72 results about "Congestion detection" patented technology

The invention provides an intelligent traffic decision-making method based on multi-source sensor data, and the method comprises the steps: obtaining vehicle sensor data and road information, and obtaining a standardized traffic flow feature vector through data synchronization, fusion, feature extraction and dimension reduction processing; inputting the standardized traffic flow feature vector into a traffic flow prediction model, and predicting the traffic flow through a vehicle dynamics model constraint state transition matrix; according to the predicted traffic flow and the real-time road condition information, the road congestion state is judged, and a real-time congestion map is generated; in combination with the real-time congestion map, the road network speed limit rule and the starting and ending point position information, an optimal path is planned, and path smoothing processing is performed through a driving behavior mode; and constructing a vehicle intelligent decision-making system, integrating traffic flow prediction, congestion detection and a path planning model, and outputting a vehicle driving strategy according to real-time vehicle sensor data.

Provided are a method, system, and apparatus for adjusting the bitrate for video streaming may be provided. The method may include: determining whether there is network congestion for a packet based on whether a filtered cell quality indicator provided from a Media Access Control (MAC) Scheduler is lower than a cell quality indicator threshold value, based on whether a scheduling queue delay of a User Equipment (UE) is greater than a queue delay threshold value, or based on UE Assistance Information (UAI) reported by a user equipment (UE); based on a determination that there is network congestion: setting an explicit congestion notification (ECN) bit in an IP packet header and setting the congestion state of a user IP to true; sending the packet; and applying adaptive bitrate to adjust a quality of a video stream based on the congestion state

Methods and apparatus for providing L4S support with regard to non-3GPP untrusted / trusted accesses in which a user equipment (UE) is enabled to monitor for uplink and / or downlink congestion with regard to L4S uplink data traffic flows at the UE, detect congestion, and perform explicit congestion notification (ECN) markings or communicate congestion information to perform ECN marking to another device are described. In some embodiments, the UE device indicates detected congestion, at the UE, in an uplink (UL) traffic flow via performing ECN marking of an innermost IP header ECN field. In some other embodiments, the UE device communicates detected congestion information, via a GRE message to a core network interface device, which communicates, via GTP-U, the detected congestion information to a UPF, which then uses the received UE detected congestion information to performs ECN marking in the innermost IP header of an uplink data packet.

The invention discloses an intelligent optimization and resource dynamic redistribution method and system based on a graph neural network. The method comprises the steps of data acquisition and modeling, network topology feature extraction, congestion detection and prediction, data flow redistribution and intelligent optimization, and real-time monitoring and feedback mechanism. According to the invention, real-time modeling and intelligent optimization of a network topology structure and a data flow are realized through the graph neural network model, so that a potential congestion area can be accurately identified and positioned; in combination with a flow redistribution strategy of a maximum entropy principle, the system can dynamically adjust the distribution of data streams and resources, relieve congestion and improve the overall transmission efficiency; by introducing an improvement rule of cascade failure, secondary congestion caused by failure of the congested nodes is effectively prevented, and the stability of the network is enhanced.

The congestion control method comprises the following steps: a data packet monitoring module captures and monitors a transmitted data packet in real time, and obtains data packet information; the congestion detection module detects the data packet information according to a preset congestion detection algorithm, judges the congestion condition of the network, and sends a judgment result to the congestion control module; the congestion control module performs congestion control based on a window flow control mechanism and a priority scheduling algorithm; the congestion feedback module sends congestion feedback information to the sending end server, and the sending end server adjusts a sending rate and congestion control parameters according to the congestion feedback information to form closed-loop control; and the adaptive adjustment module adjusts the parameters of the congestion control module based on the change of the network state. According to the method and the device, the captured data packet information is detected, the congestion condition of the network is judged, and congestion control is performed through a window flow control mechanism and a priority scheduling algorithm, so that network congestion is effectively avoided, and high efficiency and stability of data transmission are ensured.

The present application relates to devices and components including apparatus, systems, and methods for detecting congestion in wireless networks.

Methods and apparatus for providing L4S support with regard to non-3GPP untrusted / trusted accesses in which a core network interface device, e.g., N3IWF or a TNGF, is used are described. The core network interface device monitors for downlink and / or uplink congestion with regard to L4S downlink and / or uplink data traffic flows, detects congestion and perform explicit congestion notification (ECN) markings or communicates congestion information used in performing ECN marking to another device. In some embodiments, the core network interface device indicates detected congestion, at the core network interface device, in a DL traffic flow via performing ECN marking of the innermost IP header ECN field. In some other embodiments, the core network interface device communicates detected congestion information to other devices. Sometimes the congestion information is communicated via a GTP-U header to a UPF, which performs ECN marking based on the received non-3GPP congestion information.

