36 results about "Cyclic scheduling" patented technology

Managing power-consuming resources on a first computing device by time-based and condition-based scheduling of data delivery from a plurality of second computing devices. A scheduler executing on the first computing device has knowledge of recurrent schedules for activation by the second computing devices. The first computing device determines availability of the power-consuming resources and adjusts an activation time for the schedules to use the power-consuming resources when the resources are available. Managing the schedules associated with the second computing devices preserves battery life of the first computing device.

The invention provides a synchronizing cycle scheduling algorithm by accessing a wireless sensor network media to a control layer. The algorithm defines a characteristic frame structure and a time slot structure and has the characteristics of low node energy consumption, small transmission time lapse, easy realization, etc. The algorithm has the advantages that: 1) a time slot division method is adopted to avoid sending conflict between nodes and reduce the waiting time for receiving, thereby saving the node energy and having no strict need to node synchronization and easy realization. 2) The algorithm defines the characteristic frame structure and the processing flow in order that each node in a movable time slot (main time slot) has a scheduling function and can send data and receive data and information which is randomly accessed. 3) The node can freely adjust a sending and a receiving bandwidths with each adjacent node in the main time slot according to the needs. 4) Through setting a sending and a receiving cycles in a time slot, one node can acquire a plurality of chances to send the data in every frame cycle, thereby greatly reducing the network time lapse.

The invention discloses a method for scheduling a service queue, which comprises the following steps of: establishing a plurality of service queues on a network element; using the network element to measure a service quality (Qos) parameter of a service flow on each Real-time Transport Protocol (RTP) passage in a transmission layer; using the network element to distribute the service flow on each RTP passage to corresponding service queue in a network layer; adjusting a band width of each service flow and a weight value of the service queue according to the Qos parameter of each service flow and sending the service flow in each service queue to a lower layer according to weighted cyclic scheduling. Meanwhile, the invention also discloses a device for scheduling the service queue. According to the scheme of the invention, cross-layer optimized scheduling of the service queue can be realized, and the band width of the service flow and the weight of the service queue can be adjusted in real time.

The invention discloses an MPI (Moldflow Plastics Insight) information scheduling method based on reinforcement learning under a multi-network environment, aiming at overcoming the defect of low practical application performance of a high-performance parallel computer, caused by the traditional circulating scheduling method. The method comprises the steps of: initiating parameters in a process of starting an MPI system, creating Cm<2> Q tables according to a multiple Q table combined method for a computing environment matched with m networks; continuously receiving an MPI information sending request sent by application in a process of starting the MPI system, determining a current information segment, then obtaining a current environment state, scheduling the current information segment to an optimal network according to the state information of historical empirical values stored in the Q tables; and finally, computing an instant reward value obtained by the scheduling and updating Q values in the Q tables. By adopting the invention, the problems that communication loads are distributed unequally, can not adapt to the network state dynamic change and have poor adaptability on the computing environment can be solved, and the practical application performance of the high-performance parallel computer is improved.

The invention discloses an unmanned aerial vehicle relay selection optimization method based on space channel state information. Unmanned aerial vehicles are used as communication network relay nodes,the spatial positions of unmanned aerial vehicle relays relative to a ground source node and a destination node are different, meanwhile, the obtained instantaneous channel state information and theinfluence of large-scale fading are considered, and the relay nodes are selected to decode and forward the information of the source node by taking optimization of the system capacity as a target. Compared with a traditional cyclic scheduling scheme, the unmanned aerial vehicle relay selection optimization scheme provided by the invention has the advantages that the system capacity is remarkably improved, and the transmission reliability of an unmanned aerial vehicle emergency communication system is effectively improved.

The invention discloses a router queue scheduling method based on dynamic priority in a quantum metropolitan area network, and the method comprises the steps: distributing different service priorities for quantum services and classical services through the quantum metropolitan area network, and classifying cache queues on routing nodes; putting data packets generated by businesses with different business types and service priorities into queues with different priorities, distributing weighted values to the queues in the queue scheduling process by using a weighted cycle scheduling algorithm, and dynamically adjusting the weighted values of the different queues according to the network state. According to the method, the delay queue is used for processing the data packet which cannot be encrypted due to temporary shortage of the secret key, the fairness and the real-time performance of the service are ensured, the weighted cycle scheduling algorithm is used, the queue weight value is dynamically adjusted according to the network state in the queue scheduling process, and the flexibility and the adaptability of queue scheduling are improved.

