and prestack seismic attributes of the model are calculated respectively. Then, sensitive attributes are optimized from these attributes, and the obtained sensitive attributes are used as learning samples, and the superimposed relationship is identified by probability self-organizing neural network clustering. The present invention adds prestack attributes to the optimization of sensitive attributes, making the fuzzy self-organizing neural network more accurate in identifying the superimposed relationship between gas-bearing sandstone and low-velocity mudstone, effectively distinguishing low-velocity mudstone from gas-bearing sandstone, and providing support for subsequent effective reservoir prediction.

The invention relates to the technical field of unmanned aerial vehicle ad hoc network cluster management and control scheme design based on intelligent street lamps and satellite communication, in particular to an unmanned aerial vehicle ad hoc network cluster management and control system based on intelligent street lamps and satellite communication. The system comprises an intelligent street lamp subsystem, a satellite communication subsystem, an unmanned aerial vehicle cluster node and a dynamic cooperative control platform. The innovative scheme comprises the following steps: (1) the multimode communication gateway realizes seamless conversion between a satellite protocol and a ground Internet of Things protocol; (2) a street lamp sensor generates a dynamic risk map to guide cluster obstacle avoidance; (3) supporting signal interruption emergency networking by a rapid clustering algorithm based on geometric topology; (4) task priority drives time slot distribution to improve communication efficiency; and (5) the satellite-street lamp-relay unmanned aerial vehicle multistage redundancy guarantee system is continuously controllable. According to the scheme, the communication reliability, the environmental adaptability and the cooperative capability of the cluster in a complex urban area are remarkably enhanced.

The invention belongs to the technical field of data processing, and particularly relates to a rock-soil data structured conversion method. According to the method, unstructured data of rock and soil logs is split into minimum information units of entity, attribute and relation clues through information particle deconstruction, standardized entities and relations are generated through clue association network clustering and double-track reasoning model processing, and a knowledge graph is constructed and mapped into structured data; and constructing an initial geologic model by using structured data, extracting core data, converting the core data into an extended IFC format intermediate file containing a geologic special entity, and finally associating a BIM model to realize data fusion. According to the method, structured conversion of unstructured data is realized, a data format barrier is broken through, and the engineering collaboration efficiency is improved.

The present application relates to a cluster shared traffic threshold-based rate limiting method and apparatus, which are used for achieving effective bandwidth management and allocation among a plurality of nodes in a cluster and among a plurality of network card queues in the nodes. The method comprises: S1, a cluster manager issuing a cluster rate limiting threshold of a specified data stream to each node in a network cluster, and adding the forwarding process of each node into a multicast to share traffic information between the nodes, the cluster rate limiting threshold being acquired in the forwarding process of the node; S2, a node controller collecting statistics about the traffic of the specified data stream flowing into a network card per second, performing marking, sending out, by means of multicasting, a unique identifier of the node and network card traffic received per second to be shared to other nodes in the cluster, and on the basis of a multicast packet received from the cluster, calculating a node rate limiting quota threshold of the present node; S3, on the basis of each service core for processing traffic of queues in the forwarding process of the node and the bandwidth proportion of the total traffic of the nodes, a bandwidth allocation scheduler allocating a core rate limiting quota threshold of each node; and S4, on the basis of real-time data of the processed traffic of each queue in the nodes and the proportion of the total bandwidth of the nodes, a token bucket manager performing periodical and dynamical adjustment by means of a token bucket algorithm to obtain the proportion of each queue in a cluster rate limiting bandwidth, so as to limit the rate of the traffic passing through the queue.

The invention relates to the technical field of visual positioning, in particular to an improved bolt pose estimation method. The method comprises the following steps: S1, creating a virtual bolt data set for training; s2, using a deep learning-based method FPCC instance segmentation network to extract features of each point, and using a non-maximum suppression mode to search for a center point for each instance; s3, the point with the highest score is set as the geometric center point of each instance, and the remaining points are clustered to the nearest geometric center based on a network clustering algorithm, so that the instances are segmented; and S4, after the instance is segmented, performing cylinder fitting, re-estimating parameters of a cylinder by using an improved RANSAC algorithm, obtaining a direction vector of an axis of the cylinder, and determining a central axis direction of the bolt. Based on an FPCC instance segmentation network, a new bolt pose estimation method is provided in combination with an SAC-IDBSCA coarse registration algorithm, an NDT fine registration algorithm and an improved RANSAC algorithm, the FPCC instance segmentation network provided by the invention can still realize rapid and effective segmentation of bolts under a high-degree stacking condition, any training of manual annotation data is not needed, the algorithm is simple, the algorithm is easy to implement, and the method is suitable for large-scale popularization and application. The improved RANSAC algorithm provided by the invention can effectively compensate the negative influence of the traditional algorithm on the algorithm effect due to improper threshold selection.

