247results about How to "Shorten completion time" patented technology

Liquefied natural gas is used as a fracturing fluid to stimulate production of hydrocarbons from and / or injectability of fluids into subterranean formations. Proppants may be blended with the LNG prior to pumping the liquefied natural gas into the well. Optionally, the liquefied natural gas is heated after it is pumped and before it is introduced into the subterranean formation.

A rupture disc assembly and a float tool incorporating the rupture disc assembly is disclosed. The rupture disc assembly may include a rupture disc assembly comprising a rupture disc, an upper tubular portion and a lower tubular portion, and a securing mechanism for holding the rupture disc between the upper and lower tubular portions. A float tool for creating a buoyant chamber in a casing string may include the rupture disc assembly and a sealing device for sealing the lower end of the casing string, the buoyant, sealed chamber may be created there between. In operation, applied fluid pressure causes the rupture disc to move downward. The rupture disc may be shattered by contact with a surface on the lower tubular portion. Full casing internal diameter may be restored in the region where the rupture disc formerly sealed the casing.

A RAID system access a physical disk and perform Rebuild / Copy back processing according to a host I / O request, so as to implement high-speed Rebuild / Copy back processing without interfering with the processing of a normal I / O. When one disk device fails, out of a plurality of disk devices constituting a RAID configuration, the controller performs Rebuild / Copy back processing to reconstruct the RAID. In Rebuild / Copy back, the controller reads the data from one disk and writes the data to another disk, so the presence of a normal I / O is judged, and when a normal I / O is absent, read and write of these different disk drives are executed simultaneously. By this, the Rebuild / Copy back time can be decreased.

The invention provides a method for high-efficiency task scheduling of a heterogeneous multi-core processor. The method comprises the following steps of: clustering certain special tasks which are large in communication overhead and easy to cluster in a task image to a precursor node of the tasks by adopting a linear task clustering method; starting from a topological structure of the whole task image, selecting parameters capable of comprehensively reflecting the importance of the task in the whole task image as priority weights; selecting a free critical path node to perform allocation first, and if multiple free critical path nodes exist, allocating the free critical path nodes in a sequence from high to low according to the node priority weights, and allocating all non-critical path free nodes in a sequence from high to low according to the priority weights; performing redundancy judgment, and deleting redundant tasks in a scheduling result; and performing adjustment according to the scheduling result after deleting the redundant tasks, and recalculating the earliest finish time of each task. According to the method, the efficiency of the task scheduling of the heterogeneous multi-core processor is improved, the power consumption of the processor is reduced, and the performance of the multi-core processor is promoted.

The invention discloses a dispatching method and a system of a distributed system. The method comprises the following steps: a dispatching request comprising data reading operation is received by a data dispatcher, and data is stored in at least one entity providing data service in the distributed system; status of each data service corresponding to the dispatching request is determined by the data dispatcher, dispatching response consenting to conduct reading operation on each data service is sent by the data dispatcher when each data service is in an idle / reading status; and each data service is at least one same data service. The invention can effectively solve the defects of resource waste, low task processing efficiency and the like in the distributed dispatching method in the prior art, realizes reasonable resource utilization, and improves task processing efficiency.

The invention provides a liver and tumor segmentation method and system based on multitask deep convolution network. The method comprises the steps of conducting data pre-processing and expanding; establishing the multitask deep convolution network; establishing a supervising layer having inter-task constraint; conducting network training; generating data test result. The invention is advantageousin that the multitask network includes two pathways, which are respectively used for realizing the identification and segmentation of liver and liver tumor; through sharing of the pathway part, the volume of the deep convolution network can be reduced, and the demand of model learning on the training data amount can be reduced; through connecting to a characteristic extracting module relevant torespective task and a corresponding output module after the sharing of the pathways, the multitask output can be realized; the aim of mutual constraint of the liver and liver tumor can be achieved bymeans of a supervising and learning module of multitask geometrical association information; liver and liver tumor can be accurately identified and segmented.

