1452 results about "Traffic volume" patented technology

The invention provides a sequential network traffic prediction method and system based on swarm intelligence parameter optimization, and relates to the technical field of network traffic prediction. The method comprises the following steps: acquiring indexes such as throughput packet loss rate and round-trip delay of a target link by using a network probe, and performing deletion filling normalization and multi-scale decomposition to obtain a standardized traffic sequence; calculating information entropy, constructing a traffic complexity feature vector, and dividing a training set and a verification set; constructing a hybrid depth prediction model composed of a one-dimensional convolutional network and a gating cycle unit, and establishing a hyper-parameter search space; using particle swarm optimization and entropy-driven inertia weight adjustment and mutation probability mapping to reconstruct a speed and position updating strategy, and iteratively outputting a global optimal hyper-parameter; and generating a benchmark prediction result according to full-amount training, extracting a residual error, training a nonlinear residual error compensation model to carry out superposition correction and reverse normalization, obtaining a final flow prediction result, and improving prediction precision and generalization ability.

The invention discloses a bus and station interactive scheduling method and system based on V2X and deep reinforcement learning decision, a medium and equipment, and the method comprises the steps: collecting bus operation dynamic data, station passenger flow and environment data in real time, and combining V2X network interaction information to construct a full-dimension perception system; a deep reinforcement learning model is adopted for dynamic decision making, intelligent closed-loop control of vehicle scheduling, station service and traffic signal cooperation is achieved, the bus punctuality rate is remarkably increased, the waiting time of passengers is shortened, operation safety is guaranteed through active early warning of abnormal conditions, and intelligent upgrading of a bus system from passive response to active prevention is achieved.

The invention relates to the technical field of multi-modal behavior anomaly detection scheme design, in particular to a multi-modal behavior anomaly detection method and system under the condition that encrypted traffic is not decrypted. The method comprises the following steps: capturing a network encrypted traffic data packet in real time; on the premise that decryption is not carried out, multi-mode non-decryption features such as flow layer statistics, time sequence interaction, encryption handshake and context association are extracted in parallel; establishing a dynamic normal behavior baseline model of each feature based on historical data; the real-time features are compared with the baseline model, comprehensive judgment is carried out through a multi-mode correlation analysis algorithm, and an anomaly detection result is output; and when the abnormal condition is judged, the network control equipment is automatically linked for blocking. The method thoroughly gets rid of dependence on traffic decryption, realizes high-precision and self-adaptive detection and rapid automatic response to abnormal behaviors in encrypted traffic through multi-dimensional feature fusion and dynamic baseline technologies, and effectively solves the problem of failure of a traditional detection technology in an encrypted environment.

The invention provides a system abnormity intelligent diagnosis and recovery method and system fusing time sequence logs, and relates to the field of distributed system operation and maintaining.The method comprises the steps that operation logs are collected from a plurality of service nodes of a distributed system, time sequence alignment is conducted, and calling relation and performance measurement data are extracted; time sequence change features are calculated in the sliding time window, dynamic feature vectors are generated through fusion coding, and a cross-service time sequence association graph is constructed; identifying an abnormal service node and matching the abnormal service node with historical fault data to obtain a historical propagation path and a feature vector; calculating a propagation convergence coefficient and a characteristic deviation degree based on a historical propagation path to obtain a causal intensity score; and identifying a fault influence degree according to the score, and adaptively adjusting a resource isolation and flow scheduling strategy. According to the invention, accurate diagnosis and efficient recovery of distributed system faults are realized.

The invention discloses a global dynamic perception space-time traffic flow prediction method based on graph packet representation learning, and belongs to the technical field of traffic flow prediction, and the method comprises the following steps: S1, traffic data input, S2, traffic graph packet construction, S3, graph packet initial feature extraction, S4, time sequence feature extraction, S5, spatial feature extraction, and S6, traffic flow prediction and output. Through a space-time modeling technology of graph packet representation learning and global dynamic perception, space-time characteristic elements of a traffic road network can be comprehensively covered, traditional traffic indexes such as flow and speed are concerned, elements such as road network topological association and cross-regional multi-hop association are also included, a dynamic dependency relationship between a time sequence and a spatial dimension is deeply mined, and a real-time dynamic perception effect is achieved. Therefore, the prediction result can reflect the real evolution law of the traffic flow more accurately, and a more scientific basis is provided for traffic management and decision making.

