47 results about "Resource leveling" patented technology

The invention provides a multi-dimensional resource scheduling method under a Kubernetes cluster architecture system. Scoring each server node in the cluster for the compute-intensive service according to the resource idleness; and for common services, scoring each server node in the cluster according to the resource requirements of the scheduling tasks, the resource priorities of the server nodesand the resource balance degrees of the server nodes, and selecting the server node with the highest score to bind the pod scheduling task and execute the pod scheduling task. The scheduling method provided by the invention meets diversified resource requests of various services, and improves the flexibility and expandability of the system.

Methods, apparatus, and products are disclosed for dynamically balancing resources in a server farm, the server farm comprising a plurality of servers organized in functional server groups with the servers in each functional server group assigned a same type of data processing task, the servers operatively coupled to data storage through a packet switching fabric, the servers operatively coupled to a system management server, the methods, apparatus, and products including: monitoring, by a resource balancing module of the system management server, CPU utilization in at least one of the functional server groups; identifying, by the resource balancing module in dependence upon the monitored CPU utilization, an overburdened functional server group, the overburdened functional server group's CPU utilization exceeding a CPU overburden threshold; and increasing, by the resource balancing module, CPU resources of the overburdened functional server group, including moving a transfer server from a source functional server group into the overburdened functional server group.

The invention discloses a grid-based Internet content delivery method and a grid-based Internet content delivery system. In the method, a content resource leveling and slicing processing method is provided. The system performs slicing processing on a complete content resource according to preset rules to generate a plurality of small resource files with the same size or different sizes, and then intelligently delivers the plurality of small resource files into each serving node of a network. The problems of content resource redundancy in each serving node are remarkably reduced, system spaces of each serving node are effectively utilized, the hit rate of Internet content accessing of a user is also increased, the user can access nearby networks and intelligently divide network traffic, and the response of the network is greatly quickened.

The invention discloses a virtual machine distributed task scheduling method under a cloud calculating platform. The method comprises the following steps: (1), in case of a downtime event of a physical server, migrating the load on the physical server to a normal physical server; (2), when the load of a certain physical server is quite high, under the condition of uninterrupted application, migrating a relatively high load to a physical server with a relatively low load; and (3), when the load of a certain physical server is quite low, under the condition of the uninterrupted application, migrating the load on the physical server to other physical servers, and performing dormancy or shutdown on idle physical servers. The method provided by the invention realizes diversity and flexibility of a scheduling mode; resource equalization scheduling is generally considered from a virtualization VCPU mapping mechanism so that online migration, high availability and load balancing of a virtual machine are realized; and electricity-saving scheduling is generally considered from the virtualization VCPU mapping mechanism so that the economic operation of the virtual machine is realized, and the energy conservation effect is achieved.

The invention provides an optimization algorithm based on multi-objective resource-constrained project scheduling model. The scheduling model requires scheduling the start time of each activity to achieve the optimal goal under the condition of satisfying the relevant constraints. Based on the RCPSP model, the invention introduces the optimal resource balance as the objective, and expands the model to a multi-objective model. The solution of RCPSP is mainly based on the heuristic algorithm. When the task list is used to encode chromosomes in the heuristic algorithm, the task list initialized randomly may not satisfy the constraint relation between the top and bottom. The invention provides an individual generation mode based on control relation, which presents a new crossover operator andmutation operator based on the NSGA-II algorithm. The invention can greatly reduce the time complexity of the algorithm, realize the balanced allocation of resources, improve the production efficiencyand save the production cost while ensuring the solution precision of the algorithm, thereby improving the economic benefit of the resource scheduling production process.