The invention provides a Lyapunov optimization-based multi-server mobile edge computing unloading method and device, and the method comprises: building a task cache queue for a task generated by eachmobile device, and building a virtual task cache queue for a task which needs to be unloaded and is not processed by each mobile device; establishing a terminal power consumption model, a bandwidth model and a QoE model; collecting task cache queue information and virtual cache queue information of the mobile device and the bandwidth condition of the server at each preset time slice; constructinga Lyapunov drift and penalty function according to the collected information; and based on Lyapunov drift and a penalty function, a calculation unloading decision in the current time slice is solved.The technical effects of calculating and unloading based on the multi-server MEC, effectively reducing the task completion time and reducing the energy consumption of the mobile device are achieved.

A metal-stamping die or tool is provided. Another aspect uses an additive manufacturing machine and material to create a die. A further aspect provides a method of making a die from an additive manufacturing process and / or using such a die to stamp a metal part, such as a fastener or clip.

Computerised automatic translation method characterised by the use of multi-tasking with two processors or a dual core that duplicates the system into two twins, one becoming server of the other and instructing the first to send a remaining part that is less than half to the second while the first begins the translation of the first part to then, on completion of its work, pick up the text translated by the second and joint it to the first part that has already been translated.

The invention relates to an interference-prevention-based multi-automatic-guided-vehicle (AVG) path planning method for a logistics storage system. On the basis of analyses of arrival and departure times of multiple AGVs at and from all road sections and nodes in a logistics storage system, driving overlapping frequencies of the AGVs on the road sections and nodes are calculated. With combination of an interference threshold value, a multi-AGV shortest path planning model with an interference prevention constraint is established by using multi-AGV operation time as a target. With a frame of an ant colony algorithm, an interference-prevention-based multi-automatic-guided-vehicle path planning method with inducing ant colony and particle swarm fusion for a logistics storage system is designed by keeping a pheromone factor is kept, removing a visibility factor, and adding a A <*> factor and an inducing factor. Road features of typical logistics storage systems like a dock, a warehouse, a distribution center, a container station and various storage yards are combined and a multi-automatic-guided-vehicle path planning method is provided. Therefore, the interference can be avoided effectively; the AGVs can arrive at destinations according to respective shortest paths; and thus the working efficiency and security of the logistics storage system can be improved.

The invention discloses a method for constraining workflow scheduling in a cloud environment based on the ant colony optimization algorithm through deadline. The method comprises the steps: employing an ant colony system with a candidate list; respectively searching a workflow scheduling scheme in the cloud environment through a plurality of ants; carrying out the communication of a workflow scheduling result among the ants in a pheromone mode, thereby guiding the deciding of the subsequent search direction of ants and the workflow scheduling scheme. Compared with a conventional workflow scheduling method, the method can reduce the cost of the workflow scheduling in the cloud environment and improves the service quality for cloud users under the condition of meeting the deadline time QoS requirements of users.

The invention discloses a method and device for generating a task scheduling plan in a scientific workflow in a cloud environment. The method includes the following steps: step 1, obtaining all tasks to be scheduled; step 2, using weighted directed The ring graph describes the tasks to be scheduled; step 3, in the directed acyclic graph, traverse from the start node to the end node to obtain all paths; step 4, calculate the time consumption of each path, according to the time consumption by Sorting all paths in descending order and determining the priority of the paths in descending order; step 5, generating a task scheduling scheme according to the priority order of the paths; the device includes a task acquisition module, a task description module, a node traversal module, a path sorting module and Program generation module. The invention can make full use of the idle time of the processor, improve the parallelism of scientific workflow task execution, improve the utilization rate of the processor, and shorten the completion time of the scientific workflow task.

