Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

55results about How to "Dynamic Load Balancing" patented technology

Method for balanced distribution of virtualization cluster load in a plurality of physical machines

The invention discloses a method for balanced distribution of virtualization cluster load in a plurality of physical machines, comprising the following steps of: (1) periodically collecting current load information of each virtual machine; predicting load information in a subsequent period through a formula (1); (2) selecting any index in the load information as a migration index; adding migration indexes of all virtual machines in each physical machine so as to obtain estimated values of the migration indexes of each physical machine; (3) checking whether the estimated values of the migration indexes of each physical machine are in respective preset threshold ranges; making a migration policy; and (4) migrating the virtual machines according to the made migration policy so as to realize load balance. By means of the invention, the cluster load change tendency can be predicted accurately; the migration of the virtual machines between the physical machines can be carried out with low acceptable performance loss; the original relationship cannot be destroyed; and the dynamic load balance of the whole cluster system can be achieved.
Owner:ZHEJIANG UNIV

Task processing method and system and nodes based on distributive type calculation system

The invention discloses a task processing method and system and nodes based on a distributive type calculation system. The method comprises the steps that all nodes monitor self states and store state information, and a main node obtains the state information of all working nodes in a timing mode; when the main node determines an over-load working node, the main node informs non-overload working nodes of conducting load condition predication; the main node adjusts the task type of the overload working node according to predicated overload condition so as to reduce the load of the overload working node. Through the method, when overload occurs in a working node of the distributive type calculation system, and the main node adjusts the task type processed by all the working nodes in a dynamic mode according to the predicated load condition of all the working nodes in the future, so that dynamic load balance of all the working nodes of a cluster is realized, and the load balance of a system resource level is achieved. Consequently, the largest overall processing capacity of the cluster is improved.
Owner:CHINA UNITED NETWORK COMM GRP CO LTD

Resource scheduling method of cluster virtual machine

The invention discloses a resource scheduling method of a cluster virtual machine. The resource scheduling method comprises the following steps of: acquiring resource utilization parameters of each physical host in the cluster for a first preset time period before the current time point; according to the resource utilization parameter and the preset physical host selection strategy, determining a target physical host having need to migrate the virtual machine; determining a target virtual machine to be migrated in the target physical host; determining a target host machine according to the resource utilization parameter; and migrating the target virtual machine to the target physical host. The target virtual machine in the target physical host is migrated to the target host machine. Through the dynamic migration of the virtual machine, the virtual machine on the target physical host with high resource utilization can be migrated to other physical hosts to realize dynamic load balance of the physical hosts, and fully use a variety of physical resources in the cluster, so that the problem of resource imbalance in the cluster is solved and efficient resource utilization is maintained.
Owner:INSPUR BEIJING ELECTRONICS INFORMATION IND

Cluster framework capable of realizing cloud computing flexible service

The invention discloses a cluster framework capable of realizing cloud computing flexible service. The cluster framework comprises a service registering system, a configuration center, a load balancer and a management system. The service registering system is used for registering service information; the configuration center collects the service information and resources and stores the service information and resources, and carries out dynamic update through monitoring service running state and expected state; the management system obtains the service information and resources from the configuration center, establishes a resource-service data table, and obtains the running state of the current service from the configuration center regularly; and the load balancer realizes load balance of the service according to the resource-service data table. Through the mode above, the cluster framework can integrate components with different functions, and realizes service discovery and optimal resource utilization and load balance of the service.
Owner:FUJIAN TQ DIGITAL

Inventory and distribution management system based on cloud computing

The invention discloses an inventory and distribution management system based on cloud computing. A Hadoop software architecture is applied for achieving distributed processing of mass Web data of the inventory and distribution management system, so that the safety of the inventory and distribution management system with respect to mass data storage is improved; in the cloud computing technology, distributed data storage can achieve dynamic load balance and automatic takeover of a failure node, so that high reliability, high performance, high availability and high extendibility are achieved; the inventory and distribution management system is established on a cloud computing public technology service platform so that abundant enterprises on a supply chain can conduct inventory management and logistics distribution in a finer and dynamic mode, and informationized running cost of export-oriented enterprises is reduced; the system can be applied to intelligent terminals; by the adoption of a Redis database, the functions of cluster deployment dynamic expansion, real-time data analysis, real-time data query, real-time data collection, real-time uploading, real-time communication and the like can be achieved.
Owner:CHANGCHUN UNIV OF SCI & TECH