An example process may detect capacity breaches in an area of interest (AOI) of an open radio access network (RAN). Data is queried for cells in the RAN network over a sampling period to retrieve hourly-traffic data for the cells. Outliers may be removed from the hourly-traffic data for the cells. In the trimmed hourly-traffic data, top-download-traffic hours are identified on different days in the sampling period for each of the cells. The example process may include aggregating the trimmed hourly-traffic data for each of the cells at the top-download-traffic hours to generate busy-hour indicators for each of the cells and busy-hour indicators for sectors associated with cells. The busy-hour indicators may be extrapolated using subscriber growth in the AOI to generate forecast indicators for each of the cells and for the sectors associated with the cells. The forecast indicators are compared to capacity thresholds to forecast capacity breaches.

The application relates to devices and components including apparatuses, systems, and methods for detecting congestion in a wireless network.

The invention discloses a traffic jam detection and early warning method based on an unmanned aerial vehicle video stream, and belongs to the technical field of intelligent traffic. The system is combined with a floating vehicle triggering model, collects road videos in real time through an unmanned aerial vehicle, and realizes high-precision vehicle detection and tracking in combination with improved YOLOv8 and DeepSort algorithms; unmanned aerial vehicle data and floating vehicle GPS data are fused, three elements of traffic flow are quantified, and a dual-mechanism congestion detection model is constructed; respectively utilizing a GRU cooperative traffic wave theory to predict the congestion dissipation duration and utilizing an improved GRU + GCN model to predict the traffic situation; the signal lamps are dynamically regulated and controlled through multi-agent reinforcement learning, and active congestion relieving is achieved. The method has the advantages of wide-area coverage, high-precision perception and intelligent response, and the urban traffic control efficiency is remarkably improved.

The invention relates to the technical field of congestion detection and solution of a high-performance network-on-chip, and relates to a congestion detection and self-adaptive control method and system of a 2D (two-dimensional) network-on-chip (NoC). The method comprises the following steps: based on a 2D mesh NoC topology, generating a data packet injection rate of each node by using a Poisson distribution flow model, and modeling and recording a buffer load value and an arbitration waiting request number through an NoC simulator; classifying nodes according to node centrality annular distribution characteristics, and initializing a threshold register value; when congestion control is input, an input blocking index is periodically calculated, and a threshold value register is dynamically adjusted according to a threshold value; a congestion control path is output, a data packet is redirected when an output busy signal is activated, and a new request is blocked if all output ports are busy; through off-line estimation optimization and on-line detection adjustment, NoC congestion is effectively solved, and system performance and reliability are improved.

An example process may collect performance data from a cell site of an open radio access network (RAN) in an area of interest (AOI). The cell site may include sectors and the sectors comprising cells. Busy-hour indicators may be determined based on the performance data from the cell site. The busy-hour indicators may be determined by applying a percentile method to outliers in the performance data. A subscriber growth model in the AOI can be forecast for a forecast period. The busy-hour indicators can be extrapolated using the subscriber growth model to generate forecast indicators for the forecast period. A gain function can be applied to the forecast indicators to generate revised forecast indicators. A capacity breach at a cell or a sector of the cell site in the AOI can be detected in response to an indicator from the revised forecast indicators exceeding a capacity threshold.

Example systems, processes, and articles of manufacture tend to detect capacity breaches in an area of interest (AOI) of an open radio access network (RAN). An example process includes generating a subscriber growth model in the AOI of the RAN, querying data for cells in the AOI of the RAN over a sampling period, and of extrapolating the data using the subscriber growth model to generate forecast indicators for the cells and for sectors associated with the cells. The forecast indicators are compared to capacity thresholds to forecast sector capacity breaches at the sectors. The process may also include forecasting a virtual distributed unit (vDU) capacity breach in response to forecasting the sector capacity breaches, forecasting a virtual central unit (vCU) capacity breach in response to forecasting the sector capacity breaches, and identifying a capacity expansion in response to the vDU capacity breach or the vCU capacity breach.

