30 results about "Congestion management" patented technology

The invention discloses a congestion management system and method based on vehicle-road cooperation and dynamic group path optimization, and relates to the technical field of intelligent traffic systems. The method comprises the following steps: S1, collecting original traffic data through a multi-modal sensor array to carry out space-time alignment, and constructing a microscopic traffic flow data set; s2, bidirectional information interaction is carried out through a vehicle-road cooperative communication network; s3, calculating a multi-modal fusion confidence coefficient parameter based on the data quality index, and generating traffic state information and road section real-time saturation; s4, fusing historical and static road network data, constructing a dynamic digital twinborn model and a road network state feature map, and generating a road network load balancing index; and S5, making a decision by adopting a hierarchical-distributed architecture, and generating a group path induction strategy through multi-objective optimization. The efficient collaborative decision is realized through the graph convolutional network and the attention mechanism, and the road network traffic efficiency is comprehensively improved through stable and reliable multi-objective optimization on the premise of guaranteeing the user fairness.

The invention discloses an urban traffic flow prediction method fusing a graph attention network and a Transform, and belongs to the field of traffic flow prediction. The method comprises the following steps: (1) constructing an urban refined characteristic traffic flow high-quality data set based on actual license plate recognition (LPR) probe data; (2) building an efficient space-time traffic flow prediction model of a fusion graph attention network GAT and a Transform model; and (3) traffic flow prediction model training based on time-space fusion. According to the method, the traffic flow prediction model fusing the graph attention mechanism and the Transform is established, the space-time dependency relationship of the traffic flow in the urban complex road network is accurately described, the traffic flow prediction level under the urban complex road network is improved, and efficient data support is provided for intelligent traffic management, signal control optimization and urban congestion management.

The application relates to the technical field of data transmission, and discloses a congestion management method based on a novel network congestion announcement and rate adjustment strategy, which comprises the following steps: S1: constructing a flow statistical system for counting receiving rates and generating accurate congestion announcement data packets at a receiving end; S2: judging whether accurate congestion announcement data packets are generated for a specified queue pair according to statistical information of the system, and sending the accurate congestion announcement data packets to a specified sending end; and S3: constructing a rate adjustment system at the sending end, wherein the flow statistical system comprises a queue pair rate statistical module and an RDMA rate statistical module, and each RDMA network card port needs to contain an RDMA rate statistical module. In the application, the calculated statistical rate is carried in a 16-byte reserved field of a standard congestion announcement data packet, which is compatible with an existing RoCEv2 congestion management architecture, does not need an additional detection marking function provided by a data center switch, and is easy to deploy and expand.

The invention relates to the technical field of virtual power plants, and provides a virtual power plant-based congestion management and operation control method and system, and the method comprises the steps: obtaining the electric energy data of nodes and market participants in a power distribution network; determining a blocking management strategy when the blocking management cost is minimized according to the electric energy data through a blocking management optimization model; wherein the congestion management cost is defined as the sum of the total adjustment compensation cost for adjusting the available capacity of each market participant participating in the congestion management, the total output cost for enabling each reactive power compensation device participating in the congestion management of the power distribution network to output power for the congestion management, and the network loss cost of the power distribution network related to the congestion management; the congestion management strategy comprises a target regulation capacity of a market participant set and a target output of the reactive power compensation device; and executing a blocking management action according to the blocking management strategy. Therefore, congestion caused by the fact that the virtual power plant participates in energy transaction in the market is eliminated, and safety is guaranteed.

A substrate processing congestion management apparatus includes at least one processor configured to divide a process sequence of a substrate processing apparatus into specific sections and determine whether congestion occurs in the specific sections, to set an initial suspected region corresponding to a section in which the congestion occurs, analyze outliers in events occurring in the initial suspected region, deduce a final suspected region while updating the initial suspected region based on an event in which an outlier is identified, and determine, among the events, an event with a greatest contribution to the final suspected region as a congestion cause, and to notify the congestion cause and automatically control the substrate processing apparatus to reduce process congestion and improve substrate processing throughput, based on the determined congestion cause.

