43 results about "Virtual cluster" patented technology

Disclosed in the present application is a resource multi-level scheduling method in edge scenarios. The method comprises: a CDN edge server being connected to a k8s cluster by means of a cloud-edge channel kubeedge, and being exposed to a service for use by means of a virtual cluster; on the basis of the resource requirements of the service, applying for resources to a CDN resource scheduling platform, and when a CDN service is prioritized, returning a resource list meeting a condition; a service side mapping the responded resource list to the virtual cluster, evenly distributing resources to all clusters, generating CRD deployment orchestration, and deploying same to a CDN edge cluster by means of an ESK platform; a CRD controller monitoring EdgeInfo resources and creating a pod on the basis of resource content; and a service container reporting the actual usage amount of the resources to a monitor by means of indicators, and the resource scheduling platform performing global blending on the basis of monitoring data and resource thresholds.

The invention provides a power grid day-ahead regulation and control method and device based on distributed photovoltaic virtual cluster dynamic division, and the method comprises the steps: obtaining a distributed photovoltaic virtual cluster through the dynamic division of an improved community theory of weight clustering based on distributed photovoltaic characteristic data and a regulation and control target; based on a pre-trained distributed photovoltaic prediction model, predicting future output data of each distributed photovoltaic according to historical output data, historical meteorological data and meteorological prediction data of the distributed photovoltaic in the distributed photovoltaic virtual cluster; and regulating and controlling the distributed photovoltaic virtual cluster according to the regulation and control target and the corresponding regulation and control target function based on the future output data of each distributed photovoltaic in the distributed photovoltaic virtual cluster. According to the method, distributed photovoltaic can be effectively classified, so that the regulation and control capability and the stable operation capability of a low-voltage power grid are improved; meanwhile, the economical efficiency, the safety and the reliability of low-voltage power grid operation are improved.

The invention discloses a tenant deployment method and device, electronic equipment and a computer program product. The method relates to the field of financial science and technology, and comprises the steps that a tenant creation request of a tenant to be deployed is responded, the tenant type is determined according to the tenant creation request, the tenant type comprises a first type and a second type, and the level of the first type is lower than that of the second type; under the condition that the tenant type of the to-be-deployed tenant is a first type, if the target virtual cluster does not exist in the entity cluster, creating the target virtual cluster, and if the target virtual cluster exists in the entity cluster, deploying the to-be-deployed tenant to the target virtual cluster; and when the tenant type of the to-be-deployed tenant is the second type, deploying the to-be-deployed tenant to a working service node of the entity cluster. According to the method and the device, the problems of unreasonable deployment and low deployment efficiency during isolated deployment of service resources for multiple tenants in the prior art are solved.

Methods of enabling Artificial Intelligence (Al) models to be trained in a privacy preserving manner are disclosed. A method comprises the formation of virtual cluster per privacy level and selection of a cluster head that performs the training and coordination per privacy level. A method comprises training an Al primary model on a private user data set. The Al primary model may be used to label a public data set. A secondary model may be trained using the labeled public data set. The secondary model may be shared with a network or other UEs.

An example Radio Access Network Intelligent Controller (RIC) determines that operation of a first instance of an application satisfies one or more criteria for scaling the application, the first instance of the application processing cluster messages generated by the RAN. The RIC, in response to determining that the operation of the first instance of the application satisfies the one or more criteria, determines a first virtual cluster and a second virtual cluster of the RAN. The first virtual cluster includes first one or more resources of the RAN and the second virtual cluster includes second one or more resources of the RAN. The RIC instantiates a second instance of the application. The RIC routes cluster messages from the second one or more resources of the second virtual cluster to the second instance of the application.

The invention discloses a cluster computing resource allocation method. The method supports three resource service forms of a virtual machine, a container cloud and a bare computer. Wherein the virtual machine resources are used for deploying system software with a UI (User Interface) and a C / S (Client / Server) architecture; the container cloud resource is used for deployment of system software of a B / S architecture and operation of a large test sample; the bare computer resources are used for specific function system software, Kafka middleware and / or database deployment; and service computing resource elastic scheduling and control are deployed to realize cluster computing resource allocation. According to the method, multiple resource service forms are flexibly adopted, and virtual cluster management and high-availability design are applied, so that test resource automatic deployment strategy generation and computing resource flexible scheduling and control can be realized, and high-performance, high-reliability, servitization and easy-to-use cluster computing resource allocation and deployment services are provided for users.