The invention discloses a multi-level interconnection network based on real-time flow monitoring and dynamic priority adjustment. A multi-dimensional traffic sensing model is constructed through traffic intensity, queue depth, congestion signals and static priority dynamic indexes. A dynamic urgency value is generated by adopting a configurable weighting strategy, and a three-mode closed-loop optimization mechanism is designed. A layered interconnection structure is adopted, crossbar switches are used in computing clusters, and the computing clusters are connected through a low-diameter routing network. In a cluster gateway, a dynamic arbitration unit monitors the flow intensity in real time, calculates the urgency degree in combination with a queue state and a global congestion signal, and dynamically selects a fixed priority and a weighted polling or polling arbitration strategy. The problem that the resource utilization rate of a traditional static arbitration mechanism is reduced due to task switching is effectively solved, the risk of fairness imbalance in a mixed key data flow scene is effectively solved, and the communication adaptation capacity of a reconfigurable architecture to diversified computing loads is improved.

The invention discloses a dynamic base station dormancy / wake-up method based on a flow load and a channel state, which improves the accuracy and reliability of dormancy and wake-up judgment by comprehensively considering multi-dimensional factors such as a service load, a wireless channel state, user distribution, adjacent region bearing capacity and the like. By designing a multi-level dormancy and wake-up mechanism and combining flexible management of different functional modules, reasonable balance between energy consumption reduction and service continuity is realized; by introducing a neighbor cell cooperation mechanism and a pre-wake-up strategy, the wake-up time delay is shortened while the coverage and switching stability are maintained. Meanwhile, key indexes such as energy consumption, access time delay, offline rate and switching success rate are continuously monitored in the operation process, and the feedback information is used for dynamically optimizing parameters such as criterion weight, threshold value and residence time. Through a closed-loop adjustment mechanism, the system can keep stable and effective operation in different scenes, and long-term balance between energy-saving control and service performance is realized.

The invention relates to the technical field of intelligent traffic and Internet of Vehicles, in particular to a traffic and air pollution bidirectional coupling flow prediction method based on double-path dynamic fusion. Comprising the following steps: collecting traffic flow and air pollutant concentration data, and carrying out space-time alignment and reversible instance normalization; the data is divided into two branches, the first branch extracts time-dependent features through gated convolution and probability sparse self-attention, and the second branch obtains variable interaction features through dimension remodeling, context extraction and reversible coupling transformation; bidirectional feature interaction is carried out through cross attention, weights are dynamically generated based on channel attention, and residual connection is carried out after weighted fusion; and performing linear mapping and inverse normalization on the fused features to obtain a traffic flow predicted value. According to the method, the prediction precision and robustness in a pollution sensitive scene are remarkably improved.

The invention discloses an interface request flow dynamic control method and device, a terminal and a medium, and relates to the technical field of the Internet, and the scheme provided by the invention enables a flow control strategy to reflect the actual processing capability of a server in real time by establishing the dynamic association between a flow limiting threshold and a resource state. By analyzing the relationship between the resource utilization rate and the request processing capacity, it is found that higher request processing capacity is allowed in the idle state of the resources, and the processing threshold should be reduced when the resources are nearly fully loaded. A linkage mechanism of a flow pressure index and resource capacity scheduling is further considered, when the flow pressure exceeds a preset interval, an elastic capacity expansion and contraction operation is triggered, cooperative closed-loop control of flow limiting and capacity expansion is achieved, and a flow limiting threshold value and the resource capacity form dynamic matching.

The invention discloses a client multi-service dynamic flow limiting regulation and control method, device and equipment and a medium, and relates to the field of artificial intelligence, and the method comprises the steps: calculating the priority score of a plurality of services of a client based on a plurality of preset priority dimensions and corresponding weights, and dividing each service to a corresponding priority level according to the priority score; dividing the total flow limiting quota of the downstream interface into a guarantee quota pool and a floating quota pool; predicting request traffic of each service in a specified time window in the future based on the historical data; and based on the predicted request flow, the current system state and the real-time quota use condition of each service, dynamically adjusting the quota distribution proportion of the services with different priority levels in the floating quota pool. According to the invention, the stability of the core service is ensured, and the utilization efficiency of the whole quota resource and the self-adaptive ability of the system to deal with the burst traffic are obviously improved at the same time.

The invention discloses a medium-low traffic volume train operation plan optimization method based on adaptive large neighborhood search, and relates to the technical field of medium-low traffic volume urban rail transit transportation organizations, and the method comprises the steps: obtaining rail operation basic data information based on a selected target urban rail line; a train operation scheme optimization mechanism is used for processing, and a train candidate set is generated; according to the train candidate set and the pre-processed integrated optimization decision variable, pre-configuring a train operation optimization target and a train scheduling constraint condition, and constructing a train collaborative optimization model; the train collaborative optimization model sequentially executes corresponding processing operations on a train candidate set, a pre-configured train scheduling constraint condition and the preprocessed neighborhood operator to obtain an adaptive large neighborhood search algorithm; and analyzing by using the train collaborative optimization model and the adaptive large neighborhood search algorithm to obtain an optimal train operation plan scheme. According to the invention, the flexibility of medium-and-low-traffic-volume urban rail driving and the passenger flow space-time distribution coupling are improved.