The invention discloses a satellite relay selection optimization method based on geographic location information. A spatial transmission distance between two hops of links from a source node to a destination node via a candidate satellite relay is measured and corresponding instantaneous channel state information is obtained by estimation; a relay satellite capable of decoding source node information is selected from all satellite relay nodes; a relay satellite with optimal channel state information to the destination node is selected to forward source node information; and then the destination node receives and decodes the source node information forwarded by the satellite relay. Compared with the traditional cyclic scheduling plan, the provided relay selection optimization plan enables the system interruption probability to be reduced and the system performance to be improved.

The invention discloses a multi-modal massive-data-flow scheduling method under a multi-core DSP. The multi-core DSP includes a main control core and an acceleration core. Requests are transmitted between the main control core and the acceleration core through a request packet queue. Three data block selection methods of continuous selection, random selection and spiral selection are determined onthe basis of data dimensions and data priority orders. Two multi-core data block allocation methods of cyclic scheduling and load balancing scheduling are determined according to load balancing. Datablocks selected and determined through a data block grouping method according to allocation granularity are loaded into multiple computing cores for processing. The method adopts multi-level data block scheduling manners, satisfies requirements of system loads, data correlation, processing granularity, the data dimensions and the orders when the data blocks are scheduled, and has good generalityand portability; and expands modes and forms of data block scheduling from multiple levels, and has a wider scope of application. According to the method, a user only needs to configure the data blockscheduling manners and the allocation granularity, a system automatically completes data scheduling, and efficiency of parallel development is improved.

The invention relates to the technical field of data storage, and provides a task queue arbitration management method, a storage medium and a solid state disk, the method comprises the following steps: judging whether a first task queue with an emergency queue priority is empty or not; if the task queue with the emergency queue priority is not empty, the first task queue is scheduled preferentially; in the process of scheduling the first task queue, monitoring whether the scheduling state of the task queue meets a preset priority scheduling right release condition or not; and when the scheduling state of the task queue meets a preset priority scheduling right release condition, scheduling the task queues of which the queue priorities are other levels according to a weighted cycle scheduling strategy. According to the invention, the WRR queue can be prevented from being starved during scheduling, and meanwhile, the priority scheduling of the emergency priority can be provided for the upper layer service, so that the emergency priority queue can be widely used in the actual service, and the flexibility of adjusting the priority by the service is greatly improved.

Based on a set of cyclic scheduling instruction code in closed loop, through cyclic scheduling mechanism in closed loop, the method obtains execution control authority for hardware system. Based on rule of configuration, the control authority assigns part of control authority to target operation system. Carrying out modular expansion, cyclic scheduling instruction code in closed loop through a reference mode maps modular function to target operation system so as to accomplish modular expansion for operation system. Without making any change for target operation system, the invention realizes modular expansion and functional expansion no matter whether the operation system supports the modular technique or not.

Since single and dual-arm tools behave differently, it is difficult to coordinate their activities in a hybrid multi-cluster tool that is composed of both single- and dual-arm tools. Aiming at finding an optimal one-wafer cyclic schedule for a treelike hybrid multi-cluster tool whose bottleneck tool is process-bound, the present work extends a resource-oriented Petri net to model such system. By the developed Petri net model, to find a one-wafer cyclic schedule is to determine robot waiting times. By doing so, it is shown that, for any treelike hybrid multi-cluster tool whose bottleneck tool is process-bound, there is always a one-wafer cyclic schedule. Then, computationally efficient algorithms are developed to obtain the minimal cycle time and the optimal one-wafer cyclic schedule. Examples are given to illustrate the developed method.

A method for scheduling tasks to a cyclic schedule, comprising maintaining a request queue, a count, the count being initialized to a given limit, and an index of a current time slot within the schedule. Periodically, if the request queue contains a reference to an urgent task among the tasks, that reference is removed from the request queue and the urgent task is dispatched and if the request queue is empty, the index is advanced to the next time slot within the schedule. If the next time slot is statically assigned to a task among the tasks, that task is dispatched, and if the next time slot is unassigned and the count is below the limit, the count is incremented and the index is further advanced to the next but one time slot.

