142results about How to "Load balancing" patented technology

The invention relates to an Internet of Vehicles computing power scheduling method based on a graph neural network and deep reinforcement learning, and the method comprises the steps: S1, collecting the state information of network entities in the Internet of Vehicles and the association information between the entities in real time, and constructing a dynamic time-space attribute graph; s2, inputting the dynamic space-time attribute graph into a pre-trained graph neural network encoder, and outputting a node embedding feature set containing a high-order topological relation and global graph embedding features through multi-layer message passing and feature aggregation; s3, the node embedding feature set and / or the global graph embedding feature are / is used as the state of a deep reinforcement learning agent and input to a strategy network, the computing power scheduling action at the current moment is output, and the computing power scheduling action comprises the steps of assigning an unloading target node for a to-be-processed computing task and distributing corresponding computing and communication resources; s4, dispatching actions are distributed to the corresponding network entities to be executed, environment feedback is collected and used for model updating and next round of dispatching, and the method has the advantages of improving dispatching efficiency, adaptability and system energy efficiency and the like.

The invention discloses an intelligent dynamic load balancing method and system based on Clico-VPP. The method comprises the following steps: acquiring a load state index of a back-end service pod; according to the load state index and a service capability coefficient corresponding to the back-end service pod, calculating a dynamic traffic allocation weight of the back-end service pod through a weighted calculation model; based on a dynamic threshold synchronization strategy, synchronizing the state of a first hash ring located in a control plane to a second hash ring located in a forwarding plane; and based on the second hash ring, determining a target pod for the input data stream through consistency lookup. A double-loop decoupling architecture is provided, hash rings of a control plane and a forwarding plane are separated, a synchronization strategy is determined through a dynamic threshold value, decision intelligence and forwarding stability are both considered, and jitter is avoided; meanwhile, a dynamic weight-driven consistent Hash algorithm is adopted, a real-time load index and Pod service capability are fused to calculate a dynamic weight, and the dynamic weight is mapped into the number of virtual nodes, so that intelligent scheduling based on capability and maximum maintenance of connection during capacity expansion and contraction are realized.

The invention relates to a priority-based high-visibility stream-by-stream data packet sampling method and system. Comprising the following steps: step 1, flow initiation and priority marking; step 2, flow establishment and controller decision making; step 3, rule issuing and strategy execution; and step 4, data forwarding, scheduling and sampling: a priority scheduling mechanism of a data plane and global optimization of a control plane are decoupled and coordinated. In a data plane, a terminal host marks a degradation priority for a data packet according to the number of bytes sent by a stream, and a switch performs strict queue scheduling and probability sampling based on the priority. In a control plane, a controller carries out collaborative modeling on the configuration of routing, sampling probability and degradation threshold as a nonlinear optimization problem with maximization of sampling utility as a target, and an efficient online primitive-dual interior point method is adopted for solving. According to the method, high visibility and load balancing are finally ensured, and meanwhile, the control and calculation overhead is remarkably reduced.

The embodiment of the invention is suitable for the technical field of computers, and provides a chip system and a channel interleaving method thereof, the chip system comprises a main core grain and a plurality of storage units, at least one storage unit channel is arranged between the main core grain and each storage unit, and the main core grain comprises a main interleaving module comprising a memory channel interleaving unit; the memory channel interleaving unit is configured to perform first interleaving transformation on the address of the access request according to the address of the access request and a first interleaving parameter to obtain a target address, and the first interleaving parameter comprises the number of storage units corresponding to the access request; and the main routing module is configured to transmit an access request to the target storage unit through the corresponding storage unit channel according to the target address. According to the embodiment of the invention, the address of the access request can be subjected to first interleaving transformation by the independent memory channel interleaving unit instead of a main routing module, the method is suitable for different main core grains, the access request is sent to the target storage unit, and balanced access of the storage unit is realized.

The invention provides a wave position dynamic transfer method, system and device based on inter-satellite linkage and a medium, and the method is executed by an overload satellite and comprises the steps: judging whether a self load is overloaded or not; if the load is judged to be overloaded, selecting a to-be-transferred wave position from self-managed wave positions; acquiring state information of the adjacent satellites through inter-satellite interaction with the adjacent satellites; based on the obtained state information, determining a target satellite capable of bearing a to-be-transferred wave position from adjacent satellites having coverage overlapping with the target satellite; negotiating with the target satellite through an inter-satellite link to confirm beam position transfer, and triggering the target satellite to adjust the beam to cover the to-be-transferred beam position; and after negotiation confirmation, controlling the user equipment in the to-be-transferred wave position to be switched to the target satellite, and releasing the wave position resources. By adopting the method, the communication delay of the user equipment can be reduced, the throughput of the user equipment and the constellation resource utilization rate can be improved, and the service quality and user experience of a satellite communication system can be comprehensively optimized.

