75 results about "Queuing delay" patented technology

A low-delay multi-protocol intelligent lighting synchronization system based on a unified abstraction layer comprises the steps that an instruction from a multi-protocol bridging module is received, and network round-trip time data of terminal equipment is acquired through an active detection mechanism; based on the network round-trip time data, adopting a Kalman filtering algorithm to construct a delay prediction model so as to predict the future network delay of the terminal equipment; inputting the instruction into a third-stage buffer area for processing, and dynamically adjusting the trigger frequency of the active detection mechanism according to the load state of the third-stage annular buffer area; calculating queue delay of the buffer area according to the received load state of the buffer area, and obtaining final sending time of the instruction in combination with future network delay of the terminal equipment; and at the final sending time, sending the instruction from the sending buffer area to the corresponding terminal equipment. According to the system, low-delay and high-stability synchronization of cross-protocol equipment in the field of intelligent illumination is realized.

The invention discloses an ERP (Enterprise Resource Planning) data intelligent supervision method based on the Internet of Things, which relates to the technical field of enterprise informatization, and comprises the following steps: constructing a time sequence integrity observation layer in an Internet of Things data acquisition link, embedding a mirror image time anchor in each sensor sampling point, recording electromagnetic interference, time service offset and queuing delay, generating a phase fingerprint time baseline, and obtaining a phase fingerprint time baseline; constructing a unified time reference framework; operating a causal coherent analysis mechanism based on a unified time reference frame, comparing instantaneous offsets of a mirror time anchor and a real-time timestamp, identifying a phase inversion region, extracting information of a corresponding sampling node, a production line position and an energy consumption unit, generating a high-risk time slice list, and determining a time correction boundary. According to the method, a time sequence observation layer and a time reference frame are constructed, phase abnormity is identified, a data trend is reconstructed, a regulation and control instruction draft is generated, sampling time sequence recovery and scheduling convergence are realized through time inversion control, data consistency and decision accuracy are improved, and a closed-loop control system is constructed.

The invention discloses a heterogeneous communication network queuing time delay violation probability prediction method based on a yoke theory. The method is suitable for an emergency scene emergency communication system cooperatively constructed by an unmanned aerial vehicle and a high-altitude platform. The method comprises the following steps: modeling links from an unmanned aerial vehicle to a high-altitude platform and from the high-altitude platform to a ground command center in a communication network into a two-hop heterogeneous queuing service system; secondly, modeling a dynamic evolution process of data arrival and channel service by adopting a Markov Monte Carlo method; and finally, constructing a multi-hop heterogeneous network joint arrival-service yoke process based on a yoke theory, and deducing a violation probability boundary expression of end-to-end queuing time delay. The invention provides a time delay violation probability prediction method in cooperative emergency rescue communication of an unmanned aerial vehicle and a high-altitude platform. The service reliability of a system under given time delay constraint is accurately quantified.

The invention provides a DSR transmission method and device, a communication system and a storage medium, which can be applied to the technical field of wireless communication. According to the scheme, a new DSR triggering condition is defined. When the sending window of the terminal equipment is updated, the terminal equipment calculates the remaining bytes and the remaining duration of the current task in real time; and once the residual duration is lower than the trigger threshold corresponding to the service type, the terminal device immediately triggers the DSR and reports the residual bytes and the residual duration of the task to the network device, and different types of non-video traffic services correspond to different trigger thresholds. And the network equipment reserves resources for the remaining bytes of the task in advance according to the information. When the data of the service arrives dispersedly, the data can directly fall on the reserved resources without triggering the scheduling request again, so that the problem of queuing delay is solved, and the scheduling efficiency and the transmission reliability are improved.

The application belongs to the technical field of computer network and artificial intelligence, and specifically provides a dynamic network adaptive routing method based on a graph neural network and a group relative strategy, which realizes adaptive perception of network topologies of different scales and types through a graph neural network encoder, eliminates the dependence on a value network through a group relative strategy optimization algorithm, thereby reducing the model complexity, and realizes cross-topology generalization, energy perception and load balancing on the basis of adaptive network dynamic change and effective avoidance of harmful nodes; compared with traditional shortest path routing, Q-Routing and PPO-MLP baseline methods, the application has significant advantages in key indicators such as average end-to-end delay, average queuing delay and data packet delivery rate, and has faster training convergence speed and higher cumulative reward promotion; in conclusion, the application has excellent routing performance and anti-destroying ability, and is especially suitable for routing scenes in a high dynamic and multi-fault environment.

