28 results about "Application scheduling" patented technology

An application scheduler can schedule an execution of a software application based on compliance with a safety standard and an availability of system resources. The application scheduler can determine, based on a software inventory, that the software application is associated with the safety standard. The software inventory can include metadata corresponding to the software application. The application scheduler additionally can determine, based on the metadata of the software inventory, a set of system resources used to execute the software application. Subsequently, the application scheduler can schedule an execution of the software application based on the availability of the set of system resources.

The invention relates to an edge computing application scheduling and issuing method and device based on storage resource awareness, and the method comprises the steps: obtaining the storage resource information of an edge node and the performance data of a heterogeneous storage device, and predicting the storage demand and IO bottleneck of the edge node based on a machine learning algorithm; based on a prediction result, adopting reinforcement learning and a multi-target genetic algorithm to select an optimal edge node; and executing application task scheduling by adopting the optimal edge node, and adjusting resource allocation and task migration according to task requirements and node loads. According to the method, by dynamically sensing the storage capacity and performance of the edge nodes and the characteristics of heterogeneous storage equipment, node selection is optimized in combination with reinforcement learning and a multi-target genetic algorithm, task delay is remarkably reduced, and the resource utilization rate is increased. A dynamic resource allocation and task migration mechanism ensures load balance and adapts to a complex network environment. The feedback optimization based on the execution effect further improves the scheduling accuracy and the system robustness, and has the remarkable advantages of high efficiency and intellectualization.

The invention discloses an LBE large-space operation scheduling system, method and device and a storage medium, and relates to the technical field of virtual reality, and the system comprises a development configuration module, a space mapping module, a real-time synchronization module, an application scheduling module and a remote monitoring module. According to the method, development standardization, space digitization, data real-time, task process and control remote are realized, so that the development efficiency, the operation collaboration and the scheduling agility are greatly improved, and the management range is expanded.

The method for fine-grained computing task division and scheduling of multi-intelligent application of the application divides the interrupted intelligent application into five types of subtasks, including data preparation, model preparation, hardware resource preparation, inference and result post-processing. According to the subtask attribute inheritance principle, the attribute five-tuple of each subtask is determined. All the interrupted intelligent application subtasks are input into the subtask scheduling sequence generation algorithm, the subtask application scheduling sequence is calculated, and the subtask scheduling sequence is added to the application scheduling sequence. Through the task division and subtask scheduling method, the problems of low resource utilization and high multi-task execution delay in the airborne environment are optimized. The multi-intelligent application collaborative operation process is optimized based on the intelligent application scheduling algorithm and the subtask scheduling algorithm.

The invention discloses a multi-cloud job scheduling method for cumulative data processing application. The method mainly comprises five steps of initialization, Markov decision process modeling, CDP-SS network structure model construction, CDP-SS model training and cumulative data processing application job scheduling. According to the method, for cumulative data processing application, problem definition is carried out by combining a cloud environment and application data information, a CDP job scheduling problem in a multi-cloud environment is abstracted into a Markov decision process, decision process solution is carried out by using a near-end strategy optimization deep reinforcement learning algorithm, a network structure model is constructed and model training is carried out; and finally, performing CDP application job scheduling by utilizing the model. The method is superior to a benchmarking scheme in the aspects of cost and SLA violation rate, and the applicability and superiority of the method in a CDP application scheduling scene are verified.

An embodiment of the present application discloses an application scheduling method, which includes: determining at least one first virtual node with first identification information; wherein, the first virtual node has a corresponding relationship with an edge cluster managed by an application scheduling platform; determining resource requirement information of a first container to be scheduled with second identification information; wherein, the first container to be scheduled corresponds to a virtual application instance to be created; based on the resource requirement information, determining a target virtual node from the at least one first virtual node; scheduling the first container to be scheduled to the target virtual node; creating the virtual application instance to be created by the target virtual node based on the resource requirement information of the first container to be scheduled, so that the virtual application instance to be created runs in the edge cluster corresponding to the target virtual node. An embodiment of the present application also discloses an application scheduling platform and a storage medium.

