74 results about "Deployment algorithm" patented technology

The invention discloses a service function chain deployment method based on SDN and NFV. A combination framework based on an SDN network and an NFV architecture and a modular deployment service function chain are established. Then, a service function chain deployment algorithm is carried out in the strategy controllers in the SDN network and the NFV architecture; after the user flow enters the network, the strategy controller performs strategy control; whether a network service function required by user traffic is matched with a VNF owned by a bottom layer or not is judged through a deploymentalgorithm of a service function chain; if not, the strategy control informs the management and arrangement component of the NFV of missing VNF information, and after obtaining the message, the management and arrangement component of the NFV deploys all the required VNFs into the corresponding virtual machines in a modular strategy through the NFV underlying facility resources to complete the whole deployment operation. The low time delay of the service function chain is ensured, the resource utilization rate of the service function chain is high, and the deployment time of the whole SFC is shortened.

The invention relates to the technical field of cloud computing, and in particular to a deployment algorithm of the application distribution of a virtual machine. The deployment algorithm comprises the following steps: firstly, receiving a request from a user by a cloud computing platform, and analyzing and putting each application resource request into a request queue; then, according to each application resource requirement, performing matching with each virtual machine type; then, selecting a virtual machine type which has a highest matching degree with the application resource request; then, selecting a certain virtual machine case which is operated at present from the type of virtual machines with the optimal matching degree, wherein total resource load operated on the case is the most similar to the volume set by the type of virtual machine after the application resource requirement is operated if other applications are operated on the virtual machine case and the virtual machine case can meet the application resource requirement; and adding the application resource request to the case to operate tasks of the application resource request one by one. The deployment algorithm of the application distribution of the virtual machine improves the utilization rate of virtual resources, reduces resource waste and lowers cost while the service quality of a user is guaranteed, and the deployment algorithm can be used for the application distribution of the virtual machine.

The invention belongs to the technical field of network function virtualization and bandwidth guarantee type virtual machine deployment, and in particular relates to a bandwidth guarantee type virtual network function (VNF) deployment method. The method comprises the following steps of: (1), establishing a VNF example communication diagram according to SFC and bandwidth requirements; and (2), on the basis of the generated VNF example communication diagram, establishing a corresponding bandwidth guarantee type VNF example deployment scheme. According to the bandwidth guarantee type VNF deployment method disclosed by the invention, a bandwidth guarantee type VNF deployment strategy is adopted; according to bandwidth information provided by users, better globally optimized VNF deployment can be made in combination with a current global resource use condition; by means of a VNF example communication model and a VNF deployment algorithm of a heuristic algorithm, on one hand, bandwidth requirements of users are ensured; on the other hand, virtual machines of users can be placed in a centralized manner; therefore, unnecessary bandwidth loss can be reduced; more examples can be accepted.

The present invention provides a data analysis processing system and an online model deployment method thereof. The method comprises the steps of: performing publishing of an algorithm model based ondetected user operation used for a deployment algorithm model, and displaying the published algorithm model in a user interface to allow preset users using the data analysis processing system to access and/or call the published algorithm model. The data analysis processing system and the online model deployment method thereof can provide the system or publish the algorithm model established by theusers to services capable of being accessed by other users so as to improve the cooperation of a data analysis processing system, facilitate user usage and improvement of the usage efficiency.

The invention discloses a service function chain deployment algorithm based on resource fragment avoidance, which uses resource fragment degree to measure resource fragment states of physical nodes and links of an underlying network, and minimizes the resource fragment degree as an optimization target. The method comprises steps of taking a fitness function value of an individual chromosome in thegenetic algorithm as a standard of spatial solution, and finishing mapping of a virtual network function by using a fusion simulated annealing genetic algorithm; and completing mapping of the virtuallinks by using an improved Dijkstra algorithm. According to the invention, generation of underlying network resource fragments is reduced to improve the utilization rate of physical resources, and meanwhile, the mapping success rate of the SFC is improved.

The present invention belongs the network technology field, and provides an SDN controller deployment algorithm capable of ensuring the minimum time delay of a whole network. The SDN network multi-controller deployment method capable of ensuring minimum time delay comprises: performing analysis of network time delay and a topological structure, calculating time delay from each switch to all the rest switches, selecting one switch as an initial controller deployment point at will, updating the deploying position to a new switch according to the K-medoids algorithm so as to ensure the minimum time delay of all the rest switches; selecting a switch having the maximum time delay to the controller deployment point in the whole network as another new controller deployment point, performing reassignment of the switches in the whole network according to the time delay, and updating of each controller deployment point through the K-medoids algorithm; and going on repetition the process mentioned above until there are K controller deployment points. The SDN network multi-controller deployment method capable of ensuring the minimum time delay is mainly applied to the network control and management occasions.