The embodiment of the invention provides a virtual machine placement method and a cluster management server. Candidate weighted values of physical main machines are determined according to one-machine resource balance degrees and cluster balance degrees of the physical main machines, and the physical main machines with the maximum candidate weighted values or with the candidate weighted values larger than or equal to a preset value serve as placement physical main machines of a virtual machine. Therefore, when the virtual machine placement is carried out, one-machine resource operation conditions of the physical main machines serve as constraints, and load balancing between different physical main machines in a cluster is further considered. Therefore, the requirements for promoting the use ratio of the physical main machines and reducing migration expenses of the virtual machine are both considered when the virtual machine placement is carried out.

The embodiment of the invention provides an advertising position allocation method and device. The method comprises the following steps: receiving a broadcasting request of a target video, and determining an advertising position quantity N1 produced by the target video according to a preset advertising strategy; acquiring an advertising position vacancy rate B of a previous period of time of the current period of time according to a preset time division rule; comparing B with a preset advertising position vacancy rate threshold value A; determining the quantity of the advertising position allocated to the target video when the broadcasting request of the target video is responded according to a comparison result. By utilizing the embodiment of the invention, in case when the advertising resource in an advertising bank is insufficient relative to the advertising position at the later advertising period, the rest advertising resource in the advertising bank can be evenly delivered to the subsequent video requested to be broadcasted by a user, so that the advertising delivery effect and the user viewing experience can be improved.

The invention relates to an Elasticsearch cluster expansion method supporting resource leveling. The method includes steps of S1, mounting Elasticsearch nodes according to server hardwire resource; S2, setting basic parameters of a dynamic cluster and recording some state values of the dynamic cluster, and performing data persistence on the parameters and the dynamic values in format of database or XML into a magnetic disk; S3, creating a thread, detecting file number and space occupancy regularly, and creating zones and adjusting storage strategy dynamically according to system parameters ifa threshold value is reached. According to the invention, data volume of corresponding proportions can be stored according to performance load leveling of a server in an Elasticsearch cluster and automatic creating of bases and zones are supported according a target data volume and the magnetic disk space threshold value, and the cluster is expanded dynamically. Therefore, problems of excessive data volume of one zone and local hot spots during new data insertion are avoided. At the same time, automatic recognition and load leveling on bases and zones of the Elasticsearch cluster can be realized after a new server is added into the cluster.

Dynamically balancing resources in a server farm, where the server farm includes servers organized in functional server groups with the servers in each functional server group assigned a same type of data processing task, the servers operatively coupled to data storage through a packet switching fabric, the servers operatively coupled to a system management server, and the balancing of resources includes: monitoring, by a resource balancing module of the system management server, CPU utilization in at least one of the functional server groups; identifying, by the resource balancing module in dependence upon the monitored CPU utilization, an overburdened functional server group, the overburdened functional server group's CPU utilization exceeding a CPU overburden threshold; and increasing, by the resource balancing module, CPU resources of the overburdened functional server group, including moving a transfer server from a source functional server group into the overburdened functional server group.

The invention provides a resource leveling method and device between cells. The resource leveling method between the cells comprises the following steps: acquiring measurement report MR data and network load indexes of all cells in an area to be analyzed; determining congested cells in the area to be analyzed according to the network load indexes; determining a cell, which needs parameter configuration information adjustment, from adjacent cells of the congested cells as a target adjacent cell according to the MR data of the congested cell; and adjusting the parameter configuration information of the congested cells and the target adjacent cell, and realizing the resource leveling between the cells in the area to be analyzed. By adopting the technical scheme of the invention, resource leveling between the cells can be realized automatically for the cells in the area to be analyzed according to the acquired parameter configuration information and the network indexes of the cells, so that the complexity of manual operation can be avoided.