Method for establishing connection, method for re-orienting connection and correlated equipment

The embodiment of the invention discloses a method for establishing connection, method for redirecting connection and related equipment. The method for establishing connection comprises: sending connection request message to cluster positioner; receiving connection request response message carrying address information of cluster controller; the cluster controller belonging to server cluster of highest healthy degree produced and compared by cluster positioner; establishing connection utilizing the address of cluster controller and the cluster controller. In technical scheme of the invention, network system can contain multiple server cluster by adding cluster positioner in network system and utilizing cluster positioner for implementing redirection of client connection request; dynamic balance of load of every server is implemented by comparing healthy degree of every server cluster; data processing load of single cluster controller can be reduced relatively to promote performance of whole system.
Owner:KINGDEE SOFTWARE(CHINA) CO LTD

Cloud architecture of energy efficiency management system and operation method thereof

InactiveCN103905553AReduce the impact of installation and maintenanceLow costTransmissionDynamic load balancingData acquisition
The invention discloses a cloud architecture of an energy efficiency management system and an operation method of the cloud architecture. By introducing the cloud architecture and the operation method of the cloud architecture, fast seamless connecting-in of a newly added service module and acquired data share can be achieved by the system according to continuous expanding of client service classes, meanwhile, energy efficiency data can be acquired, processed and published by the system efficiently with dynamic load balance and high quality according to the client service scale, normal operation of user service is guaranteed, and the availability and the running efficiency of the system can be substantially improved through interior monitoring and operating mechanisms of the system.
Owner:JIANGSU LINYANG ENERGY CO LTD +1

Method and system for dynamic load balancing of metadata servers

The invention discloses a method and system for dynamic load balancing of metadata servers. The method comprises the steps that whether the source utilization rates corresponding to the metadata servers are larger than a first threshold or not is judged by detecting the source utilization rate of each metadata server in a metadata server cluster; if yes, a migration request is sent to a metadata management module, the metadata in the metadata servers corresponding to the source utilization rates larger than the first threshold is migrated into a second metadata server cluster, wherein the first threshold is the maximum allowable value of the source utilization rates, and the second metadata server cluster is a cluster of the metadata servers, corresponding to the source utilization rates smaller than the first threshold, in the metadata server cluster. Therefore, the dynamic uniform distribution of the metadata in the metadata servers is achieved, the dynamic load balancing of the metadata servers is achieved, and the performance of the metadata servers is improved.
Owner:ZHENGZHOU YUNHAI INFORMATION TECH CO LTD

Wireless multi-network integration method

The invention discloses a wireless multi-network integration method which can be used for achieving integration of a plurality of wireless network cards to achieve bandwidth convergence. The wireless multi-network integration method mainly comprises the steps that (1) an automatic dialing portion mainly identifies the network cards automatically and conducts automatic dialing, (2) a network card information obtaining portion mainly obtains information of effective network cards dynamically, (3) a load balancing portion mainly achieves balanced scheduling on each dialing network card according to real-time statistics of the flow of each dialing network card, (4) a disconnection reconnection portion mainly achieves disconnection reconnection and deletes invalid network cards, and (5) a WiFi sharing portion mainly shares integrated bandwidth resources through the WiFi. Finally, the integration of the network cards is achieved to achieve the bandwidth convergence. In the wireless multi-network integration, the bandwidth resources are integrated, and the whole coverage rate and reliability can be improved.
Owner:SOUTHWEST JIAOTONG UNIV