This invention relates to an optimal scheduling method and system for an electro-hydrogen coupling system based on truck flexibility and relaxation-repair warm-start technology. The method includes: acquiring basic data of the electro-hydrogen coupling system; constructing a power system model, a hydrogen energy system model, a pipeline congestion management model, and a hydrogen truck transportation model, wherein the pipeline congestion management model is a truck-based pipeline congestion management model that treats hydrogen trucks as flexible resources; establishing constraints and constructing an optimal scheduling model with the goal of minimizing the total system operating cost over the entire scheduling cycle; transforming the optimal scheduling model into a convex programming model using a mixed-integer second-order cone programming reconstruction technique; and solving the convex programming model using a relaxation-repair warm-start algorithm, considering the physical state information of the system, to obtain the optimal scheduling result. Compared with existing technologies, this invention has the advantages of actively alleviating pipeline physical congestion and high computational efficiency.

The present disclosure relates to converging to enable congestion management. A network interface controller (NIC) that facilitates incast management at a computing system is provided. During operation, the NIC can receive a request to send data from a remote computing system via a network. The NIC can determine that the request is one of a plurality of requests from a plurality of remote computing systems that are accessible via the network. Based on a descriptor in the request, the NIC can determine a storage location of the data at the remote computing system. Then, the NIC can determine a degree of congestion at the computing system associated with the plurality of requests. The NIC can schedule data retrieval in response to the request based on the degree of congestion and with respect to the plurality of requests. Then, the NIC can retrieve the data from the storage location based on remote access.

This invention belongs to the field of airport congestion management and time slot resource allocation technology, specifically involving a method and system for assessing airport flight capacity based on congestion cost. This invention constructs an airport flight capacity assessment method based on congestion cost to achieve closed-loop linkage optimization of airport time slot capacity calculation and multi-airline demand response. Compared with existing technologies, this invention achieves rolling online updates of time slot cost signals and demand adjustments through interactive modeling of upper-layer time slot management agents and lower-layer airline response agents; it improves solution efficiency and scalability by learning multi-agent strategies in parallel under a centralized training and distributed execution framework; and it enhances the executability and stability of congestion management strategies through state interaction embedding, thereby improving airport congestion mitigation and time slot resource utilization efficiency. This provides feasible algorithmic support and application paths for real-time demand control during airport tactical operations, filling a technological gap in related fields.

Embodiments of the present application provide systems, apparatus and methods for predictive congestion management using signals from packet sources. According to a method, a network element predicts future traffic loads by receiving signals from multiple packet sources that indicate the size and timing of incoming data flows. By analysing these signals, the network element forecasts potential traffic surges. Before the predicted traffic arrives, the network element takes preventive actions to manage the data load. By addressing potential overloads in advance, the method may allow for smooth and efficient network operation, maintaining stability and preventing congestion.

The invention discloses a power transmission congestion management partition pricing method and system considering dynamic topology recognition, and belongs to the field of power market operation and intelligent power grid control, and the method comprises the steps: obtaining real-time operation data and high-frequency synchronous measurement data, and recognizing a current operation mode fingerprint of a power grid through an unsupervised machine learning model; according to the method, the blocking section is analyzed based on the mode fingerprint, the evaluation result is generated in combination with the physical elastic margin, then the multi-target optimization algorithm with optimization of partition price distortion and partition internal physical elastic margin as targets is constructed, the dynamic partition set is solved and generated, and the optimal power flow is operated on the basis to calculate and generate the partition marginal electricity price. According to the method, a data-driven operation mode recognition and elastic safety coupling optimization mechanism is adopted, the market partition can be adaptively adjusted in real time, the economic value of physical limitation is accurately reflected, and the efficiency of power transmission congestion management and the robustness of power grid operation are improved.

The invention relates to the technical field of building digital design and construction management, and discloses a BIM-driven steel bar parametric modeling and blanking management and control system. The system comprises a data analysis module, a clustering fission module, a voxel construction module, a constraint solving module and an entity generation module, wherein the data analysis module is used for extracting BIM information to generate a steel bar path and establishing an inventory index; the clustering fission module generates a machining cluster based on homologous logic and fissions the end ultralimit steel bars; the voxel construction module establishes a three-dimensional voxel grid for maintaining a congestion state; the constraint solving module executes multi-dimensional constraint solving in a legal tolerance domain, and determines an optimal connection point meeting inventory matching and a space congestion target; and the entity generation module generates a three-dimensional entity, exports a processing instruction, updates a voxel grid state in real time, and reinjects excess material data into the inventory. According to the method, the voxel potential energy field and inventory coupling solution is adopted, and closed-loop management and control considering space congestion prevention and real-time excess material recycling are achieved.