The invention discloses an AI-driven transport layer security protocol adaptive optimization system, which relates to the technical field of traffic data access and comprises a data access module, a state sensing module, a risk assessment module, an optimization transmission module and an adaptive encryption module. The data access module is used for capturing an original data flow from a network and a host in real time; the state sensing module is used for receiving the original data stream and setting a feature engineering state index; the risk assessment module is used for quantitatively assessing the safety score of the current state according to the current traffic environment state; the self-adaptive encryption module is used for constructing a password strategy library and generating an encryption configuration strategy according to a current traffic state; and the optimization transmission module is used for constructing a parameter intelligent optimization model and controlling algorithm interaction to generate performance scheduling optimization actions.

A traffic flow prediction method based on a dynamic space-time fusion attention mechanism is characterized in that a space-time decoupling embedding strategy, a dynamic weighting time attention module and a self-adaptive dynamic graph modeling module are innovatively adopted, so that space and time characteristics can be effectively decoupled and independently modeled; and meanwhile, the long-term dependency relationship of the time dimension and the spatial relevance of the road network are captured. According to the method, the accuracy and generalization ability of the model in a complex traffic flow prediction task are remarkably improved, a more reliable and more efficient solution is provided for flow prediction in an intelligent traffic system, and the method has important application value and prospect.

The invention discloses a portal data-based highway traffic incident detection method and system, and relates to the technical field of traffic intelligent management, and the incident detection method comprises the steps: obtaining the historical traffic data of an ETC portal, constructing a road network topology and traffic flow reference model, and carrying out the dynamic flow prediction through combining the real-time portal data flow, the system can identify traffic events and carry out accurate positioning. According to the method, a flow deviation accumulation and space-time aggregation mechanism is adopted, and video monitoring linkage and multi-channel information release are combined, so that real-time confirmation, check and release decision of events can be realized; according to the method, the timeliness and accuracy of event response are remarkably improved, the information issuing process is optimized, the robustness of the system is enhanced, and the false alarm rate is reduced. Sufficient technical support is provided for safe and efficient operation of the expressway, and the emergency management and traffic control level is improved.

The invention discloses an encrypted traffic detection method based on space-time fusion and small sample self-supervised learning, and the method comprises the steps: 1, multi-dimensional encrypted traffic feature extraction: extracting discriminative time sequence features and spatial header byte features from original encrypted traffic data; step 2, constructing and training a space-time fusion detection model, constructing an efficient space-time fusion detection model, and performing deep fusion and classification on the time sequence features and the space head byte features extracted in the step 1; and step 3, realizing a small sample self-supervised learning mechanism. According to the method, a space-time fusion detection model specially designed for encrypted traffic is constructed, and parallel processing and deep fusion are carried out on a time sequence and a space head byte feature. The fusion of the time-space dual features enables the model to understand the time sequence features and the structural features at the same time, significantly improves the detection precision and robustness, and can effectively cope with various encryption protocols and traffic confusion technologies.

The application discloses a financial intelligent backbone network traffic scheduling method and system based on SRv6, and relates to the technical field of network scheduling.The method comprises the following steps: step S1, identifying and dividing the entry service traffic into predefined service types; step S2, matching the corresponding SRv6 traffic tunnel model for each service type; step S3, allocating differentiated QoS strategies for different types of service flows, and performing corresponding queue scheduling; step S4, constructing the corresponding optimization objective function for path calculation according to the SLA requirements of different service types; step S5, automatically triggering the intelligent optimization process when detecting that the link utilization rate exceeds the preset threshold; and step S6, issuing the optimal SRv6 strategy calculated to the entry device for execution.The application builds an intelligent and efficient financial backbone network architecture, and realizes fine traffic scheduling strategies, thereby improving the network resource utilization rate and operation and maintenance efficiency.

This disclosure describes techniques for improving routing policy awareness in a network. The method includes detecting, by a controller, an application initiated for use at an edge node of a network. Then, generating, by an analytics engine coupled to the controller, analytical data of traffic flow at the edge node of the network wherein the traffic flow is in accordance with a routing policy for routing traffic associated with the application. Further, routing of the traffic through a path from one or more paths configured at the edge node that is in accordance with at least a Service Level Agreement (SLA) for traffic flow. Also, in response to an SLA violation during routing of the traffic, causing an action, by the controller, of routing traffic flow through another path that is in accordance with at least the SLA for traffic flow based on analytical data received of the traffic flow.