Cluster management device, system and method

The invention discloses a cluster management device, system and method. The cluster management device employs a server cluster manner, wherein according to the types of request messages and performance of server nodes, a conversation management module selects internal server nodes for issuing the request messages of external systems, thereby realizing dynamic load balance. Thus, the number of cluster server nodes is increased at peak time and decreased at normal time, thereby saving the investment cost, reducing the resource waste, and not influencing service operation.
Owner:TELEFON AB LM ERICSSON (PUBL)

P-CSCF distribution method based on geographical position and load balancing

The invention discloses a P-CSCF distribution method based on the geographical position and load balancing. The method comprises the steps that an IMS user sends a request to a geographical position allocation server for allocation of an appropriate geographical position server; the request, for allocation of the appropriate geographical position server, of the user is received by the geographical position allocation server; according to an IP address in the request and delay of the geographical position server, the appropriate geographical server is allocated to the user and returned to the user; a result returned by the geographical position allocation server is received by the user; a request for allocation of an appropriate P-CSCF is sent to a returned geographical position server address by the user; after the request for allocation of the P-CSCF from the user is received by the geographical position server, a P-CSCF which is closest in the geographical position and lightest in load is allocated to the user for registration according to IP address information of the user and the load condition of the P-CSCF; the P-CSCF information returned by the geographical position server is received by the user; a registration request is sent to the P-CSCF; according to an IMS standard procedure, the remaining registration work is finished. According to the P-CSCF distribution method based on the geographical position and load balancing, effective dynamic deployment, automatic configuration and the good load balancing effect are achieved.
Owner:CHINA UNITED NETWORK COMM LIMITED HAINAN BRANCH

Method for dynamically balancing broadband access server load in wireless local area network

The invention discloses a method for dynamically balancing broadband access server load in the wireless local area network. The wireless local area network is composed of a wireless controller (Access Controller, AC), a wireless access point (Access Point, AP) and a virtual router composed of multiple broadband access servers (Broadband Access Server, BAS); the method comprises the following steps: when users access the wireless local area network, the AP informs about the user access to the AC and the AC determines a certain BAS according to multiple BAS performance data for forwarding data from the users.
Owner:北京傲天动联技术有限公司

Load balancing optimizing method based on block level cloud storage

The invention discloses a load balancing optimizing method based on block level cloud storage. According to the method, a heteromorphosis part of a genetic algorithm is added to a load balancing strategy to improve accuracy of the strategy to search globally optimal solution as far as possible; simultaneously, a breakpoint resume function facing an internet small computer system interface (ISCSI) is designed, so that when a volume server is reselected for ISCSI reconnection, users which are uploading data needn't upload the data again, a system can automatically continue uploading from the breakpoint, and the reliability of the system is improved; and by means of existing isomerism storage environments, a hierarchical storage management mechanism based on volume life cycle is provided, and advantages and characteristics of different storage devices are fully utilized to further improving access efficiency of the system. The load balancing optimizing method can be used for solving the load balancing problem of a cloud storage system in the technical field of computer storage.
Owner:HANGZHOU DIANZI UNIV

MongoDB-based load balancing optimization system and method

The invention discloses a MongoDB-based load balancing optimization system, the MongoDB-based load balancing optimization system comprises a MongoDB system, data of the MongoDB is stored in each slice, the data is divided into data blocks of certain size and then placed in each server, and when the number of the data blocks in each server is not balanced, load balancing is realized through a balancer module; for the MongoDB-based load balancing optimization system, one load monitor module is added on the MongoDB system framework and is in charge of periodically and dynamically monitoring a cpuutilization rate NCPU, a memory utilization rate NMEMORY and a bandwidth utilization rate NBANDWIDTH of each server, and respectively setting a cpu utilization rate weight k1, a memory utilization rate weight k2 and a bandwidth utilization rate weight k3; and the server comprehensively considers adjustment according to real-time judgement on whether overloading exists and operation heat of the data blocks, and thus, MongoDB dynamic load balancing is realized. With the system and the method provided by the invention, a resource utilization rate of the server is maximized, and MongoDB dynamic load balancing is realized.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Multi-party cross-chain method based on consistent hash consensus protocol

