99 results about "Resource constraints" patented technology

The invention discloses an agent task scheduling planning method, and relates to the technical field of agent scheduling. The method comprises the steps of analyzing a task instruction to generate atomic tasks capable of being independently executed, constructing a subtask dependency graph, and defining association constraints between the tasks; determining the real-time resource occupancy state of the intelligent agent to obtain a resource state tensor, completing resource-task association anchoring and dependency priority ranking in combination with the sub-task dependency graph, and generating a task priority sequence with resource constraint; performing dynamic capability matching and predictive load balancing calculation on the sequence through a task-agent adaptation model, and determining a target execution agent of each atomic task; and based on the target execution agent and the subtask dependency graph, performing time sequence scheduling arrangement and conflict resolution, and generating a collaborative execution scheme. The method improves the reasonability and efficiency of agent task scheduling, reduces resource conflicts and execution timeout risks, and is suitable for agent cluster collaborative scheduling in a complex scene.

The invention relates to the technical field of edge computing, in particular to an operator edge computing node optimization method and system, and the method comprises the steps: obtaining local load features and cross-node association features of edge nodes in real time, and constructing a dynamic load vector and an association vector respectively; based on a preset time sequence prediction model, taking the load vector and the association vector as input, and obtaining a predicted load trend in a future preset time period; generating an optimal service migration strategy through a preset reinforcement learning model according to the predicted load trend in combination with the dynamic load vector, the association vector and the task attribute; wherein the migration strategy comprises a migration target node and a migration resource allocation scheme; wherein the task attributes comprise task priorities; and on the basis of the migration strategy, a resource pre-allocation scheme of the target node is generated in combination with a preset resource constraint condition, and the method has the advantages of improving service response, resource utilization rate, task success rate and the like in a high dynamic scene.

The invention provides a service scheme generation method and system, and relates to the technical field of computer application, and the method comprises the steps: obtaining user demand information which comprises a service type, a service scene, a resource constraint condition and an expected effect description; semantic analysis is performed on the user demand information based on the comprehensive domain knowledge graph, core service elements are extracted, and a user demand model is constructed; according to the user demand model, candidate service resources are matched in a service resource library through a heuristic search algorithm, and candidate service schemes are generated; a multi-objective optimization algorithm is adopted, real-time resource state data and user feedback information are combined, the candidate service schemes are dynamically adjusted, and the final service scheme is output, so that user requirements can be accurately analyzed, service resources are efficiently matched, the generated service scheme is optimized, knowledge and resource iteration is realized, and the scheme generation efficiency and quality are improved.

The invention relates to a dual-resource constraint flexible job shop scheduling method for reducing worker load, which comprises the following steps: S1, construction of a worker load model: dividing the worker load model into four conditions of light work, moderate work, micro-severe work and rest according to daily work arrangement of workers, and setting the maximum working time length for each worker, the calculation module is used for calculating extra workloads; in the scheduling method provided by the invention, three different initialization strategies are combined, and the proportion of the initialization strategies in a population is set, so that the diversity and quality of an initial solution are ensured, specifically, the used initialization strategies comprise random initialization, initialization according to the process completion time and initialization according to the process remaining time; under the random initialization strategy, the initial solution of the population has great diversity, which is helpful for avoiding the trouble of a local optimal solution.

The invention discloses an electric power resource hierarchical scheduling method based on dual-time scale deep reinforcement learning, and relates to the technical field of electric power scheduling, and the method comprises the following steps: S1, dual-time scale definition and constraint setting: dividing a scheduling period into a macroscopic time period (delta T) and a microscopic time step (delta t), and satisfying delta T = M * delta t (M is an integer); setting a resource constraint relationship, wherein the resource constraint relationship is a resource budget upper limit of the region r; s2, unified optimization target modeling: constructing a small-time-scale instant reward function based on time division of S1: coupling the macroscopic resource budget of S1, and designing a large-time-scale target function: S3, large-time-scale strategy modeling: based on the target function of S2, defining a regional state vector, and being capable of considering long and short-term scheduling requirements.