The invention discloses a real-time road condition-oriented AGV collaborative congestion avoidance path planning method, and relates to the technical field of AGV path planning, and the method comprises the steps: building a global road condition map based on AGV state data, and carrying out the dynamic updating of the global road condition map, and the dynamic updating comprises the weight updating based on an AGV density value and an average speed; based on the updated global road condition map, adopting a path planning algorithm to generate an AGV global optimization cooperative path set; the cooperative path set is converted into a control instruction, dynamic compensation is carried out on the control instruction through load sensing, and a corrected control instruction is obtained and issued to the AGV; according to the method, global road condition dynamic updating is combined with dynamic control of collaborative path optimization and load perception, multi-AGV global flow balance and real-time congestion prevention are achieved, and the problems that under the high load, path conflicts are frequent, local congestion cannot be actively adjusted, and the overall efficiency is reduced due to single AGV optimization are solved.

The invention discloses an attack intention blocking method and system based on encrypted traffic, a product and a medium, and relates to the technical field of network security. The invention aims to solve the problem that the existing encrypted traffic macroscopic statistical analysis technology is insufficient in feature resolution when facing a hidden attack. The method comprises the following steps: extracting an arrival timestamp and a load length of a data packet in an encrypted session, and generating a data packet interval sequence representing flow density and a directed load sequence representing a throughput direction; encoding the feature vectors to generate a time sequence feature vector and a spatial distribution feature vector; calculating the weight of the time sequence feature to the spatial feature element by using an attention mechanism, and carrying out weighted fusion to generate an attack intention fingerprint vector; and inputting the fingerprint vector into a model to predict an intention type, and blocking a hostile attack. According to the method, the key load features are actively screened and strengthened by using the communication rhythm, the microcosmic attack fingerprints are accurately stripped without decryption, and the recognition and blocking accuracy of the hidden attack intention is improved.

The invention relates to the technical field of network information security, in particular to a sequence similarity segmentation-based WireGuard multi-behavior traffic classification method and system, and the method comprises the steps: traffic collection: capturing encrypted traffic transmitted by a user through a WireGuard protocol; flow segmentation: dividing the feature sequence into equal sub-sequence fragments to form a plurality of sub-sequence sets with different sub-sequence lengths; calculating the similarity between the interior of the quantum sequence and the adjacent sub-sequences based on the maximum mean value difference function; adopting a greedy strategy to select connection points between K most dissimilar adjacent subsequences as segmentation points; feature extraction: constructing a multi-dimensional flow path based on the segmented subsequences; extracting path signature features on the multi-dimensional flow path by adopting a sliding window method; and traffic classification: inputting the path signature features into an LSTM model for time sequence modeling, and realizing classification of user behaviors through a full connection layer. According to the method, automatic, lightweight and fine-grained accurate classification of multi-user behaviors in encrypted traffic is realized.

The invention provides an on-off control method and device for a gateway port and a medium. The on-off control method comprises the steps of obtaining historical access log data and threat intelligence data of a target port in a gateway; based on the historical access log data and the threat intelligence data, performing time sequence analysis by using a pre-trained long-short-term memory network model to obtain a predicted security access time period of the target port in a future preset time period; generating a temporary port exposure preset rule of the target port according to the predicted security access time period; determining a traffic feature vector of the real-time traffic data packet of the target port; using a preset deep reinforcement learning agent to determine an on-off control instruction for the target port based on the traffic feature vector and a temporary port exposure preset rule; and executing the on-off control instruction to modify an access control list state of the gateway firewall to the target port. According to the method and the device, dynamic and refined gateway port on-off control can be realized, so that the service flexibility and security are considered.

This disclosure describes systems, methods, and devices related to multi-link traffic steering. A device may establish one or more links with a station multi-link device (STA MLD), wherein the STA MLD comprises one or more logical entities defining separate station devices. The device may generate a traffic indication map (TIM) bitmap of a plurality of bits, wherein one or more bits are associated with an association identification (AID) corresponding to the STA MLD. The device may set the one or more bits to a first value to indicate that there is data to be retrieved by the STA MLD on any of the one or more links. The device may generate one or more beacon frames each comprising a same TIM element, wherein the TIM element comprises the TIM bitmap. The device may cause to send one or more beacon frames on each of the one or more links.