The invention discloses an electric power system supercomputing platform task scheduling method and system based on a Docker container, and belongs to the field of electric power system supercomputingplatforms. The electric power system supercomputing platform task scheduling method comprises the steps: a node adjustment step: predicting the future cluster resource utilization rate, reducing thenumber of starting nodes if the future cluster resource utilization rate is lower, and increasing the number of starting nodes if the future cluster resource utilization rate is higher; a resource allocation step: predicting the future cluster resource utilization rate, if the future cluster resource utilization rate is low, increasing the resource allocation of the container within a task demandallowable range, and if the future cluster resource utilization rate is high, reducing the resource allocation of the container within the task demand allowable range; a container scheduling step: deploying the containers in the scheduling queue, and realizing load balancing of different resources or realizing load balancing of nodes; and a container migration step: predicting the resource use conditions of all nodes in the future to identify overload nodes and light load nodes, migrating out part of containers in the overload nodes, and migrating out all containers in the light load nodes toclose the nodes. The electric power system supercomputing platform task scheduling method can improve the resource utilization rate of the supercomputing platform of the electric power system, and canreduce energy consumption.

The invention provides a network bandwidth resource balanced scheduling method and device, and the method comprises the steps: S1, building a penalty function according to the link information and service information of a network, and building a network scheduling algorithm model through employing the penalty function and a particle swarm algorithm; S2, generating a network resource distribution strategy according to the network scheduling algorithm model; and S3, carrying out network bandwidth resource balanced scheduling on links and services of the network by using the network resource allocation strategy. By adopting the network bandwidth resource balanced scheduling method, the technical problems of link bandwidth saturation and low bandwidth utilization rate in the prior art are solved.

The invention relates to a resource equalization virtual optical network mapping method based on time-frequency fragment awareness, belonging to the technical field of optical fiber communication. Inthe method provided by the invention, a weight formula of a physical node and a physical link is designed, and time and bandwidth resource in a network are weighed while a virtual network request is mapped, thus, bandwidth blocking rate of a virtual request service is reduced, and resource utilization rate in the network is improved; in a process of allocating spectrums for the virtual request service, fragmentation degree of a frequency slot on the link in a physical network in a time domain and a spectrum domain is considered, a spectrum block which has low fragmentation degree in the network after allocation is selected to server the service, and thus, spectrum fragments generated on a service transmission path are reduced. The invention provides the resource equalization virtual optical network mapping method based on time-frequency fragment awareness, the method not only can effectively reduce bandwidth blocking rate in the network and realize equilibrium distribution of the resource in the network, but also improves utilization rate of the spectrum resource in the network.

The invention discloses an account number management method, device and system, and belongs to the technical field of internet applications. The method includes the steps: detecting the number of invalid requests in virtual currency acquisition requests transmitted by a terminal through a first account number in a preset monitoring duration; judging whether the number of the invalid requests is larger than a locking number threshold value or not; rejecting to respond to first virtual currency acquisition requests in the virtual currency acquisition requests transmitted by the terminal through the first account number in a locking duration preset from the current moment if the number of the invalid requests is larger than the locking number threshold value. The first virtual currency acquisition requests are virtual currency acquisition requests generated when the first account number meets virtual currency acquisition conditions and a virtual room of first account number meets preset virtual currency generating conditions. The account number management method solves the problems of large load of a server and unbalanced distribution of resources, the load of the server is reduced, and the resources of the server are uniformly distributed. The account number management method is used for account number management of KTV systems.

The invention relates to a method of reducing the fluctuation in resource profile allows exploring solutions beyond the original project duration resource. The computer-implemented method includes the following steps: providing computer processing means and computer readable media; inputting a data set including a list of projects, a list of activities to complete the project, duration data, sequence data, a genetic algorithm (GA), an schedule extension scheme, a representation method, an algorithm of generating chromosome of initial population, a selection method of chromosome for reproduction, a resource leveling metric and a cross-over percentage and a mutation percentage; setting an extension increment associated with each project of the data set; formulating a genetic algorithm based model associated with each project of the data set and the GA; calculating an evaluation metric value for the project based on the GA model; and displaying an evaluation table, which is arranged with the evaluation metric values and durations. The method allows for searching the schedules of reduced resource leveling fluctuation beyond the original duration, and provides users the schedules with low resource fluctuation and more efficient utilization of resources.

