90 results about "Flow scheduling" patented technology

The invention relates to a side cloud collaborative adaptive workflow scheduling method and system, and belongs to the technical field of distributed computing and artificial intelligence. The method comprises the following steps of: firstly, in a macroscopic candidate screening stage, reducing problem granularity through task clustering, and obtaining balance between utilization and exploration based on a weighted distance probabilistic preferential strategy; then, in a collaborative scheduling decision-making stage, a global network state diagram is constructed through a graph neural network, deep spatial features of nodes and neighborhoods of the nodes are extracted, context-aware state representation is formed, and a reinforcement learning agent makes an optimal collaborative decision in multiple options such as local execution, edge migration or cloud unloading according to the state representation; and finally, in a local adaptive optimization stage, performing fine-grained optimization after the task is issued, dynamically adjusting a scheduling frequency and a multi-target weight through an online learning mechanism, realizing balance between a task deadline and a resource utilization rate, and ensuring efficient and robust execution of a node level.

The invention discloses a flow scheduling method and device, a medium and a program product, and relates to the technical field of heat dissipation, and the method comprises the steps: obtaining a video memory access frequency as a main parameter when a parallel computing function is executed, matching with other auxiliary parameters related to heat consumption, distributing a weight, determining a heat load scoring result, and then adjusting a cold plate micro-channel flow distribution coefficient, and determining an opening value of a flow control valve and sending a flow scheduling instruction to the liquid cooling system so as to dynamically adjust the cooling liquid flow of each cold plate micro-channel. In this way, accurate temperature control and heat dissipation of the video memory area of the computing device can be achieved, energy waste caused by unnecessary circulation of cooling liquid is avoided, the heat dissipation efficiency is remarkably improved, energy consumption is reduced, and the service life of the computing device is prolonged; in addition, the mode can autonomously complete full-flow operation such as video memory heat consumption monitoring, score calculation and flow adjustment, intelligent management of the heat dissipation process is achieved, manual operation errors and cost are reduced, and the stability and reliability of operation of computing equipment are guaranteed.

The embodiment of the invention provides a logistics scheduling system, and belongs to the technical field of logistics. The system comprises a task layer which is used for generating an order task; the feedback layer is used for collecting dynamic resource data related to execution of the order task in a logistics site; the decision-making layer is respectively in communication connection with the task layer and the feedback layer, and the decision-making layer is used for adjusting a path planning strategy according to the dynamic resource data and generating a task execution instruction according to the adjusted path planning strategy; and the execution layer is in communication connection with the decision-making layer, and the execution layer is used for scheduling corresponding transportation equipment to execute the order task according to the task execution instruction. According to the embodiment of the invention, the scheduling flexibility of the transportation equipment can be improved.

The invention relates to the technical field of cloud fusion application operation support platforms, and discloses a session flow intelligent scheduling method under a fusion communication architecture, which comprises the following steps: monitoring a session flow logic sequence number of a current node; constructing an asynchronous mirror instance at the target node, and obtaining a computing power comparison parameter; adjusting an asynchronous mirror instance instruction execution rate to execute serial number chasing; after the sequence number difference value enters a synchronous threshold value, processor assembly line branch prediction data is injected, and instruction prefetching sequence filling is driven; according to the instruction level feature injection and execution phase alignment method, hardware execution momentum imbalance in a heterogeneous computing power environment is eliminated through instruction level feature injection and execution phase alignment, and progress connection and logic consistency of session streams at a migration interface are guaranteed.

The invention relates to the technical field of computers, and discloses a process scheduling method based on a tenant isolation strategy, and the method comprises the steps: receiving a process scheduling request of a tenant, and carrying out the standardization processing and legality verification; querying a predefined tenant mapping table, and determining an internal unified tenant identifier corresponding to the flow scheduling request and associated single-tenant concurrent quota, tenant resource weight, isolation level and strategy rule; obtaining a single-tenant concurrent quota and a tenant resource weight, generating a tenant isolation strategy in combination with the calculated rate limiting parameter and the tenant correction priority, and performing admission judgment; and based on the judgment result, distributing the flow scheduling request to the corresponding tenant scheduling unit according to the local priority, selecting a target tenant scheduling unit according to the scheduling qualification value and the global scheduling priority, generating an execution instance and triggering the execution instance. Through differentiated services, resource monopoly is prevented, task hunger is eliminated, system overload is avoided, multi-dimensional mutual restriction is carried out, and isolation between tenants is achieved.