The invention relates to a bidirectional stepped grid resource scheduling method based on QoS constraints, which includes: 1. QoS service is offered to all available machines for testing according to QoS request provided by the task and the testing results are recorded in a matrix form, if the request is executable, the execution time is recorded and if the request is non-executable corresponding signs are made; 2. the matrix of the testing results is deformed according to the designated principle and the deformed matrix is accumulated according to the horizontal and vertical directions, thus calculating two vectors; 3. the tasks and the resources are grouped in a non-descending order according to the two vectors; 4. the priority scheduling is conducted according to the task grouping results, wherein, the group with small value has high priority and is firstly scheduled and the interior of the grouping is scheduled according to Min-min algorithm principle; 5. if the task has the same minimum completion time with different resources in the scheduling, the scheduling is conducted according to the resource grouping results and the group with small value has high priority and is firstly scheduled; 6. the fourth step and the fifth step are repeatedly executed until the scheduling of all tasks is completed.

The invention discloses a task scheduling system and method based on cloud computing. The task scheduling system comprises an information collecting and transmitting device used for collecting resource information, a task receiving server used for receiving tasks, a task analyzing server, a task scheduling server, a task distributing server and a plurality of resource servers, wherein the input end of the task analyzing server is respectively connected with the information collecting and transmitting device and the task receiving server, and the task analyzing server takes charge of counting and analyzing the tasks and the condition of occupied resources; the input end of the task scheduling server is connected with the task analyzing server, and the task scheduling server schedules the tasks according to an analysis result of the task analyzing server; the input end of the task distributing server is connected with the task scheduling server; the input ends of the resource servers are connected with the task distributing server, and the resource servers execute the tasks distributed by the task distributing server. The defects in scheduling the tasks of a cloud computing platform of an existing cloud computing scheduling system are overcome, and a more efficient cloud computing platform is provided.

The embodiment of the invention provides a data centre network flow dispatching method and system based on space and time combination. The method and the system are applied to a switch. The method comprises the steps of receiving a data packet and a target virtual local area network serial number value sent by a sending terminal, and determining a target output port for transmitting the data packet based on the target virtual local area network serial number value; determining the priority of the data packet, and caching the data packet to a target priority queue based on the priory of the data packet; judging whether the quantity of the data packets contained in the target priority queue exceeds a preset threshold value or not, and transmitting the data packet and other data packets cached in the target priority queue if the quantity does not exceed the preset threshold value; identifying a first identifier in the packet header of the data packet if the quantity exceeds the preset threshold value, and transmitting the data packet identified with the first identifier and other data packets cached in the target priority queue by employing the target priority queue. Through application of the embodiment, the quality of service of the high priority service can be ensured, and the finishing time of each priority task can be reduced.

A novel solution for converting a walk behind floor scrubber into a sit and ride behind floor scrubber. The present invention consists of a chassis frame to which five wheels are attached. Two of the front wheels pivot and the up-front safety wheel does not. The wheels that are attached to the rear of the frame, are non-pivotal. A person sits on the cushioned seat. Upon grabbing the floor scrubber's control handles and rotating them forward the floor scrubber, as it propells forward, pulls the present invention behind it in tandem. This allows the operator for the floor scrubber to sit and rid instead of walking, while cleaning large commercial size floors. This new procedure saves enormous time and the person controlling the scrubber will be less fatigued from hours of walking. The Scrub-mate is new to the floor cleaning industry, because it eliminates walking of the operator while using a battery-powered walk behind floor scrubber.

The invention provides a method for dispatching tasks. The method comprises the steps that a corresponding CPU resource demand and a corresponding internal storage resource demand are set for any task of a user, and the time when the task is finished is predicted; the number of tasks operated by the user at the same time is predicted so that the dominated share ratios of all users in a YARN platform are identical; the total time spent on a job is calculated according to the number of the total tasks of the user, the predicted time when the tasks are finished and the number of the tasks capable of being operated by the user at the same time; the set CPU resource demand and the internal storage resource demand are changed within the preset CPU resource demand range and the internal storage resource demand range, and the steps are executed repeatedly until the worked out total time spent on the operation is finished is minimum. The subjective deviation of setting the CPU resource demand and the internal storage resource demand of the user when the YARN platform submits the job can be reduced, the job finishing time can be shortened, and the overall operating efficiency of the YARN platform is improved.

