160 results about "Cluster Node" patented technology

The invention discloses a cluster computing power energy efficiency perception scheduling and green computing system, which relates to the technical field of computers and comprises a multi-source energy efficiency perception and data acquisition module used for acquiring power consumption, utilization rate, temperature, cooling state, PUE index and environmental data of cluster nodes. According to the invention, through the multi-modal energy efficiency fusion sensing network and the multi-scale convolution and time sequence attention fusion network, multi-source heterogeneous energy efficiency data such as current, voltage, temperature, airflow and the like of a node level can be collected and fused in real time and with high precision, noise is effectively removed, abnormity self-correction is realized, the defect of energy efficiency sensing granularity in the prior art is made up, and the energy efficiency sensing precision is improved. And reliable input is provided for subsequent scheduling decisions. A cross-scale dynamic twinborn collaborative modeling mechanism is adopted, a physical information neural network and a computational fluid mechanics model are coupled, optimization is carried out through a generative adversarial network structure, and accurate prediction of a complex energy consumption evolution curve and a cooling flow field is achieved.

The invention discloses an MQTT message transmission optimization method and system. The method comprises the steps of analyzing a theme, extracting a device type, a data feature and a geographic position triple, calculating a hash value, and mapping a device to a specified Broker fragment cluster node to generate a fragment mapping table; processing the equipment data in the edge domain in the fragment mapping table through an edge calculation layer, removing invalid data according to a preset rule, merging the equipment data in the same fragment node, and embedding a fragment node ID for an aggregation message generated after merging; identifying a fragment node ID and routing to a target fragment node, positioning a corresponding shared memory pool, and writing the message into the shared memory pool; and responding to a direct access request of the client, so that the client directly accesses the data from the shared memory pool through the user mode network stack. According to the method, the problem of uneven load is effectively solved, multiple times of state switching in the data transmission process is avoided, and the MQTT message transmission efficiency is improved while the transmission cost is reduced.

The invention relates to the technical field of power loads, in particular to a power load dynamic optimization prediction method based on reinforcement learning, which comprises the following steps: acquiring real-time voltage frequency power of nodes, tracking frequency difference direction change of adjacent nodes, marking reverse disturbance to generate a distribution map, and identifying a frequent disturbance area according to the distribution map; clustering node groups with consistent fluctuation trends to determine a target area; monitoring power fluctuation inversion to lock energy steering nodes; constructing a prediction input set; comparing prediction and actual trends to extract a deviation interval, adjusting stride and rate of a reinforcement learning model, updating a decision and smoothing a curve, and outputting a power load dynamic prediction curve. According to the method, disturbance space-time dynamic identification is realized through multi-layer correlation analysis, judgment precision is improved through frequency power joint calibration, load path consistency and area extension are reflected through node clustering, power transmission tracking is enhanced through energy node identification, a feedback closed loop is constructed through offset monitoring, and curve continuity and response rate are improved. Stable convergence is predicted to be consistent with the trend under multiple disturbances.

This application provides a radio access network architecture. The radio access network architecture includes a cluster node and a serving node. The serving node provides task scheduling and executing functions, and the cluster node provides a region-level centralized collaboration function for the serving node and a collaboration function between cross-region cluster nodes.

The invention discloses an execution time aware computing power network heterogeneous GPU cluster deep learning task node allocation method and system. The method comprises the following steps: firstly, based on a deep learning task, extracting and preprocessing task features and available node features; secondly, a sampler equally divides new tasks without historical data to available nodes, and each node performs mixed sampling on the tasks until all the tasks estimate execution time data; taking execution time data as a training set, taking the task features and the node features as a test set, and using a regression decision tree model to predict the execution time of the task on each node; performing task allocation on each node by using a cost search algorithm and a short job total JCT priority strategy; and finally, periodically monitoring node resources released in the cluster to obtain an optimal node allocation result. According to the method, task delay and total task JCT are remarkably reduced, cluster node resource changes are monitored in real time, and the resource utilization rate is increased.