The invention relates to an improved DQN-based flexible job shop dynamic batch flow scheduling optimization method considering emergency order insertion and reworking, and belongs to the technical field of shop scheduling. The method comprises the following steps of: considering a flexible job shop dynamic batch flow scheduling multi-objective optimization mathematical model of emergency order insertion and reworking; based on a knowledge-driven batching method and a multi-agent DQN model solving method, a local optimal solution of a flexible job shop dynamic batch flow scheduling model problem considering workpiece batching is further explored. The problem that a traditional optimization method is poor in applicability and efficiency under dynamic event interference is solved, and flexible job shop dynamic batch flow optimization scheduling is achieved. According to the optimization method, the problem of flexible job shop dynamic batch flow scheduling optimization under the order insertion and workpiece reworking dynamic event can be efficiently solved, waste of resources such as energy, time and cost is effectively avoided, production interruption and maintenance cost are reduced, and a scheduling scheme with good completion time and order insertion workpiece delay time is obtained.

The invention discloses a service flow scheduling method, equipment and a medium. The method comprises the following steps: acquiring business flow scheduling instruction information; analyzing the service flow scheduling instruction information to obtain a service flow scheduling constraint condition corresponding to the scheduling target and an effective condition of the service flow scheduling constraint condition; obtaining queue state information of a service flow queue of each service flow scheduling level; constructing a service flow scheduling optimization model based on the service flow scheduling constraint condition and the queue state information under the condition that the effective condition is met, and solving the service flow scheduling optimization model to obtain a scheduling strategy of the first service flow; wherein the service flow scheduling hierarchy comprises a flow hierarchy, a queue hierarchy and a port hierarchy. According to the technical scheme, the problem that the multi-layer queue business flow scheduling effect needs to be improved at present is solved, the stability of business flow scheduling can be improved through collaborative scheduling management of the multi-layer business flow queues and an intelligent decision-making mechanism for dynamically adjusting parameters, and the business transmission service effect is guaranteed.

The invention belongs to the field of GPU computing performance testing, and provides a GPU flow scheduling performance measurement method and device.The method comprises the steps that in a pre-established basic execution environment, N null-kernel functions are submitted to a reference flow in sequence, and the reference flow executes the received null-kernel functions and measures the reference execution duration; alternately submitting the N null kernel functions to the first test flow and the second test flow, introducing a cross-flow synchronization event, and measuring the total execution duration; and according to the reference execution duration and the total execution duration, calculating to obtain synchronization time consumption between the streams. According to the method, the influence of a tracking tool and the like on the performance of the measured object is eliminated, the method has obvious advantages in accuracy and stability, high-precision and low-interference GPU scheduling performance measurement is realized, and a quantitative basis is provided for performance optimization of a system during GPU driving and operation.

This invention relates to the field of distributed computing technology, and in particular to a unified registration and scheduling system for AI agent capabilities in edge-cloud collaboration, comprising: a dynamic behavior mapping module for capturing client interaction behavior features and mapping them to behavior control topology, performing path adjustment when deviations occur, and registering the control behavior to a unified MCP capability center; a semantic feature compression module for dimensionality reduction and compression of the original multimodal data stream to generate low-dimensional semantic feature stubs; an asynchronous state alignment module for converting feature stubs into asynchronous stateless message streams and reconstructing context mirror data on the cloud side; an inference stream scheduling module for generating inference stream scheduling strategies based on multi-dimensional states; a thought chain flow control module for dynamically truncating the streaming output of the large model according to the strategy and extracting core control segments and confidence levels; and a residual collaborative execution module for sending the core control segments to the edge for residual logic completion, driving the topology to execute control behaviors.