The present application relates to the field of server scheduling, in particular to a scheduling method of a computing cluster, a storage medium and an electronic device. The method comprises: performing optimal computing cluster evaluation on a plurality of computing clusters to filter out initial target computing clusters; performing pre-scheduling on each server in each initial target computing cluster to determine target scheduling servers; sending a scheduling request to the target scheduling servers to create a computing application in the target scheduling servers; determining an initial target application cluster through historical data; and determining the target scheduling servers through real-time data. Thus, through twice filtering and matching of data in different time dimensions, a suitable server can be more accurately scheduled for an application. Moreover, through multiple dimensions of a cluster storage and computing resource topology ID, a cluster historical task average processing time, a cluster historical computing accuracy and cluster pressure, a cluster that meets the computing application scheduling can be more accurately determined.

The present invention relates to big data technology, and discloses a method for processing software system data, including: obtaining an original file set from a preset software system, converting the original file set into a structured data set, and storing the structured data set in a relational database; performing a merging and extraction operation on the structured data set to obtain a file set recognizable by the software system, and uploading the recognizable file set to the software system; receiving an operation instruction input by a user, parsing and processing the operation instruction to obtain a scheduling task; according to the scheduling task, and using a pre-created application scheduling task platform to upload and / or download the recognizable file set in the software system, so as to realize the automated processing of the data of the software system. The present invention also proposes a software system data processing device and a computer-readable storage medium. The present invention realizes the efficient processing of the data of the software system.

The application belongs to the technical field of cloud computing, and provides a cloud application mirror image construction and domain group management system and method. The system of the application comprises a node executor component, a mirror image manager component, a mirror image console component, a domain group controller component, an interface server component and a metadata database component; the mirror image console component obtains a request from a user side, converts the request into a specific execution task and distributes the task to the interface server component, the domain group controller component and the node executor component for joint completion. The application solves the problems of management cooperation and distribution strategy of cloud platform cluster node application mirror image resources and project domain and node domain group running application, and high-quality and efficient completes the full life cycle management, application scheduling and delivery of application mirror image, reduces the use threshold and operation and maintenance cost of users, and avoids the current waste of node resource space and application global scheduling phenomenon of the cloud platform.

The invention relates to the technical field, in particular to an intelligent scheduling management method and system for server spare parts, and the method comprises the following steps: analyzing logistics and contracts, matching addresses with an AC automaton to obtain regions and delivery volumes, extracting contract proportions to construct a customer mapping table, and counting the inventory and the number of inventory and in-transit customer parts in the regions. And calculating the failure rate, analyzing the BOM to obtain a replaceable list, calculating the total demand, subtracting the inventory and the in-transit amount to obtain a net application number, and when the net application number is greater than zero, integrating each piece of information to generate a spare part application scheduling plan. According to the method, logistics and contract information is automatically analyzed, a differentiated demand model combining customer contract proportion and component historical failure rate is dynamically constructed, fixed experience proportion is abandoned, regional real-time inventory and in-transit quantity are integrated, a net application gap is accurately calculated, and meanwhile, a replaceable component list is fused into a scheduling plan, so that the scheduling efficiency is improved. The spare part scheduling accuracy and the supply chain response flexibility are greatly improved, and the risks of resource mismatching and inventory overstock are effectively avoided.

The invention belongs to the technical field of cloud computing, and provides a mirror image construction and domain group management system and method for cloud application. The system comprises a point actuator component, a mirror image manager component, a mirror image console component, a domain group controller component, an interface server component and a metadatabase component. The mirror image console component obtains a request of a user side, converts the request into a specific execution task and distributes the task to the interface server component, the domain group controller component and the node executor component to be completed together. According to the method, the problems of management collaboration and distribution strategies of cloud platform cluster node application mirror image resources and project domain and node domain group operation applications are solved, application mirror image full-life-cycle management and application scheduling and delivery are completed in a high-quality and high-efficiency manner, the use threshold and operation and maintenance cost of a user are reduced, and the user experience is improved. The node resource space waste and the application global scheduling phenomenon of the current cloud platform are avoided.