The invention discloses a resource optimal allocation method suitable for an edge computing environment. The method comprises the steps of obtaining a current resource utilization rate of each processing node; obtaining the current residual resource quantity of each processing node in the processing node set; selecting a processing node with the maximum sum of the current residual resources from the processing node set, and setting the processing node as a processing node o; and selecting a task k from the remaining task set, adding the task k into the processing node o, recalculating the resource balance degree Pok of the processing node o after the task k is added, and performing resource optimization allocation based on the resource balance degree. On the premise of fully considering the resource load constraint condition of each edge computing device or processing node, the appropriate task is selected from the request tasks to be allocated to the appropriate edge computing deviceor node, so that the system resource utilization rate is highest, and the overall performance of the system is optimal.

The invention relates to a water resources allocation technology, which discloses a multi-objective water resources balanced allocation method based on a conditional risk value constraint, which realizes quantitative fairness and risk controllable water resources allocation. The method comprises the following steps: a. Determining an objective function of multi-objective water resources allocation; B. Determine the constraint conditions of multi-objective water resources allocation; C. Constructing a global model of multi-objective water resources allocation according to the objective functionand constraint conditions; D. The global model of multi-objective water resources allocation is optimized. The invention establishes a multi-objective linear water resource allocation model, and helps decision makers to fairly distribute water resources to industry, agriculture, household and ecology through an optimized water resource allocation strategy, and simultaneously controls the risk ofeconomic loss.

The invention belongs to the technical field of communication networks, and discloses a wireless resource dynamic balancing method and system and a computer program. A data processing node collects traffic statistical data, parameter configuration data and a collection scheme from an LTE system; a strategy judgment node judges whether a capacity expansion and reduction operation needs to be performed according to a license strategy control step based on the statistical data; and an execution node automatically generates a capacity expansion and reduction instruction script, connects the LTE system to perform operations, and collects the execution state. According to the scheme of the invention, an automatic capacity expansion and reduction balancing method is adopted, a large amount of labor cost can be saved, the period of traffic analysis and capacity expansion and reduction can be shortened, and the balancing efficiency of carrier wireless resources can be greatly improved; a flexible resource allocation mode of a wireless resource balancing system can well deal with the 'traffic tidal effect'; the application of a big data based machine learning prediction algorithm can make the balance of the wireless resources more accurate; and a large amount of license cost can be saved.

The invention relates to a rotary phased array radar task load dynamic balancing method. The method is mainly suitable for rotary phased array radar resource scheduling, a warning region is divided into a plurality of sectors according to the orientation, a task library and a time resource library exist in each sector, and task loads in further three sector task libraries are counted at the scheduling moment of the sectors. If tasks in the task libraries are overloaded, sector balancing needs to be carried out. After balancing, when the tasks in the task libraries of certain sectors are executed, the deviation angle of a wave beam can be too large, and the tasks need to be further adjusted. The tasks exceeding the deviation angle of the wave beam are adjusted to the sectors with a small deviation angle. The electric scanning capacity of a rotary phased array is fully utilized, resource balancing of the sectors is achieved, and the quality and efficiency of task completing are greatly improved.

The invention discloses a global system for mobile communications (GSM) double frequency co-located station cell resource leveling method based on gigabyte (Gb) interface signaling. According to the method, double frequency co-located station coverage cells in a GSM network are screened out according to a base station foundation database at first; then, Gb interface signaling data is collected, rate values under the co-located station double frequency cells are counted, and the configuration number of packet data channels (PDCH) under the condition that the co-located station double frequency cells meet requirements of different user sensing is calculated according to the rate value under the co-located station double frequency cells; and at last, the calculated PDCH number is compared with PDCH configuration of an existing network, and configuration for co-located station double frequency cells with unbalanced business is achieved. According to the method, cell resource balance is achieved through reasonable configuration for cell PDCH resources, configuration information of the cells is just changed, conditions of reselection parameters, coverage and power are not changed, influences on network quality, performance and test indexes of a speech network are little, and reasonable configuration for the cells can be achieved according to the level of user sensing.

