57 results about "Elastic scheduling" patented technology

The invention provides a containerized resource elastic scheduling method and system in a cloud computing environment, and relates to the technical field of containerized resource elastic scheduling, and the method comprises the steps: obtaining various resource contention events, and generating data which records a resource contention relationship between tenants in detail; identifying a preset high-frequency conflict mode by deeply analyzing the data, and determining a specific tenant group with a strong resource mutual exclusion effect; dynamically estimating a probability level of resource conflict between the new container and the specific tenant group in combination with historical contention information and a real-time resource load state; generating a set of dynamic isolation scheduling strategies according to the conflict risk indicated by the probability level; an independent conflict buffer resource pool is configured and adjusted for a specified key tenant, a tenant resource conflict mode can be identified, dynamic isolation scheduling and buffer resource configuration can be implemented, and the resource utilization efficiency and the system stability of a multi-tenant container in a cloud computing environment are improved.

The invention relates to a multi-data center elastic scheduling method, which comprises the following steps of: establishing a data center polymer (DCA) to integrate the space-time regulation potential of a dispersed data center, establishing a comprehensive model covering dynamic migration of a working load, power consumption regulation and control of a DVFS (Distributed Valve File System) and collaboration of an optical storage system, and adopting a double-layer elastic scheduling architecture, energy storage charging and discharging, photovoltaic output and other hyperopia actions are optimized to improve long-term decision robustness; and the lower layer solves short view actions such as server scheduling and load distribution in real time based on mixed integer linear programming to realize instant cost optimization, so that power-computing power collaborative scheduling optimization of the data center is realized. According to the method, flexible scheduling of time delay sensitive type and time delay tolerant type workloads is combined, the cooperative effect of an energy storage system and photovoltaic power generation is utilized, the power use efficiency and economical efficiency of the data center are optimized, and dynamic participation of multiple data centers in the power market is achieved.

The invention discloses a dynamic core binding and energy efficiency optimization method and device based on a scheduling domain. The method comprises the following steps: analyzing a CPU topological structure when a kernel is started, and identifying and registering a Cluster scheduling domain; constructing a multi-level scheduling domain hierarchy comprising a Cluster layer, an MC layer and an NUMA layer; regularly detecting the utilization rate of the current scheduling domain, and dynamically switching the levels of the scheduling domain according to a comparison result of the utilization rate and a preset threshold value; and when it is detected that the scheduling domain level switching frequency exceeds a preset frequency threshold, starting an oscillation suppression mechanism. Through the three-layer elastic scheduling domain architecture comprising the Cluster layer, the MC layer and the NUMA layer and the dynamic oscillation suppression mechanism, the task scheduling efficiency and the system energy efficiency are optimized, fine-grained load balancing can be achieved, memory access delay can be reduced, scheduling domain level oscillation caused by short-term fluctuation and floating can be avoided, and the system stability can be enhanced.

The invention discloses an industrial internet resource autonomous scheduling method based on data element micro-transaction. The method comprises the following steps: acquiring industrial internet resource energy consumption; constructing a comprehensive energy consumption model; associating the model with a real-time power grid carbon factor; the method comprises the following steps: performing parallel transaction on a double-layer market of function resources and carbon quotas, quoting by a resource party based on a comprehensive energy consumption model, performing transaction according to a carbon quota difference by a task party, combining quoted price and carbon transaction cost, solving a multi-objective optimization problem, selecting a comprehensive cost optimal resource, establishing an elastic scheduling contract between the task and the resource, and executing dynamic re-negotiation. According to the actual consumption and carbon emission closed-loop settlement recorded by the contract, the carbon net balance is subjected to token excitation or purchase compensation; according to the method, the environment cost is internalized into a market economic variable, industrial internet resources meet performance requirements, meanwhile, autonomous evolution towards a low-carbon target is achieved, the resource utilization rate is increased, and economic and environmental benefits of a scheduling system are improved.