The invention provides a biological cluster animation generation method and apparatus, and an electronic device. The method comprises the steps of generating a particle cluster moving in a virtual scene according to a preset motion rule based on a particle system; the particle swarm comprises a plurality of particle objects; for each particle object, determining a target position for attracting the current particle object, if the distance between the current position of the current particle object and the target position meets a preset condition, determining the target speed of the current particle object according to a preset parameter corresponding to the target position, and controlling the current moving speed of the current particle object to increase the target speed; and rendering the particle object in real time according to the pre-made model vertex data of the biological individual, and generating a biological cluster animation of the biological virtual cluster. In the mode, the target position for attracting the particle object is set, and the behavior state of the particle object moving towards the attraction point is increased, so that the biological population has the behavior of approaching the target position, and population movement close to nature is realized.

Embodiments of the present disclosure disclose a virtual cluster-based crowd scheduling system and device. A specific implementation of the system includes: a trace synchronization module that automatically identifies a load object created by a user in a virtual cluster, synchronizes task annotation metadata corresponding to the load object to a corresponding execution unit in a host cluster, and writes address annotation metadata corresponding to the load object in the execution unit; a scheduling module that reads task annotation metadata of each execution unit, generates a scheduling score value corresponding to each execution unit in each execution unit according to the read task annotation metadata set, and batches each execution unit to a corresponding resource adaptation node, the scheduling module being deployed in the host cluster; and a billing module configured to generate a task billing sheet. The implementation improves the versatility and resource utilization efficiency of the system.

The invention relates to a method (100) for initiating a transfer of one or more virtual functions to a virtual cluster at a cloud instance (30), comprising the following steps at a network function (10) of a 3GPP core network (20): - Establishing (101) a subnetwork for enabling the exchange of context specific information within the subnetwork, - Initiating (102) a setup of a virtual cluster at a cloud instance (30) associated with the subnetwork, and - Initiating (103) a transfer of one or more virtual functions (45, 55), which are associated with a respective user device (40, 50) of the subnetwork and are running outside of the cloud instance (30), to the virtual cluster for enabling a coordinated exchange of information within the virtual cluster.

The present invention discloses a virtual cluster time synchronization method based on PCIe passthrough, belonging to the technical fields of virtualization and network time synchronization. First, based on the PCIe passthrough technology, the virtual cluster nodes are bound to the underlying clock card to obtain the underlying physical clock time; then, a soft interrupt signal is generated through a timer to enable the virtual nodes to read the clock information of the underlying physical clock card at the same agreed time, while measuring the timer delay and correcting the time read from the clock card in real time; finally, the clock error between the virtual cluster nodes can be obtained by calculating the physical time values of the two clock cards. The present invention utilizes the high-precision hardware of the clock card and, with the help of the PCIe passthrough technology of the virtual machine, can accurately achieve the measurement of system time synchronization between virtual clusters.

The application discloses an electric two-wheeled vehicle charging system and method based on dynamic allocation and adjustment, and a storage medium, relates to the electric two-wheeled vehicle charging management technical field, and the system and the method realize digital modeling and dynamic correlation analysis of electric two-wheeled vehicle charging pile cluster by building a virtual cluster system, rely on multi-dimensional data integration of geographical distribution, capacity scale and power consumption attribute, combine the comprehensive computer mechanism of space correlation and load correlation, form the digital twin model that can map the physical cluster state in real time, through the deep learning of the historical charging demand time sequence characteristics of the LSTM model, combine the quantitative analysis of the dynamic connection index and the pre-connection reasonable value, build the smooth transition mechanism of the current strategy and the prediction strategy, ensure that the current charging allocation and adjustment strategy not only meets the current demand, but also maximizes the convenience of subsequent strategy connection and switching.

The embodiment of the invention relates to a creating method, device and system based on a GPU virtual cluster. The creating method based on the GPU virtual cluster comprises the following steps: acquiring configuration information of a network topology corresponding to a current GPU physical cluster; according to the available nodes of the current GPU physical cluster and the number of nodes required by the GPU virtual cluster, a node combination is selected based on the configuration information of the network topology to create the GPU virtual cluster, and the node combination comprises at least one available node in the available nodes of the current GPU physical cluster. Therefore, when the GPU virtual cluster is created, the current optimal node combination can be selected according to the network topology, so that the resource utilization rate is improved, and the operation and maintenance operation is simplified.

