78results about How to "Reduce migration costs" patented technology

An arbitrary customer instance is transferred from a customer environment to a target managed-infrastructure-as-a-service cloud environment as a transferred image. An image adjustment plan, capturing at least one adjustment required to render the transferred image compliant with standards of the target managed-infrastructure-as-a-service cloud environment, is formulated. The image adjustment plan is executed to adjust the transferred image to obtain an adjusted image compliant with standards of the target managed-infrastructure-as-a-service cloud environment. The adjusted image is on-boarded into the managed-infrastructure-as-a-service cloud environment as a standard image thereof.

The present invention provides an effective method for migrating the system services on which applications depend, rather than all of the system services, from a source OS platform to a target platform, in order to provide a suitable and consistent environment for the applications, while reducing the cost of the migration. The migration method further classifies the configurations of system services on different platforms into common configurations and specific configurations to accelerate the determination of the source of a migration error.

The invention discloses a key-value data distributed caching system and a method thereof. The system comprises a key-value access proxy cluster and a key-value data storage cluster, wherein the key-value access proxy cluster is composed of a plurality of data access proxy nodes, and the key-value data storage cluster is composed of a plurality of data fragmentation storage replication clusters; the data access proxy nodes are used for sending a node business storage request, routing a data read and write request to a target data storage node, and storing or reading business data; and in the data fragmentation storage replication clusters, a master-slave data replication mechanism is adopted to determine that a single point of failure does not exist in the data, read data are read from a plurality of slave nodes, and load balance of the read data is determined. By adopting the technical scheme provided by the invention, key-value data automatic fragmentation storage is realized through a consistency hash algorithm, and horizontal expansion of data storage capacity of the system is guaranteed.

The invention discloses a satellite network load balancing method for an SDN and NFV collaborative deployment framework. The satellite network load balancing method specifically comprises the following steps of A, designing an SDN / NFV collaborative deployment satellite network model: A1, realizing separation of a control layer and a data layer by an SDN; enabling the GEO satellites to realize theSDN control layer function in the satellite network architecture, and enabling the MEO / LEO layer satellites to perform NFV responsibilities; A2, dividing the satellite network into an arrangement plane, a control plane and a data plane based on a software defined network of the satellite network and a network function virtualization collaborative deployment framework; B, establishing a hidden Markov model: converting the business arrangement process into the hidden Markov model, and optimizing and solving the MLB-Viterbi algorithm of the hidden Markov chain; finding an appropriate migration target, and achieving the minimum migration cost under the condition that load balance is guaranteed. According to the method, optimal distribution and load balancing of network resources are realized.

The invention discloses a container cluster-oriented energy consumption optimization resource scheduling system and and a method for thereof. The system comprises a server resource monitor, a container performance test pool, a container energy consumption model manager, a container energy consumption caching module, a container scheduling decision-making device, a dynamic adjustment module and a plurality of servers. The scheduling method comprises the steps of: periodically collecting characteristic parameters of the container operation environment and checking the state of the container energy consumption estimation model; and according to the energy consumption estimation value of the container energy consumption estimation model, performing dynamic optimization scheduling decision, meanwhile, copying the container in the production environment to the container performance test pool to iteratively train the data set and update the model to improve the accuracy of the container energy consumption estimation value. The scheduling strategy is customized with the minimum overall energy consumption of the data center as the target, the requested container is scheduled to a proper server in real time to achieve the optimal energy consumption, the self-updating and iteration capacity is achieved, server resources are integrated while the energy consumption is reduced, the resourceutilization rate is increased, and the operation cost of the data center is saved.

The invention relates to the technical field of cloud computing and big data, in particular to a big data hybrid scheduling model on the private cloud condition. The big data hybrid scheduling model comprises an access control module, a task decomposition module, an overall situation scheduler module based on virtual resources, a resource virtualization mapping module, a virtual resource monitoring module, a physical resource monitoring module, and a local scheduler module based on physical resources. The big data hybrid scheduling model is a hybrid scheduler including physical resource scheduling, virtual resource scheduling, overall situation scheduling and local scheduling. User tasks are decomposed into a plurality of independent subtasks which are distributed on different clusters or computational nodes. Parallel and rapid execution of the tasks is ensured, network and data transfer costs are reduced, physical resource scheduling is utilized for further decomposing subtasks, cluster resources are utilized to be maximum extent, and the task execution time is further shortened.