The invention discloses a multi-party cross-chain method based on a consistent hash consensus protocol. The method comprises the following steps: (1) formulating a consensus protocol for a multi-partycross-chain system; (2) finding the position of a corresponding virtual node according to a consistent hash algorithm; (3) enabling multi-party users to interact with each other; (4) storing user data to corresponding virtual nodes; (6) receiving the verification interaction request, triggering the smart contract to carry out a cross-chain consensus process, and completing data cross-chain afterthe interaction verification is passed and a consensus is reached. According to the multi-party cross-chain method, efficient consensus between cross-chains can be achieved, and the consensus efficiency is improved through the consistent hash algorithm, so load balancing of the system in the cross-chain interaction process of multiple parties is achieved.
Owner:HANGZHOU YUNXIANG NETWORK TECH

Method and system for dynamically adjusting topological structures of underlying network spanning trees

The invention provides a method and system for dynamically adjusting topological structures of underlying network spanning trees. The method comprises following steps: periodically obtaining load information of an underlying network switch; calculating the total weight of a current underlying network spanning tree in real time according to the load information; determining a minimum spanning tree according to the total weight of the current underlying network spanning trees and dynamically adjusting the topological structures of the network spanning trees. The system comprises an information collection module and an STP (Spanning Tree Protocol) module. According to the invention, the underlying network switch is managed and controlled centrally through an SDN (Software Defined Network) controller; an OpenFlow protocol module is taken as a management interface; the topological identification function of the underlying network is finished and the spanning tree structures are constructed on the controller. In the operation process of the network, the controller obtains the forwarding traffic information of the underlying network switch in real time; some backup link bandwidths are used; therefore, the dynamic load equalizing function of the network is realized; and the condition that the second network business forwarding appears loop and forms network storm is prevented.
Owner:SPACE STAR TECH CO LTD

Efficient dynamic load balancing system and method for processing large-scale data

The invention discloses an efficient dynamic load balancing system and method for processing large-scale data, and belongs to the technical field of processing the large-scale data. The efficient dynamic load balancing system structurally comprises a central control system, a computing cluster system, a storage system and a high-speed network. A CPU and GPU mixed heterogeneous architecture is adopted in a middle node of the central control system; a CPU and GPU mixed heterogeneous architecture is adopted in middle nodes of the computing cluster system, or a CPU architecture is adopted in nodes of the computing cluster system; the storage system is divided into a shared storage and a local storage, a CPU architecture is adopted in middle nodes of the shared storage, and the local storage is used for storing data of nodes of the central control system or the nodes of the computing cluster system; the high-speed network is used for connecting the middle node of the central control system, the middle nodes of the computing cluster system and the middle nodes of the shared storage to form the centralized system for processing the large-scale data. The problem that a current server computing system is insufficient in network bandwidth and small in storage capacity and therefore cannot process the large-scale data is solved.
Owner:LANGCHAO ELECTRONIC INFORMATION IND CO LTD

Dynamic reactive compensation system based on magnetic control electric reactor

The invention relates to a dynamic reactive compensation system based on a magnetic control electric reactor. The dynamic reactive compensation system comprises a passive filter FC and an MCR (Magnetic Control Reactor), wherein the passive filter FC is used for reactive compensation and harmonic filter, the MCR is used for balancing an inductive load. The dynamic reactive compensation system disclosed by the invention has the advantages that the reliability if high, 20-year basic maintenance-free running can be realized, and the maintaining and repairing cost can be reduced to a large extent; the response ability is quick, and the response speed can be up to 20ms; the regulating range is large, and the regulating range in more than 100 times can be reached; the occupied area is small, the installation is convenient, and a device can be naturally cooled by adopting an oil immersion mode; the harmonic wave is small and has no pollution to a power grid and has no any bad influence on a capacitor group, and the traditional device is conveniently utilized in a reform occasion; the overload ability is strong, 30-second 100% overload and half-hour 40% overload can be realized; the consumption is less, the MCR is in large capacity, the consumption is less than 0.5%, and in a common system, only 0.8%-1.5% of the consumption can be realized; the overvoltage ability is strong, the voltage limiting ability is good, and the dynamic reactive compensation system has a natural automatic voltage limiting ability; and no electromagnetic pollution works on the environment and the human body.
Owner:青岛海电电气有限公司