The invention relates to the technical field of flexible job shop scheduling in intelligent manufacturing and production scheduling, in particular to a flexible job shop scheduling optimization method for solving and adjusting resource constraints. Comprising the steps of initializing parameters and randomly generating an initial population; sequentially using a crossover operator and a mutation operator to evolve the current population; executing a hybrid decoding strategy on the current population; sorting the individuals in the current population from small to large according to the maximum completion time to form an elite population, and updating the elite population through question specific local search; and judging whether an evolution condition is met or not, if so, executing CP-based mathematical evolution, and outputting a final solution when the running time reaches the total running time. The method has the positive effects of reducing the resource waiting time, improving the machine utilization rate and improving the resource utilization efficiency and the scheduling performance of the whole workshop production.

The invention is suitable for the technical field of intelligent manufacturing scheduling, and provides a discrete manufacturing workshop multi-stage dynamic scheduling method based on transportation state feedback, which comprises the following steps: determining a multi-stage structure of tasks in a workshop, and establishing a corresponding task flow chart and a resource dependence model; a scheduling modeling basis with resource constraint and physical connection is formed; based on the current state of the system, key state variables are extracted, and a scheduling action space is defined; a transportation index is introduced into the reinforcement learning structure, and a composite reward function is constructed; reinforcement learning is adopted for training, and scheduling strategy parameters are iteratively optimized based on interaction between the intelligent agent and the environment. According to the method, rapid restoration and resource continuity maintenance of a scheduling strategy in a dynamic disturbance environment are realized, the real-time response capability and scheduling adaptability of a scheduling system under complex resource constraints are remarkably improved, and the method is suitable for manufacturing scenes facing high-frequency task change and transportation bottleneck problems.

The invention discloses a resource-limited equipment data-free federation incremental learning method and system, and relates to the technical field of transfer learning, and the method comprises the steps: training a model based on an incremental data flow through a deviation correction mechanism, obtaining a trained local parameter, uploading the trained local parameter to a cloud, and carrying out the data-free federation incremental learning of the equipment; calculating a difference value of the parameters to obtain a gradient of each edge computing device, calculating a federal average updating direction, calculating an aggregation weight according to a deviation degree between the updating gradient and the federal average updating direction, and performing weighted fusion on the updating gradient to obtain an updated global model; a synthesis sample of the old task is generated with the purpose of minimizing diversity loss; and carrying out knowledge distillation based on the synthetic sample, migrating old task knowledge to the updated global model, obtaining a final global model, and issuing the final global model to an edge end. Through deviation correction training, deviation degree and information entropy dual-perception aggregation and attention-guided data-free synthesis and distillation, federal incremental learning of resource-constrained edge equipment is realized.

Computerized systems and methods useful for resource-constraint scheduling using visual representations on a graphical user interface to build one or more schedules across a business network, where the schedules are dynamically reconfigured based off real-time changes to resource availability, constraints and requirements that must be satisfied, where interactions by the user with the schedule at the user interface cause the dynamic, real-time recalculation of possible appointments meeting the constraints, after which a schedule is reconfigured and displayed at the user interface.

The invention discloses an aviation composite material laying workshop man-machine scheduling method and system considering a collaborative learning effect, and the method comprises the steps: taking the minimum maximum completion time, the minimum maximum team task load, and the maximum worker proficiency degree improvement total amount as objective functions; a dual-resource constraint flexible job shop scheduling model considering a worker collaborative learning effect is constructed, and the scheduling model is solved through a multi-target whale optimization algorithm driven by domain knowledge; according to the method, the individual learning effect and the collaborative learning effect of workers are considered, a corresponding skill proficiency improvement model is constructed, and an optimal scheduling scheme is solved by designing a hybrid initialization method, a neighborhood search operator, an adaptive leader whale division strategy and an adaptive similarity threshold strategy and predation and search operators based on domain knowledge. And a scheduling scheme of worker and equipment resources can be generated more accurately, so that the processing efficiency is improved, and a resource allocation mechanism is optimized.