Solutions are disclosed that enable capacity-aware local repair of tunnels in packet switched wide area networks (WANs). Traffic engineering agents on the routers are programmed to create the tunnels and include sets of primary and alternate tunnels sharing the same source and destination. A tunnel source router is provided a traffic split for allocating incoming traffic to its primary and alternate tunnels for when the primary tunnel is operating at or near full capacity operation, and another traffic split that shifts at least some traffic from the primary tunnel to the alternate tunnel, when the primary tunnel's capacity drops below a threshold. A tunnel may lose capacity for commonly-occurring reasons, such as a disturbance to cabling and faults in optical transceivers. Traffic engineering agents along the tunnel report capacity to the tunnel source router, permitting the network to respond to capacity changes more rapidly than waiting for network tunnel reconfiguration.

The invention discloses a multi-level linkage ramp control method and related equipment based on multi-source data fusion, and the method comprises the steps: carrying out the clustering analysis of target multi-source traffic trajectory data, and obtaining travel trajectory feature data; on the basis of the travel track feature data, performing weight calibration on the on-bridge ramp of the expressway to obtain on-bridge ramp control priority data; performing short-time prediction on the current traffic flow data to obtain a short-time flow prediction result; performing congestion prediction according to the short-time flow prediction result and the dynamic bearing capacity of the expressway to obtain a congestion section prediction result; and according to the short-time flow prediction result, the congestion section prediction result and the on-bridge ramp management and control priority data, carrying out ramp control on the predicted on-bridge ramps of the expressway congestion section by adopting a layered management and control strategy. The method can achieve the precise dynamic sorting of the turn-off priorities of the ramps, balances the load of the road network, avoids the secondary congestion, improves the overall traffic efficiency of the road network, and can be widely applied to the technical field of traffic control.

The invention provides a charging demand prediction method and device for a highway service area. The method comprises the following steps: acquiring positions of a plurality of service areas in a highway target road section and positions and congestion lengths of a plurality of congestion points; according to the position of each service area, the position of the congestion point closest to the service area and the congestion length, the driving-in traffic volume of each service area in the target time period of the workday is determined; based on the historical vehicle passing data of each service area in the target time period of the workday, determining a plurality of charging parameters of various vehicle types driving into the service area in the target time period of the workday; based on the driving-in traffic volume of each service area in the workday target time period and the multiple charging parameters of the various vehicle types driving into the service area, the charging demand prediction amount of each service area in the workday target time period is determined. The prediction precision of the charging demand of the service area is improved.

The invention discloses a traffic shaping scheduling method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a target service type of a first data stream at a first time, and obtaining a second data stream at a second time corresponding to the target service type; the second time is before the first time and comprises flow data of a plurality of time periods; determining flow characteristic data of a third data stream at a third time according to the second data stream; the flow characteristic data is used for describing the flow rate and the burst degree of the third data flow; and determining a control instruction of a token bucket shaper of the flow queue based on the flow characteristic data, and adding a token to the token bucket shaper based on the control instruction to meet the flow transmission of the third data flow. According to the invention, through real-time adjustment of the token bucket parameters, accurate control of network congestion is realized.

The invention belongs to the technical field of intelligent traffic, and particularly discloses an urban road network traffic state and congestion propagation probability prediction method and system. The method comprises the following steps: firstly, introducing information such as spatial distance and historical flow correlation on the basis of road topology to form a weighted gate road network; secondly, a conditional denoising diffusion model based on a bayonet space-time diagram is provided, the model takes historical multi-step diagram signals and a road network structure as conditions, and modeling is carried out on conditional distribution of future multi-step diagram signals through forward noise adding and reverse denoising processes; according to the method, multiple traffic evolution sample tracks in the future are obtained through multiple times of sampling, node operation indexes are mapped into discrete congestion levels, the occurrence frequency of each node under different congestion levels is counted, and the node congestion level probability is obtained; and further counting a time sequence co-occurrence relationship of congestion states between adjacent nodes, estimating a propagation condition probability of congestion in a road network, and constructing a key node influence degree index and a high-risk propagation path.

Aspects of the subject disclosure may include, for example, selecting a latency comparison, a throughput comparison, a security comparison, a reliability comparison, movement information or a combination thereof for an end user device executing a communication service according to a service type resulting in a selection criteria, wherein the comparisons are evaluations of each of different available connections; and generating a switching decision by selecting one of the connections. Other embodiments are disclosed.

A traffic policy includes policy rules that specify branch actions in their action fields. A branch action specifies another policy rule in the traffic policy. Packet filters generated from the traffic policy represent the traffic policy rules and execution order semantics of the branch rules.