This invention relates to the field of satellite communication technology, specifically to a dynamic routing method for large-scale low-Earth orbit (LEO) satellites that adapts to network queuing delay. Based on a greedy heuristic approach for dynamic routing in large-scale LEO satellite networks, it utilizes parameters such as satellite communication distance and direction, the estimated minimum number of hops from the current satellite to the receiving location, the average queuing delay in the network, and the queuing delay of the next-hop relay satellite. A value function is proposed to find the next-hop satellite, where the function value reflects the distance traveled to the receiving location in a single-hop transmission and the magnitude of the relay satellite's queuing delay. By plotting the change curves of the weights corresponding to the shortest transmission path delay versus the average satellite queuing delay, the optimal weights are found as the average queuing delay changes, thus achieving adaptive network load conditions. Verification shows that, compared to other routing methods that allow non-adjacent satellites to use ISL communication, this invention has the advantage of shorter total delay for networks with different on-board queue load conditions.

The application discloses a kind of 6G network multidimensional resource AI model dynamic deployment optimization methods based on category theory, belongs to intelligent collaborative optimization technical field;Method is: the cross-layer consistency dependency of end-to-end AI reasoning service is formalized by functor form;Establish the joint optimization model with long-term average end-to-end delay minimization as target, while being constrained by multidimensional resource and service quality;Convert long-term random optimization problem into time-slot online decision problem;Get AI model dynamic deployment and task scheduling result.The application realizes cross-layer consistency description to task scheduling and model deployment through category theory unified modeling and functor composite mechanism, reduces the inconsistency and redundant constraint caused by hierarchical modeling, improves the structured degree and explainability of joint decision;Under the constraint of multidimensional resources such as calculation, memory, storage and bandwidth, dynamic adaptive optimization is realized, node resource over-limit and load imbalance are effectively avoided, and congestion and queuing delay are reduced.

The present application relates to the technical field of financial management, in particular to a digital one-network financial marketing management method and system, comprising the following steps: acquiring node data contrast queuing delay task sequence, reading dependent chain comparison time length analysis and splitting link extraction, extracting standby capacity contrast residual time weight distribution task, matching regional distribution order according to business currency time limit, reading branch comparison delay insertion position to obtain execution scheme. In the present application, the processing delay, the queuing quantity and the capacity of the transaction node are compared in real time, the task entering order and the node position are optimized, the dependent chain comparison and the link information extraction are combined, the split task is reorganized under the condition of maintaining the dependent order, the resource utilization rate is improved by matching the standby channel capacity, the task residual time and the dependent weight, the priority is adjusted according to the business type, the currency type and the time limit across regions, and the overall waiting time is shortened by inserting the branch of the confluence node according to the delay optimization.

The application discloses a kind of based on rolling optimization's giant constellation network path selection method, this method includes: constructing giant constellation network and static network;Mapping giant constellation network and static network obtains mapping information;According to mapping information, each LEO satellite periodically exchanges queuing delay information with each LEO satellite within three hops connected LEO satellite, and the queuing delay information after exchange is saved in link state data table;Link state data table is handled, and the shortest path information is obtained;According to the shortest path information, the next hop LEO satellite is selected, and the rolling optimization's giant constellation network path selection result based on is obtained.The application adopts rolling optimization idea, and global optimal path calculation is decomposed into multiple local optimal path calculation, can reduce calculation complexity, accelerate routing convergence speed;At the same time, link state information exchange is limited in local area, and signaling overhead can be reduced.

The application discloses a kind of video transmission methods, devices and electronic equipment for mobile robot. Among them, the method comprises: obtaining the generation timestamp of current video frame transmitted by mobile robot to control terminal, confirming arrival time, and the transmission delay of current video frame transmitted by mobile robot to control terminal;Based on generation timestamp, confirming arrival time and transmission delay, the current queuing delay of the video frame to be sent in sending queue is obtained;Based on current queuing delay, determine rate adjustment factor and frame discard survival time threshold, the rate adjustment factor is used to control video frame transmission rate;According to rate adjustment factor and frame discard survival time threshold, the video frame to be sent in sending queue is transmitted to control terminal.The application solves the technical problems that video transmission control method in related art under mobile robot scene causes algorithm complexity, rate and discarding strategy disconnection, queue backlog is serious, leading to high end-to-end delay, picture lag.