The invention provides an application copy scheduling method and device, a medium, electronic equipment and a program product, and relates to the technical field of resource scheduling, and the method comprises the steps: obtaining a target configuration file comprising a plurality of to-be-deployed application copies and a topological relation among the plurality of application copies, creating a corresponding virtual cluster and a virtual scheduling unit, performing scheduling simulation on the virtual scheduling unit in the virtual cluster according to the topological relation to obtain a simulation scheduling mode, and deploying the plurality of application copies in the resource cluster based on the simulation scheduling mode, so that a user only needs to concern the distribution form of the application copies in the plurality of resource clusters; and the deployment of the high-availability application can be completed without understanding the attribute information of the infrastructure in the resource cluster. Due to the fact that the topological relation describes the distribution form of the application copies in the multiple resource clusters, even if the deployed application copies break down, the application copies can be re-deployed based on the target configuration file, and the target configuration file does not need to be modified.

The invention discloses a single-particle test monitoring system based on a virtual cluster, solves the problem that a traditional monitoring system is difficult to meet the requirements of different experimental environments, and belongs to the field of particle physical experiments. The method comprises the following steps: a virtual cluster comprises a management node and a plurality of working nodes, and each node is a Docker container; each component is packaged in a Docker container to operate; the data acquisition engine assembly communicates with an accelerator through an EPICS system, obtains process variable data in a single event test of the accelerator in real time, and stores the process variable data in the time sequence database assembly. The data acquisition engine assembly is also used for connecting the time sequence database assembly and the visual tool assembly; the time sequence database component stores process variable data in the single event test of the accelerator in real time, and the data carries a timestamp; and the visualization tool assembly displays the process variable data in the form of a chart and an instrument board. The method is suitable for the single-particle test system of the proton heavy ion accelerator.

An example method for encrypting clusters during deployment may include retrieving, from a blueprint, resource information required to deploy a cluster including a host computing system and a virtual cluster manager node to manage the host computing system. The resource information may include host information and disk information required to deploy the virtual cluster manager node, and encryption information associated with a key provider. Based on the host information and the disk information, a clustered datastore may be created on the host computing system. Further, the virtual cluster manager node may be deployed on the clustered datastore. Based on the encryption information associated with the key provider, the virtual cluster manager node and associated disks may be encrypted. Upon encrypting the virtual cluster manager node, a cluster may be created and the host computing system may be added to the cluster.

The invention discloses a multi-tenant virtual cluster creating method and device, equipment, a medium and a program product, and relates to the technical field of cloud computing, and the multi-tenant virtual cluster creating method comprises the steps of obtaining a parameter description file, and submitting the parameter description file to a preset physical cluster, the parameter description file is used for describing parameters of the multi-tenant virtual cluster; according to the parameter description file, a multi-tenant virtual cluster is created, and the multi-tenant virtual cluster comprises namespaces corresponding to a plurality of tenants respectively; creating a tenant cluster namespace in the physical cluster according to the parameter description file; and creating a control plane component for the multi-tenant virtual cluster based on the tenant cluster namespace to obtain a control plane, the control plane being used for controlling the multi-tenant virtual cluster according to the tenant demand. According to the method and the device, the isolation among the API resources of the tenants in the cluster is improved, and the flexibility of cluster configuration adjustment is improved.

Embodiments of the present disclosure relate to extensions of open radio access network applications. An example Radio Access Network Intelligent Controller (RIC) determines that operation of a first instance of an application meets one or more criteria for extending the application, the first instance of the application handling a cluster message generated by the RAN. In response to determining that the operation of the first instance of the application satisfies one or more criteria, the RIC determines a first virtual cluster and a second virtual cluster of the RAN. The first virtual cluster includes a first one or more first resources of the RAN, and the second virtual cluster includes a second one or more second resources of the RAN. The RIC instantiates a second instance of the application. The RIC routes the cluster message from a second one or more resources of the second virtual cluster to a second instance of the application.

The embodiment of the invention discloses a group scheduling system and device based on a virtual cluster. A specific embodiment of the system comprises a traceability synchronization module which automatically identifies a load object created by a user in a virtual cluster, synchronizes task annotation metadata corresponding to the load object to a corresponding execution unit in a host cluster, and writes address annotation metadata corresponding to the load object in the execution unit; the scheduling module is used for reading the task annotation metadata of each execution unit, generating a scheduling score value corresponding to each execution unit in each execution unit according to the read task annotation metadata set, scheduling each execution unit to the corresponding resource adaptation node in batches, and deploying the scheduling module in a host cluster; the charging module is configured to generate a task charging list. According to the embodiment, the universality and the resource utilization efficiency of the system are improved.

A computer-implemented method, according to one approach, includes: maintaining an inventory of available data storage and / or data processing components in a distributed system. A data request is received, and the computer-implemented method further includes determining a combination of the available data storage and / or data processing components that is capable of satisfying the data request. The combination of available data storage and / or data processing components is synthesized into a virtual cluster, and the virtual cluster is used to satisfy the data request.