The invention discloses a cloud edge cooperation system and method based on KubeEdge, relates to the technical field of edge computing, and realizes more accurate edge application scheduling by integrating multi-dimensional operation indexes on edge nodes. Reasoning delay and cloud cost are remarkably reduced through a cloud-side cooperative processing mechanism of a reasoning request; an enhanced edge node task management framework realizes observable task state, customizable process and failure self-healing; and a lightweight edge node group flow closed-loop mechanism is provided, and network isolation and cooperative configuration of cross-domain edge applications are simplified.

A method for application placement management. The method comprising identifying, by a storage agent, a first server from a plurality of servers or a first cluster from a plurality of clusters, the first server or the first cluster can access a first volume through which an application can be executed; identifying, by the storage agent, data associated with the application, wherein the data is stored in the first volume; identifying, by the storage agent, a group of servers from the plurality of servers or a group of clusters from the plurality of clusters having access to the data; updating, by the storage agent, data accessibility associated with each server of the group of servers or each cluster of the group of clusters; and notifying, by the storage agent, the updated data accessibility associated with each server of the group of servers or each cluster of the group of clusters.

The invention provides an edge application scheduling method and device, equipment, a medium and a product, and relates to the technical field of edge computing, and the method comprises the steps: obtaining resource state data of a plurality of edge nodes; dividing the edge nodes into a plurality of groups according to the resource state data; wherein at least one of the groups is configured as a point-to-point network group for mirror distribution; allocating a corresponding priority to each group based on the resource state data and the group type; wherein the priority is used for determining a distribution sequence of the edge applications; and scheduling the edge applications to each group in batches according to the priority sequence of the priorities. Therefore, efficient distribution of edge applications is realized by performing information acquisition and dynamic grouping on the edge nodes and combining a point-to-point networking technology and a priority scheduling strategy.

The embodiment of the application provides a multi-cluster service gateway fusion method and device and electronic equipment, and relates to the field of communication. The method first installs a Consul cluster; synchronizes Consul services of the Consul cluster in a preset container orchestration cluster; configures the Consul cluster in a preset application program scheduling and management cluster, and synchronizes management scheduling services of the application program scheduling and management cluster to the Consul cluster; configures a preset gateway management tool in the preset container orchestration cluster, and integrates the gateway management tool with the Consul cluster; performs rule configuration based on the gateway management tool to obtain routing rules; and matches the routing rules with access requests obtained through an external service access mode to provide services corresponding to the access requests. The embodiment of the application can realize registration and management of different services on the same service gateway, and guarantees the availability and security of application programs.

The invention relates to a security deployment system and method for a functional security cloud platform. The security deployment system comprises a security application scheduling module running in a cloud management platform and a deployment verification module running in security middleware. A plurality of copies of the security application respectively run on full middleware of different target servers, and the security application copies are connected through security application nodes of a double 2-vote-2 structure; the security application scheduling module performs multi-dimensional compliance verification on a physical machine resource pool before deployment of a virtual machine, and allocates resources for each channel of a security application node; and the deployment verification module verifies the CPU state, the memory state and the independence of a security application node channel in real time based on a two-out-of-two architecture. Compared with the prior art, on the premise of not depending on special hardware, high reliability, high deployment efficiency and simple architecture design of the functional security cloud platform are achieved, stable operation of train control application software on the cloud platform is ensured, and security constraints of the cloud platform are met.