The invention provides a dynamic self-adaptive DNN collaborative reasoning method supporting a backspacing mechanism, relates to the technical field of image processing, and designs an elastic two-way task flow from equipment to edge to equipment, so that the elastic two-way task flow becomes an intelligent scheduling decision point. And when the edge server is overloaded, the task can be actively returned to the source mobile equipment to be executed, so that the bottleneck of queuing delay caused by edge resource competition is fundamentally avoided. A rollback decision is introduced, so that an unloading strategy is upgraded from'static 'or'semi-static' to real'dynamic self-adaption ', the change of edge resources can be directly responded, and a decision target is expanded from optimizing a single task to optimizing a global system load. Three key dimensions, namely a backspacing decision, resource allocation and a model segmentation point, are arranged in a unified framework for joint optimization. Through an integrated reinforcement learning model, the three decisions are output at the same time, so that the three decisions can cooperate with each other and have a synergistic effect.

The invention provides a congestion control method and system based on active queue debt compensation, and the method introduces a queue debt mechanism in a BBR frame, and comprises the steps: initializing a state variable, and carrying out the zero setting of a last-round bandwidth estimation value and an accumulated queue debt; identifying a bandwidth detection behavior by comparing new and old bandwidth estimated values, calculating a single queue debt and accumulating the single queue debt to an accumulated queue debt; calculating a bandwidth delay product based on the current bandwidth and the minimum round-trip delay, and correcting the bandwidth delay product by using the cumulative queue debt to obtain a target in-transit data volume; limiting the in-transit data volume to the target in-transit data volume in an emptying stage of the BBR algorithm so as to actively repay the debt; and after emptying is finished, the debt is reset to finish the compensation cycle. According to the method, accurate quantification and active compensation of queue debt generated by bandwidth detection are realized, the inherent defects of queue accumulation and delay growth caused by periodic detection of a traditional BBR algorithm are overcome, and the network queuing delay is remarkably reduced while high throughput is maintained.

One example method includes creating an ILP model that includes a delay model, an energy model, and a QoS model, and modeling, using the integer linear programming model, a VNF placement problem as an ILP problem, and the modeling includes: using the delay model to identify propagation, transmission, processing, and queuing, delays implied by enabling an instance of the VNF at an edge node to accept a user VNF call; using the energy model to identify energy consumption implied by enabling an instance of the VNF at an edge node to accept a user VNF call; and using the QoS model to identify end-to-end delay, bandwidth consumption, and jitter, implied by enabling an instance of the VNF at an edge node to accept a user virtual network function call. The problem modeled by the ILP model may be resolved by a heuristic method.

A traffic control method and network system for service data backhaul, applied to a network system comprising N terminals and a gateway, wherein at least two terminals use different communication modes to perform service data backhaul operation with a server through the gateway, characterized in that the method obtains decision information of each time slot in a future preset period by time slot by time slot, and controls the data transmission operation of the terminal and the gateway based on the decision information, so that the weighted sum of the average transmission delay in the service data transmission process of each terminal and the average transmission delay in the service data forwarding process of the gateway is minimized in the entire preset period, effectively controlling the data queuing delay on the terminal side and the gateway side, and realizing efficient backhaul of data.

The embodiment of the invention relates to a context-aware and stateless deep learning auto-tuning framework. Systems and methods are provided for improving auto-tuning procedures using stateless processing with a remote key value store. For example, the system may implement task launchers, schedulers, and agents to launch, schedule, and execute decomposed auto-tuning phases, respectively. Scheduling policies implemented by the scheduler may perform operations beyond simple scheduling policies (e.g., FIFO-based scheduling policies), which may result in high queuing latency. By utilizing auto-tuning domain-specific knowledge, queuing latency is reduced and resource utilization is improved compared to conventional systems.