The embodiment of the invention discloses a load balancing control method and related devices so as to optimize the load balancing effect. The method includes the steps of determining a virtual machine to be transferred according to the loads of all physical NUMA nodes and the loads of all the virtual machines, representing the virtual machine to be transferred as the target virtual machine, calculating transfer expenses spent on transferring the target virtual machine according to different transferring methods, and transferring the target virtual machine according to the transferring method with the lowest expenses. Visibly, when the virtual machine to be transferred is determined, the loads of the physical NUMA nodes and the loads of the virtual machines are taken into consideration; due to the fact that the loads of the physical NUMA nodes are taken into consideration, the load balancing effect of all the physical NUMA nodes is superior to the load balancing effect in the prior art after transferring is conducted. In addition, the transferring method with the lowest expenses is selected according to the transferring expenses of the virtual machines, and transferring cost can be reduced while load balancing is achieved.

The invention discloses a migration decision and resource optimization distribution method for a mobile edge computing ultra-dense network, and belongs to the field of wireless communication. For theapplication scene that a computing terminal and a communication terminal simultaneously initiate task request in the mobile edge computing ultra-dense network, a computing request terminal task migration decision and resource optimization configuration method capable of guaranteeing the minimum communication rate requirement of a communication request terminal is disclosed. The method takes the weighted sum of the task migration processing time delay and the energy consumption of each computing request terminal as the task migration cost, and an optimization model is established by taking thetask migration cost sum of all the computing request terminals as the target, the optimization model is decomposed into a calculation resource optimization configuration model and a joint channel configuration and power configuration optimization model, a KKT condition is adopted to obtain a calculation resource optimization configuration decision; an alternative iteration is adopted to obtain a channel and power suboptimum configuration decision.

Embodiments of the invention disclose a page building processing method, device and system. The system comprises a module standard maintenance unit, a module grouping and storage unit, a data puttingsystem access unit and an interaction unit, wherein the module standard maintenance unit is used for providing a plurality of different module standards corresponding to business identifiers accordingto self-defined page standards of the business identifiers; the module grouping and storage unit is used for grouping and storing modules according to different corresponding business identifiers, soas to generate a plurality of module pools; the data putting system access unit is used for accessing data putting systems into the page building processing system, wherein the data putting systems respectively accord with self-defined page standards of the corresponding business identifiers; and the interaction unit is used for providing a system function interface, and determining a target business identifier to which a target page belongs when a processing request of the target page in the aspect of a target system function is received through the system function interface. Through the method, device and system, the universality of page building systems is improved.

The invention provides a virtual machine migration method and device. The virtual machine migration method includes the steps that historical resource utilization data of physical machines are obtained, alarm data greater than preset standard thresholds and preset times are determined and are input into an autoregressive model adopted in a time sequence trend prediction method to obtain prediction values, the migrated probability of virtual machines in the alarm physical machines with the alarm data is obtained if the prediction values are greater than the preset thresholds, and the virtual machines to be migrated are selected based on the migrated probability and are migrated. The interference of other external complicated factors can be effectively reduced, SLA can be guaranteed, unnecessary virtual machine migration operation caused by explosive rise of the virtual machine resource usage rate can be avoided, the virtual machines in the alarm physical machines are migrated before overload of the alarm physical machines occurs, continuous uninterrupted normal operation of the alarm physical machines is ensured, the migration cost of the virtual machines can be effectively reduced, the resource utilization rate of the alarm physical machines after migration of the virtual machines can be ensured, and resource waste can be avoided.

The invention relates to a service function chain reconfiguration method based on load balancing, and belongs to the technical field of mobile communication. The method aims at solving the problem that in a network function virtualization framework, server loads are uneven due to the fact that the wireless rate requirement of a user SFC changes. On the premise of ensuring the load balance of eachserver and the user request performance, the migration overhead of a virtual network function instance is optimized by taking the wireless subcarrier resource capacity and the limited link bandwidth resource capacity of a small base station as constraints, and a resource reconfiguration and virtual network function migration strategy is formulated for a deployed service function chain. According to the method, based on a Duffing Dep Q Network reinforcement learning algorithm, the load balance of each server and the performance requirement of a user request are ensured, the stability of the network is improved, and server resources are saved.

The invention relates to a database migration method and device from MySQL to Oracle and computer equipment. The method comprises the steps of selecting an initial MySQL database; acquiring table nameinformation of all database tables of the initial MySQL database; circularly traversing the database table according to the table name information to obtain initial table structure definition information; according to the database table and the initial table structure definition information, converting to obtain target table structure definition information meeting Oracle requirements; and generating a target Oracle database according to the database table and the target table structure definition information. According to the scheme, the table name information and the initial table structuredefinition information are obtained, the initial table structure definition information is converted to obtain the target table structure definition information, and finally the corresponding targetOracle database is generated, so that the database can be selected for migration according to actual needs, and migration cost is reduced while accurate migration of the database is guaranteed.