The invention relates to a deep learning task resource allocation method and device, equipment and a medium. The method comprises the following steps: respectively analyzing a computational graph structure and a historical resource monitoring log corresponding to a deep learning task, and generating a tensor dependency graph and a resource use time sequence matrix; performing time-varying demand prediction on the basis of the matrix, generating a time-phased resource constraint table, performing memory allocation processing on the basis of a tensor dependency graph, and generating a tensor memory partitioning scheme and an inter-partition communication cost matrix; and performing static resource pre-allocation based on the time-phased resource constraint table and the tensor memory partitioning scheme, generating pre-allocated resource configuration, and performing resource scheduling and outputting real-time resource configuration through a deep reinforcement learning model according to the time-phased resource constraint table, the inter-partition communication cost matrix and the pre-allocated resource configuration. According to the method, by means of dynamic resource allocation, cross-partition communication cost optimization, reinforcement learning optimization and the like, the resource utilization rate and task execution efficiency of a deep learning task are remarkably improved.

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 provides a task scheduling method, system and device based on multi-constraint optimization and a storage medium. The method comprises the following steps: acquiring a cluster real-time resource state and historical resource use characteristics of a to-be-executed task; determining constraint information based on the cluster real-time resource state and task configuration metadata of the to-be-executed task; the constraint information comprises an available resource constraint, a task concurrency constraint and a variable domain constraint; substituting the available resource constraint, the task concurrency constraint and the variable domain constraint into a linear programming model to solve the model; and generating a task scheduling strategy according to a model solving result. According to the method, the resource utilization efficiency and the task execution performance in a large-scale distributed computing environment are effectively improved.

The invention discloses a service adaptation method and device based on a skill dependence graph and QoS perception, and a robot method comprises the steps: responding to a task execution request sent by a client, and according to task demand information carried by the task execution request, presetting the skill dependence graph, and retrieving a plurality of available alternative atomic micro-services; the preset skill dependence graph is composed of a plurality of nodes and edges between the nodes; under the resource constraint of a preset multi-objective optimization model, determining an optimal service combination scheme from the plurality of alternative atomic micro-services; carrying out containerization deployment on each atomic micro-service in the optimal service combination scheme to obtain a deployed micro-service instance for task execution; in the execution process, when it is detected that service performance degradation or resource bottleneck exists according to the QoS index and resource information sensed in real time, the optimal service combination scheme is optimized, and the step of containerization deployment continues to be executed. Therefore, by adopting the embodiment of the invention, the execution efficiency of the task can be improved.

The application provides a robot complex task dynamic arrangement method, belongs to the field of robot task arrangement, and is used for solving the problems of weak dynamic environment adaptation capability of traditional static task arrangement, poor multi-robot collaboration and insufficient risk prediction in the related art. The method collects robot state and event data, constructs a double matrix, fuses the double matrix into a tensor, performs low-rank decomposition, dynamically generates and optimizes a threshold, calculates a task priority based on multiple factors, combines resource constraints and federated learning to allocate resources, synchronously adapts across scenes, pre-plans and optimizes visual feedback in execution, and realizes dynamic adaptation, efficient collaboration and stable execution of complex tasks.

The present application relates to the technical field of log analysis, and particularly relates to a kind of audit system operation and maintenance log automatic generation method and equipment.The method parses log stream to distinguish business log entries from unassociated abnormal entries, constructs thread execution sequence and calculates the idle time slice between adjacent business log entries in thread execution sequence;Load the resource constraint mapping table defining hardware resource type and minimum duration;Get the candidate business entries of unassociated abnormal entries, and perform mutual exclusivity and capacity physical verification using the resource constraint mapping table to filter out effective candidate business entries;According to the time difference between unassociated abnormal entries and its effective candidate business entries, filter out the best matching business entries, and then backtrack the business context, inject the exception stack and correct the state to generate structured audit records.The present application realizes non-invasive and high-precision exception attribution based on the rules of runtime resource constraints, and improves the integrity and accuracy of audit data.