An embodiment of the present invention relates to an AI application scheduling method, device, and electronic device based on K8s. The method includes: when receiving a resource scheduling request for creating an AI application, parsing the resource scheduling request to obtain resource scheduling conditions and identification information corresponding to the resource scheduling application scenario; determining a resource scheduling object according to the identification information corresponding to the resource scheduling application scenario; when the resource type to be scheduled includes heterogeneous acceleration cards, screening out nodes with heterogeneous acceleration cards from the resource scheduling objects; after reserving the resources of the nodes with heterogeneous acceleration cards according to a pre-configured reservation ratio, determining the remaining resources of each node with heterogeneous acceleration cards, where the remaining resources include the type of remaining resources and the resource quantity corresponding to each type of remaining resources; when the remaining resources of a first node meet the scheduling conditions, using the first node as the target node to complete the scheduling of the AI application.

The embodiment of the invention provides a communication mode adjusting method and system, and the method comprises the steps: responding to a received diagnosis request, entering a diagnosis communication mode, and transmitting a diagnosis communication request to a slave node which is determined according to the request information carried in the diagnosis request, the diagnostic communication request is used for indicating the slave node to enter a diagnostic communication mode; determining a message scheduling mode based on a response state of the slave node, the response state being used for indicating whether the slave node responds to the diagnostic communication request, the message scheduling mode comprising a diagnostic scheduling mode or an application scheduling mode; a communication mode is adjusted based on the message scheduling mode, and the communication mode comprises a diagnosis communication mode corresponding to the diagnosis scheduling mode or an application communication mode corresponding to the application scheduling mode. The technical problem that in the prior art, a vehicle network cannot give consideration to real-time performance and sudden fault processing requirements is solved.

Embodiments receive historical application data from at least one historical application, receive incoming application data about at least one incoming application, extract a first set of features from the historical application data and a second set of features from the incoming application data using at least one machine learning model, convert the first set of features to a first set of feature vectors and the second set of features to a second set of feature vectors, perform a vector similarity search by comparing the first set of feature vectors to the second set of feature vectors, determine a matching vector based on the vector similarity search, and schedule execution of the at least one incoming application using a node based on the matching vector.

The invention relates to an edge computing application scheduling and issuing method and device based on computing resource awareness, and the method comprises the steps: collecting computing resource data of edge nodes in real time, and predicting a future resource use trend through a machine learning model based on a time sequence; based on the prediction result, generating a task scheduling scheme by using a multi-objective optimization framework; and deploying the task to the target edge node based on the scheduling scheme. According to the method, the edge node resources are sensed in real time, the trend is predicted in combination with machine learning, intelligent task scheduling and issuing are achieved, and the resource utilization rate and the system efficiency are remarkably improved. The multi-objective optimization framework balances load, delay and energy consumption, and dynamic adjustment ensures adaptation to a heterogeneous environment. Containerization deployment and a fault-tolerant mechanism enhance task stability and system robustness, and reduce resource waste and node overload risks.

The application provides an edge application scheduling method and device, equipment, medium and product, relates to the technical field of edge computing, and comprises the following steps: acquiring resource state data of a plurality of edge nodes; dividing the edge nodes into a plurality of groups according to the resource state data; wherein at least one group in each group is configured as a point-to-point network group for mirror distribution; allocating corresponding priorities to each group based on the resource state data and the group type; wherein the priority is used to determine the distribution order of the edge application; and batch scheduling the edge application to each group according to the priority order of the priority. As can be seen, through information collection and dynamic grouping of the edge nodes, in combination with the point-to-point networking technology and the priority scheduling strategy, efficient distribution of the edge application is realized.

The embodiment of the invention discloses an application scheduling method and device. The method comprises the following steps: acquiring a first demand instruction input by a user; obtaining MCP service description information configured by each application in one or more applications on the cloud mobile phone platform; determining first MCP service description information corresponding to the first demand instruction according to the first demand instruction; when a user demand corresponding to the first demand instruction meets an application scheduling intention, determining a target application in the one or more applications corresponding to the first MCP service description information according to the first MCP service description information and MCP service description information configured for each application in the one or more applications; and calling the target application. Through the scheme, the cloud mobile phone intelligent agent can utilize a standardized MCP protocol to automatically discover and call the scheduling capability provided by the application according to user requirements, so that the efficiency, the flexibility and the stability of application scheduling are remarkably improved.