The invention discloses a controller load balancing system and method based on efficient switch migration. The system comprises a switch, an agent, a controller additionally provided with a load measurement module, a switch selection module, a target controller selection module and a switch migration module, and a sub-domain network. The method comprises the following steps: collecting load information of each sub-domain network through a controller; judging the load state of the controller, outputting the overload controller and the light load controller set, selecting the switch to be migrated by minimizing the migration cost, and migrating the switch from the switch set controlled by the overload controller to the switch set controlled by the light load controller to realize the balanced distribution of the load of the controller. The method is used in an elastic optical network with interconnected data centers, and the load balancing effect of the controller is remarkable.

The application discloses a flexible scheduling method and device for database comprising following steps: obtaining the performance parameter values of a database server and database instances that participate in the flexibility scheduling; selecting a database server whose performance parameter value exceeds a preset capacity upper limit; selecting a database instance from the database server and migrating it to a database server capable of accepting; determining whether or not a predetermined scheduling termination condition is satisfied, and if not, turning to and executing the step of selecting the database server whose selection performance parameter value exceeds the preset capacity upper limit. The application provides a flexible scheduling device for database at the same time. The use of the flexible scheduling method for database provided in this application avoids the jitter caused by the real-time change of the performance of the database instance, on the other hand can reduce the number of migrating database instances, reduce the migration cost, and use the heuristic method to avoid the complicated calculation process, effectively improve the efficiency of the implementation.

The invention discloses a hotspot migration method for cloud resource scheduling and is used for solving the technical problem that the existing hotspot migration method wastes resources and requires a large migration cost. The invention adopts the technical scheme that virtual machines on physical machines are divided into Master virtual machines and Slave virtual machines, the virtual machines on each physical machine consist of one Master virtual machine and a plurality of Slave virtual machines, and each business runs on the Master virtual machine; in order to ensure that the business normally runs when the Master virtual machine suddenly breaks down due to overload, a plurality of Slave virtual machines are distributed on other physical machines for each Master virtual machine and carry out data synchronization with the Master virtual machine at regular time. A node controller is arranged on each physical machine for collecting resource information on each virtual machine. When the node controller finds that hotspots exist on a certain physical machine, the node controller notifies a cluster manager, the cluster manager makes judgment according to hotspot conditions on each physical machine and selects a proper physical machine to migrate the hotspots, thereby eliminating the hotspots, and migration cost is lowered.

The invention discloses a data extracting and loading method based on mass data migration. The realizing process of the method comprises the steps of extracting data firstly, leading an external table and a data source to be separated via constructing a casual user, and carrying out partitioning and parallel segmentation on the mass data to generate a plurality of dump files; then performing data loading, namely carrying out analysis and processing on the data, transforming and filtering abnormal data, and finally adopting a bulk import data mode to migrate the data to a target data source. Compared with the prior art, the data extracting and loading method based on the mass data migration can quickly extract and load the mass data from various data sources, has very little influence on the system of a data source, guarantees the accuracy of the data, reduces the influence on an operation system to the maximum extent, and is strong in practicability and wide in the range of application, thereby having very good popularization and application values.

The invention discloses an automatic service transition method and an automatic service transition apparatus. The method comprises steps: after a network topology is transitioned, a current service transition scene and landing devices selected by a user are acquired; target services to be transitioned at this time are automatically selected from current original path services according to the network transition scene and the landing devices; service transition parameter configuration is carried out on each target service, and a target protocol required by each target service for changing a service model is selected from a protocol pool, the target protocol is issued to a network topology device, and each configured target service is issued to the corresponding landing device, and change of the service model is completed. Thus, the whole transition process of services is finished. In the process, the user only needs to select the service transition scene and the landing devices; and the calculation selection of services, parameter configurations, protocol selection and the like are automatically completed by the system, such that the time and labor consumption are greatly reduced, and moreover, the service transition costs are reduced and the service transition efficiency is improved.

The invention provides a data migration method. The data migration method comprises the steps of establishing connection between a source object storage cluster and a target object storage cluster through an S3 protocol interface; reading a user list or a bucket list from the source object storage cluster by utilizing the S3 protocol interface; allocating a data migration task according to the user list or the bucket list; and executing the data migration task, reading object data and writing the object data into the target object storage cluster in real time. According to the method, the datamigration operation is simplified, and the data migration efficiency is greatly improved. The invention further provides a data migration system, a storage medium and a data migration terminal, whichhave the above beneficial effects.

The invention provides a non-intrusive load identification method based on metric learning, and the method comprises the steps: mapping load current characteristics to a metric space through a one-dimensional convolutional neural network, achieving the clustering of the characteristics through the triple loss during network training, and carrying out the similarity discrimination of the characteristics of the metric space, thereby achieving the load identification. According to the method, the unknown load can be effectively identified, and the generalization ability is high; on the other hand, metric learning serves as one of small sample learning methods, dependence on training samples can be relieved, and high practicability is achieved.