The invention discloses a GPU resource scheduling method based on data awareness and computer equipment, and the method comprises the steps: carrying out the real-time monitoring of a cluster node, obtaining a current cluster load state, and predicting the cluster load state in a future time period; creating services according to an input service definition description file, adding the services into a to-be-scheduled service queue, periodically selecting the services from the to-be-scheduled queue, and allocating computing nodes for the services; distributing a target service for the user request according to the current cluster load state, establishing a session, and analyzing the intention of the user; dynamically adjusting and allocating static resources through deep reinforcement learning based on a hybrid expert model according to a user intention analysis result and a cluster load state; required resources are loaded to a GPU through a multi-level cache architecture, and after calculation is completed, a calculation result is returned to a user through a session. According to the method, the utilization rate and the performance of GPU resources in an interactive GPU acceleration service scene can be improved, and the energy consumption and the cost are reduced.

The invention discloses a traffic flow prediction method for a double-layer multi-scale dynamic graph convolutional network, and relates to the technical field of traffic, and the method comprises the following steps: constructing a double-layer structure of a traffic network, which comprises a node layer composed of traffic sensor nodes and a region layer formed by clustering nodes in the node layer, node layer traffic flow data and area layer traffic flow data are extracted; respectively mapping the node layer traffic flow data and the region layer traffic flow data to a potential space to obtain a node layer initial hidden state and a region layer initial hidden state; inputting the initial hidden state of the node layer and the initial hidden state of the region layer into a sequence containing at least one space-time module for processing so as to capture a dynamic space-time dependency relationship; the method has the effect of providing more reliable decision support for traffic management and travel planning.

The invention provides a Pod fault injection method and system based on kubemark in a kubernetes cluster, and the method comprises the steps: firstly providing a fault collection tool which is used for collecting Pod fault information in a real cluster; meanwhile, using modified Kubemark in a simulation cluster to create a virtual node with the same specification as a real cluster node, and deploying a CRI-Proxy (a container runtime interface agent) component to execute fault injection and container life cycle management; a fault scene is simulated through a'fault recording-fault broadcasting 'mode, and Pod and container life cycle abnormity are simulated through fault injection, so that the stability and the recovery capability of the system are tested, valuable performance test data and system optimization guidance are provided for a real cluster, resources are saved, the test efficiency is improved, and the test cost is reduced. And meanwhile, problems can be reproduced, potential defects can be found, and various risks can be avoided in advance.

The invention relates to an automatic cluster recombination method, a distributed system and computer equipment. Determining a plurality of independent network partitions after the distributed system is subjected to network partitioning; for each independent network partition, determining first existence information of each cluster node in each independent network partition; determining a target local leader node and a target follower node from the cluster nodes of the independent network partitions according to a preset consensus recombination strategy based on the first existence information; establishing a first local consensus cluster corresponding to the independent network partition according to a following relationship between the target local leader node and the target follower node; according to the invention, automatic reorganization of cluster nodes during network partitioning is realized, so that each independent network partition can still maintain local consensus and service availability under the condition that global intercommunication cannot be realized, service is provided to the greatest extent, the availability is ensured, and the service continuity and the overall availability of the system after network partitioning are remarkably improved.

This invention discloses a method and apparatus for implementing a high-availability cloud firewall cluster, relating to the field of cloud firewall technology. The method includes session-based traffic splitting of data packets using a Session Flow Table (SLB); simplified processing of data streams for ALG-related protocols; and real-time monitoring of the health status and concurrent session count of each firewall node via SLB to achieve dynamic scaling of firewall nodes. This invention supports automatic elastic scaling of cloud firewalls, as well as multi-active high-availability clusters for NAT and ALG scenarios, while avoiding hot session standby between cluster nodes.