The invention relates to a probe deployment method based on vertex cover and weak vertex cover. The probe deployment method comprises the following steps: determining the quantity of probes and deployment locations of test probes in a network. The probe deployment method provided by the invention has the advantages as follows: based on a greedy algorithm of minimal vertex-covering problems, the method is improved on the basis of the algorithm, and a probe deployment algorithm based on the vertex cover and weak vertex cover is provided. Firstly, minimum vertex cover is used, so that the quantity of flow monitors is minimum under the condition that the flow of each link is obtained, and then the minimum vertex cover is improved as minimum weak vertex cover. Simulation results show that compared with a deployment scheme based on the minimum vertex cover, the scheme provided by the invention has the advantages that fewer probes are used, in addition, the algorithm is simpler, the consumed time is short, and the scheme is a more excellent network flow monitoring probe deployment scheme.

The invention relates to a relay node robustness covering method for a double-layer structure wireless sensor network. The method is a relay node 2-cover deployment algorithm based on local search, the global deployment problem is degraded to a local deployment problem, the robustness is guaranteed, and the optimal deployment is realized. The method specifically includes two steps: first 1-cover and secondary 1-cover, wherein the first 1-cover includes: three steps of relay node candidate deployment position construction, sensor node grouping, and relay node local deployment, sensors are grouped via a novel grouping method, the complexity of the algorithm is reduced, and the optimality of the deployment is guaranteed; and the secondary 1-cover includes: the threshold is adjusted, sensor nodes covered only by one relay node are selected from each group, 1-cover of the sensor nodes is performed by employing the 1-cover method, the robustness is guaranteed, the deployment quantity of the relay nodes is reduced, and the problem solving time is shortened.

The invention discloses a water-saving irrigation internet of things integrated system for crop cultivation. The system comprises a WSN (Wireless Sensor Networks) ad-hoc network for crop greenhouse cultivation and a node deployment module; the ad-hoc network comprises an ad-hoc network formed by WSN nodes and a WSN base station; the WSN nodes include sensor nodes, control nodes, a gateway and a relay node; a virtual force algorithm based on a variable step is adopted by the node deployment module to deploy the sensor nodes in a node static sensing range; and the virtual force algorithm based on the variable step changes a movement step of each of the sensor nodes based on a sigmoid function by establishing a two-dimensional planar model of a cultivation area and a sensing model of each ofthe nodes. According to a water-saving irrigation WSN node deployment algorithm for the crop cultivation provided by the invention, while the later convergent stability is guaranteed, the purpose of optimal effect for covering an equal number of nodes in a relatively short time can also be achieved; and thus, the time for obtaining a deployment strategy is shortened, the monitoring coverage rate is improved, and the comprehensiveness and the integrity of data monitoring are guaranteed.

The invention discloses an industrial multi-core network construction method. According to the method, through adoption of a multi-center clustering placement algorithm, a topological structure of a multi-layer multi-core SDN smart network is divided logically. All nodes in the network are abstracted into an original graph, and the original graph is shrunk to a suitable scale; regional division and node clustering are carried out according to node attribute values; and divided sub-graphs are tracked back into the original graph according to the topological structure, thereby realizing a largescale network slice grouping effect. The industrial multi-core network construction method provided by the invention is simple and feasible, the engineering realization is facilitated, a complex taskincapable of being processed by a single smart network can be solved, the load capacity of the network is improved, and the communication quality required by the industrial Internet is ensured well.

The invention provides a virtual network function deployment method suitable for multi-dimensional resource optimal configuration. The method comprises the following steps: step 1, acquiring a networkstate, and updating available resources of all nodes and residual bandwidths of links; 2, when a service function chain deployment request is detected, judging whether the network meets deployable conditions or not; 3, determining a deployable node set of the request according to the sequence constraint of each virtual network function in the request; 4, calculating the node resource capability and the path resource capability of each deployable node; 5, determining an optimal deployment path by adopting a service function chain deployment algorithm based on a Viterbi backtracking method; and6, deploying the virtual network functions according to the optimal deployment path and the node sequence to form a target service function chain, updating the network state, and returning to the step 1. According to the method, various resources can be balanced according to respective use degrees, and the network performance is considered while the overall resource consumption of network configuration is optimized.

The invention provides a deployment algorithm of large-scale RFID (radiofrequency identification) readers in three-dimensional space. The deployment algorithm is characterized by utilizing a quantification method to respectively convert a reader-writer model and a to-be-covered region model in the three-dimension space into a three-dimensional matrix, and transforming the deployment of the reader-writer into the deployment of the three-dimensional matrix according to the matrix theory; to difference in propagation directions of reader antennas, providing a method for building a reader three-dimensional covering model matrix set through rotation matrix so as to realize mapping setting of the reader antennas; further, providing methods for calculating performance index of coverage rate and overlap rate in the deployment algorithm; finally, to deployment of the RFID readers, providing an improved strategy of a particle swarm algorithm on the basis of rule of elimination. Reader border crossing and elimination systems are added in the strategy, and the standard particle swarm algorithm is improved.

The invention discloses a service function chain deployment method based on breadth-first search. The deployment algorithm proposed by the invention does not constrain the scale or the sparse characteristics of the network, and thus can be applied to most networks. The algorithm proposed by the invention is based on the shortest path between a service terminal and a user to implement the service function chain deployment, so the bandwidth cost and delay consumed by the deployment are reduced, and the deployment cost is reduced accordingly. In the selection of nodes, the node load rate and thelink load rate are considered, an optimal selection factor is designed to reflect the impact of the load rate on the node selection, and the load balancing is optimized.