The invention discloses an intention point resource scheduling management method and system supporting credit dynamic adaptation, and the method comprises the steps: obtaining academic data of a student, and dynamically calculating a rigid demand urgency index; based on the rigid demand urgency degree index, allocating a first type of virtual resources for the auction of the necessary course to the student, and dynamically determining a second type of virtual resource upper limit for the auction of the selected course, the rigid demand urgency degree index being in negative correlation with the second type of resource upper limit, and forming an asymmetric resource constraint; and course seat scheduling is executed according to the allocated resources, necessary course allocation is guaranteed preferentially, and then selection course allocation is completed. The corresponding system comprises a demand analysis module, an asymmetric resource management module, a staged scheduling engine and a monitoring feedback module. According to the method, accurate guarantee of rigid academic requirements and reasonable guidance of flexible requirements are realized by quantifying academic urgency and establishing an asymmetric resource constraint and scheduling mechanism.

The invention discloses a fault elastic DAG task scheduling strategy in vehicle edge calculation based on Lagrange duality, which effectively processes task dependence and resource constraints, realizes rapid task rescheduling and reduces energy consumption. Firstly, DAG task scheduling is expressed as an optimization problem with resource constraints, and aims to minimize energy consumption. Constraint is converted into dual variables, so that the dual form of the target function is maximized. Secondly, proposing a dual-based DROPS algorithm for a task scheduling fault strategy in the edge environment of the Internet of Vehicles; and finally, after a server fault is detected, the affected server is deleted from the feasible set, and a DROPS algorithm is used to carry out priority ranking and redistribution on uncompleted subtasks according to the current dual price.

The invention belongs to the technical field of scheduling optimization, and discloses a manufacturing industry advanced plan scheduling system and method based on artificial intelligence, and the method comprises the steps: generating an initial scheduling scheme according to production order data and manufacturing resource constraint data; analyzing the initial scheduling scheme to establish a basic time sequence graph, and performing man-hour probability distribution fitting on each task node based on historical production data to obtain a probability time sequence graph; and traversing each task node, calculating and correcting the material ready time based on the man-hour probability distribution function of the previous task node and a preset on-time completion confidence coefficient, updating the plan time of each task node, and obtaining a final production schedule. Adjacent processes form a parallel overlapping relation by starting a time delay mechanism, so that the production cycle is effectively shortened; and meanwhile, the planned time is dynamically adjusted based on the man-hour probability distribution, the time margin can be reserved according to the difference of the actual fluctuation characteristics of each process, and the robustness of the scheduling scheme is improved.

The invention relates to the technical field of industrial internet-of-things automatic control, and discloses an actuator internet-of-things multi-protocol adaptation system and method.The method comprises the steps that a protocol module constructs a state machine model for each protocol adapter, cross-protocol state collaboration and abnormal event release are achieved through tense logic rule verification, and a resource module receives abnormal events and sends the abnormal events to a server; the method comprises the following steps: dynamically updating a global resource constraint graph, analyzing an optimal resource reallocation scheme and an atomic task sequence, deconstructing the task sequence into a pi-calculation concurrent process network by applying a reconstruction module, recombining the process network and mapping the recombined process network into a cross-protocol instruction set to drive an executor, and finally, executing the Pi-calculation concurrent process network. Full-link adaptation from protocol layer state consistency guarantee and resource layer dynamic optimization scheduling to application layer process flexible reconstruction is realized, and the reliability and response efficiency of a multi-protocol actuator system in a complex industrial environment are improved.