Load balancing method and device, storage medium and electronic equipment

An embodiment of the invention discloses a load balancing method and device, a storage medium and electronic equipment. The method comprises the steps: receiving a service request, for a target network service, of a client, determining at least one container contained in a first network node, and determining that the first network node contains the available first container if there is an available first container in the at least one container; if the at least one container contains the target network service, responding to the target network service in the first container, determining a second network node containing an available second container in the distributed network if the at least one container does not contain the first container, and indicating the second network node to respondto the target network service in the second container. By adopting the method disclosed in the embodiment of the invention, the load balancing effect can be improved.
Owner:SHENZHEN HEYTAP TECHNOLOGY CO LTD +1

Method, device and system for processing data

The embodiment of the invention discloses a method, device and system for processing data. According to one specific embodiment, the method comprises the steps: determining a time interval between anaccess request and a last access request as a first time interval in response to receiving the access request; obtaining a preset complete binary tree from the management server side, wherein the value of a non-leaf node of the complete binary tree is related with the time interval of the last two access requests received by the metadata server, and the leaf node is used for representing a virtualnode corresponding to the metadata server in the distributed system; selecting a target path from the complete binary tree according to the first time interval; and sending the access request and thetarget path to a metadata server corresponding to the leaf node of the target path. According to the embodiment, the load balancing of the distributed system is realized.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Traffic control method, device, equipment, storage medium

The invention relates to a traffic control method, device and equipment, and a storage medium. The method comprises the following steps: receiving a connection request to a first access machine serverby a first client, judging whether the first access machine server is connectable at present; if the first access machine server is connectable, sending the connection request to the first access machine server, and updating the total connection amount of the first access machine server; if the first access machine server is not connectable, searching through Zookeeper till to acquire a second access machine server which is connectable at present, and returning the connection information of the second access machine server to the first client. The maximum connection amount of the server can be flexibly arranged according to the server resource configuration; the resource of the server is sufficiently utilized, the workload for operation and maintenance is reduced, so that the operation and maintenance cost is saved, and the working efficiency is improved; the connection amount and the operation state of the access machine server are monitored in real time through the Zookeeper, and the dynamic load balancing and traffic control are realized in the cooperation with an automatic switching strategy.
Owner:SF TECH

Load-balancing-based virtual asset data storage method

The invention discloses a load-balancing-based virtual asset data storage method comprising initial data storage path designing, data storage and data redistribution. After data storage, whether redistribution of data of a system needs to be carried out is decided according to a system load situation. To be specific, the data redistribution includes: setting a system load standard different threshold value and calculating a current system load standard difference; comparing the system load standard different threshold value with the system load standard difference; implementing a data redistribution algorithm; and carrying out data reading. According to the invention, machine performances are considered and the load needed by data is predicted; the correlated processing distribution method is applied to storage of massive virtual asset information; data transferring only occurs between adjacent nodes; and dynamic load balancing of the system is realized with the low calculation load. Therefore, the method is suitable for data storage of a massive multi-structure virtual asset data management system.
Owner:NAT UNIV OF DEFENSE TECH

Method and device for dynamically deploying system services

The embodiments of the present invention, related to the computer field, provide a method and device for dynamically deploying system services, which can detect the execution state of current application, achieve dynamic load balancing of system services in a multi-core operating system, allocate the tasks in a fine-grain way to the hardware suitable for running these tasks, and dynamically adjust resource allocation in the course of task running. The method includes: obtaining the detection information of the system service kernel and application kernel, wherein the detection information includes current execution state information of system service kernel, current execution state information of application kernel and topology position data of current application; according to the detection information, obtaining the optimal topology scheme corresponding to current application by a preset scheme, wherein the optimal topology scheme is used to indicate the execution interaction route of the system service kernel and / or application kernel of current application; according to the optimal topology scheme, adjusting the system service kernel and / or application kernel which executes current application.
Owner:HUAWEI TECH CO LTD +1

