75 results about "Traffic type" patented technology

An apparatus, method, and computer program product are provided for generating a frame associated with a shared transmission opportunity (TXOP). The frame indicates at least one of (i) whether a station (STA) can communicate during the shared TXOP with (a) the apparatus or (b) the apparatus and one or more other STAs, (ii) a maximum duration of the shared TXOP during which the STA can communicate, or (iii) at least one of one or more permissible traffic types that can be communicated during the shared TXOP or one or more permissible streams that can be communicated during the shared TXOP. The apparatus, method, and computer program product further provide for transmitting the frame to the STA.

Methods, systems, and devices for wireless communications are described. A UE may obtain, via an application program interface (API), an indication of an application type of an application at the UE and information including an indication of performance requirements associated with the application, an indication of a traffic type associated with the application, an indication of whether the performance requirements are being met, an indication of quality of service (QoS) information associated with a packet data unit (PDU) session established for communication by the application, an indication of a network slice associated with the PDU session, an indication of a power consumption of the UE, an indication of whether a power budget of the UE is being met, or any combination thereof. The UE may communicate one or more wireless signals via a subset of multiple antennas of the UE based on the application type or the information.

The application discloses a traffic transmission method and device, computer equipment and a storage medium. It belongs to the technical field of communication. The method can specifically include the following steps: after receiving to-be-transmitted traffic, determining a current transmission path and a traffic type of the to-be-transmitted traffic. First path quality information of the current transmission path is determined. Based on the traffic type and the first path quality information, first path feasibility of the current transmission path is determined. According to the first path feasibility and the current transmission path, a target transmission path is determined. The to-be-transmitted traffic is transmitted based on the target transmission path. The application can not only determine path quality information, but also determine path feasibility in combination with the traffic type, so that the quality of a communication service is effectively ensured, and user experience is improved while path quality monitoring is realized.

The invention discloses a network flow classification method and device based on multi-modal feature fusion, and the method comprises the steps: obtaining network flow data, extracting an IP address as a node, and constructing a communication graph; time modal features and event modal features are extracted for each node, and standardization processing is carried out on the time modal features and the event modal features; the time modal features and the event modal features are aligned; fusing the two types of aligned features; performing multi-layer neighbor sampling and hierarchical aggregation on the communication graph by using a graph neural network model to obtain structure-enhanced node features containing multi-hop neighbor information, inputting the node features into a linear classifier, outputting a category probability, selecting a category with the maximum probability as a prediction result, and performing iterative training to obtain a classification model; and mapping the classification model to a data plane of the programmable switch to realize online reasoning of the data packet. According to the method, high-precision identification of various network traffic types is realized by fusing the spatial modal, time and event modal characteristics.

An apparatus discontinues transmission of a first message of a first traffic type in a first time slot or sub-slot and does not resume the transmission in the first time slot or sub-slot. The apparatus then stores a payload of the first message. The apparatus later fully retransmits the payload in a second time slot or sub-slot after the first time slot or sub-slot.

This disclosure provides systems, methods, and apparatus for access control techniques for restricting access from a user equipment (UE) (102) to a non-terrestrial network (NTN). A network entity, such as a satellite 106B or a terrestrial base station 106A, communicates access control information (130) to the UE indicating that access to the NTN is barred based on a traffic type. There are various mechanisms for indicating barring, traffic type, and relationships with NTN. For example, a network entity may indicate barring via a non-access stratum (NAS), a radio resource control (RRC), or a system information message. In some examples, a network entity transmits a UE (User Equipment) Routing Policy (URSIP) with a Routing Policy (URSIP) rule that includes an indicator indicating barring and a traffic descriptor (TD) describing a type of barred traffic. The UE avoids accessing the NTN based on the access control information (160).

A method has the step of: transmitting a downlink control information message for scheduling an uplink or downlink transmission of a plurality of data pieces of a plurality of traffic types in a single data block via a communication resource, the plurality of traffic types comprising a first traffic type for transmission via a first portion of the communication resource and a second traffic type for transmission via a second portion of the communication second resource.