The invention belongs to the field of security protection, and particularly relates to a cross-border traffic pool dynamic elastic scheduling system and method, and the method comprises the steps: collecting the real-time quality and traffic parameters of a multi-operator link, and generating a scheduling detection sequence in combination with historical data and the hidden intention of a service appeal text, generating state data through fusion calculation and sending the state data to a cross-border traffic pool dynamic scheduling platform; the flow pool dynamic scheduling model is used for decoupling a time sequence delay coupling relation between parameters, flow consumption fluctuation caused by cross-domain routing convergence is predicted, a feature vector containing a flow excess risk probability and link quality fluctuation is extracted, a target scheduling instruction is generated in response to a cross-domain linkage scheduling condition, and a flow distribution proportion is adjusted or a path is switched. According to the invention, elastic resource allocation and excess risk early warning are realized, and the utilization rate of cross-border traffic resources is improved.

The invention discloses a load-algorithm bidirectional elastic scheduling method and device for a hybrid energy storage system, and belongs to the technical field of water, wind and light stations, and the method comprises the steps: obtaining the operation data of a water, wind and light hybrid energy storage system through a collection CPU; performing wind and light ultra-short-term prediction and load evaluation through the prediction CPU, and evaluating the battery state and the water and electricity available capacity to obtain a prediction result; computing resources, priorities, resource allocation proportions and levels of energy storage algorithms of control tasks of multiple time scales are determined by scheduling a CPU according to the operation data and the prediction result, calculation-communication pre-preemption is triggered after an early warning event is generated, and a task list and a resource allocation matrix at the current moment are generated; executing a control operation by controlling the CPU according to the task list and the resource allocation matrix; adjusting a next scheduling cycle strategy or executing a thermal migration mechanism according to a result after execution control, and performing backfilling execution on selectable sub-graphs of the directed acyclic task graph in an empty window period; and bidirectional elastic adaptation of the load and the algorithm is ensured.

The invention discloses an elastic scheduling method and system for a power grid based on a dynamic security domain, and relates to the technical field of elastic scheduling methods, and the method comprises the steps: determining the boundary of a non-key constraint based on an elastic adjustment factor, a power grid operation event corresponding to the power grid, and a plurality of constraints; the corresponding optimization event is determined according to the dynamic security domain, the boundary of the non-critical constraint and the real-time working data of the power grid, and the elastic scheduling system of the power grid is determined based on the optimization event, the real-time load data of the power grid and the corresponding real-time power supply data, so that the accuracy of the elastic scheduling system of the power grid is improved; and the elastic scheduling effect of the power grid is further improved. Therefore, the plurality of sub elastic scheduling projects are determined according to the identification of the elastic scheduling mode, the power optimization event of the power grid is determined based on the project content of each sub elastic scheduling project, the corresponding project position and the real-time load data of the power grid, and the accuracy of the online optimization logic of the power grid is ensured.

The invention discloses a massive heterogeneous task elastic scheduling method based on multi-granularity state awareness, which belongs to the field of cloud computing, and adopts the technical scheme that the method comprises the following steps: collecting operation data of a system in a continuous time window; processing the operation data to obtain a fusion state vector; splicing the fusion state vector and the feature vector of the current to-be-scheduled task to obtain a state required by a task scheduling decision; and generating a candidate target node set according to task feature information and system resource constraints to construct an action space, and transmitting the fusion state vector and related features of the current to-be-scheduled task as input to a strategy network based on reinforcement learning to obtain a scheduling result. The elastic scheduling method for the massive heterogeneous tasks has the beneficial effect that the elastic scheduling method for the massive heterogeneous tasks can realize multi-granularity state sensing in a long-term dynamic environment.

The invention discloses a smart park distributed monitoring system and method based on heterogeneous computing power elastic scheduling, the system is constructed by a distributed architecture in which a central configuration scheduling node and heterogeneous computing power nodes are separated, and the system comprises a central configuration scheduling node, a plurality of heterogeneous computing nodes and one or more AI model online reasoning units; the central configuration scheduling node communicates with the heterogeneous computing node through a network, and the heterogeneous computing node communicates with the AI model online reasoning unit through a high-performance RPC protocol; the central configuration scheduling node is responsible for unified management of task configuration and resource scheduling, the heterogeneous computing node is responsible for execution and state maintenance of a task process, and the AI model online reasoning unit is specially used for model reasoning calculation, so that three-layer decoupling of a computing task, resource scheduling and model reasoning is realized. According to the scheme, the problems that an existing intelligent monitoring system is rigid in hardware configuration, low in computing power resource utilization rate and incapable of achieving low-cost elastic expansion are solved.