The invention provides a virtual network mapping method and system based on classification. The virtual network mapping method comprises the steps that according to network topology information of each region, virtual nodes in a request for a virtual network are classified, the requested virtual network is partitioned into small-sized virtual network sub-requests according to a classification result, the virtual network sub-requests are dispatched to management entities in all the regions, and concurrent mapping processing is conducted; when the management entities in all the regions map the virtual network sub-requests, a resource equalization mechanism is introduced, equalization processing is conducted on demand limits of the virtual network sub-requests and available resources of a bottom layer physical network of the regions, and mapping of the virtual nodes and mapping of virtual links are coordinated and integrated; after the management entities in all the regions complete mapping, a global management entity integrates mapping results of the management entities in all the regions and feeds back the mapping results to a user. Compared with the prior art, the virtual network mapping method and system based on classification has the advantages that computation complexity is low, the mapping rate is high, and bottom layer physical network loads are better equalized.

The invention discloses a web system resource management method and system in a cloud computing environment based on an SDN. The method comprises the following steps: S1, constructing a web application system in the cloud computing environment based on the SDN; S2, acquiring the number of instantaneous session connections and the instantaneous link traffic of each server at every preset time; S3, if the numbers of instantaneous session connections obtained by any server for two consecutive times are greater than the maximum threshold of the number of instantaneous session connections, performing a resource leveling operation, and otherwise, executing step S4; S4, acquiring the average number of session connections and the average link traffic; S5, separately comparing the average number of session connections of each server with the maximum threshold of the average number of session connections and the aggregated threshold of the average number of session connections; and S6, performing the resource leveling operation or resource aggregation operation according to comparison results. The web system resource management method and system disclosed by the invention have the beneficial effects of saving server resources and effectively improving the utilization efficiency of existing resources.

The invention provides a distributed message system and an expansion method thereof. The system comprises a cluster resource monitoring module used for monitoring hardware resource use information of an agent side in real time and summarizing resource use standard exceeding rate of the agent side, and sending an expansion request when the resource use standard exceeding rate of the agent side reaches a threshold value; a cluster resource management module used for receiving the expansion request sent by the cluster resource monitoring module, calculating expansion required resources according to the expansion request and sending a resource equalization request; and a load balance notification module used for receiving the resource equalization request sent by the cluster resource management module, initiating resource change operation to a public address monitored by a message sending side and a message receiving side, and recording the expansion required resources in the public address. The system can realize automatic expansion.

The invention provides a resource self-migration method and system based on a cloud computing platform, belongs to the cloud computing technical field, and can solve the problems that an existing cloud computing resource equalization mechanism cannot ensure computing resource and storage resource to be dispatched on a same physical machine; the resource self-migration method comprises the following steps: mirroring the computing resource and storage resource, configured to a virtual machine, to the corresponding physical machine; checking whether the computing resource and storage resource configured to the virtual machine are mirrored to the same physical machine or not; if not, locating the physical machine with the storage resource, and self-migrating the computing resource to the physical machine with the storage resource.

The invention provides a resource deployment method and system for a Linux container. The method comprises the steps that (1) for each physical host, the matching degree of the physical host and the container in each dimension of resource is calculated according to the requirement condition of the container to be built for N-dimensional resources and the condition that the physical host can provide the N-dimensional resources, and N is larger than 1; And 2) in the N-dimensional space, based on the feasible domain range determined by the set feasible domain boundary value m, one or more physical hosts of which the matching degrees is or are screened with the container on the resources of each dimension are in the feasible domain range, and m is greater than 0. According to the invention, resource fragments can be effectively reduced, the resource utilization rate of the host under the condition of close full load is improved, and resource waste is avoided. And moreover, compared with the traditional greedy strategy deployment, the resource balance degree of the method is improved by about 100% through testing.