The present invention discloses a one-key start control system and method for the whole process section of tobacco industry silk thread making. The control system comprises: a data computing platform, two server optical fiber switches, a main PLC control machine, two bottom-level control main optical fiber switches, a human-machine optical fiber switch, at least two human-machine interaction monitoring machines and at least two bottom-level controllers. The data computing platform comprises: a cloud virtual cluster computing platform server, a data storage IO server, a production process information management server, a leaf group raw material formula information management server, a leaf storage vertical warehouse material information management server and a silk storage vertical warehouse logistics information management server. The first bottom-level switch, the second bottom-level switch, the third bottom-level switch, the fourth bottom-level switch, the fifth bottom-level switch and the first bottom-level switch of the bottom-level controller are connected in sequence to form a ring network. The two bottom-level control main optical fiber switches are respectively connected to any one of the bottom-level switches in each bottom-level controller.

A disclosed method for developing and testing a hyper-converged infrastructure (HCI) platform creates a snapshot pool with one or more virtual resource snapshots that include one or more virtual node snapshots, one or more virtual cluster snapshots, or both. The snapshot pool may be maintained with a desired quantity of the virtual resource snapshots by adjusting the composition of the snapshot pool in response to snapshot events, including an event that alters either a composition of the snapshot pool or a configuration of the HCI platform. The desired quantity of virtual resource snapshots may be determined in accordance with one or more snapshot thresholds. The snapshot thresholds may include a snapshot pertaining to a quantity of virtual node snapshots in the snapshot pool and / or a snapshot pertaining to a quantity of virtual cluster snapshots. Specifically, the threshold may include a cluster maximum and minimum and a node maximum and minimum.

This invention discloses a hierarchical mobility management method and system for satellite-ground collaboration in low-Earth orbit (LEO) satellite networks. It primarily addresses the problems of excessive mobility signaling overhead and over-reliance on ground stations leading to network robustness issues in existing technologies for user mobility management. The solution involves: selecting key nodes for deploying Mobility Management Functions (AMFs) through network deployment planning to eliminate the maintenance overhead of virtual clusters; decoupling location updates from high-speed satellite movement by constructing dynamic activity areas for users and implementing a lazy location update strategy; establishing a mapping relationship between user identifiers and multiple nodes to achieve distributed on-board storage of user data, avoiding strong dependence on ground stations; and establishing a hierarchical paging mechanism, calculating the PCI index based on the user mobility model, and dynamically selecting paging strategies to achieve an optimal balance between paging overhead and paging latency. This invention can significantly reduce the overall signaling interaction cost while ensuring service continuity and eventual data consistency, effectively improving the robustness and autonomous operation efficiency of large-scale LEO satellite networks in scenarios with limited satellite-ground links, and can be applied to satellite communication networks.

The present invention provides a database deployment method and device for multiple platforms, and relates to the technical field of virtual cluster deployment. The method comprises: configuring an installation package file according to the installation paths of different virtual platforms; receiving a user's database installation request, parsing the installation package file according to the database installation request, and obtaining installation information corresponding to the database installation request; copying the installation package data file of the platform corresponding to the database installation request and creating a new installation directory according to the installation information; executing the installation script to complete and take effect the set environment variables, and starting the cluster to complete the database deployment. The present invention realizes unified operation during the installation, deployment, upgrade and expansion of virtual clusters under multiple platforms, and at the same time, the consistency check of the operating systems of different virtual clusters can be ignored during the installation process, and the configuration process is simple, which can improve efficiency and reduce error rate.

An example method for encrypting clusters during deployment may include retrieving, from a blueprint, resource information required to deploy a cluster including a host computing system and a virtual cluster manager node to manage the host computing system. The resource information may include host information and disk information required to deploy the virtual cluster manager node, and encryption information associated with a key provider. Based on the host information and the disk information, a clustered datastore may be created on the host computing system. Further, the virtual cluster manager node may be deployed on the clustered datastore. Based on the encryption information associated with the key provider, the virtual cluster manager node and associated disks may be encrypted. Upon encrypting the virtual cluster manager node, a cluster may be created and the host computing system may be added to the cluster.