The invention provides a congestion control method and device, switching equipment, a medium and a readable storage medium, and is applied to the field of communication. The method comprises the following steps: in response to a received back pressure signal sent by downstream equipment, determining a first congestion value of at least one data packet according to attribute information of the data packets in a first port queue; determining a second congestion value of at least one data stream corresponding to the at least one data packet according to the first congestion value and the priority; under the condition that a target data stream with a second congestion value meeting the congestion condition exists in the at least one data stream, switching a port queue used for forwarding a data packet corresponding to the target data stream from the first port queue to a second port queue; and sending the early warning event to a detection server, so that the detection server controls the rate of sending the data packet corresponding to the target data stream by the upstream equipment according to the congestion detection result for the target data stream under the condition that the detection server forwards the data packet corresponding to the target data stream through the second port queue.

The invention relates to the technical field of intelligent traffic, and provides an expressway congestion detection method and system and a computer, and the method comprises the steps: obtaining an expressway monitoring video, building a plurality of vehicle bounding boxes, and obtaining the historical trajectory data of a plurality of vehicles; linear fitting is carried out on the historical trajectory data of the vehicle, and the vehicle driving direction of the to-be-detected vehicle is determined; determining a first detection point and a second detection point in the vehicle bounding box; acquiring an uplink statistical line coordinate and a downlink statistical line coordinate, and counting the number of uplink vehicles and the number of downlink vehicles; and setting a time window, determining a plurality of detection frame images, and obtaining a congestion condition. Through the method, the driving direction of the to-be-detected vehicle is analyzed, the statistical accuracy of passing vehicles is improved, and whether congestion exists or not can be judged in real time.

The invention discloses a secure data transmission method based on multi-thread control, and relates to the technical field of network information security, and the method comprises the following steps: extracting a sensitivity identifier from a data packet header, adopting a lookup algorithm to match a preset sensitivity grading table, dividing data into a high-sensitivity type, a medium-sensitivity type and a low-sensitivity type, determining a priority queue distribution proportion according to the sensitivity, obtaining an initial flow shaping parameter, obtaining current network flow data according to the initial flow shaping parameter, analyzing a preset congestion detection threshold value and a historical transmission record, judging a network congestion degree by adopting a token bucket algorithm, and if the congestion degree is higher than the preset congestion detection threshold value, sending the current network flow data to the priority queue; if yes, the token generation rate of the high-sensitivity data is adjusted, and an adjusted traffic shaping strategy is obtained; according to the secure data transmission method based on multi-thread control, the network transmission efficiency can be effectively improved while the data security is ensured, and the method is particularly suitable for a complex network environment in which data with different sensitivities needs to be processed at the same time.

The invention provides an end-network cooperative rate control method based on explicit congestion notification, a medium and equipment, and belongs to the field of RDMA rate control. According to the control method, the buffer area of the RLC layer of the gNB serves as a congestion detection point, the queue length of the RLC layer is detected, whether congestion response needs to be made or not is determined according to the queue length, and the congestion response is that a CNP message is actively generated on the gNB and returned to the RH. The RH slows down when receiving the CNP message; the RH updates the congestion feedback coefficient alpha when not receiving the CNP message for a long time; the RH is provided with two counters ntime and nbytes, and the RH is accelerated when any one of the two counters is updated. According to the method, the operation of returning the CNP is directly carried out on the network node sensing the network congestion point, so that a wireless link with long propagation time delay is avoided; and the link data volume is always kept to be up and down fluctuation of the bandwidth delay product, and the congestion influence is reduced to the minimum.

The invention discloses a mixed domain AI high-performance network flow congestion suppression control method, which relates to the technical field of computer networks, and comprises the following steps: a congestion detection step: introducing data packet transmission round-trip time and a switch queue length as congestion detection signals, and a switch queue length management coefficient lambda and a data packet transmission round-trip time management coefficient theta are set. The method comprises the following specific steps: acquiring the current queue length Q of the switch, the data packet round-trip time RTT and the reference round-trip time baseRTT; and when the switch queue length Q is less than the queue length lower limit Kmin or greater than the queue length upper limit Kmax, calculating the data packet congestion marking probability P according to a formula. According to the invention, on the basis of the ECN, RTT indexes which can be collected without special support of network equipment are introduced as congestion detection signals together, and Q and RTT management coefficients are set, so that the response sensitivity of the network to congestion is further improved.