The invention discloses a data migration method and device, a storage medium, electronic equipment and a program product, and relates to the field of distribution.The method comprises the steps that original transaction data of a host side is split into N data fragments according to service types and time windows; encrypting each data fragment into a target data fragment; leader nodes corresponding to the target data fragments are selected from the L cluster nodes, and each target data fragment and the corresponding data version vector are sent to the corresponding leader node; performing consensus confirmation on the target data fragment received by the leader node through the leader node and the M replica nodes to obtain a consensus result of the target data fragment; and migrating the target data fragment from the host end to a storage node in a cluster. The technical problem of low consistency judgment efficiency before and after data migration caused by lack of a data version control mechanism during data migration of a distributed storage system in the prior art is solved.

The invention relates to the technical field of cloud computing, and particularly provides a cloud native database kubernetes dynamic scheduling method and equipment based on a tensor structure. The method comprises the following steps: acquiring a resource creation request; collecting multi-dimensional resource information of the cluster nodes in real time, and determining Pod types corresponding to all Pods in the cluster nodes based on the multi-dimensional resource information; the Pod type comprises a computing type, a storage type, a network type and an I / O type; based on the Pod type, the time dimension and the resource dimension, constructing a three-order tensor structure; dynamically calculating a node combination weight of the three-order tensor structure, and determining a target scheduling node; and scheduling the Pod corresponding to the resource creation request to the target scheduling node. According to the method, the problems of performance bottleneck and uneven load caused by resource view limitation are avoided, the technical problem of single measurement index in resource scheduling is solved through multi-target weight optimization, and the accuracy of target scheduling node selection is remarkably improved.

The invention belongs to the technical field of big data, and discloses a big data cluster building method and device.The method comprises the steps that a master control node obtains cluster node data and analyzes the cluster node data to obtain multiple pieces of work node information; connecting the corresponding working node according to the working node information; when each working node is successfully connected, acquiring an EDH program and a configuration file, transmitting the EDH program and the configuration file to a preset directory of each working node, and sending a starting instruction to each working node; the working node receives the starting instruction, analyzes the configuration file and starts the EDH program, and the EDH program generates heartbeat and sends the heartbeat to the master control node; taking a working node corresponding to the received heartbeat as a server node; the master control node obtains big data cluster information, a component and a script library; and analyzing the big data cluster information, sending the configuration information, the script library and the corresponding component to the target node, executing the installation script, and completing big data cluster establishment. The building efficiency of the big data cluster can be improved.

This application discloses a protocol migration method, apparatus, electronic device, and medium, relating to the field of database technology. The method includes: generating a flow control rule set based on a preset migration order and node information of cluster nodes in a target database that have enabled a dual-protocol stack listening mechanism; the target protocol address is generated by the cluster nodes based on a stateless address auto-configuration mechanism; distributing the flow control rule set to network devices connected to the cluster nodes, enabling the network devices to perform flow control on the cluster nodes according to the flow control rule set; and controlling the target database to update the address field of the cluster nodes in the cluster topology table from the original protocol address to the target protocol address, so that the cluster nodes switch node communication from the original protocol to the target protocol based on the updated cluster topology table. This application achieves full-process automation of protocol migration, precise flow control at the node level, and seamless and smooth decommissioning of old protocols without any service interruption.

In some embodiments, a computer cluster system comprises a plurality of nodes and a software package comprising a user interface and a kernel for interpreting program code instructions. In certain embodiments, a cluster node module is configured to communicate with the kernel and other cluster node modules. The cluster node module can accept instructions from the user interface and can interpret at least some of the instructions such that several cluster node modules in communication with one another and with a kernel can act as a computer cluster.

The invention discloses a power distribution network topological structure construction method and system adaptive to a double-high characteristic, and relates to the field of topology, and the method comprises the steps: collecting double-high characteristic data through a sensor, building an evaluation system, and calculating a node comprehensive influence index; k-means clustering grouping is carried out based on the index and the geographic position, an intra-group minimum spanning tree initial topology is constructed with the transformer substation as the center, and dynamic adjustment is carried out after simulation verification; then, the inter-group power exchange requirement is determined according to the load and new energy characteristics, and the optimal contact topology is determined through multi-objective optimization; and finally, the intra-group topology and the inter-group topology are integrated to form a complete structure, and a verification model is established to test the performance under different scenes. The method has the advantages that the challenges of high-proportion new energy and power electronic equipment are effectively coped with and stable and efficient operation of a power distribution network is guaranteed by comprehensively collecting double-high data, scientifically clustering nodes, hierarchically optimizing intra-group and inter-group topologies and combining double-high scene simulation dynamic adjustment and performance verification.