P2SP (Peer to Server & Peer) multi-source download system

ActiveCN103795766ADynamic Load BalancingMake full use of hardware resourcesTransmissionFault toleranceNetwork communication
The invention provides a P2SP multi-source download system suitable for the field of network communication. The system comprises multiple tracker connection servers and a tracker connection managing server, wherein the multiple tracker connection servers report self load information regularly, and according to the load information reported by the multiple tracker connection servers, a suitable address and port for the tracker connection server are returned to a client which requests connection. The system realizes dynamic load balance of tracker servers according to load conditions of the tracker connection servers, hardware resource of the system can be fully utilized, equipment investment is reduced, the system efficiency is increased, emergency can be handled, and the total fault tolerance and stability of the system are improved.
Owner:TENCENT TECH (SHENZHEN) CO LTD +1

Emission trading system and trading method

The invention discloses an emission trading system and an emission trading method. The trading operation of the whole system and back-stage management are finished based on webpages. The trading system can finish emission permit quota trading and quota-free trading. An emission permit quota trading method adopts quota pending order trading including pending buy order and pending sell order, the trading premises comprise membership and emission permit quota admission, and the quota information of each member account synchronizes with a government quota register. The emission permit is coded according to the unit and the flow direction is tracked in a trading process.
Owner:LIAONING EMISSIONS EXCHANGE CO LTD +1

File transmission method under link aggregation linking conditions

The invention belongs to the field of communication, and provides a file transmission method under link aggregation linking conditions. A data uploading method comprises the following steps: step 1, a client randomly selects a port from n ports to send a write request to the client, wherein the request parameters contain information of all of the n transmission ports of the client; step 2, a server returns ACK to the client, wherein the serial number of the ACK is 0; step 3, the client randomly sends data blocks in a sliding window by the n ports at the same time; step 4, the server generates to-be-returned ACK with a serial number m according to data cache contents after receiving the data blocks, and returns the ACK; step 5, the client receives the ACK with the serial number m, slides the window forward to m+1, and continues to send the data in the window in parallel by the n ports; and step 6, the sending step is repeated until the ACK serial number arrives at the position of the last data block, and the transmission is accomplished.
Owner:XIAN AVIATION COMPUTING TECH RES INST OF AVIATION IND CORP OF CHINA

Network load balancing method based on WeChat platform and system thereof

InactiveCN106411984AImprove reliabilityReal-time monitoring of load conditionsData switching networksPublic accountWeb service
The invention discloses a network load balancing method based on a WeChat platform and a system thereof. The method comprises the following steps that WeChat information is sent to an external network through a web server and a proxy server; the proxy server sends the WeChat information to a load balancing server; the load balancing server forwards the WeChat information to a service processing server; the service processing server sends the WeChat information to a WeChat software client; and the load balancing server adjusts load balancing among service processing servers according to a load balancing algorithm. In the technical scheme of the invention, load conditions of the different service processing servers in the WeChat platform are monitored in real time; and according to a load distribution condition, a flow direction of a data flow is dynamically adjusted so that reliability of WeChat platform operation is increased. The method and the system can adapt to a demand of a sudden WeChat service of a large data flow, and demands of growing WeChat personal users and public account numbers to multimedia WeChat information are satisfied.
Owner:TVM BEIJING TECH

A value-at-risk simulation dynamic task scheduling method based on collaborative computing

The invention discloses a dynamic task scheduling method of value-at-risk simulation based on collaborative computing. Under a three-layer parallel computing framework composed of a core node, a management node and a computing node, the computing node partitions tasks in a Monte Carlo simulation process and establishes a task queue. The task queue is composed of a core node, a management node anda computing node. The computing task snatching branch is carried out by the corresponding Pthread of the computing device; At last, that computing node sorts the compute results of the simulation process in parallel, and then merges and sort them to lighten the load of the management process. The invention mainly adopts the divide-and-conquer method to carry out dynamic task scheduling according to different computing devices of CPU and MIC, and realizes dynamic load balancing in the computing process so as to maximize the computing efficiency.
Owner:GUANGDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products