38 results about "Pipeline scheduling" patented technology

A method of communicating data frames between nodes in a network comprised of one or more end system nodes where each end system node has a unidirectional ingress port and a unidirectional egress port. The method comprises transmitting a data frame from an egress port of one end system node to the ingress port of another end system node, the receiving end system node then determining whether it is the final destination for the data frame. If the receiving end system node is the final destination of the data frame, the receiving end system node absorbs the message. If not, the receiving end system node buffers and then retransmits the data frame through its own egress port. The method provides scalability, low cost, distributed pipeline scheduling, maximum complexity of the network fabric, and maximum speed.

A dynamic bandwidth allocation method of an Ethernet passive optical network, comprises a predictor and a rule of QoS-promoted dynamic bandwidth allocation (PQ-DBA); the predictor predicts a client behavior and numbers of various kinds of packets by using a pipeline scheduling predictor consisted of a pipelined recurrent neural network (PRNN), and a learning rule of the extended recursive least squares (ERLS); the present invention establishes a better QoS traffic management for the OLT-allocated ONU bandwidth and client packets sent by priority.

The invention discloses a mixed group intelligent optimization method for distributed blocking pipeline scheduling, which includes: performing cooperative initialization on multiple factories and multiple workpieces to generate a plurality of first factory workpiece processing sequences; calculating the processing sequence of each first factory workpiece The adaptive parameters of the sequence are adjusted according to the adaptive parameters to generate multiple workpiece processing sequences of the second factory; multiple workpiece processing sequences of the third factory are generated through local search and adjustment within the factory and between factories; some of the workpiece processing sequences of the third factory are selected for processing Regeneration mechanism, updating multiple third factory workpiece processing sequences to determine the current optimal factory workpiece processing sequence; return to the second step to iteratively update the current optimal factory workpiece processing sequence until the preset iteration termination condition is met to output the optimal Optimal factory workpiece processing sequence. This method combines adaptive search and local search, so that individuals in the population can adjust the search range by themselves, and balance the coarse search and fine search capabilities of the algorithm.

This application relates to sample test pipeline task scheduling methods, systems, and computer storage media, including the out-of-order submission mechanism after pipeline task conflicts occur when submitting in test order, and is designed to avoid out-of-order submission from affecting the orderly progress of the overall experiment The priority mechanism, and the cross-contamination avoidance mechanism designed on this basis. Solve the problem that the pipeline scheduling method of the existing sample test will cause the decrease of the instrument test throughput and the efficiency of the pipeline.

An embodiment of the present invention provides a distributed flexible pipeline scheduling method, including: constructing a distributed flexible pipeline scheduling model according to the processing start date, processing time and workpiece delivery date of each workpiece in each processing stage; according to the greedy iterative search The algorithm performs iterative search to solve the scheduling problem of the distributed flexible pipeline scheduling model. If the iteration time meets the preset conditions, the optimal scheduling scheme for all workpieces is obtained to schedule the distributed flexible pipeline. The embodiment of the present invention establishes a distributed flexible pipeline scheduling model, and effectively improves the search efficiency according to the greedy iterative search algorithm, and realizes the fast calculation of the optimization target of the distributed flexible pipeline scheduling model, so that the algorithm can get better results in a shorter time. The scheduling scheme can effectively and efficiently solve the large-scale distributed flexible pipeline scheduling problem.

The invention relates to an optimal scheduling method for multi-type cable processing, and belongs to the technical field of intelligent optimal scheduling of production workshops. The scheduling model is determined by determining the processing sequence of various cables, and the multi-objective optimization of the model is carried out by using the cuckoo algorithm. The scheduling model is a replacement assembly line workshop scheduling model. Using the cuckoo algorithm to obtain the optimal production sequence of multiple types of cables, while optimizing the maximum completion time and carbon emissions of cable production, this is a green dual-objective pipeline scheduling problem. The invention adopts the improved cuckoo algorithm to solve the dispatching model, and its objective function is: maximum completion time and carbon emission. Using the cuckoo algorithm to update iterations, optimize the modeling of the problem, and solve the cuckoo algorithm, the excellent solution for the production and processing of multiple types of cables can be obtained in a relatively short period of time.