The invention discloses a network dynamic flow scheduling method, device, equipment and product, and relates to the technical field of network scheduling, and the method comprises the steps: monitoring the change of target parameters of the equipment in real time through obtaining the state data and historical data of each piece of equipment in real time, and analyzing the behavior and flow trend of the equipment. The method comprises the following steps: calculating a Q value of each device through a Q learning algorithm to obtain an optimal Q value of each device under a current task, calculating an optimal path and a time slot allocation result of each device under the current task according to the optimal Q value, and scheduling a network dynamic flow according to the optimal path and the time slot allocation result to ensure that the path is shortest and the resource allocation is most reasonable, thereby improving the network transmission efficiency. And the risks of time delay and network congestion are reduced. The dynamic flow scheduling mechanism can flexibly adjust the flow load of each path in the network according to the real-time data and the historical trend, thereby ensuring the efficient utilization of network resources, and improving the certainty of equipment in the dynamic network.

The invention discloses a warehouse logistics scheduling method and system based on cloud computing, and relates to the field of warehouse logistics management, and the method comprises the steps: collecting to-be-processed cargo information and available robot state information in a warehouse management system in real time based on a cloud scheduling platform; carrying out the clustering of the to-be-processed goods, carrying out the calculation and evaluation of a clustering result, and obtaining an optimal task partition division scheme; obtaining the shortest collision-free path from each available robot to each task partition, and calculating the path length of the shortest collision-free path; calculating path suitability, load suitability and electric quantity sufficiency between each available robot and each task partition; determining an optimal allocation scheme between the available robots and the task partitions based on the three features; and scheduling the available robots based on the optimal allocation scheme and monitoring the operation states of the robots in real time. According to the invention, real-time, efficient and balanced global integrated scheduling can be carried out on logistics robots and order tasks, and the collaborative operation capability of a robot cluster is improved.

The invention discloses a multi-link flow scheduling method and device based on convergence and shunting, and a medium, and relates to the technical field of flow scheduling, and the method comprises the steps: collecting access messages, merging flow clusters, carrying out the statistics of the total business volume and the message number of the flow clusters, generating a business observation column and the average message length, executing link light detection and interface counting, and generating a link observation column; generating a normalized service volume sequence and a service discrimination threshold, obtaining a service phase sequence, generating a bearing state quantity and a link discrimination threshold, and obtaining a link phase sequence; generating a phase conflict value sequence and a time limit carrying quantity sequence, forming a candidate link set, solving a synchronization completion moment, and generating a link service quantity; according to the candidate link set and the link traffic, in combination with the average message length and the message number, the final number of continuous message blocks is generated, the continuous message blocks are segmented, and shunt sending is executed, so that link selection and service distribution are more targeted, and the coordination, the performability and the stability of multi-link traffic scheduling are improved.

This disclosure provides a day-ahead and intraday collaborative robust optimization scheduling method for hydrogen-containing multi-energy microgrids, relating to the field of microgrid integrated optimization technology. The specific implementation involves: constructing a multi-stage robust optimization scheduling model incorporating uncertain variables and unexpected mechanisms; performing day-ahead offline training on the multi-stage robust optimization scheduling model to obtain a day-ahead stage unit combination scheduling strategy for handling worst-case scenarios and an intraday multi-stage robust optimization scheduling model; generating control commands based on the day-ahead stage unit combination scheduling strategy for handling worst-case scenarios to control the operating status of the unit combination components during the day-ahead stage; applying the intraday multi-stage robust optimization scheduling model online during the day to obtain energy flow scheduling strategies for each stage of the day; and generating control commands based on the energy flow scheduling strategies for each stage of the day to control the operating status of the energy flow components for each stage of the day. This disclosed technical solution can improve the feasibility and robustness of the intraday scheduling strategies for hydrogen-containing multi-energy microgrids.

According to the wide area network flow scheduling method for sensing link congestion disclosed by the invention, the congestion hotspot link in the network is identified in advance by analyzing the link congestion condition, the virtual link capacity is generated by scaling the link capacity of the congestion hotspot link, and the flow scheduling for coping with the network fluctuation is carried out based on the virtual link capacity. According to the method, the traffic is enabled to avoid the congestion hotspot link, so that a buffer space is provided for the traffic fluctuation, the robustness to the traffic fluctuation is improved, a subsequent routing strategy is optimized by generating the virtual link capacity, and a specific traffic engineering scheme does not need to be bound, so that the method can be seamlessly integrated into various existing traffic engineering schemes; only a small number of congestion hotspot links are intervened, so that the utilization rate, namely the median performance, under the conventional condition is slightly influenced while the performance under the worst condition is greatly improved to deal with burst traffic.