The invention discloses a resource scheduling optimization method and system based on dynamic load awareness, and belongs to the technical field of resource scheduling, and the method comprises the steps: carrying out the index collection of a consumer group and an AI model through a load awareness agent when the consumer group processes real-time business data, and obtaining a plurality of operation indexes; if the operation index meets a preset resource scheduling condition, performing resource allocation according to the operation index and the service priority of the real-time service data, and constructing a resource scheduling rule; based on the operation index and the resource scheduling rule, calculating an optimal scheduling action through a dynamic scheduling engine; and updating the concurrency number of the consumer group and the configuration parameters of the AI model by using the optimal scheduling action. Therefore, by implementing the method and the device, the problems of low business processing efficiency and resource waste caused by the fact that the consumption capability of the data processing cluster and the reasoning capability of the AI model cannot meet actual requirements due to the fact that resources cannot be dynamically allocated in the prior art can be solved.

The application relates to a kind of distributed unmanned aerial vehicle ad hoc network routing methods based on deep reinforcement learning, comprising;According to Markov decision process, the deep reinforcement learning architecture of unmanned aerial vehicle communication network is built;Running Dijkstra algorithm sends original data packet from source node to destination node and generates original training data according to the routing process of original data packet to pre-train the deep reinforcement learning architecture;The coordinates of the destination node D of target data packet are input, the next hop node B of current node A is obtained using the pre-trained deep reinforcement learning architecture, and target training data is generated, and the deep reinforcement learning architecture is retrained according to the original training data and target training data;Next hop node B is used as starting node, until the next hop node is the destination node, the routing of target data packet is completed, and the application can enhance the robustness of network and improve the life of unmanned aerial vehicle communication network.

The utility model provides a kind of silage machine header transmission gear box, including input gear box, first transfer case and second transfer case, the output end of input gear box is transmissionally connected with the input end of first transfer case, the first output end of first transfer case is transmissionally connected with the input end of second transfer case;Second output end of the first transfer case is transmissionally connected with first conveying gear box, first feeding gear box and second feeding gear box;The output end of the second transfer case is transmissionally connected with second conveying gear box, third feeding gear box and fourth feeding gear box.The utility model is adopted, power of input gear box is evenly configured by first transfer case and second transfer case, single input driving multiple output is realized, so each feeding wheel and conveying wheel of header can be driven simultaneously, and power distribution is reasonable, load balancing;A large number of transmission mechanisms are saved, and the compactness and reliability of header are improved.

This application relates to a point-to-point load balancing method, apparatus, device, storage medium, and program product, applied to a first node in an enhanced Ethernet network. The method includes: generating a load balancing task when establishing a service network connection between the first node and a second node; when executing the load balancing task, if the second node is idle, configuring a network test connection between the first node and the second node with a lower priority than the service network connection; performing a load balancing test on the first node and the second node through the network test connection; if the test result shows an unbalanced load, establishing a new network test connection between the first node and the second node, and performing the load balancing test again, until a target network test connection with a load-balanced result is obtained; and replacing the service network connection between the first node and the second node with the target network test connection. This method can achieve point-to-point load balancing in an online environment without affecting existing service traffic.

This application discloses a service resource allocation method, electronic device, storage medium, and product, relating to the field of computer technology. The method includes: responding to receiving a service resource allocation request sent by a terminal device, determining a target service region based on the regional ranking results of at least two service regions; if no preset server cluster exists among the N server clusters contained in each service region, determining a target server cluster from the N server clusters contained in the target service region based on the historical traffic information corresponding to each server cluster in the target service region; and controlling the target server cluster to allocate service resources to the terminal device according to the service resource allocation request. By determining and prioritizing the use of service resources in idle target server clusters, this application can balance the service resource load of each service region as a whole, thereby improving the overall utilization efficiency of service resources.

This application discloses a load balancing method and related equipment for distributed storage links, which can effectively improve the overall load utilization of a distributed storage system. The method includes: obtaining initial link grouping information corresponding to the distributed storage, wherein the distributed storage includes M storage links; determining T data acquisition time points corresponding to the current processing cycle; acquiring load data corresponding to each of the M storage links based on the T data acquisition time points; determining a first maximum load value corresponding to the M storage links based on the initial link grouping information and the load data; determining a second maximum load value corresponding to target link grouping information based on the load data and the initial link grouping information; and adjusting the M storage links according to the target link grouping information if the difference between the second maximum load value and the first maximum load value satisfies an adjustment condition.