The invention discloses a distributed assembly type permutation flow shop scheduling optimization method and system. The efficiency of a distributed permutation flow shop is increased; and the completion time and the energy consumption are reduced. The method comprises the steps of: with the purpose of reducing the minimum weight value of the completion time and the total energy consumption, constructing a distributed assembly type permutation flow shop optimization problem model with a crane; solving the distributed assembly type permutation flow shop optimization problem model with the craneby adopting an improved whale swarm algorithm, so that a scheduling optimization scheme is obtained; and scheduling work-pieces of various factories in the distributed assembly type permutation flowshop by utilizing the obtained scheduling optimization scheme.

The invention discloses a multi-coflow scheduling method based on graph neural network deep reinforcement learning. A multi-coflow scheduling model is established based on a deep reinforcement learning framework; a cascaded graph neural network and strategy network is adopted as a deep reinforcement learning agent, wherein the workflow DAG feature extraction is completed by a graph neural network, so that the model can process the workflow DAG with different numbers and connection modes of nodes, and the generalization ability of the model under the unpredictable input DAG is effectively improved; by introducing the strategy converter, a fine-grained coflow scheduling strategy can be generated according to the scheduling priority list, the efficiency of the scheduling process is improved,and the completion time of workflow is effectively shortened.

The embodiment of the invention discloses a data distribution method and device based on MapReduce as well as a computer readable storage medium. The method can comprise the following steps; running apreset Map function on an input to-be-processed document, and obtaining a key value pair set; calculating a type number of keys in the key value pair set by utilizing a preset counting method; calculating a standard numerical value corresponding to each key by utilizing a preset algorithm; carrying out reminder calculation on the standard numerical values and the type number, so as to divide keyvalue pairs with the same type number in the key value pair set into one partition, thus at least one partition is obtained, and the number of at least one partition is the same with the type number;and based on a quantity of the key value pairs, corresponding to at least one partition, of at least one partition and a quantity of at least one to-be-distributed key value pair corresponding to at least one Reduce task, establishing corresponding relationship between at least one partition and at least one Reduce task, so that processing can be carried out on the key value pairs of at least onepartition by at least one Reduce task.

The invention discloses a transmission control method for a DCN (Data Center Network) based on multilevel congestion feedback. The method comprises the steps of setting a switch cache queue length threshold which comprises a first-level queue marking threshold 1 and a second-level queue marking threshold 2; monitoring a current queue length by each switch in a transmission path when multiple sending parties send data concurrently; comparing the current queue length with the first-level queue marking threshold 1 and the second-level queue marking threshold 2, and feeding back a current network congestion state; reducing a window increasing speed in a slow start stage according to first-level congestion feedback; and timely logging out the slow start stage, and entering a congestion avoiding stage according to the second-level congestion feedback. According to the method, the throughput breakdown phenomenon resulting from the fact that the window increasing speed is too fast in the slow start stage when DCN concurrent transmission is carried out can be effectively avoided. The network throughput is greatly improved, and the integrated performance of a network application is improved.

The invention discloses a cloud service workflow scheduling method based on budget constraint, and belongs to the technical field of cloud computing scheduling. In the method, cost of renting cloud service by a user does not exceed capital budget of the user is used as a constraint condition, and workflow makespan minimization is used as a goal, and a corresponding virtual machine is distributed to each task in the workflow. The method further respectively performs initial scheduling and rescheduling through two constructed weights, so that an algorithm simpler and faster. The method realizes efficient supply of cloud environment resources, under the condition that workflow of the user is ensured to be completed in the user budget, time of completion of the workflow is minimized. The algorithm is simple and easy to realize.