The invention relates to the technical field of live broadcast services, in particular to a live broadcast stream scheduling method, device and equipment and a computer readable storage medium. According to the invention, when the flow load of the first server node exceeds the limit value, the live broadcast stream needing to be transferred out in the first server node is determined based on the first Hash algorithm, and the target transfer-out node of the live broadcast stream is determined again based on the second Hash algorithm; according to the embodiment of the invention, the live broadcast stream needing to be transferred out in the first server node is scheduled to the target transfer-out node to relieve the load pressure of the first server node, and the scheduled live broadcast stream can realize networking on the target transfer-out node, so that the problem that the source returning cost is increased due to non-networking traffic can be solved.

The invention provides a traffic scheduling method and device, equipment and a storage medium, and the method comprises the steps: determining the current health degree of each link according to the historical health degree of each link and each index value in a current time period; therefore, the health degree is determined more accurately, and the link health degree is evaluated more accurately. In addition, a data transmission mode between the first network device and the second network device is determined according to the current health degree of each link, and then a flow scheduling rule in the corresponding data transmission mode is determined. Therefore, the dynamic transfer of each link can be determined, and the situation that the links are idle is avoided, so that the link utilization maximization and experience optimization are realized. The method is suitable for various IP network environments and various network topology structures, can be used for traditional copper cable access and wireless access scenes, and can also be used for optical fiber access scenes including an FTTR (Fiber To The Room) all-optical access network.

The embodiment of the invention relates to a traffic scheduling method and device, equipment, a storage medium and a program product. The method comprises the steps that when a user query request is received, performance weight values corresponding to candidate clusters in a candidate cluster list are determined, the performance weight values are determined according to performance index data of the corresponding candidate clusters, and the performance index data are used for reflecting the current running states of the candidate clusters; and determining a target cluster corresponding to the user query request from the candidate cluster list according to the performance weight value corresponding to the candidate cluster, and forwarding query traffic corresponding to the user query request to the target cluster, so that the target cluster processes the query traffic. According to the embodiment of the invention, the probability of forwarding the traffic to the abnormal cluster can be reduced, and the availability and stability of the service are improved.

The invention provides a day-ahead and intra-day collaborative robust optimization scheduling method for a hydrogen-containing multi-energy micro-grid, and relates to the technical field of micro-grid comprehensive optimization. The specific implementation mode is as follows: constructing a multi-stage robust optimization scheduling model containing an uncertain variable unexpected mechanism; performing day-ahead off-line training on the multi-stage robust optimization scheduling model to obtain a day-ahead stage unit combination scheduling strategy and an intra-day multi-stage robust optimization scheduling model which cope with the worst case; a control instruction is generated according to the day-ahead stage unit combination scheduling strategy for dealing with the worst condition, and the working state of day-ahead stage unit combination elements is controlled; and performing intra-day online application on the intra-day multi-stage robust optimization scheduling model to obtain an intra-day energy flow scheduling strategy of each stage, and according to the intra-day energy flow scheduling strategy of each stage, generating a control instruction to control the working state of an energy flow element of each stage in the day. According to the technical scheme of the invention, the feasibility and robustness of the scheduling strategy of each stage in the day of the hydrogen-containing multi-energy micro-grid can be improved.

The application discloses a kind of vehicle-mounted Ethernet dynamic flow scheduling method and system, it is related to vehicle communication field, comprising: T1, the data stream feature registration and global view management of the equipment of access vehicle-mounted network are carried out;T2, time window is taken as scheduling unit, multiple time slots are divided in time window, and hierarchical time slot scheduling model is constructed;T3, based on flow quota, network data is monitored and flow shaping in real time, and burst flow is inhibited;T4, according to the trigger of high priority emergency data stream, time slot preemption and time window dynamic reconstruction are executed;T5, according to network transmission quality feedback, the bandwidth quota of each data stream is adaptively adjusted.Through the above scheme, time window and three-level time slot physically isolate burst flow, ensure that safety data bandwidth such as braking, steering is monopolized, significantly reduce the packet loss rate, realize key business strong guarantee.