The invention relates to the technical field of distributed computing and resource management, and provides a hardware performance test system and method based on hierarchical nodes and containerization, and the system comprises a Web front end which is used for providing a virtual cluster configuration interface, a test plan configuration guide, a test state monitoring panel and test report display; the Server rear end interacts with the storage service module, the Web front end module, the cache session service module, the database module and the Agent module and is used for providing data storage management, API interface service, test process control and WebSocket communication functions; the Agent module interacts with the Server back-end module and the Docker warehouse module and is used for executing a test task, arranging and managing a container and collecting result data; and the storage service layer and the Docker warehouse are used for storing the preset test tool mirror image. According to the invention, the Docker container technology is applied to the large-scale cluster performance test, the complete standardization of the test environment is realized, and the large-scale cluster test efficiency is improved.

The invention provides a virtual cluster creation method and device, equipment, a storage medium and a program product, and relates to the technical field of computer simulation, in particular to the technical field of large-scale cluster simulation. The method comprises the following steps: in response to a received first simulation instruction for a processor in a physical node, creating a virtual processor; in response to the received second simulation instruction for the interface associated with the processor, creating a virtual interface; creating a virtual node corresponding to the physical node based on the virtual processor and the virtual interface; a virtual cluster is created based on the plurality of virtual nodes. According to the method, the large-scale cluster environment can be effectively simulated, meanwhile, the hardware dependence can be reduced, and the cost can be saved.

The application discloses a multi-level resource scheduling method in an edge scene, which comprises the following steps: a CDN edge server is connected to a k8s cluster through a cloud edge channel kubeedge mode, and is exposed to a business through a virtual cluster; according to the resource requirement of the business, the CDN resource scheduling platform is applied for resources, and a resource list meeting the condition is returned on the premise of CDN business priority; the business side is mapped to the virtual cluster according to the responded resource list, and is divided into all clusters, CRD deployment arrangement is generated, and is deployed to the CDN edge cluster through an ESK platform; a CRD controller listens to EdgeInfo resources and creates a pod according to the resource content; and the business container reports the actual resource consumption to monitoring through an index, and the resource scheduling platform globally adjusts according to the monitoring data and the resource threshold.

The invention relates to a distributed photovoltaic edge virtual cluster coordination control method considering communication time delay, and the method comprises the steps: determining an edge virtual cluster which can carry out task distribution according to the load states of all edge virtual clusters; according to the number of the to-be-allocated tasks and the number of the edge virtual clusters, determining the number N0 of the tasks needing to be allocated for each edge virtual cluster; sequentially distributing the tasks to be distributed to the sorted edge virtual clusters according to a time sequence, wherein N0 tasks to be distributed are distributed to each edge virtual cluster; and in the distribution process of the to-be-distributed task, the weighting and transmission delay between each distributed device and the connected edge virtual cluster is minimized, and the weighting and calculation delay between each edge virtual cluster and the cloud server is minimized. According to the invention, through optimizing the time delay compensation mechanism and the coordination control algorithm, reasonable allocation of computing resources is carried out, and cooperative scheduling between photovoltaic and energy storage is ensured to be more efficient.

This application discloses a VIP binding method and apparatus based on a database backup database, applied to read / write separation scenarios in an openGauss database cluster. The method includes: upon cluster startup, a collection and preemption phase is initiated, where the cluster management server distributes backup database VIP pool information, the proxy detects and reports any existing virtual IPs, and the server arbitrates allocation; after entering the balancing phase, only normal backup databases are allowed to hold virtual IPs, and the server evenly distributes the virtual IPs in the VIP pool to each normal backup database, prioritizing those with fewer virtual IPs; virtual IPs are released when the status is abnormal or the role is switched to the primary database; and all virtual IPs are released when the cluster shuts down. This invention, through dynamic binding of virtual IPs to backup database roles, ensures that the business side always connects to the backup database via a fixed IP, achieving IP-level load balancing and role adaptation, reducing the coupling between the business layer and the database high availability mechanism, and improving system read performance and fault tolerance.

The invention relates to the technical field of data processing and clustering analysis, in particular to a grid point set complementing method and system based on anchor point clustering. The method comprises the following steps: preprocessing a point set containing two-dimensional coordinates and radiuses, and extracting features; clustering the X and Y coordinates by using DBSCAN and calculating features; screening anchor point and non-anchor point clusters according to a threshold value; complementing non-anchor points, generating a virtual cluster to obtain a fixed number of complete clusters, and optimizing residual clusters; a purification point set meeting the biaxial constraint is screened; and finally, constructing a grid, and deducing missing points and radiuses. According to the method, outlier and class spacing abnormity can be processed, the controllable clustering number is ensured, the complementation precision is high, high-robustness and high-precision grid point set complementation is realized, the limitation of a traditional method in a fixed distribution scene is solved, and the method can be widely applied to the fields of industrial detection, image processing and the like.