The invention relates to the technical field of universal parallel computing clusters and multi-tenant management, in particular to a load balancing system, method and device for a multi-tenant scheme in a universal parallel computing cluster and a medium. The system comprises cluster nodes, wherein each cluster node comprises one or more CPUs, a node mapping table and a device redirection layer; the global mapping layer / load balancing layer is used for creating a parallel processor pool, selecting a target processor and maintaining an equipment state table, a scheduling feedback table and a strategy table; and the parallel processor pool is used for performing abstraction management on the general parallel processors in the cluster, and issuing, monitoring, recording and releasing of the application programs are executed by the equipment scheduler. Fine-grained calling and high utilization rate of the parallel processor are realized, and the scheduling capability and utilization efficiency of the parallel processor are improved.

The invention discloses a freeswitch cluster capacity expansion system and device based on NAT (Network Address Translation) equipment, and relates to the technical field of cluster capacity expansion. The system comprises a virtual private cloud, an NAT (Network Address Translation) device, a freeswitch cluster and a port mapping configuration module, wherein the virtual private cloud is used for carrying out network planning and security configuration on the virtual private cloud according to actual requirements; the NAT equipment is deployed at a boundary position of the virtual private cloud and an external network, and a voice communication request sent by the external network to a specific public network IP and a port is converted into a private IP and a corresponding port of an internal freeswitch cluster node by configuring a DNAT rule of the NAT equipment; the freeswitch cluster consists of a plurality of freeswitch nodes, is uniformly distributed in a second subnet in the virtual private cloud, and is used for realizing call request processing of cluster load balance based on internal communication; and the port mapping configuration module is used for carrying out corresponding port mapping setting on the NAT equipment according to a service port provided by the freeswitch cluster node.

The embodiment of the invention discloses a container load drift method between cluster nodes and a computer program product. The method comprises the following steps: determining a drift node and a drifted node in a first node and a second node based on a drift trigger type of the first node in response to the fact that a node load of the first node in a cluster is not in a load threshold range; in the drift node, a target container is determined based on matching degree sorting of each container load and the load difference value; determining a target node in the second nodes based on the matching degree between the load demand vector of the target container and the residual load vector of the drifted node; and performing load drift on the target container between the first node and the target node. In the embodiment of the invention, the container drift is carried out with the minimum drift distance, the shortest drift time and the lowest energy consumption, the load balancing can be automatically carried out on the cluster nodes, the failure rate caused by the abnormal load is reduced, and the reliability and the utilization rate of the cluster are improved.

The embodiment of the specification discloses a mirror warehouse distributed cache method and device, wherein the method comprises: deploying a service for a plurality of data center mirror warehouses, deploying and running a cache service corresponding to each data center; in response to a first data center pulling a first image request instruction, obtaining corresponding first image metadata in the mirror warehouse; querying whether the first image block file corresponding to the first image metadata has been saved in the first data center cache; when not saved, saving the first image block file to the first data center cache service and sending the first image to the first cluster node of the first data center; when saved, sending the first image to the first cluster node of the first data center, wherein the first image comprises the first image metadata and the first image block file saved in the cache service of the first data center. The scheme can significantly reduce the mirror warehouse traffic pressure, improve the image pulling speed, and reduce the network communication cost.