A method, computer software product and system for solving cyclic scheduling problems. Specifically, the present disclosure significantly improves the method in a previous patent (H. K. Alfares, 2011, “Cyclic Combinatorial Method and System”, U.S. Pat. No. 8,046,316), by eliminating a time-consuming combinatorial procedure. A procedure is described which significantly decreases the number of iterations, and hence computational time and cost. The processes of the present disclosure have many applications in cyclic workforce scheduling, cyclic transportation system scheduling, cyclic scheduling of data packet transmitting as applied to networks having a plurality of nodes and cyclic production scheduling.

The invention discloses a big data task scheduling method, which comprises the following steps of S1, dividing a plurality of big data analysis tasks into a plurality of priorities, dividing the big data analysis tasks with the same priority into the same group, and determining the complexity of each big data analysis task in each task group; and S2, constructing a task scheduling subroutine basedon a cyclic scheduling learning algorithm neural network in the Hadoop computing cluster, and allocating computing resources of the Hadoop computing cluster to each big data analysis task by the taskscheduling subroutine according to priorities and complexity. According to the method, the computing cluster can reach the optimal running state during big data analysis, the problem of excessive resource preemption of the computing task is solved, and meanwhile, the computing resources of the Hadoop cluster are recycled in time, so that the computing resources are fully utilized.

The invention provides a dragging-type-based rapid intelligent scheduling method. The method at least comprises the following steps: formulating personnel shifts of personnel in a unit / organization; formulating a post template according to the fixed post and the special post in the special period; performing matching in a dragging mode according to the personnel shift and the post template, forming regular scheduling, and providing copying and cyclic scheduling; and providing intelligent supplement and intelligent recommendation scheduling according to the specific historical scheduling data of the personnel and the skilled fields thereof. The beneficial effects of the technical scheme are that intelligent processing is performed on scheduling of all personnel in a unit / organization so that regular scheduling is formed, intelligent supplement is performed by considering the time and the skilled field of the personnel, realization of rationalization of scheduling is facilitated, the pressure of manual scheduling is reduced and the scheduling time is saved.

The invention discloses a three-phase balance dispatching method and device based on phase-change switches. The method is characterized by, calculating a predicted power value of each phase-change switch under a current time period through analysis of historical power data; then, carrying out simulated reality cyclic scheduling based on three-phase power and the predicted power value of each phase-change switch to find out a switching set of the phase-change switches; and finally, sending a phase-change instruction in the switching set to the corresponding phase-change switch. Compared with the prior art, the method does not judge whether the three phases are balanced directly, but judge whether the three phases are balanced by judging whether the switching set of the phase-change switches obtained through simulated reality cyclic scheduling is null.

The embodiment of the invention discloses a session processing method and device, equipment and a storage medium. The method comprises the following steps: when it is detected that a session node corresponding to a currently received message is not stored in a cache unit set, creating the session node corresponding to the message, determining a first absolute timeout time based on the current timeand a relative timeout time corresponding to the session node, and storing the first absolute timeout time and information of the message in the created session node; determining a target cache unitcorresponding to the session node according to the scheduling start time and the first absolute timeout time corresponding to the cache unit set, and storing the created session node into the target cache unit, wherein the cache unit set comprises a plurality of cache units which are sequentially arranged, and each cache unit is sequentially and circularly scheduled according to the arrangement sequence so as to carry out timeout maintenance on session nodes stored in each cache unit, thereby improving the session timeout maintenance efficiency, saving equipment resources and improving the processing performance.

The invention discloses a multi-modal massive-data-flow scheduling method under a multi-core DSP. The multi-core DSP includes a main control core and an acceleration core. Requests are transmitted between the main control core and the acceleration core through a request packet queue. Three data block selection methods of continuous selection, random selection and spiral selection are determined onthe basis of data dimensions and data priority orders. Two multi-core data block allocation methods of cyclic scheduling and load balancing scheduling are determined according to load balancing. Datablocks selected and determined through a data block grouping method according to allocation granularity are loaded into multiple computing cores for processing. The method adopts multi-level data block scheduling manners, satisfies requirements of system loads, data correlation, processing granularity, the data dimensions and the orders when the data blocks are scheduled, and has good generalityand portability; and expands modes and forms of data block scheduling from multiple levels, and has a wider scope of application. According to the method, a user only needs to configure the data blockscheduling manners and the allocation granularity, a system automatically completes data scheduling, and efficiency of parallel development is improved.