This invention relates to a method for elastic scheduling of AI computing resources based on business awareness, comprising the following steps: predefining a business criticality level BK, and mapping the business criticality level BK to a corresponding weight coefficient V. bk The system automatically identifies the current iteration cycle stage of a task and predefines the corresponding dynamic weight coefficient C for the iteration cycle. It calculates and generates a dynamically changing priority score PF using a calculation function. It calculates and allocates the elastic quota FHQ for each business project, obtaining a total quota AHQ. When an urgent task is received, resource preemption assessment is performed. This invention employs a business-aware method, system, device, processor, and its computer-readable storage medium for elastic scheduling of AI computing resources. This achieves deep integration of business and technology, improves resource utilization, effectively suppresses users' false reporting of resource demands, thereby enhancing the overall utilization of the cluster; reduces preemption losses, avoids waste of computing resources, and maximizes the effective computing efficiency of the cluster.

The invention discloses an optimal scheduling method for a virtual power plant, and relates to the technical field of power regulation, and the method comprises the steps: obtaining multi-modal data of a detection region, calculating a regional load fluctuation index and a resource mobility index, and generating a dynamic feature data set; performing real-time clustering division on the power grid nodes through a clustering algorithm based on the dynamic feature data set to generate a dynamic sub-region set; if the sub-region feature fluctuation exceeds a boundary stability threshold value, triggering boundary redivision; according to the dynamic sub-region set, comparing a building power consumption predicted value with the available load of the charging pile in real time to calculate a demand difference, and generating an elastic scheduling instruction through multi-objective optimization; uncertain factors are monitored in real time, a risk index is calculated, and the priority and the resource allocation strategy of the elastic scheduling instruction are dynamically adjusted based on the risk index; and generating a risk avoidance scheduling scheme through a robust optimization algorithm.

The present application relates to the technical field of cluster resource scheduling, in particular to a dynamic computing resource elastic scheduling method for a heterogeneous server cluster, comprising: receiving an upper-layer application computing task description and analyzing resource demand characteristics and dependency constraints; pre-selecting initial candidate server nodes in a cluster global resource state space through an improved deep reinforcement learning algorithm with a dynamically adjustable reward function; constructing a multi-objective constraint optimization model in combination with node real-time load and task demand; calculating an adaptation score and scheduling the task to an optimal node for execution; and collecting task execution progress in real time and comparing it with resource demand to dynamically adjust reinforcement learning algorithm parameters. This method makes node pre-selection more in line with task demand, keeps scheduling decisions consistent with real-time cluster and task states, optimizes cluster load allocation states, and enhances the dynamic adaptation capability of the scheduling process.

This invention provides a method and system for elastic scheduling of cloud-edge resources in intelligent converged terminals for low-latency scenarios, relating to the field of resource scheduling technology. The method includes: acquiring and decomposing the end-to-end latency constraints of a target low-latency service request, and setting N initial candidate execution paths; mapping the N initial candidate execution paths to path state vectors and performing multi-dimensional evaluation analysis; performing path iterative search of the N initial candidate execution paths based on the comprehensive evaluation vector; configuring an elastic scheduling strategy using the path iterative search results; and performing intelligent scheduling management of the target low-latency service request. This invention solves the technical problems of existing cloud-edge-device scheduling methods that rely on static rules or single-node load, leading to unstable latency and low resource scheduling efficiency for low-latency services. It achieves the technical effect of improving the latency stability and resource scheduling efficiency of low-latency service requests through multi-dimensional constraint decomposition and path iterative optimization to realize cloud-edge-device collaborative scheduling.

The application discloses a network security product interconnection and intercommunication method and system based on elastic scheduling, and belongs to the technical field of network security. In order to solve the technical problems of poor compatibility, difficulty in dynamically adapting network environment fluctuation and low cooperative defense efficiency caused by manufacturer barriers among network security products, the application obtains standard data by uniformly converting the protocols, interfaces and data formats of each security product; determines target scheduling instructions based on the standard state data and performs elastic adjustment of paths, tasks and resources by using a strategy and a value network; generates global threat intelligence based on standard threat data and distributes cooperative protection strategies; and performs abnormal monitoring and self-repairing on the adjusted running state. The application can be widely applied to the key information infrastructure scene of multi-type security product cooperative protection, and significantly improves the resource utilization rate and the reliability of network defense.