The invention provides a salt marsh vegetation long-term change monitoring method, which belongs to the technical field of salt marsh vegetation monitoring, and comprises the following steps: establishing a multi-level monitoring grid with main monitoring point spacing of 500m and auxiliary monitoring point spacing of 100m, and configuring a multi-source sensor to obtain environmental data; a wavelet transform technology is used to separate seasonal change and long-term change trends, a matrix equation is calculated through seasonal change amplitude to dynamically adjust sampling frequency, and an ecological network connectivity analysis algorithm based on a graph theory is constructed to calculate a network clustering coefficient and a shortest path length to evaluate habitat fragmentation. A fuzzy C-means clustering algorithm is adopted to process the boundary fuzziness of a vegetation community based on multi-dimensional environmental factors, a multi-scale matrix mapping hierarchical processing system is established to realize pixel-to-landscape scale information fusion, and the technical problem that the monitoring result is not accurate enough due to insufficient monitoring precision of long-term change of salt marsh vegetation is solved.

The invention discloses an underwater acoustic sensor network clustering method, system and device and a medium, and relates to the technical field of underwater acoustic communication, and the method comprises the steps: obtaining the current network state characteristics of each node of a target underwater acoustic sensor network, inputting the current network state characteristics into an underwater acoustic sensor network clustering model, and obtaining a current optimal clustering scheme; based on the current optimal clustering scheme, electing cluster head nodes through a dynamic role rotation mechanism, and generating an adaptive network topology structure; performing performance evaluation on the adaptive network topology structure to obtain a group of performance indexes; and if the performance index does not meet the performance threshold value, or the confidence coefficient of the current optimal clustering scheme output by the underwater acoustic sensor network clustering model is lower than a confidence coefficient threshold value, starting a complete optimization learning process. According to the technical scheme, the technical problem that it is difficult to balance multi-target performance online and adaptively and carry out continuous self-optimization to adapt to the dynamic underwater environment through an existing clustering method is effectively solved.

The invention relates to the technical field of coal mine communication, and discloses a mine signal blind area ad hoc network cluster system which can support multi-person talking, is low in cost and can quickly recover communication after a disaster, the mine signal blind area ad hoc network cluster system comprises a relay unit and a terminal unit, and the relay unit comprises a plurality of relay devices arranged at intervals. At least one relay device is in wired or wireless connection with the ground node to receive and transmit emergency signals, each relay device adaptively adjusts radio frequency parameters, and adjacent relay devices are connected through a LoRa single-channel link and communicate through a Mesh protocol; the terminal unit comprises a plurality of carry-on terminals which are connected with the nearest relay device or the strongest-signal relay device through a LoRa single-channel link, and each carry-on terminal comprises a transmitting mode and a receiving mode; and when receiving the emergency signal or a random access request sent by the portable terminal, the relay device forwards the emergency signal or the personnel sound signal to an adjacent relay device, or sends the emergency signal or the personnel sound signal to the portable terminal in a receiving mode in a broadcast mode.

This invention provides an energy-saving clustering routing method for wireless sensor networks based on improved multi-target ant colony optimization, comprising: Step 1, initialization; Step 2, determining the set of active sensor nodes in the current round; Step 3, completing network clustering; Step 4, maintaining the Pareto optimal path solution set; Step 5, repeating steps 2 to 4 until the maximum number of iterations is reached or the solution set converges, outputting the Pareto optimal path solution set as the routing scheme for network data transmission. This invention improves network energy efficiency and extends network lifetime by constructing a globally collaborative energy management framework that integrates sleep scheduling, cluster head election, and routing optimization, while ensuring the real-time performance and reliability of data transmission.