The invention provides a reconfigurable computing-based cryptographic operation drive implementation method and system, and relates to the technical field of computers, and the method comprises the following steps: obtaining a cryptographic operation task request of an application program; the cryptographic operation task request comprises a task type and task data; driving loading is carried out according to the password operation task request of the application program, and password operation data packaging parameters in the reconfigurable password card are obtained; performing application scheduling on the application program and performing task processing on the task data according to the cryptographic operation data packaging parameter and the task type to obtain operation result data of the cryptographic operation task; and performing data encapsulation on the operation result data according to the task data to obtain to-be-operated data, and performing operation on the to-be-operated data by the password operation core. According to the method, the cryptographic operation data packaging parameters of the reconfigurable cryptographic card are obtained according to the cryptographic operation task request, data packaging is completed according to different cryptographic operation data packaging parameters, and the adaptation capacity of reconstruction of different cryptographic resources is improved.

The invention provides an endurance control method and system applied to an intelligent terminal. The method comprises the following steps: acquiring brightness dynamic adjustment information, volume dynamic adjustment information and content color dynamic adjustment information of an application program; associating the brightness dynamic adjustment information, the volume dynamic adjustment information and the content color dynamic adjustment information with basic power consumption of the intelligent terminal to obtain an endurance scheduling unit; generating a basic scheduling path of the endurance scheduling units of the plurality of application programs; traversing the basic scheduling path based on an ant colony algorithm to obtain an endurance scheduling control scheme, and controlling the operation of the intelligent terminal according to the endurance scheduling control scheme; the method provides strong global search capability and parallel processing capability, effectively avoids the problem of falling into a local optimal solution, has relatively high robustness, is suitable for application scenes of multi-screen display, especially split-screen application scenes of a folding screen, improves the scheduling control efficiency of application programs, effectively improves the endurance of the intelligent terminal, and reduces the power consumption of the terminal.

The invention discloses a task processing method based on an intelligent assistant and related equipment, and the method comprises the steps: generating a to-be-processed task in response to a received task instruction; obtaining domain data associated with an account and the task instruction through an intelligent assistant; performing task splitting processing on the to-be-processed task according to the domain data to obtain a sub-task set; and performing multi-application execution processing on the sub-task set through the intelligent assistant scheduling application component, and outputting to obtain a task processing result. According to the embodiment of the invention, the task processing fluency and intelligent degree are improved, and the method can be widely applied to the technical field of computers.

The application discloses a kind of intelligent robot control algorithm scheduling method and system based on dynamic directed acyclic graph.The scheduling method includes receiving the change of robot state or environment data, traversing conditional directed acyclic graph from root node, when executing to end node, dynamically generating intelligent robot control algorithm scheduling instance;Wherein, conditional directed acyclic graph contains at least one condition node, for activating corresponding model branch according to input data.This application scheduling method can effectively speed up the deployment of robot control algorithm when facing different scenarios, and reduce the complexity of deployment and implementation.

A computer-implemented method identifies a set of system applications of a system and a set of resources. A composite performance score is determined for each of the resources and the resources are ranked. The system applications are classified in at least two classifications such that each system application corresponds to a single classification and the classifications include a hierarchy of importance. The resources are ranked based on the composite scores. A highest ranked available resource is scheduled to an unscheduled system application having the highest classification of unscheduled system applications as a primary resource. A next highest ranked available resource is scheduled to the unscheduled system application as a secondary resource. The ranking and scheduling is reiterated until all system applications have been assigned to a resource. A schedule of resources identifying each system application and each resource scheduled to the system applications is output.