One or more embodiments of the invention provide a heterogeneous energy flow linkage optimization platform and device for an integrated energy system, and electronic equipment. A load prediction model is established and optimized by collecting historical data and real-time data, and day-ahead load prediction and cyclic load prediction are carried out by using the obtained load prediction model; data including a day-ahead load prediction result, a cyclic load prediction result, the total operation cost of the energy system and the operation condition of energy supply equipment are used as input parameters of a non-local sorting genetic algorithm, the algorithm is operated to obtain day-ahead scheduling parameters and cyclic scheduling parameters, simulation scheduling is performed on the energy supply equipment according to the scheduling parameters, and the operation result obtained by simulation is subjected to contrastive analysis with an actual operation result. Finally, the energy characteristics can be fully exerted in allusion to the heterogeneous energy flow, and a cycle optimization strategy is flexibly provided in combination with the demand change.

The embodiment of the present application provides a task scheduling method and device, wherein the method includes: obtaining a task scheduling request; the task scheduling request carries the task path corresponding to the task to be executed; according to the task path corresponding to the task to be executed and the task configuration information, determine the Execute the result output path and execution method corresponding to the task respectively; send the task path, result output path, and execution method corresponding to the task to be executed to the task execution device to execute the task; after determining that the task to be executed is successfully executed, the The result output path corresponding to the execution task is re-used as the task path corresponding to the task to be executed; the above process is repeated until the cyclic scheduling and execution of the task ends. Through the embodiment of the present application, the maintenance cost of task scheduling can be reduced, and the efficiency of task execution can be improved.

The invention discloses a scheduling method and device for a regular tetrahedral topological network. Node No. 1, Node No. 2, Node No. 3 and Node No. 4 in the regular tetrahedral topological network respectively follow the scheduling sequence [4,3,2, 0,0,0], [0,0,1,3,4,0], [0,1,0,2,0,4 and [1,0,0,0,2,3] for data scheduling ; Among them, the scheduling sequence of four nodes constitutes a round-robin scheduling table, the length of the time slot for executing the round-robin scheduling table is one-third of the propagation delay, and the frame length is twice the propagation delay, and the numbers in the scheduling sequence represent the current A time slot sends a data packet to the node corresponding to the number, and 0 indicates receiving a data packet in the current time slot. The invention realizes full-connection fair and perfect scheduling of the regular tetrahedral topology network of four nodes by equally dividing the propagation time delay.

A control method for heating electric boilers to participate in the primary frequency regulation of the power grid, which is used to solve the problem of insufficient primary frequency regulation capability of the power grid due to complex and changeable power loads and large-scale grid connection of unstable power sources such as wind power. The method comprises the following steps: a. calculating a frequency modulation command; b. designing a frequency modulation filtering logic to filter the calculated frequency modulation command; c. performing cycle scheduling on the electric heater according to the filtered primary frequency modulation command. The present invention adds a frequency modulation instruction filtering logic and cycle scheduling logic in the control process of heating electric boilers participating in the primary frequency modulation of the power grid, which not only avoids the frequent action of the electric boiler heater switch, but also realizes the average use of each heater, thus prolonging The service life of the equipment. The invention can greatly improve the primary frequency regulation capability of the power grid and ensure the stable operation of the power grid.

The invention discloses a scheduling method and device for a regular tetrahedron topological network. A first node, a second node, a third node and a fourth node in the regular tetrahedron topologicalnetwork perform data scheduling according to scheduling sequences [4, 3, 2, 0, 0, 0], [0, 0, 1, 3, 4, 0], [0, 1, 0, 2, 0, 4 and [1, 0, 0, 0, 2, 3] respectively, wherein the scheduling sequences of the four nodes form a cyclic scheduling table, the time slot length for executing the cyclic scheduling table is one third of the propagation time delay, the frame length is two times of the propagationtime delay, the number in the scheduling sequence indicates that one data packet is sent to the node corresponding to the number in the current time slot, and 0 indicates that one data packet is received in the current time slot. According to the method, propagation time delay is equally divided, so that full-connection fair and perfect scheduling of the regular tetrahedron topological network with four nodes is realized.

The invention relates to an on-line monitoring and scheduling control technology, in particular to an intelligent reactive compensation capacitor monitoring and cyclic scheduling method. The method comprises the following steps: 1) acquiring current and voltage data of a capacitor through a current transformer and a voltage terminal wire; 2) transmitting the voltage and current data back to a comprehensive monitoring and scheduling terminal system through an intelligent data acquisition device by using an NBIOT Internet of Things; 3) analyzing the acquired voltage and current data through a comprehensive monitoring system, and finishing time matching storage; 4) completing the voltage and current data calculation and statistical analysis through a back-end intelligent algorithm after analysis and matching to obtain the switching rate and health state judgment of each intelligent capacitor; 5) enabling a scheduling system to judge and complete the capacitor scheduling among different capacitor cabinets according to the intelligent capacitor switching rate and the health state calculated by the monitoring system, and sending out scheduling and maintenance instructions. The method canprovide effective reference for intelligent capacitor switching monitoring and scheduling control of a power distribution network.