The invention provides a task processing method, a Switch chip, a distributed computing network, an electronic device and electronic equipment, and relates to the technical field of distributed computing networks, an aggregation operation task is shared to a master PM and a slave PM, the master PM and the slave PM respectively undertake aggregation operation of a part of task data, and then the master PM obtains a final target aggregation operation result, so that the task processing efficiency is improved. Therefore, the problems of centralized calculation hotspots and unbalanced resource utilization are relieved to a certain extent, the calculation efficiency is improved, and the queuing delay is reduced.

This invention relates to the field of engineering resource scheduling technology, specifically a network-based hydropower construction resource collaborative management system, including a coverage area division module, a resource capacity calculation module, a dependency graph construction module, a call order filtering module, and a collaborative scheduling generation module. This invention constructs a signal spatial sequence and analyzes fluctuation deviations to define stable communication intervals, calculates transmission capacity based on the lowest signal strength and verifies the equipment's carrying capacity limit, and combines real-time active node statistics with the planned scheduling quantity to perform capacity access judgment, avoiding network congestion caused by over-limit operations. It integrates connectivity testing and queuing delay data to construct dynamic dependency relationships, and triggers scheduling after confirming both the link and the preceding task are ready, ensuring that equipment enters the site in an orderly manner while meeting communication quality and process constraints. This solves the network collapse problem caused by multiple machines operating concurrently in confined spaces and guarantees the real-time transmission and accurate execution of collaborative operation instructions.

The application provides a DSR transmission method, device, communication system and storage medium, which can be applied to the technical field of wireless communication. The scheme defines a new DSR triggering condition. When the terminal device updates the sending window, the terminal device calculates the remaining bytes and the remaining time length of the current task in real time. Once the remaining time length is lower than the triggering threshold corresponding to the service type, the terminal device immediately triggers the DSR and reports the remaining bytes and the remaining time length of the task to the network device, and different types of non-video traffic services correspond to different triggering thresholds. The network device reserves resources in advance for the remaining bytes of the task according to the information. When the data of the service arrives, it can directly fall on the reserved resources, without the need to trigger the scheduling request again, solving the queuing delay problem and improving the scheduling efficiency and the transmission reliability.

The invention discloses a collaborative environment-oriented service deployment and request scheduling optimization method and device, and relates to the technical field of edge-cloud collaborative mobile edge computing in the power industry, and the method comprises the steps: constructing a multi-instance queuing network model and a multi-dimensional hierarchical soft actor-commentator algorithm; based on the multi-instance queuing network model, modeling a multi-instance execution relationship in a power station task processing process, and providing a performance evaluation basis for a request scheduling strategy by quantifying task transmission delay, queuing delay and calculation delay; and based on the multi-dimensional hierarchical soft actor-commentator algorithm and in combination with the current state of the power information system, determining the deployment number and distribution position of each micro-service instance, and formulating a request scheduling strategy. According to the method, the dependency relationship and the multiplexing characteristic between the micro-services are fully considered, the request response delay can be effectively reduced, the network load and the system energy consumption can be balanced, and the service quality and the resource utilization efficiency of the electric power station are improved.

The application discloses a dual-time-scale congestion control method of an RDMA lossless data center network and belongs to the technical field of data center network congestion control. The application constructs a dual-time-scale congestion control framework. The method introduces a reinforcement learning model in a coarse-grained layer, realizes the control of data sending rate and a sending window by multi-dimensional perception of global network state, traffic distribution characteristics and historical performance indexes, and thus achieves an optimization decision from a global perspective. In a fine-grained layer, the instantaneous link state is perceived in real time based on a fast feedback congestion mechanism, and fine adjustment of traffic and fast convergence of a micro-time scale are completed. By the optimization capability of the reinforcement learning in dual-dimensional scheduling of the rate and the window, and in combination with the low-delay response characteristics of the fast feedback congestion mechanism, the application can effectively inhibit the accumulation of switch queues, block the risk of congestion diffusion, and thus achieve a dynamic balance among high network throughput, multi-flow fairness and ultra-low queuing delay.