The utility model provides an energy feedback time-phased output system of a gantry crane, and belongs to the technical field of energy utilization. The portal crane energy feedback time-phased output system comprises a generator, a rectifier, a storage battery, a first switch, an inverter module, an electric quantity monitoring module and a control module, the input end of the rectifier is connected with the output end of the generator; the output end of the rectifier is connected with the input end of the storage battery; the first end of the first switch is connected with the output end of the storage battery, the second end of the first switch is connected with the input end of the inverter module, and the control end of the first switch is connected with the control signal output end of the control module; the electric quantity monitoring module is connected with the storage battery; the output end of the inverter module is used for grid connection; the generator is configured to convert mechanical energy of the crane into electrical energy. According to the invention, the stability and reliability of energy feedback can be improved.

The application discloses a kind of dynamic partitioning method and system based on data skew model, it is related to big data technology field, including collecting data and pre-processing data, establish data skew evaluation model to predict pre-processed data, according to data characteristics, the data skew degree in job processing process is predicted, determines partition optimization strategy, designs evaluation experiment to compare dynamic partitioning with static partitioning, and repeatedly optimizes dynamic partitioning.This application proposes dynamic partitioning algorithm based on data skew model, which can select suitable partitioning strategy according to the skew degree of the data being processed, use the algorithm of three optimization methods based on Spark dynamic partitioning to process data performance comparison experiment, design and verify the universality and efficiency of the above dynamic partitioning scheme, can make the load balancing of the whole computing cluster, make full use of the computing resources of cluster, more efficiently complete data processing and calculation.

The application discloses a multi-format electronic archive intelligent preview method and device and equipment. The method comprises the following steps: obtaining a file URL and a permission control parameter; optimizing Nginx load balancing and distributing Nginx reverse proxy based on the file URL and the permission control parameter; performing format conversion on the electronic archive based on the Nginx reverse proxy; and previewing and inserting a watermark based on the format conversion result. The application pre-generates a same-name file of each file in a file system, which reserves the original content of the file. When a user needs to preview and view the file in the file system, the corresponding same-name file is obtained, so that it is not necessary to consider whether the client can directly identify the file format of the file to be previewed, and the format conversion time consumption caused by the fact that the file format cannot be directly identified after receiving a preview instruction is avoided.

The invention discloses a functional fabric preparation method and finishing equipment for realizing fabric functionalization, and relates to the technical field of textile fabric functionalization and finishing equipment. According to the preparation method of the functional fabric, the functional finishing agent and fabric fibers can be triggered to be subjected to chemical grafting reaction through ultraviolet irradiation and / or heating, and the textile fabric is subjected to one-time continuous multifunctional finishing; the finishing equipment comprises two functional modules, an ultraviolet light initiation module and a thermal initiation module, can support different finishing processes of fabrics, realizes chemical covalent bond grafting reactions of different principles, has strong production operability and high flexibility, and has ideal popularization and application values in the fields of textile fabric finishing and engineering.

The application discloses a distributed document analysis method, device, equipment and medium, the method comprises the following steps: obtaining a target to be analyzed document; extracting the content feature data of the target to be analyzed document; the content feature data is used to reflect the content complexity of the target to be analyzed document; according to the content feature data, the estimated time consumption of analyzing the target to be analyzed document is determined; based on load balancing, according to the estimated time consumption, the target analysis task of the target to be analyzed document is distributed to the target computing power node; so that the target computing power node executes the target analysis task to obtain the analysis result. Therefore, the content feature data of the document is used to estimate the analysis time, rather than relying on the file size to determine the estimated time consumption, which is adaptive to the time consumption fluctuation characteristics of different documents, improves the estimated time consumption accuracy, and based on load balancing, the estimated time consumption is used for computing power stage distribution, which improves the resource utilization and the load balancing effect of the system.

This invention relates to the field of food processing technology, and specifically discloses a conveying device for industrial food processing with an anti-spillage structure. The device includes a working platform, a first support fixedly connected to the top of the working platform, an anti-spillage adjustment device fixedly connected to the top of the first support, a cleaning device fixedly connected to the inner wall of the first support below the belt conveyor, an automatic feeding device fixedly connected to the top of the working platform on one side of the first support, and a material distribution device rotatably connected to the top of the working platform on one side of the first support. This conveying device for industrial food processing with an anti-spillage structure, equipped with an anti-spillage adjustment device, ensures stable material transport along a predetermined path, preventing accumulation or spillage. The cleaning device prevents food debris from adhering to the conveyor belt, avoiding contamination of subsequent batches of products and improving product quality.