A server accesses vehicle data from each connected vehicle (CV) of a subset of a plurality of CVs on a roadway portion, the vehicle data comprising at least one of: a position, a velocity, or a headway. The server generates, based on the accessed vehicle data, a long-term shared world model. The server generates, using the long-term shared world model, a data structure representing predicted future velocities on the roadway portion by position and time by applying a traffic flow model to the long-term shared world model. The server transmits, to a connected autonomous vehicle (CAV), a control signal for controlling operation of the CAV based on the generated data structure.

This application provides a vehicle congestion intelligent management method based on cloud computing spatiotemporal grid division. The method includes: acquiring real-time traffic flow information under different grids; detecting vehicle density in the real-time traffic flow information under different grids; and acquiring the current grid number; performing vehicle density detection based on vehicle travel direction on the highway under the current grid number; acquiring the latitude and longitude information of the highway under the current grid number; acquiring vehicle information under the latitude and longitude information of the highway under the current grid number; and intelligently managing vehicles when the vehicle type in the vehicle information does not meet the driving lane requirements, or when the vehicle speed in the vehicle information does not meet the driving speed required by the driving lane. This application improves the efficiency of intelligent congestion resolution on highways and saves vehicle travel time by acquiring information on vehicles causing congestion under specific latitude and longitude.

A system and method for reducing bottleneck queues in the Open Radio Access Network (O-RAN) architecture through classification of Packet Data Convergence Protocol (PDCP) and Radio Link Control (RLC) queues at the Centralized Unit-User Plane (CU-UP). The system analyzes and determines a category for the CU-UP PDCP queue for the Data Radio Bearer (DRB), x, at the CU-UP and analyzes and determines a category for the DU RLC queue for the DRB, x, at the CU-UP. If the Congestion Indicator indicates Congestion Experienced (CE) for this DRB in the RAN, the system at the CU-UP starts inserting CE in the IP packet header for packets going in the reverse direction towards the application source, which in turn will modify the rate of transfer based on the number and duration of CE received.

The invention discloses a method and a device for predicting electricity price of an electricity market. The method comprises the following steps: inputting preprocessed electricity price data of an electricity market into a QPSO-VMD data decomposition model to obtain a plurality of electricity price subsequences; respectively inputting the plurality of electricity price subsequences into a CNN-BiLSTM electricity price prediction model for prediction to obtain a prediction result of each electricity price subsequence; and performing precision evaluation on the prediction result of each electricity price sub-sequence to obtain an evaluation result. According to the invention, a promising decision support can be provided for power generation enterprise bidding strategy optimization, power selling company risk management and control and power grid congestion management, and the economic benefits and decision reliability of power market participants are significantly improved.

The invention relates to an RDMA (Remote Direct Memory Access) network congestion control method and system based on dynamic cache management. The method comprises the following steps: dividing a cache region into a global cache shared pool and a plurality of virtual dynamic queues in a switching unit; mapping incoming RDMA data streams to corresponding virtual dynamic queues through a Hash algorithm; monitoring the used depth of the virtual dynamic queue, and generating a congestion control cell which packages the ID of the virtual dynamic queue and a rate adjustment factor according to the used depth of the virtual dynamic queue; and transmitting the congestion control cell to a transmitting end, and accurately adjusting the rate of the corresponding data flow by the transmitting end according to the cell. The system comprises a data packet dynamic cache management module, a data packet marking and flow identification module and a congestion management module. The problems of PFC deadlock risk, head blockage and fairness existing in a data packet caching mode and congestion control of a traditional RDMA protocol network are solved, efficient and accurate congestion control is achieved, dependence on a PFC mechanism is reduced, delay is reduced, fairness is improved, and the throughput of the RDMA protocol network is improved.

The embodiment of the present application discloses a network congestion method and related device, which are used for controlling network congestion. The method of the embodiment of the present application comprises the following steps: a first network device sends a first rate value to a second network device; if an actual rate value is less than the first rate value, the first network device sends a second rate value to the second network device, and the second rate value is less than the first rate value.

The invention discloses a road network traffic state unified representation learning method. Comprising the following steps: acquiring multi-source traffic state data of a target area from a traffic perception system, and constructing a graph structure containing road nodes and traffic state attributes; designing a traffic network encoder based on the graph neural network, and extracting a semantic representation vector of each road node; designing a traffic environment encoder based on the full-connection neural network, and extracting a representation vector of each traffic environment combination; and constructing a positive sample pair and a negative sample pair according to a structural relationship between roads and traffic state similarity, defining and minimizing a comparison loss function, and performing comparison training on a traffic network encoder and a traffic environment encoder to obtain a unified traffic state semantic representation space. The method has remarkable advantages in the aspects of multi-source heterogeneous data fusion, traffic state space consistency modeling and semantic interpretability, and is widely applied to intelligent traffic application scenes such as traffic prediction, congestion management and data completion.