The invention relates to the technical field of digital information transmission, in particular to an inclined elevator safety wireless communication method and system based on the Internet technology, and the method comprises the steps: building a WIFI communication network in an area where an inclined elevator is located, and presetting an evaluation period; acquiring a first characteristic value and a second characteristic value of each link in each period, and acquiring a third characteristic value of each link by combining the total throughput of all routers in each link with the total average queuing delay of the data packets; recording the communication link from the inclined elevator to the main gateway in each period as a main link; measuring whether each main link is congested or not; respectively acquiring link measurement results of each link in the current period when the main link is congested and not congested; and carrying out routing selection according to the OSPF protocol. According to the method, the network change is responded in time, the optimal transmission path is selected, it is ensured that a transmission guarantee with the higher priority is provided for safe wireless communication of the inclined elevator, and then the real-time performance of safe monitoring of the inclined elevator is ensured.

The invention discloses a memory access management method and device for data processing and a medium, and relates to the technical field of data processing, and the method comprises the steps: receiving a read-write access request sent by a processor, writing the read-write access request into an access request queue, carrying out the message disassembly and field analysis of the read-write access request, obtaining a request feature field, and storing the request feature field in a database; generating an access stream window parameter according to the process identifier in the request feature field; and acquiring congestion characterization data around the access request queue, executing congestion judgment to obtain a flow limiting control signal, updating access flow window parameters according to the flow limiting control signal, and setting an uncompleted request admission threshold, so that the access request queue forms a controlled request queue constrained by the uncompleted request admission threshold. According to the method, the scale of the access request queue is controlled through linkage of congestion judgment and the uncompleted request admission threshold, the access rhythm under concurrent reading and writing is controllable, uncompleted request accumulation and queuing delay fluctuation are reduced, and the overall throughput stability and operation reliability are improved.

The present disclosure provides a method for scheduling test tasks, relating to the technical field of computer, and the implementation scheme is: obtaining a test task to be scheduled, a test data set, and a state of computing power and bandwidth resources; calculating an algorithm feature vector, a data set feature vector, and a test strategy feature vector based on the test task, the test data set, and the state of computing power and bandwidth resources; constructing a ternary relationship graph based on the algorithm feature vector, the data set feature vector, and the test strategy feature vector; performing feasibility judgment and cost evaluation on each ternary relationship graph; selecting a target ternary relationship graph to generate a task execution scheme based on the feasibility judgment and the cost evaluation; and binding the test task to the matched resource slot and data set for execution according to the task execution scheme, which can realize the integration of algorithm features, data set features, and test strategies into decision-making, can prioritize the coverage of key scenarios, and can improve resource utilization, reduce queuing delay, and reduce data transfer cost.

The application discloses a reliable edge network cloud cooperative task scheduling method and system for computing power endogenous scene, equipment and storage medium, and relates to the field of mobile communication. Including: for the first scheduling period, according to the total CPU core number of the base station and the CPU core number occupied by the communication task, the endogenous available CPU core number and the time delay reservation coefficient of the base station are determined; according to the single CPU core computing capacity of the base station, the time delay reservation coefficient, the queuing delay estimation value and the task parameter value of each received task, the effective schedulable time limit and the required minimum CPU core number of each task are determined; according to the required minimum CPU core number and the endogenous available CPU core number, the base station local task set and the remote network cloud node task set are determined; the base station uses the endogenous available CPU core number to execute the base station local task set and schedule the remote network cloud node to execute the remote network cloud node task set, so as to form an efficient cooperative closed loop among the three of "cloud-edge-end".

The invention relates to the technical field of financial management, in particular to a digital one-network financial marketing management method and system, and the method comprises the following steps: obtaining a node data comparison time delay queuing arrangement task sequence, reading a dependency chain comparison time length, analyzing, splitting and extracting a link, extracting a spare capacity comparison remaining time weight distribution task, and obtaining a task sequence; and according to a business currency time limit matching region distribution sequence, reading branch comparison delay insertion positions to obtain an execution scheme. According to the method, the processing time delay, the queuing number and the capacity of the transaction nodes are compared in real time, the task entering sequence and the node positions are optimized, and the reorganization of the detachable tasks is completed under the condition that the dependency sequence is kept in combination with dependency chain comparison and link information extraction; the resource utilization rate is improved through matching of standby channel capacity, task remaining time and dependency weights, the priority is adjusted in a cross-region mode according to service types, currency types and time limits, and confluence nodes shorten the overall waiting time according to delay optimization branch insertion.