Since single and dual-arm tools behave differently, it is difficult to coordinate their activities in a hybrid multi-cluster tool that is composed of both single- and dual-arm tools. Aiming at finding an optimal one-wafer cyclic schedule for a treelike hybrid multi-cluster tool whose bottleneck tool is process-bound, the present work extends a resource-oriented Petri net to model such system. By the developed Petri net model, to find a one-wafer cyclic schedule is to determine robot waiting times. By doing so, it is shown that, for any treelike hybrid multi-cluster tool whose bottleneck tool is process-bound, there is always a one-wafer cyclic schedule. Then, computationally efficient algorithms are developed to obtain the minimal cycle time and the optimal one-wafer cyclic schedule. Examples are given to illustrate the developed method.

The invention discloses a method for scheduling a service queue, which comprises the following steps of: establishing a plurality of service queues on a network element; using the network element to measure a service quality (Qos) parameter of a service flow on each Real-time Transport Protocol (RTP) passage in a transmission layer; using the network element to distribute the service flow on eachRTP passage to corresponding service queue in a network layer; adjusting a band width of each service flow and a weight value of the service queue according to the Qos parameter of each service flow and sending the service flow in each service queue to a lower layer according to weighted cyclic scheduling. Meanwhile, the invention also discloses a device for scheduling the service queue. According to the scheme of the invention, cross-layer optimized scheduling of the service queue can be realized, and the band width of the service flow and the weight of the service queue can be adjusted in real time.

The invention discloses a continuous execution method for realizing single-machine circular scheduling through judgment. The method comprises the following steps: constructing a logic circular queue, and initializing a dynamic allocation storage space, a queue head pointer of the logic circular queue and a queue tail pointer of the logic circular queue; carrying out dequeuing, enqueuing and variable or constant assignment operations; setting priority switches of the tasks; inserting a single task to be executed into the logic round-robin queue, constructing a test group round-robin queue by the single task, setting a test group priority, constructing a test task set round-robin queue by the test group round-robin queue, and setting a priority of the task set round-robin queue; firstly executing the test groups according to the setting of the priorities, after the test groups are executed, executing a test set consisting of the test groups, and quickly testing to generate a test report; and finally, packaging the completed algorithm data into a group of APIs. According to the method, the execution time of the automatic items is set differently, the automatic test items are executed in a polling mode, 7 * 24-hour task continuous execution is achieved on a single machine, and the machine utilization rate is increased.

The invention discloses an MPI (Moldflow Plastics Insight) information scheduling method based on reinforcement learning under a multi-network environment, aiming at overcoming the defect of low practical application performance of a high-performance parallel computer, caused by the traditional circulating scheduling method. The method comprises the steps of: initiating parameters in a process of starting an MPI system, creating Cm<2> Q tables according to a multiple Q table combined method for a computing environment matched with m networks; continuously receiving an MPI information sending request sent by application in a process of starting the MPI system, determining a current information segment, then obtaining a current environment state, scheduling the current information segment to an optimal network according to the state information of historical empirical values stored in the Q tables; and finally, computing an instant reward value obtained by the scheduling and updating Q values in the Q tables. By adopting the invention, the problems that communication loads are distributed unequally, can not adapt to the network state dynamic change and have poor adaptability on the computing environment can be solved, and the practical application performance of the high-performance parallel computer is improved.

The invention discloses a three-phase balance dispatching method and device based on phase-change switches. The method is characterized by, calculating a predicted power value of each phase-change switch under a current time period through analysis of historical power data; then, carrying out simulated reality cyclic scheduling based on three-phase power and the predicted power value of each phase-change switch to find out a switching set of the phase-change switches; and finally, sending a phase-change instruction in the switching set to the corresponding phase-change switch. Compared with the prior art, the method does not judge whether the three phases are balanced directly, but judge whether the three phases are balanced by judging whether the switching set of the phase-change switches obtained through simulated reality cyclic scheduling is null.