A piece of networking equipment facilitating efficient congestion management is provided. During operation, the equipment can receive, via a network, a plurality of packets that include portions of a data segment sent from a sender device to a receiver device. The equipment can identify, among the plurality of packets, one or more payload packets comprising payload of the data segment, and at least a header packet comprising header information of the data segment and a header-packet indicator. The equipment can determine whether congestion is detected at the receiver device based on a number of sender devices sending packets to the receiver device via the equipment. Upon determining congestion at the receiver device, the equipment can perform flow trimming by forwarding the header packet to the receiver device and dropping a subset of the one or more payload packets.

A system for congestion management using per data type packet queues in a virtual desktop infrastructure (VDI) includes maintaining one or more packet queues configured to buffer data packets for transmission through a single virtual channel for a call initiated using a VDI server at a client device. Each packet queue is associated with a data type and a congestion threshold. In response to receiving a first packet corresponding to a respective data type determining that a fill level exceeds a respective congestion threshold. In response to the determination a congestion state is set for the single virtual channel and a second packet selected from one of the one or more packet queues based on the congestion state and a respective data type is transmitted through the single virtual channel.

The invention discloses a congestion management method, electronic equipment, a storage medium and a program product, and belongs to the technical field of communication. The method comprises the following steps: sending a congestion detection packet to a source spraying node according to a preset detection period in response to the fact that the unused time of a target entropy marked as congestion exceeds a threshold value; the target entropy marked as congestion is at least packaged in the congestion detection packet, and the source spraying node determines a congestion spraying path of the congestion detection packet through the target entropy marked as congestion, and sprays the congestion detection packet based on the congestion spraying path; and in response to a detection response packet of the received congestion detection packet and a congestion mark in the detection response packet indicating that congestion does not exist, marking the target entropy marked as congestion as non-congestion, thereby improving the utilization rate of network resources.

Devices, systems, methods, and processes for incast congestion management are described herein. Typically, in a Packet Sequence Number (PSN) based Remote Direct Memory Access (RDMA) network, Priority Flow Control (PFC) is asserted upstream when an incast congestion event occurs, which can victimize unrelated flows. Thus, instead of asserting PFC, a switch in the PSN based RDMA network detects an incast congestion event and directly notifies one or more Reliable Connection (RC) Queue Pairs (QPs) of various sending devices, associated with the incast congestion event using Receiver Not Ready (RNR) negative acknowledgements (NACKs). These RNR NACKs are associated with unique pause time-periods. The associated RC QPs receive the RNR NACKs and pause packet transmission. The associated RC QPs resume packet transmission upon expiration of corresponding pause time-periods. Thus, the packet transmission from the contributing RC QPs is spaced out, avoiding all packets reaching a switch output port at the same time.

Systems and methods for robot congestion management are provided, the system comprising: a robot monitoring server configured to track positions of a plurality of robots within a navigational space; and a plurality of robots. The plurality of robots are in communication with the robot monitoring server, and each of the plurality of robots comprises: a processor; and a memory storing instructions that, when executed by the processor, cause the autonomous robot to: determine, from a task list assigned to the robot, a first pose position corresponding to a first task, receive, from the robot monitoring server, congestion information associated with the first pose position, identify a congestion state of the first pose position indicated by the congestion information, in response to the identification of the congestion state, select a second task from the task list, and navigate to a second pose position corresponding to the second task.

The invention discloses a network live broadcast content monitoring system and method based on a mixed playing mode, and relates to the technical field of network live broadcast content monitoring, and the system comprises a plurality of network live broadcast content monitoring platforms which are dispersedly deployed in a communication network and are used for monitoring network live broadcast content in real time; the multicast tree construction module constructs a multicast tree taking a live broadcast source as a root according to network topology and bandwidth requirements; the monitoring platform selection module selects a target monitoring platform based on the number of the additional links so as to realize real-time monitoring by monitoring a transmission path; the congestion management module maintains a congestion set, periodically reselects a target monitoring platform and constructs a monitoring transmission path, and sends the target monitoring platform and the monitoring transmission path to the monitoring platform selection module. According to the invention, the congestion can be periodically adjusted and relieved, and the monitoring efficiency and reliability can be guaranteed with low bandwidth consumption in a multicast and anycast mixed mode.