The embodiment of the invention discloses a terminal data management method and device, electronic equipment and a storage medium. Through a multi-terminal cluster management triggering mechanism, monitoring data, installation position data and equipment operation state data are classified, only core data are transmitted and matched with terminal identifiers, the transmission efficiency is improved, and redundant data occupation is reduced; secondly, a standby switching design of a main communication module and a virtual operator network cluster communication module is adopted, so that the problem of data interruption caused by link instability in a complex environment is solved; and meanwhile, the core data are uniformly reported to the multi-terminal management server, so that multi-terminal uniform management and control and real-time state control are realized, the problems of low reliability and poor management efficiency of the existing scheme are solved, and the reliability and management efficiency of terminal data management are improved.

The invention relates to the technical field of complex network analysis and data mining, and provides a scientific research cooperation analysis method for edge crossing attribute network clustering, and the method comprises the steps: obtaining original data, and carrying out the preprocessing of the original data; an undirected empowerment cooperative network is constructed and processed to obtain a core sub-graph, and the maximum connected component LCC of the core sub-graph is extracted; constructing a node multi-dimensional feature vector by using a natural language processing technology; using an ECV algorithm to determine an optimal community number; constructing a topological feature matrix and an attribute similarity matrix by adopting an ANCA algorithm, and fusing the topological feature matrix and the attribute similarity matrix; hyper-parameters of the ANCA algorithm are adjusted and optimized in a grid search mode, and community division and analysis are carried out. The method has an extremely important application value and a wide social prospect in optimizing resource configuration, evaluating team influence, promoting academic communication and cooperation and guiding development of a scientific research direction.

The invention relates to a large-scale heterogeneous multi-attribute equipment scheme clustering decision-making method and a medium. The method comprises the following steps: uniformly converting heterogeneous attribute data in a digital twin decision-making information system into binary connection numbers; determining an attribute weight by adopting an MEREC method, and constructing an attribute non-compensable value based on the attribute weight and the binary connection number; generating a scheme similar network according to the attribute non-compensable value; performing network clustering operation on the scheme similar network, and outputting a scheme clustering result; and based on the scheme clustering result, calculating the comprehensive target distance of the scheme in the cluster by adopting the grey target theory, and fusing the global value of the scheme and the comprehensive target distance to generate a final scheme score. According to the method, the problems of heterogeneous information fusion distortion, attribute non-compensatory mechanism deficiency and low large-scale scheme clustering efficiency in a digital twinborn decision scene are solved by constructing heterogeneous data unification-attribute non-compensatory mechanism modeling-network clustering-intra-cluster decision.

The application provides a sensor network clustering routing method based on coverage area division and energy consumption balance, and the method comprises the following steps: obtaining a network structure of sensor nodes; performing area division on the network structure according to a pre-set sink node, so as to obtain at least two node areas; calculating a distance factor and a residual energy factor of nodes in each node area according to the node areas obtained by division; calculating a cluster head selection threshold of each node according to the distance factor and the residual energy factor of each node and the node area where each node is located; determining a cluster head in a current period according to a pre-set selection rule and the cluster head selection threshold of each node, and the remaining nodes are ordinary nodes, and clustering the ordinary nodes according to the cluster head; and performing a fusion task for the nodes after clustering until the next period, so that the network structure is processed in a hierarchical manner, the sensor nodes can be effectively managed, the network energy consumption is reduced, and the network resources are optimized.

The invention relates to the technical field of vehicle communication, in particular to an intermittent control method for an intelligent traffic unmanned vehicle communication network, and the method comprises the steps: carrying out the precise modeling of the unmanned vehicle communication network of an intelligent traffic system through employing a positive complex network model, so as to obtain a state space model, and then assuming an isolated node, and communicating with other network clusters to realize information interaction. And secondly, by designing an observer and a periodic intermittent control protocol thereof, the unmanned vehicle communication network of the intelligent traffic system can normally achieve synchronization without real-time communication, so that the stability of the unmanned vehicle communication network under various actual conditions is ensured, and the control efficiency of each unmanned vehicle is improved.

The invention discloses a large model optimization method based on multi-round diagnosis and treatment experience learning. The method comprises the steps that variable-length multi-modal time sequence modeling and unified embedded representation learning are carried out on dynamic domain experience through a heterogeneous tense multi-graph expression model; the disease course evolution is constructed into a heterogeneous, multi-modal, multi-scale and uncertainty weighted signal graph network cluster with a time sequence concept; carrying out strategic random walk resampling with a time concept on the network cluster; and performing large model optimization according to the sampling and multi-round diagnosis and treatment experience. According to the method, through a multi-modal domain experience unified representation modeling technology based on heterogeneous multi-graph progressive embedding learning, higher-quality feature expression is learned from multi-modal input data.