The invention discloses a live broadcast flow intelligent scheduling method and system based on edge calculation, and the method comprises the steps: accurately evaluating a flow state value through collecting the number of access users, uplink and downlink flows, residual bandwidth and other multi-dimensional indexes of an edge node in real time, so as to master the bearing capability of each node, predicting the future live broadcast flow demand according to the flow change, and achieving the intelligent scheduling of the live broadcast flow. The scheduling priority is calculated in combination with the traffic state value, the traffic is dynamically allocated to the high-priority node from the low-priority node, and intelligent balanced scheduling is realized, so that the situation that a single node is overloaded, and when user requests in a certain area are suddenly increased, the traffic can be quickly allocated to the low-load node, all requests can be responded in time, and the problem that the response is not timely in the prior art is solved; meanwhile, based on an edge computing architecture, traffic scheduling is dispersed to each edge node, requests are processed close to a user side, the data transmission distance and path are shortened, then traffic is reasonably distributed according to node states, network congestion is avoided, data waiting and queuing delay is reduced, and transmission delay is effectively reduced.

The invention relates to the technical field of network security protocols, in particular to a network communication information encryption transmission method and system, and the method comprises the following steps: collecting transmission delay and queuing delay, summing up to generate total delay, carrying out error normalization to form a delay redundancy mask, judging an interval, adjusting an encryption level and a key length, and carrying out encryption transmission. The method comprises the following steps of: constructing topological mapping in combination with node processing capacity and communication distance, allocating tasks by an HEFT algorithm, generating a node task table, generating a control factor by weighted average, optimizing encryption hierarchy and task allocation, and improving transmission safety and efficiency. Fluctuation is dynamically coped with, the encryption hierarchy and the key length are adjusted, task allocation is optimized in combination with the node capacity and the communication distance, the efficiency is improved through the HEFT algorithm, excessive or insufficient encryption is avoided through weighted average generation of control factors, and the transmission safety and efficiency are enhanced.

The application discloses a kind of power internet of things energy-saving communication methods for mass equipment, comprising the following steps: constructing power internet of things based on CF-NOMA edge computing;According to the signal-to-interference noise ratio model of device end, the device end data rate model is constructed;According to the device end local task processing energy consumption model and the total power consumption model of unloading task energy consumption model, the total power consumption model of system is constructed;Through the data rate model of all devices in the system and the total power consumption model of system, the objective function is constructed, and the constraint condition is constructed by combining the SIC decoding of CF-NOMA and the task queuing delay;With the maximum of objective function as optimization goal, optimize wireless resource block allocation vector, task segmentation vector, resource allocation vector, device end transmission beamforming vector, binary SIC decoding index, so that the system energy efficiency of power internet of things reaches maximum value.The application not only has wide application range, but also effectively reduces interference, reduces energy loss, and strengthens communication quality.

The application provides a self-adaptive event priority scheduling method and system, the method comprising: firstly listening to asynchronous events generated by a development environment and extracting waiting time, processor load and event urgency; then generating a weight vector online using a reinforcement learning algorithm, calculating event priority in real time according to the updated weight and inserting into a minimum heap queue; after the event is completed, using the queuing delay as reward feedback to update the decision network, thereby continuously optimizing the scheduling strategy under a dynamic load scenario. The application reduces the average queuing delay of high-urgency events from 270 ms to 165 ms, significantly improving real-time response capability. The application can be widely applied to IDE-AI auxiliary tools and DevOps pipelines.

The invention provides an end-network collaborative rate suggestion and adjustment method, and the method comprises the steps: obtaining multi-dimensional state data of a current to-be-processed queue under the condition that a sending terminal is determined to support a rate suggestion; the multi-dimensional state data comprises at least two of queue depth, queue delay and packet loss rate; calculating a congestion score based on the multi-dimensional state data, and generating a rate suggestion strategy based on the congestion score; and packaging the rate suggestion strategy to obtain a rate suggestion message. According to the method, the device and the electronic equipment provided by the invention, under the condition of determining that the sending terminal supports the rate suggestion, the congestion score is calculated based on the multi-dimensional state data which is acquired in real time and comprises at least two of the queue depth, the queuing time delay and the packet loss rate; and the rate suggestion strategy is generated based on the congestion score, so that the timeliness and the effectiveness of the generated rate suggestion strategy are improved, and the bandwidth utilization rate and the data sending performance of the sending terminal are further improved.