The invention relates to the technical field of modeling systems, and discloses a portable cluster three-dimensional rapid modeling system and method, and the system comprises an integrated case unit which is internally integrated with a main computing node and a sub computing node; the power supply and power management module is used for monitoring the load of each computing node in real time and dynamically adjusting power supply; a KVM switching table in the man-machine interaction module is used for supporting a user to switch among a plurality of computing nodes through a keyboard or a mouse; the scheduling and modeling module is used for performing three-dimensional modeling on the target area according to the image data; and the environment adaptation module is used for carrying out real-time monitoring and intelligent regulation and control on the internal environment temperature and humidity of the integrated case unit. According to the method, rapid generation and result export of the three-dimensional model of the target area are realized through a closed-loop process of data acquisition by the unmanned aerial vehicle, cluster node parallel calculation and local aggregation optimization.

The invention provides a reconstruction method of a big model data processing tool, belongs to the technical field of big data processing, and adopts a Spark cluster mode to submit a task to solve the communication problem between a K8s service layer cluster node and a Spark data layer cluster node. The Spark data layer places a task processing result in an HDFS public storage, and the K8s service layer obtains the task processing result on the HDFS public storage through downloading, so that the problem that the K8s service layer in a Spark cluster mode cannot obtain the task processing result of the Spark data layer in real time is solved; and for the task which fails to return in the K8s service layer, the Yarn logs is independently called to obtain the detailed abnormal stack log, so that the problem that the K8s service layer in the Spark cluster mode cannot obtain the detailed log of the Spark data layer is solved.

The invention provides a mimicry transformation system based on a service component, and the system comprises the steps: determining N distribution requests after determining the installation of a service in a new service request, matching N heterogeneous cluster nodes, creating corresponding M kubernates cluster connections according to the matching of the N heterogeneous cluster nodes and corresponding heterogeneous information, and generating a command to create N service components. The method comprises the steps of storing a cluster node path and service component information into a database table, obtaining relevant configuration and role information of service components, generating serviceRoleUi, determining an installation sequence of each service component according to a dependency relationship existing among the service components, generating a new service command according to the installation sequence, and installing N service components, and different processing modes are designed according to N response results returned by N service component requests, so that the safety characteristic of the service component is improved, and the anti-attack capability of the whole platform is enhanced.

The present application relates to a kind of pneumonia detection model training method, specifically to a kind of hierarchical topology pneumonia detection model based on collaborative learning system and method.It overcomes the difficulty of existing pneumonia detection model training system, low efficiency and the problem that local detection node cannot achieve optimal detection performance.First, each node uses local pneumonia data to pre-train respective pneumonia detection model locally, then, center node is based on the feedback data of local model to build hierarchical topology collaborative learning system;After that, each cluster node and child node uses local pneumonia data to train respective pneumonia detection model locally;Finally, collaborative training is carried out, including intra-cluster collaborative training and inter-cluster collaborative training;Intra-cluster collaborative training includes cluster node aggregation training and child node random interactive training.The present application has small data transmission, storage and calculation pressure, and is easy to implement;At the same time, different client is provided with different model parameters, so that each hospital detection node achieves local detection performance maximization.

This invention discloses a method, system, and terminal device for displaying a 3D geographic information system based on multiple screens, relating to the field of 3D display technology. The method includes: acquiring 3D geographic information data; constructing a 3D geographic scene in a 3D rendering engine; determining the observer's viewpoint within a physical space, which is enclosed by multiple planar display screens forming a multi-screen display; deploying a corresponding number of virtual cameras facing the corresponding screens, with the observer's viewpoint as the origin; configuring the cameras in a physical trapezoidal combination based on the physical size and position of the screens relative to the observer and calculating the asymmetric view frustum projection matrix; allocating rendering tasks to pre-built distributed rendering cluster nodes, and controlling the synchronous output of each camera's image to the corresponding screen through a hardware synchronization mechanism. This invention achieves naked-eye stereoscopic display on multiple screens, eliminates perspective distortion at screen junctions, ensures seamless synchronization of multi-screen images without tearing, and enhances the immersiveness and accuracy of 3D geographic information display.