One or more aspects of the present disclosure relate to detecting and mitigating congestion in a storage area network. In embodiments, peer congestion Fabric Performance Impact Notification (FPIN) messages can be used to infer congestion on a target port that has not received a direct congestion FPIN. Upon receiving a peer congestion FPIN for a target port, the embodiments determine if the target port received a direct congestion FPIN. If not, the embodiments infer congestion on the target port based on the peer notification. The embodiments then control messaging to the congested port to mitigate the congestion, such as by adjusting bandwidth limits. This approach enables congestion detection and mitigation even when severe congestion prevents the delivery of direct notifications to the affected port. Accordingly, the embodiments leverage existing FPIN infrastructure and connectivity information to provide a simple, standards-based solution for identifying and addressing congestion issues in storage networks.

The application provides a vehicle congestion detection method and system based on multi-source data fusion, equipment and medium, belonging to the field of vehicle congestion detection. The method comprises the following steps: acquiring visual perception data, vehicle positioning data and terminal service instruction data, and mapping to construct a multi-source fusion object; constructing a dynamic operation mask to verify the legality of the multi-source fusion object; removing functional blocking objects; performing logical conflict judgment on the remaining multi-source fusion objects after verification, and marking objects with physical state of static and service intention indication of driving, idle non-parking or operation timeout retention as abnormal retention nodes; calculating node clustering density and tail reverse spread rate, confirming congestion situation and outputting detection results. The vehicle congestion detection method and system based on multi-source data fusion, equipment and medium provided by the application fuse service instructions and physical perception, and accurately distinguish functional blocking from pathological congestion based on logical conflict.

Methods and apparatus for providing L4S support with regard to non-3GPP untrusted / trusted accesses in which a core network interface device, e.g., N3IWF or a TNGF, is used are described. The core network interface device monitors for downlink and / or uplink congestion with regard to L4S downlink and / or uplink data traffic flows, detects congestion and perform explicit congestion notification (ECN) markings or communicates congestion information used in performing ECN marking to another device. In some embodiments, the core network interface device indicates detected congestion, at the core network interface device, in a DL traffic flow via performing ECN marking of the innermost IP header ECN field. In some other embodiments, the core network interface device communicates detected congestion information to other devices. Sometimes the congestion information is communicated via a GTP-U header to a UPF, which performs ECN marking based on the received non-3GPP congestion information.

The invention discloses a cross-regional edge node congestion collaborative early warning method based on federated learning. The method comprises the steps of data set construction, federated learning framework initialization, local model training, global model aggregation, congestion detection and congestion early warning. The invention relates to the technical field of cross-regional edge network intelligent monitoring, in particular to a cross-regional edge node congestion collaborative early warning method based on federated learning, which comprises the following steps of: initializing a sequence model at an edge node, constructing local loss combined with binary cross entropy and time sequence smooth punishment, and stably training by Adam and early stop; through weighted average aggregation disturbance parameters based on data volume and loss, performance degradation after fusion is prevented by adopting momentum fusion and a rollback threshold value; and meanwhile, an attention mechanism is embedded to realize joint prediction of probability, severity and duration, cross-regional propagation parameters of the graph neural network are utilized, loss is verified, and invalid sharing is rejected, so that prediction accuracy and timeliness are improved, and node congestion is effectively relieved.

The invention relates to the technical field of highway congestion intelligent detection, and discloses a video AI technology-based highway congestion intelligent detection system, which comprises a video tracking module, a congestion analysis module and a scheduling processing module, and is characterized in that the video tracking module comprises a video data acquisition unit, an error evaluation unit and a source tracking unit; the congestion analysis module comprises a congestion analysis unit and a comprehensive evaluation unit. The scheduling processing module carries out scheduling processing on the video tracking module and the congestion analysis module. According to the system, data are collected in real time through the video tracking module, a congestion source is positioned, meanwhile, the equipment state is monitored, the congestion analysis module is combined with multi-dimensional data to generate a congestion severity coefficient, a quantitative basis is provided for decision making, and the scheduling processing module uniformly coordinates all the modules, so that the advantages of real-time response, high precision, high expandability and the like are achieved, and the system is suitable for popularization and application. The highway traffic efficiency can be obviously improved, the management cost is reduced, and the influence of congestion on the society is reduced.

The invention discloses a computing power network bandwidth estimation method, relates to the technical field of bandwidth estimation, and solves the technical problem that an available bandwidth estimation method which is high in precision, low in delay and high in adaptability is needed urgently to meet the strict requirement for network transmission efficiency in a cloud game / cloud electronic sports scene. The method comprises the following steps: acquiring an RTCP feedback frame of a video stream, and respectively carrying out bandwidth sampling, congestion detection and link capacity detection according to the RTCP feedback frame to obtain current bandwidth sampling data, congestion signals and link capacity; correcting the bandwidth sampling data according to the link capacity to obtain current bandwidth data; if congestion is generated, iteratively calculating the current available bandwidth from the sending end to the receiving end through a congestion signal; and if the congestion is not generated, iteratively calculating the current available bandwidth from the sending end to the receiving end through the bandwidth data. The method can improve the utilization rate of bandwidth, reduce delay and be suitable for various scenes.