This application discloses a traffic management method, apparatus, equipment, and storage medium, relating to the field of data processing technology, for predicting and timely managing traffic congestion. The method includes: acquiring basic traffic data for multiple roads; determining the throughput of each road based on average vehicle speed and the number of vehicles passing per unit time; dividing the multiple roads into multiple road sets based on the throughput of each road, with different sets corresponding to different throughput ranges; determining the boundaries of roads included in different road sets; acquiring target influencing factors in the road network at each boundary that cause traffic congestion with an impact greater than or equal to a threshold, inputting the target influencing factors into a prediction model, determining the predicted road congestion level corresponding to each target influencing factor, and determining a congestion management strategy corresponding to each target influencing factor based on the predicted road congestion level.

The invention discloses an evaluation method and system based on a congestion control scheme of a toll station and electronic equipment, and the method comprises the steps: obtaining control parameters of the congestion control scheme of a target toll station, and determining an evaluation range; a multi-level evaluation index system is constructed based on the management and control parameters, the multi-level evaluation index system comprises a plurality of first-level evaluation indexes, and each first-level evaluation index comprises at least one second-level evaluation index; collecting traffic operation data by using a traffic detector, and calculating a secondary evaluation index quantized value; distributing index weights for the first-level evaluation index and the second-level evaluation index to construct a dynamic fuzzy comprehensive evaluation model; obtaining a membership function of each secondary evaluation index corresponding to a plurality of evaluation grades, and calculating the membership; and performing step-by-step evaluation on the membership degree to generate an evaluation result of the congestion management and control scheme. According to the method, the evaluation range is defined, a multi-stage targeted evaluation index system is constructed, and a dynamic fuzzy comprehensive evaluation model is introduced, so that scientific quantitative evaluation of the toll station congestion control scheme is realized.

One or more computing devices may comprise congestion management circuitry, one or more client file system request buffers, and DESS interface circuitry. The congestion management circuitry is operable to determine an amount of congestion in the DESS. The one or more client file system request buffers is / are operable to queue first client file system requests of a first priority level and second client file system requests of a second priority level, wherein the first priority level is higher priority than the second priority level. The DESS interface circuitry is operable to control a rate at which the first file system requests and second file system requests are fetched from the one or more client file system request buffers based on the amount of congestion in the DESS, on the first priority level, and on the second priority level.

A system for Remote Direct Memory Access incast congestion management is provided. The system may access one or more receive work queue entities (RWQEs) associated with one or more send work queue entities (SWQEs), determine a transmission rate based on an available bandwidth and a number of transmitter devices associated with the one or more SWQEs, and transmit a rate control notification (RCN) message to a transmitter device associated with a send work queue entity of the one or more SWQEs, wherein the rate control notification message comprises the determined transmission rate.

In one implementation, congestion in a satellite communications network is managed based on current resource usage information received for a primary satellite servicing a terminal that is requesting to initiate a communications session. The current resource usage information is received within a communications session setup procedure that identifies a type of the communications session being requested by the terminal. Resources for serving the communications session are determined based on the type of the communications session being requested by the terminal. Thereafter, a determination is made as to whether sufficient resources are available at the primary satellite for servicing the communications session. In response to determining that sufficient resources are not available at the primary satellite for servicing the communications session, a congestion mitigation strategy is determined for servicing the communications session and sent to the primary satellite for implementation.

The present application relates to the technical field of edge computing architecture, and more particularly to an edge computing method and system capable of realizing direct exchange of remote memory data, in the FPGA of a heterogeneous processing unit, innovative integration of key components such as a hardware RoCE v2 RDMA engine, a high-speed memory pool, a reconfigurable calculator, and a flow control and congestion manager, with the aid of a QDMA IP core, a high-speed PCIe data channel is constructed with an edge inference module containing a CPU, a GPU and an AI accelerator, overcoming the disadvantages of low system integration and heavy hardware dependence of traditional RDMA solutions, realizing efficient collaboration of computing acceleration and RDMA function, at the same time, the problem of limited on-chip resources in large-scale connection scenarios can be solved, ensuring stable and efficient data transmission, supporting preprocessing when data flows, deeply integrating with AI inference, breaking the separation pattern of computing and communication, and having strong flow control and scheduling capabilities.