The utility model provides a computing system, network equipment, a distributed network cluster system and a PCB computing board card, and the computing system comprises a mainboard which comprises a first expansion bus interface; the DPU waste chip acceleration card is connected to the first expansion bus interface, the DPU waste chip acceleration card comprises an independent CPU subsystem and an acceleration engine, the CPU subsystem is normal, the acceleration engine has a fault, so that the DPU waste chip acceleration card is used as a CPU daughter card of a single board, and the DPU waste chip acceleration card is connected to the first expansion bus interface. The CPU subsystem and the acceleration engine have power supply and clock systems that are independent of each other. According to the technical scheme provided by the invention, the inherent CPU subsystem in the DPU waste piece can be reused as a computing node of other equipment, so that the waste is reduced.

Techniques are disclosed for a computing system comprising processing circuitry having access to a storage device, the processing circuitry configured to: generate, by a network controller executing in a software defined network (SDN), an advertisement in a first network cluster executing within a container orchestration platform of the SDN, wherein the advertisement conforms to a routing protocol and comprises information identifying a network service executing in the first network cluster, wherein the network service exposes a backend of a network application to the container orchestration platform of the SDN; and broadcast, by the network controller and to a second network cluster executing within the container orchestration platform of the SDN, the advertisement in accordance with the routing protocol.

The present invention relates to a hybrid channel allocation method applicable to wireless self-organizing networks in the field of wireless self-organizing networks, and is particularly applicable to wireless self-organizing network environments that adopt a time division multiple access (TDMA) mechanism. First, the network cluster head node centrally allocates dedicated channels for newly connected nodes, which can ensure the reliable transmission of time-sensitive services of each node; at the same time, considering that the dedicated channel of each node has the characteristic of being spatially reused by nodes beyond two hops, a mechanism for locally maintaining a shared channel list is designed, and a mechanism for competing to occupy a shared channel on a reserved channel is proposed, which can avoid collisions caused by reservation message conflicts and reduce the number of information interactions in competing for a shared channel, ultimately meeting the large-capacity data transmission needs of each node. The hybrid channel allocation method of the present invention makes full use of all channel resources of the network, is simple and easy to implement, and can effectively improve the transmission capacity of the entire network.

The invention discloses a computing resource scheduling method and system based on a computing power network cluster, and relates to the technical field of computing power network clusters, and the method comprises the steps: determining computing tasks matched with a plurality of computing power nodes according to the calculation amount of the plurality of computing tasks, the node load states of the plurality of computing power nodes and a resource scheduling system; and the matching accuracy of the plurality of computing power nodes to the computing task is ensured. Therefore, a calculation progress distribution diagram of the computing power network cluster is determined according to the calculation progress of the plurality of computing power nodes on the calculation task and the calculation modes of the plurality of computing power nodes; according to the computing progress distribution diagram of the computing power network cluster, the computing resources matched with the computing power nodes and the task states of the computing tasks, the optimization system of the computing resources is determined, the computing power of the computing power nodes in the computing process is dynamically optimized, further optimization of the computing resources is achieved based on the optimization system of the computing resources, and the computing efficiency is improved. And the computing power of the computing power node in the computing process is improved.

The present application belongs to the technical field of data processing, and particularly relates to a kind of geotechnical data structured conversion method.The method splits geotechnical log unstructured data into the minimum information unit of entity, attribute, relationship clue by information particle deconstruction, generates standardized entity and relationship through clue association network clustering and double-track reasoning model processing, constructs knowledge graph and maps into structured data;Then, the initial geological model is constructed using structured data, the core data is extracted and converted into an extended IFC format intermediate file containing geological special entities, and finally data fusion is realized by associating BIM model.The method realizes the structured conversion of unstructured data, breaks through the data format barrier and improves the efficiency of engineering collaboration.

The invention discloses construction and application of an interpretability model for virus molecular propagation network clustering. The construction comprises the steps of sorting a sample data set, preprocessing the data set, constructing a model, training, selecting an optimal model for interpretability analysis and the like. The method has the advantages that sequences and epidemiological information are converted into digital signals at the same time, comprehensive information fusion is carried out, and interpretable comprehensiveness and accuracy are achieved; meanwhile, an SHAP black box model is used for explaining a framework, an optimal model is selected for interpretability analysis, the SHAP value of each sample feature is calculated, contribution of the features to a model prediction result is quantified, and composition and features of the network are more effectively explained.