The invention provides a congestion detection method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of flow analysis. According to the method, the original link data is logically split according to the to-be-detected special line, and a technical path from fine-grained sampling to macroscopic portrait evolution is constructed by combining periodic congestion detection and cross-period aggregation analysis. According to the method, not only is the perception capability of micro burst congestion improved, but also the automatic identification of the congestion time period and the main liability flow thereof is realized in a systematic mode, and more comprehensive and operable insight is provided for network performance management.

The application discloses a kind of based on the naming data network hop-by-hop congestion control method of forwarding path number, including router congestion detection and router congestion control;Router calculates the congestion degree of local router by means of active queue management method.Routers determine local congestion state and update the congestion information of data packet.Downstream adjacent router is based on the number of forwarding path and executes multipath forwarding strategy or interest packet sending rate adjustment strategy.When router executes multipath forwarding strategy, the router calculates the shunt proportion of interest packet flow of current interface according to the congestion information of data packet and forwards flow through current or relatively suboptimal interface.When router executes interest packet sending rate adjustment strategy, the router adjusts the interest packet sending rate of same name prefix according to the congestion information of data packet.The application proposes two router control strategies for the characteristics of multiple-source multipath transmission of named data network, to cope with single-path flow and multi-path flow in network.

The application discloses a large-scale multi-mode traffic parallel simulation method and system based on CPU and GPU, relates to the technical field of traffic control, and comprises the following steps: acquiring traffic road networks to be simulated and multi-mode traffic demand data, dividing the traffic road networks to be simulated and the multi-mode traffic demand data based on a preset dynamic spectrum division algorithm to obtain a multi-mode traffic network division result; performing dynamic congestion detection and information feedback processing on the multi-mode traffic network division result based on a preset cross-process congestion feedback algorithm and an MPI communication optimization strategy to obtain congestion state information; inputting the congestion state information into a pre-established microscopic traffic intelligent agent model to perform microscopic behavior parallel calculation, and outputting microscopic behavior data based on the limitation of a regionalized Bucket communication mechanism; and performing simulation processing based on the microscopic behavior data to obtain a final traffic parallel simulation result, so that the simulation precision and efficiency are significantly improved.

The embodiments of the present application disclose a lane congestion detection method, device, electronic device, and storage medium, wherein the method specifically includes: obtaining real-time video stream data in a target monitoring scenario, and determining a driving road focus area map in the target monitoring scenario based on the video stream data; determining an optical flow matrix corresponding to the driving road focus area map based on the video stream data and the driving road focus area map, in combination with a pre-trained optical flow extraction neural network model; determining a segmentation result feature map of the road idle area and the road occupied area in the target monitoring scenario based on the video stream data, in combination with a pre-trained semantic segmentation neural network model; and determining a road congestion detection result based on the optical flow matrix and the segmentation result feature map using a pre-trained congestion detection model. The embodiments of the present application detect road congestion results based on two feature indicators, the optical flow matrix and the segmentation result feature map, thereby improving the accuracy of the road congestion detection results.

The application relates to a congestion detection method, device, system, cloud server and storage medium. The method comprises the following steps: obtaining first road condition information in a non-shielding area and second road condition information in a shielding area reported by a first roadside device in a target road section; the second road condition information is obtained by the first roadside device from a second roadside device located in the shielding area; the first roadside device is located in the non-shielding area; and the congestion condition of the target road section is obtained according to the second road condition information and the first road condition information. The application improves the accuracy of congestion detection.

The present application discloses a method, apparatus, device, and storage medium for detecting transient congestion on a chip. The method comprises: obtaining the resource occupancy rate of a chip port queue; judging whether the port queue meets a preset transient congestion capture condition based on the resource occupancy rate; when the transient congestion capture condition is met, triggering a preset capture engine to enter a transient congestion capture state, capturing transient congestion event information of the port queue; and storing the captured transient congestion event information. The transient congestion detection method provided by the present application can capture and record transient congestion events within a very short duration of transient congestion, and the solution can be applied to extremely fine detection granularity of port queues, facilitating subsequent analysis and reducing the impact of transient congestion traffic on network and application performance.