The invention discloses a medical large model reasoning and deploying method and device, equipment and a medium, relates to the field of artificial intelligence, is applied to reasoning nodes, and comprises the steps of constructing a model structured data table based on an input mode, an output mode and model metadata of a to-be-deployed medical large model, determining a target reasoning framework matched with the model type of the large model from a preset reasoning framework library, so as to generate a corresponding target model reasoning mirror image according to the target reasoning framework and the model structured data table; performing reasoning verification on the target model reasoning mirror image, and packaging the reasoning verification process after the verification is passed to obtain a target reasoning service; and deploying the target reasoning service to a preset medical cluster node so as to feed back a medical reasoning result corresponding to the medical reasoning demand of the preset medical cluster node through the target reasoning service. Therefore, the capability of the large medical model can be provided for the user through the interface in a service mode, and then the deployment flexibility and efficiency of the model are improved.

This invention discloses a method and system for energy-saving management and control of computing power clusters based on load prediction, belonging to the field of energy-saving management and control technology. It collects load utilization data, node energy density data, and task latency adaptation data; constructs a data sampling time period and a set of computing power cluster nodes; constructs a basic state matrix of all computing power cluster nodes at the data sampling time point; calculates the comprehensive load state quantity of the computing power cluster nodes; calculates the maximum adjustable power and the adjustable range of task latency; calculates the comprehensive energy-saving potential value; based on the comprehensive energy-saving potential value and the comprehensive load state quantity, calculates the node load-potential matching degree of the computing power cluster nodes; calculates the node load migration amount of the computing power cluster nodes at the data sampling time point; analyzes and performs energy-saving management and control, ensuring that the energy-saving process takes into account performance constraints, scheduling rationality, and system stability, thereby improving the overall energy efficiency and operational reliability of large-scale computing power clusters.

The invention provides a node scheduling method and device, electronic equipment and a storage medium, and the method comprises the steps: screening a candidate node set from cluster nodes according to a resource request of a to-be-scheduled job and a predefined node access condition, the candidate nodes in the candidate node set comprise nodes of which the deployed resource type and the corresponding resource surplus meet the resource request and meet the node admission condition; for any candidate node in the candidate node set, screening a target resource set corresponding to the candidate node from a predefined resource set, the target resource being a resource not deployed by the candidate node; determining a priority score of the candidate node according to the weight of each target resource in the target resource set; and taking the candidate node with the highest priority score as a target node, and executing the resource request of the to-be-scheduled job by using the target node.

The application discloses a low-duty-cycle sensor network data collection method based on a mobile robot, which comprises the following steps: S1, network initialization; S2, when each node forwards data, determining to adopt a static sink routing mode or a cluster node routing mode; S3, a sensor network node determines a data fusion waiting time: after the node senses or receives data, waiting for a certain time, fusing multiple data packets that arrive, reducing the number of data forwarding times and reducing energy consumption; S4, according to the data sending mode determined in the step S2, a sensor network node selects a next hop routing node for data forwarding, and forwards data; and S5, when the mobile robot passes through the cluster node, the cluster node sends the buffered data to the mobile robot. Through dynamic selection of a data sending mode, a data fusion technology and a cluster node sleep scheduling mechanism, the application realizes the guarantee of a mobile data collection delay performance and the improvement of data collection energy efficiency of the robot under the working scene of uncontrolled movement and low-duty-cycle nodes.

The invention specifically relates to an unmanned cluster identification method based on motion topology reasoning, and belongs to the technical field of artificial intelligence and unmanned systems. The method comprises the following steps: firstly, collecting a historical track sequence of unmanned cluster nodes, and constructing an interpretable feature system containing three types of physical features of motion, interaction and topology; inputting the feature vector into a self-adaptive encoder containing dynamic graph construction, multi-head attention and time sequence aggregation components, and outputting a high-order cluster feature vector of time sequence aggregation; then, target identity recognition and node interaction topology reasoning are completed in sequence, and a cluster node future trajectory prediction result is output through a dual decoder; and finally, identifying and predicting performance through joint optimization of a multi-objective loss function, and updating model parameters in real time to adapt to a dynamic task scene. According to the method, the problems of poor scale adaptability, task decoupling and feature black box of an existing method are effectively solved, and end-to-end joint optimization of identity recognition and trajectory prediction is realized.