The invention discloses an engineering manpower informatization management scheduling method and system based on AI and big data, and the method comprises the steps: inputting the basic information and working state information of engineering personnel through employing a deep learning-based personnel capability evaluation model, precisely evaluating the fitness scores of the personnel for different tasks in a data-driven manner, and improving the working efficiency of the engineering personnel. Subjective and one-sided evaluation of manual evaluation is avoided, a scientific basis is provided for task allocation, and task efficiency and quality are improved; meanwhile, a task scheduling optimization model based on reinforcement learning is adopted, fitness scores, tasks and environment information are input, an optimal allocation strategy is learned through interaction with the environment, intelligent decision making is achieved, the method is more suitable for complex scenes, and allocation rationality and effectiveness are improved; besides, an initial allocation scheme is optimized by combining engineering real-time requirements and resource constraints, re-evaluation and dynamic adjustment are performed, and an optimal allocation state is kept on the premise that conditions are met, so that engineering manpower management scheduling is flexible and efficient, and engineering uncertainty is better dealt with.

The invention relates to a resource adjustment method and device, computer equipment, a storage medium and a program product. Comprising the steps that the task number of various types of tasks and the resource utilization rate of each computing node in a preset time period are acquired; determining a total cold start rate according to the task quantity of each type of tasks; determining a total load imbalance degree according to the resource utilization rate of each computing node; solving a target capacity expansion threshold value and a target capacity reduction threshold value of each instance pool by taking the sum of the minimum total cold start rate and the total load imbalance degree as a target and taking a node resource constraint condition and an instance concurrency constraint condition as constraints; and adjusting the instances in each instance pool according to the target capacity expansion threshold and the target capacity shrinkage threshold corresponding to each instance pool. Under the condition that the load is increased, more instances can be created to execute the task, and the task execution efficiency is improved; and under the condition that the load is reduced, redundant instances are destroyed to release idle resources, so that the utilization rate of the resources is improved.

The embodiment of the invention discloses a schedule management system and method, and the method comprises the following steps: building a digital duplication model of parameter personnel based on basic information, obtaining a plurality of schedule arrangement schemes based on the digital duplication model, and obtaining a plurality of schedule arrangement schemes based on the schedule feedback data and historical competition watching behavior data of audiences. Constructing an audience preference model; and based on the audience preference model, taking the causal increment income as a weight factor in an optimization objective function, combining a fairness constraint, a site resource constraint and a time conflict constraint, and optimizing the schedule arrangement scheme according to a multi-objective optimization algorithm to generate an optimal schedule arrangement scheme. The technical problems that the competition scheduling efficiency is low, the performance of athletes is difficult to predict, the audience participation degree lacks scientific evaluation, and the competition schedule optimization result is not ideal are solved.

The present disclosure relates to a method and a system for handling resource constraints in a network The method comprises receiving, by a transceiver unit [302], an instantiation event associated with a Network Function (NF) from an Inventory Manager (IM). Further, the method comprises generating, by a processing unit [304], a create task event based on the instantiation event. The method further comprises transmitting, by the transceiver unit [302], the create task event to a scheduler service. Further, the method comprises receiving, by the transceiver unit [302], a termination event associated with the NF, from the IM. Furthermore, the method comprises transmitting, by the transceiver unit [302], a delete task event based on the termination event, to the scheduler service. Thereafter, the method comprises halting, by the processing unit [304], a job associated with the create task event, based on the delete task event.

The present application relates to the technical field of flexible job shop scheduling in intelligent manufacturing and production scheduling, and particularly relates to an optimization method for solving flexible job shop scheduling with adjusted resource constraints. The method comprises the following steps: initializing parameters and randomly generating an initial population; using a crossover operator and a mutation operator in sequence to evolve the current population; executing a hybrid decoding strategy on the current population; sorting the individuals in the current population in ascending order of maximum completion time to form an elite population, and updating the elite population through problem-specific local search; judging whether the evolution condition is met, and if yes, executing mathematical evolution based on CP, and outputting a final solution when the running time reaches the total running time. The present application has the positive effects of reducing resource waiting time, improving machine utilization, and improving the resource utilization efficiency and scheduling performance of the entire workshop production.