A communication method, device and apparatus based on wireless ad-hoc network. The method comprises: collecting real time network topological information of a plurality of candidate communication terminals; screening the target communication terminal and the communication terminals for a target network central node and a plurality of network sub-central nodes, determining current central communication terminal and initial communication terminals corresponding to the plurality of network sub-central nodes; generating a list of centrality and generating a forwarding sequence table according to the list of centrality, generating a data time slot scheduling table based on the data time slot scheduling information, sending or forwarding the list of centrality, the forwarding sequence table and the data time slot scheduling table in the target RF channel; sending management and control instructions in the target RF channel and controlling all the initial communication terminals in the network cluster to execute the management and control instruction.

The invention discloses a multi-dimensional resource oriented container scheduling and load balancing method and system in a computing network cluster, and the method comprises the steps: constructing a cluster resource state monitoring and index calculation module, and collecting the multi-dimensional resource use data of a physical node and a container in real time, calculating a resource ratio of node volume to container volume based on black box and white box monitoring modes; based on a calculation result, identifying overload nodes and selecting containers to be migrated, processing the overload nodes according to a descending order of node volumes, and selecting migration containers in each node according to a descending order of container volume-to-resource ratios; and selecting immigration nodes for the target container, investigating potential target nodes according to an ascending order of node volumes, finishing container migration on the premise of meeting capacity constraints, and iteratively executing until a cluster has no overload nodes or no executable migration. According to the method, efficient dynamic resource scheduling is provided for diversified workloads in the heterogeneous container cluster environment, the cluster resource utilization rate and scheduling efficiency are improved, and technical support is provided for large-scale containerization deployment.

The invention discloses a low-carbon park capacity configuration and optimization method for photovoltaic and electric heavy trucks. A Monte Carlo sampling method is adopted to simulate the daily driving mileage and the charging starting time of the pure electric heavy truck, and a pure electric heavy truck charging quantity model is established; the method comprises the following steps of: carrying out scientific division on peak, flat and valley periods by adopting a self-organizing map (SOM) neural network clustering method, and optimizing time-of-use electricity price and the charging amount of the pure electric heavy truck by taking a fuzzy demand response mechanism based on a Logistic function as a basis and adopting a non-dominated sorting genetic algorithm (non-dominated sorting genetic algorithm-II); an upper layer system capacity configuration planning model with the minimum park equipment investment cost as the target and a lower layer low-carbon optimization scheduling model with the minimum system operation cost as the target are established, and a green power supply mode of photovoltaic power station-charging pile-pure electric heavy truck is established. According to the strategy provided by the invention, carbon emission and economic cost are reduced, and collaborative development of green low-carbon power supply and economic benefits is realized.

The invention discloses a regional comprehensive energy operation optimization method considering flexible adjustment of a multi-energy network, and relates to the technical field of energy operation optimization, and the method comprises the following steps: S1, constructing an electric heating hybrid energy network cluster and a multi-DIES cluster; s2, constructing a regional power distribution network model and a regional heat supply network model; s3, constructing an electric heating hybrid energy network cluster division model according to the regional power distribution network model and the regional heat supply network model; s4, constructing a multi-DIES cluster double-layer collaborative operation optimization model; and S5, solving the electric heating hybrid energy network cluster division model and the multi-DIES cluster double-layer collaborative operation optimization model, and completing optimization. According to the two-stage optimization method provided by the invention, the power demand of each DIES on the power distribution network can be reduced in the load peak period, the main transformer overload risk is reduced, and the economical efficiency of system operation is improved.

To automatically onboard network functions to a credential vault, a orchestration processor actuates establishment of an cluster account for a network cluster, and actuates a cluster configuration of a processor of the vault to enable authentication of a network cluster. For each of a plurality of network functions associated with the network cluster, the orchestration processor generates an identifier, sets values for parameters of an initialization parameter set, actuates assignment of access permissions for a code address on a memory of the vault, actuates assignment of elevated access permissions for a credential address on the vault memory, and actuates association of the network function with a cluster account of the network cluster. The vault memory thereby defines credential addresses each corresponding to a respective network function.