This invention discloses a rocket-shaped rotating amusement ride, belonging to the field of amusement equipment technology. The ride includes a column, a lifting and rotating assembly that can move up and down along the column, and multiple rocket cabin assemblies suspended from it. The lifting mechanism includes a fixed pulley at the top of the column and a drive pulley system on the ground. A steel cable passes around the fixed pulley, connecting the lifting and rotating assembly and the drive pulley system, and is balanced by a counterweight. The drive pulley system uses a hydraulic cylinder to change the distance between its internal upper and lower pulley systems to raise and lower the steel cable, achieving efficient and stable lifting. The lifting and rotating assembly can rotate horizontally, and the rocket cabin assemblies can rotate around their own axes. This invention has a novel structure, greatly enhancing the richness and excitement of the amusement experience through multiple composite movements such as lifting, revolution, and rotation.

This invention provides a method and system for distributing I / O across SAS expanders between a controller and a disk. The method includes: an ITS module retrieving I / O requests from an I / O request queue and encapsulating them into SCSI commands; selecting a target device address; selecting the local expander channel address for odd-numbered slots and the peer expander channel address for even-numbered slots; the SAS driver transmitting the SCSI command to the local expander via the SAS bus; the local expander selecting the corresponding channel for transmission based on the SAS address encapsulated in the SCSI command; and when the local expander fails to distribute the I / O, it returns a corresponding I / O error to the ITS module, which modifies the SAS address in the SCSI command to the corresponding channel address on the peer expander and re-distributes the I / O. This invention provides a method and system for distributing I / O across SAS expanders between a controller and a disk, allowing I / O to be distributed to the storage disk via the expander belonging to the peer controller when I / O distribution between the current controller and the expander / storage disk fails.

The embodiment of the invention provides a transcoding task allocation method and device and a readable storage medium, after an electronic device receives a transcoding task from a terminal, when an absolute idle card of an encoding module is sufficient, the absolute idle card is preferentially and randomly selected and the transcoding task is allocated; and when the absolutely idle cards of the coding module are not sufficient, the relatively idle cards are selected and the transcoding tasks are allocated, so that the purpose of improving load balance is achieved while the hardware transcoding cards are randomly selected. Besides, in the field of AI analysis, after the edge AI gateway receives the AI request from the terminal equipment, randomness and load balance are taken into consideration when the service node is selected, and poor real-time performance and service node performance bottleneck caused by accumulation of a plurality of AI requests to the same service node are avoided.

The invention discloses an orchard multi-robot task allocation optimization method based on hierarchical path reconstruction, and the method comprises the steps: S1, building a multi-target mathematical model, optimizing the maximum completion time and total energy consumption, including robot load, speed, energy consumption and battery capacity constraints, and employing VLDIM to generate an initial solution population; s2, optimizing the task sequence of each path by using DRRM in the microscopic layer; s3, robot-level DRRM optimization, TRRM task redistribution, CRRM charging path reconstruction and environment selection are executed iteratively; and S4, splitting the longest path by using the SRRM, redistributing the longest path through the MILP1, and outputting a non-dominated solution set. Through hierarchical coding, multi-stage collaborative optimization and a special reconstruction mechanism for core constraints, the task allocation efficiency and scheme quality of a multi-robot system under complex constraints are significantly improved, and the method is suitable for agricultural automation and warehouse logistics scenes.

The invention discloses a wireless communication method, device and equipment, and belongs to the field of communication, and the wireless communication method comprises the steps that a terminal obtains first information; wherein the first information comprises at least one of the following items: at least one uplink carrier group, at least one downlink carrier group, at least two uplink carriers and at least two downlink carriers; the terminal determines a target uplink carrier according to the first information, and the terminal sends first uplink random access information based on the target uplink carrier; and / or, the terminal determines a target downlink carrier according to the first information, and the terminal receives first downlink random access information based on the target downlink carrier.

The utility model relates to pre -stress construction technical field discloses a kind of machine head of threading machine, including base, including base, the horizontal tensile mechanism is separately arranged on the base along its length direction, and the steel strand clamping mechanism is arranged at each horizontal tensile mechanism end portion;When working, the steel strand clamping mechanism at different positions is alternately clamped to steel strand, and the horizontal tensile mechanism is alternately operated, and the relay conveying to steel strand is completed;The utility model can realize the efficient, stable, continuous threading operation of steel strand, and improve work efficiency.