The application discloses a tunnel flow dynamic scheduling system for small-granularity slice networks and relates to the fields of network slicing and traffic engineering.The application aims to solve the problems of low resource utilization of small-granularity slices and the difficulty of guaranteeing service experience by passive response scheduling in the prior art.The system comprises a small-granularity slice sensing layer, a dynamic strategy engine and a tunnel execution layer.The sensing layer collects queue depth and time delay data of tunnels in real time;the strategy engine predicts congestion based on a prediction model and identifies idle slices to initiate resource lending; and the execution layer dynamically adjusts paths and queue parameters to complete the lending.The application realizes prediction-based active elastic scheduling, significantly improves network resource utilization and guarantees the performance of high-priority services.

The invention discloses a distributed node collaborative elastic scheduling and cloud rendering splicing method and system. The method comprises the following steps: constructing a distributed node cluster supporting FPGA acceleration; node resources and network states are monitored and predicted in real time; rendering tasks are flexibly scheduled and migrated based on a prediction result; signal preprocessing is completed at an edge node, and rendering and splicing are completed at a cloud node; and finally outputting to a control system. The system comprises a node cluster used for executing the steps, a scheduling engine and a splicing assembly line. Through distributed cooperation and intelligent elastic scheduling, efficient and low-delay cloud rendering and splicing processing is realized, and the resource utilization rate and the system reliability are effectively improved.

The present application belongs to the field of safety protection, and particularly relates to a cross-border traffic pool dynamic elastic scheduling system and method, comprising: collecting real-time quality and traffic parameters of multiple operator links, combining historical data and implicit intention of business appeal text to generate a scheduling detection sequence, generating state data through fusion calculation and sending to a cross-border traffic pool dynamic scheduling platform; using a traffic pool dynamic scheduling model to decouple the time sequence delay coupling relationship between parameters, predicting the traffic consumption fluctuation caused by cross-domain route convergence, extracting a feature vector containing traffic excess risk probability and link quality fluctuation, generating a target scheduling instruction in response to cross-domain linkage scheduling conditions, and adjusting the traffic distribution ratio or switching the path. The present application realizes elastic resource allocation and excess risk early warning, and improves the utilization rate of cross-border traffic resources.

The application discloses a cross-cloud resource elastic scheduling method and system for management system development, relates to the technical field of resource scheduling, and solves the technical problems of cross-cloud edge resource static configuration and dynamic business demand mismatch, task scheduling and resource elastic expansion independent of each other, difficulty in collaborative optimization, lack of cross-cloud unified perception of container stretching mechanism, and rigid instance adjustment. Through a real-time load vector, short-time load accurate prediction is completed, and combined with service level agreement constraints, overall resource demand is accurately calculated. The existing resource quota, predicted resource demand and edge node cooperative cache ratio are included in the unified decision variable, a multi-objective optimization model is built, and balanced and reasonable allocation between resource domains is realized. Based on the optimization result, the expected number of resource instances is determined, and the PID controller is used to smoothly regulate the number of container and virtual machine instances. An improved differential polling scheduling mechanism is deployed at the network outlet, and the scheduling granularity is dynamically adjusted in combination with the business message characteristics and the resource load state.

The invention provides a large-scale data multi-thread processing method based on dynamic partition and cursor management. According to the large-scale data multi-thread processing method based on the dynamic partition and cursor management, the resource utilization rate and processing efficiency of large-scale data processing can be remarkably improved, rapid breakpoint recovery and elastic scheduling are achieved, the system interrupt rescheduling time is shortened to be within 3 seconds, and the lock conflict problem under high concurrency is effectively avoided.