The application relates to the technical field of factory scheduling, in particular to a multi-factory collaborative scheduling optimization method and system considering resource constraints. The method comprises the following steps: analyzing historical order delivery information of each factory, determining order delivery capacity values of each factory, and distributing orders of the multiple factories according to the order delivery capacity values to determine initial distribution order values of each factory; analyzing collaborative scheduling information of each factory to obtain supplementary scheduling order values and cancellation scheduling order values of each factory to other factories, wherein the collaborative scheduling information is used for representing idle order values and new order values of each factory in a current scheduling period; and based on the supplementary scheduling order values of each factory to other factories, the cancellation scheduling order values of each factory to other factories and the initial distribution order values of each factory, target distribution order values of each factory are determined. The application can improve the utilization effect of production resources of a production cluster composed of multiple factories.

Methods, apparatus, and systems are disclosed for container attestation in client-based workloads. An example apparatus includes at least one memory, machine readable instructions, and processor circuitry to at least one of instantiate or execute the machine readable instructions to access a container attestation and an owner policy, the container attestation including a first signature and the owner policy including a second signature, determine that the first signature and the second signature are valid, iterate through configuration sets of the owner policy to identify a match between a claim of the container attestation and a configuration set, identify a resource constraint associated with the configuration set, and generate a resource description based on the resource constraint, the resource description to determine execution of a container workload on a client-based platform.

The invention provides a MicroROS-oriented lightweight adaptive real-time task scheduling method and system, and the method comprises the steps: building an isolation type double-layer scheduling frame, and distributing a MicroROS event task and a real-time task to different scheduling layers; the real-time task layer adopts a scheduling strategy combining priority preemption and time slice rotation, and the event task layer adopts a non-preemption type collaborative execution strategy; shared resource competition is processed through a dynamic priority improvement mechanism, and when a real-time task applies for a shared resource, the priority of the shared resource is automatically improved to the highest priority of waiting for the resource and safety increment; and dynamically adjusting the CPU time quota of the event task layer, and dynamically optimizing resource allocation based on a self-adaptive time window model according to the real-time task load, the event queue depth and the task execution time. According to the method, an isolated double-layer scheduling framework is adopted, and the cooperative scheduling of a real-time task and a MicroROS communication task under resource constraints is realized in combination with a dynamic priority lifting and self-adaptive time window model.

This invention discloses a task scheduling method, apparatus, terminal device, and storage medium for multi-scenario intelligent applications, belonging to the field of task scheduling technology. The method involves: acquiring data such as task load, device status, business indicators, node topology, and several tasks to be executed; calculating a system state vector, a scenario embedding vector, a resource constraint vector, and the similarity between the scenario embedding vector and each historical scenario embedding vector; determining optimal strategy parameters based on the similarity, historical strategy parameters, system state vector, resource constraint vector, and several tasks to be executed; and finally calculating a resource allocation share based on the optimal strategy parameters, system state vector, resource constraint vector, and tasks to be executed, and executing the corresponding tasks under the resource allocation share. By implementing this invention, the problem of resource allocation imbalance that exists in existing technologies that use fixed rules or fixed optimization strategies to allocate computing resources to tasks to be executed can be solved.

The invention relates to the technical field of business agent dynamic construction, and discloses an event-driven business agent dynamic construction method. The method comprises the following steps: receiving and analyzing an original event stream, and extracting entity attributes and event intentions; summarizing a task target and a resource constraint based on the retrieval historical interaction record; performing pattern recognition on a task target and a resource constraint by using a machine learning model, and automatically generating an agent forming framework defining a plurality of seed agents and a preliminary dependency relationship thereof; according to the resource constraint and dependency relationship, virtual resources are allocated to each sub-agent, and a basic function mirror image is loaded to form an initialized service agent set; and finally, the set is adjusted through iteration, and dynamic construction of the service agent is completed in combination with a real service environment. According to the method, full-process automation and self-adaption of the intelligent agent system from structure definition to resource deployment are realized, and complex and changeable event streams can be efficiently responded.