A vehicle safety system comprising: at least one occupant safety device (6) for protecting an occupant of the vehicle (1) in the event of a side impact; and a control unit (7) operable to receive information from one or more vehicle sensors (2, 3, 4, 5) and to provide a trigger signal to activate the occupant safety device (6). Under normal driving conditions, a default deployment algorithm is used by the control unit (7) to determine whether the trigger signal should be generated; and if it is determined that loss of control of the vehicle (1) is occurring, or is expected to occur, and the longitudinal speed of the vehicle (1) exceeds a first threshold, the control unit (7) employs a first further deployment algorithm to determine whether the trigger signal should be generated. The first further deployment algorithm being adapted to cause the trigger signal to be generated a shorter time after the initiation of a side impact than is the case for the default deployment algorithm.

The invention discloses a micro-cloud deployment and user task scheduling method under a wireless metropolitan area network environment, which overcomes the defects of micro-cloud overload and long queue time by introducing a network delay threshold which can be tolerated by the system, and effectively reduces the average system response time. The invention also discloses a micro-cloud deploymentand user task scheduling method under a wireless metropolitan area network environment. The optimization of micro-cloud deployment scheme and user task scheduling scheme is studied in order to reducethe average waiting time of unloaded tasks. According to a given integer K being equal or greater than 1, K micro-clouds are deployed at K receiving points in the wireless metropolitan area network (WMAN), and then user tasks in the WMAN are scheduled to the micro-clouds according to certain rules, so that the average waiting time of the unloaded tasks of the user is minimized. On the basis of theload priority algorithm, the invention optimizes the obvious defects of the algorithm, and proposes a density priority deployment algorithm which is closest to the optimal algorithm according to theactual situation, so as to effectively minimize the system response time and remarkably optimize the mobile application performance of the metropolitan area network.

A device for vehicle occupant protection. A processor connectable to at least two sensors may execute a deployment algorithm, and, in response to a failure of at least one of the sensors, may alter a sequence of execution of the deployment algorithm according to a point in time of the failure.

The present invention relates to the technical field of cloud computing, and in particular to a virtual machine cluster deployment algorithm. The virtual machine cluster deployment algorithm comprises the steps of: analyzing a resource type of a cluster; filtering out a request that cannot be met; creating a priority queue; cyclically traversing all physical machines, and calculating a load coefficient L of each physical machine, and determining whether the physical machine can be selected as a deployment node; calculating a load value of each physical machine according to the resource type of the cluster, inserting the load value into the priority queue, and sorting elements of the priority queue in descending order of the load values; performing virtual machine mirror image transmission one by one in an order of the queue; and starting all virtual machines of the cluster, so as to complete cluster deployment. The present invention realizes a cluster deployment algorithm based on load value calculation; and the algorithm can be used for virtual machine cluster deployment.

The invention provides an Ethereum deployment method and system based on a ZYNQ heterogeneous computing platform. The Ethereum deployment method comprises the following steps: obtaining the calling frequency of each cryptographic algorithm to be deployed and the running speed at an ARM end and an FPGA end; inputting the obtained calling frequency and running speed data into a preset integer linearprogramming model, and solving a deployment scheme of each cryptographic algorithm at the ARM end and the FPGA end, wherein the preset integer linear programming model is the maximum value of the sumof the products of the running speed, the decision factor and the calling frequency of each cryptographic algorithm. Performance indexes of the to-be-deployed algorithm and different operation modesof each algorithm are considered, so that the operation speed after deployment and the utilization rate of resources are greatly improved.

The embodiment of the invention discloses an algorithm management method and device for edge computing equipment, the method is applied to the edge computing equipment, and the method comprises the steps that a packaging algorithm file is received, and the packaging algorithm file is at least obtained by packaging a main entry file and an assistance file operated by a to-be-deployed algorithm; and parameter configuration data of the to-be-deployed algorithm is received, parameter configuration of the to-be-deployed algorithm is finished, and a deployable algorithm which can be used in a dispatched manner is acquired. According to the scheme, a coupling relation does not exist between the deployment algorithm and the edge computing device, the algorithm form that the main entry file is matched with the assistance file compression package is adopted, multiple types of algorithms can be adapted, the flexibility of algorithm deployment is improved, and the operation difficulty is reduced.

The invention discloses a virtual network service chain deployment method based on superposition for improvement of availability. The virtual network service chain deployment method comprises the steps of: determining influences of superposition on an NFVE problem, including influences on SFC availability, link consumption and SFC dependency; further analyzing challenges of implementing superposition, including some limitations on superposition, link design and availability calculation, and proposing a deployment principle based on superposition; modeling the NFVE problem as a nonlinear 0-1 planning problem for the deployment principle, wherein the nonlinear 0-1 planning problem allows superposition and minimizes resource consumption under availability constraints; and proposing a heuristic deployment algorithm to solve the NFVE problem. The virtual network service chain deployment method proposed by the invention greatly improves the availability and resource utilization of NFV.