The invention relates to a dynamic threshold value-based cloud-computing virtual-machine migration control method. An average utilization rate of CPUs in physical machines can be increased while SLA violation frequency is reduced, low-energy-consumption physical machines can be emptied at the same time, and thus the number of active physical machines is decreased. In addition, compared with traditional methods, the method of the invention can reduce unreasonable virtual-machine migration frequency, ensure, as far as possible, that migration costs become lowest, and achieve an effect of low energy consumption and high energy efficiency.

The invention discloses a data visual query language system. The system comprises a DVL builder, a DVL analysis engine module and a data analysis engine module, wherein the DVL builder builds a DVL statement by a user operation model and a data model; the DVL builder is connected with a data model module, an operation model module and a DVL grammar rule module; the DVL analysis engine module is connected with the DVL builder to analyze the DVL statement to obtain executive plan trees of executive sub-processes; the data analysis engine module executes the executive plan trees of the executive sub-processes one by one according to an executive sequence, and fuses graphic information and data information to generate a graphic data model; and obtained graphic data is transmitted to a visual engine module, and the visual engine module renders the graphic model data into a BI chart visible for a user. According to the system, front-end visual chart display and a back-end data analysis process of the system are subjected to DVL-level isolation, so that complete decoupling of graphic display and back-end data processing is realized and a language-level standard data visual interface can be provided for outside.

The invention discloses a cross-platform multi-engine supported mass data migration device. The system comprises an original data storage system, a migration data storage system, a migration flow configuration module, a flow engine execution module and a flow engine scheduling module, wherein the original data storage system is used for storing an original data set to be migrated, and the migration data storage system is used for storing the migrated data set; the migration process configuration module is used for visually configuring the migrated business process logic; the process engine execution module is used for executing an actual migration process; and the flow engine scheduling module is used for regularly scheduling the migrated business flow. The device disclosed by the invention ensures that the data can be migrated by using an engine technology which is most suitable for data characteristics; the processing time delay is reduced to the maximum extent, the processing efficiency is improved, the migration cost is reduced, and the calculation engine can be quickly switched when the data timeliness is changed and the data volume is changed so as to adapt to new data characteristics without the secondary coding development.

The invention relates to the technical field of computer application, in particular to an Oracle database cross-platform physical migrating system implementation method. A platform differential processor in the method encapsulates file operating methods of different types of platforms, instructions for calling and operating a database and batch processing file types and calling methods in order to obtain a cross-platform. Based on the broadband condition, a large file segmentation concurrence transmission device segments database files and transmits the database files to a target terminal, the small files are combined and restored, and large file efficient transmission is achieved; a whole process script reestablished by the database is written into batch processing files through database reestablishment process scheduling, and then the batch processing files are called to achieve process management. The method achieves efficient Oracle database cross-platform physical migrating and is applicable to the cold standby and migration of big-data Oracle databases.

The embodiment of the invention provides a data migration method and device, and the method comprises the steps: carrying out the centralized storage and management of all routing data through a pre-built routing service cluster, and carrying out the real-time updating of the state information and node identification information in the routing data stored in the routing service cluster in a data migration process, and therefore, routing data with high accuracy and high consistency can be quickly queried from the routing service cluster; in this way, in the routing service processing process, the current state of the routing object can be inquired from the routing service cluster firstly, only the service of the routing object in the migration state is affected, the routing service of the routing object in the normal state is not affected, and therefore it is guaranteed that normal routing service service is provided for a user to the maximum extent, the user use experience is improved,automatic data migration in a routing service processing process is ensured, the data migration cost is reduced and data migration efficiency is improved.

The invention belongs to the technical field of the communication network, and discloses a two-stage C-RAN carrier migration scheduling method based on an improved LR algorithm. The method comprises the following steps: acquiring a business type feature of a load business in a to-be-migrated base station and a correlated variable of each specific load business in operation; according to the acquired business type feature and the correlated variable, establishing a migration scheduling mathematical optimization model based on the minimum system total service value loss by taking the situations that the business interruption time cannot exceed the maximum delay requirement and the time consuming for completing the whole migration process cannot exceed the maximum allowable migration time as the constraint condition; resolving the migration scheduling mathematical optimization model by using the two-stage migration scheduling model resolving method based on the improved LR algorithm to obtain the final migration scheduling method. By using the two-stage C-RAN carrier migration scheduling method disclosed by the invention, the defect that the existing C-RAN carrier migration scheduling method is long in migration time consuming and high in cost is effectively solved, the system total service value loss caused by completing the migration process is greatly lowered.