This application discloses a method and apparatus for rapid deployment and elastic scheduling of model inference services based on declarative workload pooling. The method includes: after a user submits a declarative configuration of the inference resource pool, the inference pool controller constructs a preheating resource pool base and establishes lock-free pooling state management rules based on metadata tags; after a user submits the inference service configuration, the inference service controller matches and locks the target workload through a multi-dimensional pooling scheduling framework, completing activation and service deployment; when the service terminates, the two controllers collaboratively execute differentiated resource reclamation. This invention eliminates the need for an external database, reduces the cold start time of the inference service to the second level, adapts to business tidal scenarios to achieve efficient reuse of computing power, and meets the complex scheduling requirements of a pre-filling and decoding separation architecture.

The invention discloses an AI (artificial intelligence) model training-oriented automatic elastic computing power capacity expansion and contraction method and an AI model training-oriented automatic elastic computing power capacity expansion and contraction system. According to the method, training indexes and overall resource use information are collected, a resource demand curve is generated in combination with a lightweight prediction model, and whether capacity expansion and shrinkage are needed is judged based on a resource mapping matching degree score. And when it is detected that the resources are insufficient or over-matched, the system sequentially executes actions such as training fine adjustment, structured slicing, transverse expansion and contraction, topological adjustment and task-level arrangement so as to realize on-demand dynamic adjustment of the resources. The corresponding system comprises a training performance acquisition module, a resource monitoring module, an elastic scheduling strategy module, a resource control execution module and a training task management module, resource application or release can be completed under the condition that training is not interrupted, and the consistency of the training process is guaranteed. Compared with a traditional fixed allocation scheme, the resource utilization rate can be remarkably increased, the training time can be shortened, resource abnormity alarms can be reduced, and a user can obtain an efficient and low-cost training process without manual intervention.

This application discloses a method and apparatus for dynamic core binding and energy efficiency optimization based on scheduling domains. The method includes the following steps: parsing the CPU topology during kernel startup, identifying and registering the Cluster scheduling domain; constructing a multi-level scheduling domain hierarchy including Cluster, MC, and NUMA layers; periodically detecting the utilization rate of the current scheduling domain, and dynamically switching the scheduling domain hierarchy based on the comparison result of the utilization rate and a preset threshold; and activating an oscillation suppression mechanism when the switching frequency of the scheduling domain hierarchy exceeds a preset frequency threshold. This application optimizes task scheduling efficiency and system energy efficiency through a three-layer elastic scheduling domain architecture including Cluster, MC, and NUMA layers and a dynamic oscillation suppression mechanism. It can achieve fine-grained load balancing, reduce memory access latency, avoid scheduling domain hierarchy oscillations caused by short-term fluctuations, and enhance system stability.

The application relates to the technical field of cloud computing and big data processing, and particularly discloses a big data computing resource elastic scheduling and management system for a hybrid cloud environment, which collects events of each resource node and adds a hybrid logical timestamp to the events to form a global event set; the events are sorted and grouped based on the timestamp, and a set of to-be-scheduled transactions is extracted; the transactions are simulated to be executed in sequence, a resource occupation state graph is dynamically constructed, resource conflicts and cyclic waiting paths are detected, and a consistency verification result is generated; according to the verification result, if there is no conflict, all the transactions are converted into parallel scheduling instructions, if there is a conflict, part of the transactions are intelligently removed based on a dynamic relaxation scoring strategy to resolve the conflict, and a final scheduling instruction set is formed; the instruction set is synchronously issued to each resource node in an atomic operation mode for execution, and state events generated by the execution are fed back to the collection end to drive the next round of scheduling, so that the strong consistency and safety of scheduling decisions are ensured.

The invention discloses an electric power data quality checking method and system based on dynamic elastic scheduling, and aims to solve the problems that in the prior art, centralized scheduling cannot process massive electric power data, the checking time consumption is long, the upper limit of parallel tasks is low, and a traditional database is slow in query. The method comprises the following steps of: segmenting data into a plurality of blocks through data volume estimation, single server processing capacity and maximum allowable check duration, and scheduling a plurality of execution servers to perform parallel processing by a container cloud; a distributed storage architecture is adopted, an LSM tree structure is adopted to store check results, and the storage and query efficiency is optimized in combination with an exclusive check result table, LZ4 and ZSTD dual-mode compression, timestamp column value and other fragmentation strategies. According to the electric power data quality checking method and system, the time consumption of data checking is low, the checking result query speed is high, and the problems of timeliness and result query of data checking in the electric power data are effectively solved.