A hybrid task board and a critical path based project application are described here. Tasks can be visualized and tracked through automatic generation of a task board based on data from a project management application and data transferred from a task board to a project management application. Summary tasks, which represent grouping of related tasks in project management, are pivoted such that sub-tasks can be laid out in task board rows or "stories." Progress status indicators in a task board (or columns) are derived automatically from intrinsic and traditional project management application fields like "percent complete" enabling users to take advantage of traditional project management features such as dependencies, resource leveling, etc., while presenting a simplified and intuitive task board interface to a project manager and / or a project team.

The invention provides a virtual machine resource allocation method and device and an electronic device. The virtual machine resource allocation method comprises the following steps: determining the type of a dominant resource of a physical machine cluster according to a virtual machine resource application request; determining the physical machines of which the types of the dominant resources arethe same as the types of the dominant resources of the physical machine cluster as candidate physical machines; and determining the candidate physical machine with the minimum occupation ratio of theresources with the type the same as that of the dominant resources as the target physical machine for creating the virtual machine on the target physical machine. According to the virtual machine resource allocation method and device and the electronic device provided by the invention, a large-specification virtual machine can be conveniently applied and created, different types of resources in asingle physical machine can be uniformly occupied, and the physical machine operation and maintenance risk of a user can be conveniently reduced.

The invention belongs to the technical field of services of web servers, and discloses a service system and a service method based on a multi-web server, and a storage medium. The service system comprises a data communication module, a parameter configuration module, a main control module, a data updating module, a resource balancing module, a database module and a test module. According to the service system provided by the invention, under the condition that no additional load balancing device is deployed, a Web application system achieves the load balancing through the resource balancing module, thereby reducing the complexity of deployment and maintenance; meanwhile, the test personnel does not need to manually construct a test script according to a Web element identifier and other information through the test module; and a connection can also be established with the Web server to be tested through a Telnet protocol to test the Web server to be tested, so that the time used by thetest personnel for manually testing the Web server by using a browser can be saved. Therefore, the test efficiency of the Web server can be improved by the service system provided by the invention.

The invention discloses a container scheduling method for secondary scheduling. The method comprises the following steps: monitoring the examples of each container, node and service on a container cloud platform in real time; obtaining the running states, resource data and affinity characteristics of the examples of the containers, nodes and services in real time; and providing a result indicatinga node where container increase or decrease operation is needed to be carried out through adopting strategies such as resource balance, affinity satisfaction and service disaster tolerance on the basis of greedy, simulated annealing and genetic algorithms. According to the method of the invention, aiming at solving the problem that the default scheduler of a current container cloud platform doesnot support container deletion operation, does not support batch scheduling and is poor in short-term multi-scheduling-request effect, the resource balance and service disaster tolerance strategies for container deletion operation and a batch scheduling optimization algorithm for the container cloud platform are introduced to meet the scheduling requirement of the secondary scheduling system and improve the scheduling effect of the platform.

The embodiments of the invention provide a message system resource balancing device, method and equipment. The balancing device comprises a load monitoring engine, an analysis engine and an operationexecution engine, the load monitoring engine is used for collecting a Kafka index from the Kafka cluster and sending the Kafka index to the analysis engine; the analysis engine is used for, generatinga first equalization scheme corresponding to all subscribers according to the Kafka index, the hard target of the Kafka cluster and the soft target of the Kafka cluster, and sending the first equalization scheme to an operation execution engine, wherein the hard target is a target that must be realized by a plurality of Kafka clusters, and the soft target is a target that is preferably realized by a plurality of Kafka clusters; and the operation execution engine is used for generating a plurality of operation instructions according to the first equalization scheme and sending the plurality ofoperation instructions to the Kafka cluster so as to enable the Kafka cluster to perform resource equalization according to the operation instructions. According to the invention, the resource automatic equalization operation can be executed by taking hard and soft targets as a core basis, and the performance of a message system and the user experience are improved.