The application discloses a campus network flow prediction method and system, relates to the technical field of flow prediction, and comprises the following steps: step one, historical flow analysis, step two, flow distribution and step three, flow scheduling. The flow information of each region in each time period in each historical preset period is analyzed, the total demand of the current period campus flow is predicted, the flow priority and the flow threshold of each region in each time period are obtained, the flow distribution of each region is carried out based on the flow priority of each region in each time period, the speed of each region in each time period is analyzed when the flow threshold is reached, the network management strategy is refined, the flow resource is dynamically adjusted, the network resource utilization is greatly improved, and finally, the flow of each region in each time period is scheduled, so that the on-demand distribution and dynamic optimization of the campus flow are ensured.

The application discloses a mixed flow scheduling method and device, and relates to the technical field of network scheduling. The method comprises the following steps: determining a shortest scheduling path of a mixed flow based on network node information and basic information of the mixed flow, wherein the mixed flow comprises at least a periodic flow and a continuous flow; generating an arrival curve of the continuous flow based on characteristic demand information of the continuous flow; determining port time slot data after the periodic flow is scheduled based on the shortest scheduling path of the periodic flow, and determining a port residual time slot service curve based on the port time slot data; determining a service curve of the continuous flow with different priorities based on the shortest scheduling path of the continuous flow, the arrival curve of the continuous flow and the port residual time slot service curve; determining time delay data of the continuous flow based on the service curve of the continuous flow; and scheduling the mixed flow based on the shortest scheduling path of the mixed flow when the time delay data of the continuous flow meets scheduling requirements. In the above manner, the mixed scheduling of the periodic flow and the continuous flow can be simultaneously supported.

The invention discloses an offline store intelligent scheduling method and device, and relates to the technical field of big data and electronic commerce. A specific embodiment of the method comprises the steps of performing calculation based on environment data and visitor flow data of each store to obtain predicted visitor flow data of each store, and judging whether each store has flow overflow or not in combination with business data of each store and the predicted visitor flow data. And in response to traffic overflow of any store, determining a corresponding scheduling strategy so as to perform traffic scheduling on any store based on the scheduling strategy. According to the embodiment, data intercommunication of the stores can be realized, and the flow conditions among the stores are globally analyzed to perform collaborative scheduling, so that the balance of the global flow is guaranteed.

One or more embodiments of the present specification provide a traffic scheduling method and device, electronic equipment and machine readable storage medium. The method comprises: in response to a resource allocation event of a target service, determining a first target cloud computing resource to be scheduled from cloud computing resources carried by at least one edge cloud node, and creating a cloud computing instance for the target service based on the first target cloud computing resource; adding the cloud computing instance created for the target service on the same edge cloud node to a cloud computing instance set of the target service corresponding to the edge cloud node, and creating a logical service object for each cloud computing instance set of the target service; determining service capabilities that can be provided by each logical service object of the target service according to cloud computing resources allocated to each cloud computing instance of the target service; and scheduling service traffic of the target service by taking each logical service object of the target service as a traffic scheduling object corresponding to each edge cloud node.

The invention relates to a time delay sensitive flow scheduling method, device and equipment, a medium and a program product. The method comprises the following steps: when each data packet of a data stream sent by a sending end reaches a source switch, the source switch performs routing decision according to the feature information of the data packet and the length of a current port queue; therefore, low flexibility caused by fixed shunting and path selection is eliminated, and a higher link bandwidth utilization rate can be obtained. When the out-of-order data packets arrive at the destination switch, the destination switch allocates the out-of-order data packets to the corresponding cache queues according to the data packet identification information; and the destination switch takes out the data packets from the cache queue according to a correct sequence through a priority queue scheduling mechanism and then sends the data packets to a receiving end. Therefore, a large-range retransmission phenomenon and a service waiting timeout event are effectively avoided, the influence of an out-of-order data packet on the performance of a direct access memory network is reduced, and the stability and the reliability of the network are improved.

The present application relates to a kind of flexible job shop energy-saving batch flow scheduling multi-objective optimization method considering processing preparation resources, belong to workshop scheduling technical field.It includes steps: flexible job shop energy-saving batch flow scheduling multi-objective optimization mathematical model considering processing preparation resources;Model solution method based on knowledge-driven batching method and improved multi-objective evolutionary algorithm;Based on the tooling adjustment strategy of adjacent process.The optimization method proposed in the present application can efficiently solve the flexible job shop energy-saving batch flow scheduling multi-objective optimization problem considering processing preparation resources, realize the efficient collaborative optimization of workpiece batching, machine allocation, process sequencing, tooling allocation, and obtain the scheduling scheme with good completion time, total energy consumption and total processing cost.