A method for reducing time in performing an imaging function by an imaging device. The method includes receiving at least one media sheet against an image capture window of the imaging device, detecting whether a lid for covering the image capture window is closed, capturing an image of the at least one media sheet in the image capture window in response to detecting a closed lid, receiving a start signal indicative of a user request to start an image capture operation after capturing the image, and sending a final image based upon the captured image to a destination.

The invention belongs to the technical field of data processing, and discloses a resource scheduling method and system based on a multi-dimensional constraint genetic algorithm, and the method comprises the steps: carrying out the initialization of a prediction model, a task matrix, and a node matrix, and building a dual-fitness function; formulating an option-Copying operator, a cross operator and a variation operator; and after multiple iterations, obtaining a globally optimal resource allocation mode. In order to seek a better resource allocation scheme, the invention provides a Hadoop resource scheduling algorithm based on a multi-dimensional constraint genetic algorithm, and a Hadoop resource scheduler is realized through the algorithm; by the adoption of the algorithm, the cluster resource distribution efficiency can be effectively improved, and the overall completion time of cluster tasks is shortened by about 20%.

The invention belongs to the field of data center networks, and particularly relates to a stream scheduling method for task classes in a data center. The stream scheduling method includes the steps that an SDN controller is additionally arranged in a data center network, after servers receive new tasks, network stream information of the tasks is packaged in a message, and the packaged information message is sent to the SDN controller; the SDN controller operates a central scheduling algorithm, and whether the tasks should be received or abandoned is judged; for the received tasks, the SDN controller sends routing table items of the tasks to a middle switch according to the calculation result of the central scheduling algorithm and meanwhile sends transmission time slices of the tasks to the corresponding servers. Emergent network streams can be preferably scheduled before cut-off time, the network throughput is increased, the average network stream transmission time is shortened, and maximization of the number of the tasks finished before the cut-off time is achieved.

The invention discloses a selective explicit congestion notification marking method (SECN for short) for a data center; the SECN implementation is divided into two parts: 1, a sending end writes estimated flow rate into the head of a data packet; 2, a switch judges the state of the flow speed rate and the like by reading the rate value of the head of the data packet, and the switch marks the flowwith high sending speed rate. The method, namely the SECN, in the invention is a first ECN marking method for distinguishing the flow state, and the method is low-load. According to the method, the link throughput can be obviously improved, the flow finishing time can be shortened, and the throughput of the multi-bottleneck flow can be improved.

The invention discloses a load balancing method and system based on accurate congestion feedback in a cloud data center. The load balancing method comprises two main aspects: an accurate source end flow balancing method and an accurate flow rate control method. The source end flow balancing method is based on accurate end-to-end delay monitoring, the congestion degree of a plurality of equivalentpaths among nodes in a cloud data center can be obtained in time, and flow path distribution is carried out in a balanced manner, so that load balancing among the plurality of equivalent paths is ensured, and the link bandwidth utilization rate is improved. The accurate flow rate control method is based on congestion feedback marks, and congestion feedback which does not belong to the current state due to path switching is eliminated, so that the accuracy of congestion feedback information is improved, and the stability of a data flow sending rate is ensured. According to the method, the accuracy of load balancing under the asymmetric network of the data center is improved, a hardware switch does not need to be modified, and the method has the performance advantage of competing with a customized hardware load balancing method.

The invention discloses an information imperceptible Coflow scheduling system capable of automatically adjusting a queue threshold and a scheduling method thereof. The scheduling system comprises a monitoring system (MS) and a central controller (CC), wherein the monitoring system and the CC are distributed on a terminal host; the monitoring system is used for collecting Coflow information on a terminal host. And the central controller adjusts a set of degradation thresholds according to the information of the Coflow, observes a scheduling result of the Coflow as an award of a reinforcement learning algorithm, and further optimizes the degradation threshold of the queue through the award.