This invention relates to an AI-driven dynamic elastic scheduling optimization method for cloud operations and maintenance resources, comprising the following steps: Step S1, multimodal operations and maintenance data acquisition, obtaining multimodal operations and maintenance data streams of cloud infrastructure, including time-series performance index data, unstructured log text data, and application topology relationship data; Step S2, multimodal alignment and feature tensor construction, inputting the multimodal operations and maintenance data streams into a pre-trained AI model, the AI ​​model including at least a multimodal alignment encoder, a causal inference module, an elastic policy generator, and a prediction head; through the multimodal alignment encoder, the time-series performance index data, log text data, and application topology relationship data are mapped to a unified embedding space, constructing a multidimensional feature tensor representing the operating status of cloud resources; this invention can better drive dynamic elastic scheduling optimization of cloud operations and maintenance resources.

The application discloses a cloud-computing-based distributed simulation platform elastic scheduling method and system, and relates to the technical field of computer systems.The cloud-computing-based distributed simulation platform elastic scheduling method and system comprise a cross-field dynamic dependency processing module, a real-time task ultrafast scheduling module, a hybrid cloud resource adaptation module and an elastic scheduling core engine; the cross-field dynamic dependency processing module is used for realizing dynamic processing of dependency relationships in multi-field collaborative simulation, cross-domain collaborative allocation of resources and breakpoint self-recovery of task chains.The cloud-computing-based distributed simulation platform elastic scheduling method and system realize dynamic analysis of multi-field dependency relationships, cross-domain collaborative allocation of resources and breakpoint self-recovery of task chains through the cross-field dynamic dependency processing module, solve the problem of rigid cross-field dependency processing mechanism in the prior art, reduce cross-field data synchronization delay, and improve resource utilization and stability of task chains.

This invention relates to the field of cloud computing and intelligent resource scheduling technology, specifically providing a method and apparatus for elastic resource scheduling on a cloud platform. A monitoring and acquisition module collects metrics and topology information of hosts and VMs; a feature preprocessing module performs short-term smoothing, anomaly denoising, and holiday and event marking to provide cleaned input for prediction; a hybrid prediction module outputs the resource demand prediction and confidence interval for each VM within a future window T; a decision optimization module generates candidate action sequences, which are then selected and fine-tuned by an RL strategy; a security policy engine performs compliance and risk verification on the actions; the Executor executes the actions step by step on the cloud platform, performing canary deployments, monitoring checks, and rollbacks during execution; the Execution Coordinator and the Feedback Learning module store execution data, supporting offline replay training and online fine-tuning. Compared with existing technologies, this invention maximizes resource utilization and reduces operational costs while ensuring business continuity.

The embodiment of the invention provides an overseas cloud mobile phone AI-driven elastic synchronization method and system, and belongs to the technical field of data processing, and the method specifically comprises the steps: collecting a user operation sequence and transnational network link quality data; predicting a session interruption risk value R by using an AI model in which GNN and Transform are fused; when R exceeds a threshold value, selecting an optimal target node from the compliance node list to trigger hierarchical elastic scheduling; layering state changes according to high and low priorities through a semantic-level differentiated state synchronization engine, and performing incremental coding on high-priority operation to generate minimum instruction set synchronization; a data compliance strategy is automatically executed during cross-border transmission; and the global strong consistency of the metadata is guaranteed by adopting a Raft protocol optimized by a wide area network. Through the scheme disclosed by the invention, the problems of high delay, easy interruption and data compliance of overseas cloud mobile phones in a complex network environment are solved, and high continuity, low delay synchronization and reliable operation of sessions are realized.

The application provides an elastic scheduling method based on dynamic grading of multi-tenant monitoring resources. First, multi-tenant index data is collected. When an index update event is triggered, a weighted average update interval is calculated according to the multi-tenant index data. The weighted average update interval is matched with preset grading rules to obtain index grading information. The multi-tenant index data is dynamically collected according to the index grading information, and the elastic scheduling of dynamic grading of multi-tenant monitoring resources is completed. The method can sensitively perceive changes in tenant business load, dynamically adjust resource allocation and collection frequency, and realize dual optimization of resource utilization rate and service stability.