This invention discloses a joint optimization method for mobile edge computing and service caching assisted by multiple UAVs, comprising: constructing a multi-UAV-assisted edge computing system model; constructing a communication model; dividing the system decision time into a set of large-timescale periodic sequences and a set of small-timescale time slot sequences, each large-timescale periodic sequence containing multiple consecutive small-timescale time slot sequences; deriving expressions for the total task processing latency and total energy consumption of the system in any time slot; establishing a joint optimization objective function with the goal of minimizing the total system latency and total energy consumption; constructing a Markov decision mechanism; employing the SAC deep reinforcement learning algorithm to implement the dual-timescale decision-making of the system; and solving the joint optimization objective function to obtain the optimal joint optimization scheme. This invention can significantly improve the edge service cache hit rate, optimize UAV load balancing, and reduce task processing latency and overall system energy consumption.

This invention provides a multi-UAV sensor data acquisition trajectory planning method based on deep reinforcement learning, comprising the following steps: S1, establishing the basic framework of a UAV-assisted sensor data acquisition model in a land scenario; S2, constructing a persistent trajectory planning strategy based on an improved deep reinforcement learning algorithm according to the basic framework, and generating a UAV flight trajectory map that satisfies energy balance constraints and maximizes data acquisition value based on velocity vectors. This invention introduces a feature extraction unit module containing self-attention weight calculation to extract spatiotemporal differential features of sensor observations based on traditional multi-agent deep reinforcement learning algorithms, and combines a packet retransmission mechanism and an energy balance coefficient to optimize UAV flight energy consumption while improving the value and reliability of data acquisition. This system improves the processing efficiency of UAVs for dynamic monitoring tasks.

Embodiments of the present specification provide a resource scheduling method and device, wherein the resource scheduling method comprises: determining a target deployment area of a target service and deployment resources corresponding to each target deployment area according to deployment resource requirements of the target service, wherein the target service is one of at least one to-be-deployed service, the target deployment area is one of at least one to-be-deployed area, each to-be-deployed area corresponds to one or more edge nodes, and the deployment resources include deployment resources on the edge nodes; deploying the target service based on the deployment resources; determining a target edge node for processing a client request of the target service according to the client request, so that the target edge node processes the client request. By determining the target deployment area of the target service and the deployment resources corresponding to the target deployment area, and assigning a corresponding target edge node for the client request, the running efficiency of the edge node is improved.

The invention relates to a load balancing method and device based on a space-ground integrated core network, and communication equipment. Wherein a data plane satellite-borne network element is newly added to each network node of the space-ground integrated core network, and the space-ground integrated core network is used for parallel transmission of a control plane link and a data plane link in an inter-satellite link based on a service interface (SBI) / data transmission interface (DTI) dual-bus link. The method comprises the following steps: a first network node receives a user task, wherein the user task is a task which is unloaded to a space-based network for execution after a ground data network performs a load balancing decision; the first network node makes a load balancing decision according to the geosynchronous orbit GEO node state information to obtain a first GEO node, and the first GEO node is used for executing a load balancing strategy to send a user task to a corresponding low earth orbit LEO node through an inter-satellite link for data processing. According to the invention, the average processing time delay of user tasks can be reduced.

The invention relates to the technical field of intelligent processing of campus operation and maintenance work orders, and discloses an intelligent analysis and service optimization system for campus informatization maintenance work orders. According to the system, standardization processing of multi-source work order data is achieved through a work order information aggregation module; the intelligent priority evaluation module adopts a deep learning model to analyze fault text semantics, generates a dynamic priority coefficient and improves the accuracy of work order grading; the resource scheduling optimization module generates an optimal allocation scheme based on the priority and the personnel state; and the redundant communication management module constructs an active-active architecture by using a software defined network, so that load balancing and rapid fault switching of a data stream and a control signaling are realized, and the communication reliability of the system is effectively guaranteed. According to the invention, the problems of inaccurate priority judgment and insufficient communication guarantee of a traditional work order system are solved.

The application relates to the technical field of Internet of Things and edge computing, and discloses an Internet of Things data access and processing system based on edge computing, which comprises a data acquisition module, an environment sensing module, a data preprocessing module, a transmission strategy analysis module, an edge distributed analysis module, a multi-source data fusion module, a deep intelligent analysis module, a resource scheduling analysis module and a global resource optimization module; through the arrangement of the nine functional modules, the whole-process processing of Internet of Things data from access, preprocessing, transmission, edge analysis, multi-source fusion, deep intelligent analysis to resource scheduling optimization is realized; compared with the prior art, the data processing delay is significantly reduced, the resource utilization rate and the data processing accuracy are improved, the application is suitable for various Internet of Things application scenarios, and has wide popularization value.