The application discloses a maximum flow scheduling method and device for intelligent traffic flow scheduling, and the method comprises the following steps: constructing an intelligent traffic network directed graph; the intelligent traffic network directed graph comprises N network nodes and M directed edges, and N and M are positive integers; initializing the intelligent traffic network directed graph and the N network nodes to obtain initialized intelligent traffic network directed graph parameters and initialized network node parameters; processing the intelligent traffic network directed graph according to the initialized intelligent traffic network directed graph parameters and the initialized network node parameters to obtain a maximum flow scheduling result. The method can adapt to the intelligent traffic network environment, and can ensure the global optimality and synchronism of flow scheduling.

The invention discloses a computing power network-oriented function, namely a service resource sensing overall planning method, and belongs to the fields of cloud computing, server-free computing and computing power networks. The invention provides an efficient resource awareness and unified scheduling scheme which is divided into three stages: a task execution time prediction stage, a workflow scheduling stage and a data-driven FaaS platform construction stage. In the task execution time prediction stage, the transmission and execution time of the task is predicted by utilizing the dynamic change characteristics of the task in the system. In the workflow scheduling stage, the predicted transmission and execution time of the task is utilized, attributes such as the structure and the data size of the workflow and the function category are comprehensively considered, and computing power nodes are reasonably distributed so as to reduce the execution time delay of the workflow. In the data-driven FaaS platform construction stage, a FaaS platform normal form capable of making decisions by depending on data streams is constructed, so that system time delay caused by a workflow processing flow in the platform is reduced. According to the method, the computing power resource utilization rate and the FaaS service response efficiency are remarkably improved, the cold start delay is reduced, unified perception and efficient overall planning of heterogeneous and cross-domain resources are achieved, reliable support is provided for high-performance and cross-domain server-free application, and the method has wide application value and development prospects.

The invention discloses a congestion large flow rerouting method and system based on network state perception, and the method specifically comprises the steps: carrying out the statistical calculation of the contribution degree of each flow to a queue in a congestion state, dynamically determining a large flow judgment threshold value through combining with the number of active flows, and recognizing the flow with the contribution degree exceeding the large flow judgment threshold value as a responsibility elephant flow; based on the liability elephant flow list and the network state information, modeling the rerouting problem into a mixed integer programming model with the goal of minimizing the maximum link utilization rate, and solving to obtain a global optimal path allocation scheme; and according to the global optimal path distribution scheme, a new path forwarding rule is installed on each switch and an old path rule is deleted by adopting a first-building and second-dismounting strategy. According to the invention, through cross-layer cooperation of the data plane and the control plane, sub-second congestion response and global optimal flow scheduling are realized, and the problem of congestion migration caused by traditional reactive rerouting is effectively avoided.

The invention discloses a traffic scheduling method and device for a complex cloud environment, equipment and a storage medium, and relates to the technical field of cloud computing, and the method comprises the steps: obtaining a traffic migration request initiated by a user, the traffic migration request comprising source domain name information and destination domain name information; determining a migration scene type according to the source domain name information and the destination domain name information, wherein the migration scene type comprises same-cluster same-namespace migration, same-cluster different-namespace migration and different-cluster migration; determining a corresponding target traffic scheduling strategy according to the migration scene type; and carrying out distribution scheduling on the service traffic between the source domain name and the target domain name according to the target traffic scheduling strategy. According to the method and the device, differentiated flow scheduling strategies are dynamically generated and executed for same / cross clusters, different architectures and domain name types, so that multi-scene compatible and flow lossless domain name migration is realized.

The application provides a service flow scheduling model generation method and a service flow scheduling method. The service flow scheduling model generation method comprises the following steps: acquiring multi-source data of service flow scheduling tasks in multiple fields, training a large language model based on the multi-source data to obtain an intermediate model, and the multi-source data comprises a physical mechanism of a service flow; inputting sample scheduling task data into the intermediate model to obtain sample scheduling decision text output by the intermediate model; determining a training reward based on the accuracy of scheduling parameters in the sample scheduling decision text; updating the intermediate model based on the training reward to obtain a service flow scheduling model. The application can reduce the deployment cost of the service flow scheduling model.