The invention discloses a vehicle fault checking method and device, equipment and a medium. The method comprises the following steps: acquiring service flow data and link state data of each link in a vehicle-mounted communication network; classifying the traffic according to the service traffic data of each link to obtain a plurality of service scene traffic categories; monitoring a link health state according to the link state data of each link to obtain a link state evaluation result of each link; determining a routing path according to the link state evaluation result of each link and the traffic type of the service scene of each link; if the link state evaluation result of any link in the links indicates that the link is abnormal, obtaining fault diagnosis data; identifying a fault type and a fault position according to the fault diagnosis data to obtain a fault checking result; and automatically triggering a routing adjustment strategy according to the troubleshooting result, and reporting the troubleshooting result and the routing adjustment strategy to the cloud. According to the invention, the accuracy of vehicle troubleshooting is improved.

The present invention provides according to one of its aspects a method of communication in a wireless network comprising an access point and a plurality of stations, the method comprising, at one of the stations:receiving a trigger frame from the access point, the trigger frame reserving a transmission opportunity on at least one communication channel of the wireless network, the transmission opportunity including random resource units that the stations may access using a contention scheme, wherein the trigger frame includes a first indicator specifying a traffic type of data allowed to be sent on at least one of the random resource units;determining, based on the first indicator, eligible resource units, among the resource units in the reserved transmission opportunity, for the station to contend for access for transmitting data; andtransmitting data on a determined eligible resource unit using a contention scheme.

The invention discloses a low-delay transmission control method and system for an Ethernet switch, relates to the technical field of network communication, and solves the problem that in the prior art, when a large number of data packets are transmitted at the same time, a preset dequeue rate is used for transmission, so that queue blockage is caused. If an efficient dequeue rate is always used for transmission, resource waste is caused, and certain flexibility is lacked. The method comprises the steps of obtaining a plurality of to-be-transmitted data packets; analyzing and processing the plurality of to-be-transmitted data packets to obtain a traffic type and an emergency degree; distributing the plurality of data packets to a plurality of corresponding message queues based on the traffic types; adjusting the transmission of the plurality of data packets based on the emergency degree; monitoring the plurality of message queues, and scheduling transmission of the message queues according to monitoring data; network fluctuation can be quickly responded, a transmission strategy is automatically adjusted, and stability is kept.

A first codeword is generated by encoding a first code block of a first code block group that is associated with a first traffic type, and a second codeword is generated by encoding a second code block of a second code block group that is associated with a second traffic type different from the first traffic type. The first code block includes information bits from only the first traffic type, and the second code block includes information bits from the second traffic type and bits associated with the first code block. The first codeword is decodable independently of the second codeword, and is further decodable jointly with the second codeword.

A method for timer adjustment in packet transmission and a user equipment are provided. The method includes: obtaining a plurality of service data units comprising a first service data unit; initializing a discard timer corresponding to the first service data unit of a first traffic type; performing logical channel prioritization to select a second service data unit from the plurality of service data units; determining a second traffic type of the second service data unit; and in response to determining the second traffic type, adjusting the discard timer for the first service data unit in a buffer.

Methods, systems, and devices for wireless communications are described. A UE may obtain, via an application program interface (API), an indication of an application type of an application at the UE and information including an indication of performance requirements associated with the application, an indication of a traffic type associated with the application, an indication of whether the performance requirements are being met, an indication of quality of service (QoS) information associated with a packet data unit (PDU) session established for communication by the application, an indication of a network slice associated with the PDU session, an indication of a power consumption of the UE, an indication of whether a power budget of the UE is being met, or any combination thereof. The UE may communicate one or more wireless signals via a subset of multiple antennas of the UE based on the application type or the information.

The invention relates to the technical field of network construction, and particularly provides a resource planning method and device, a medium and a program product, and the method comprises the steps: obtaining the traffic use information of a plurality of users in an administrative region to which a target region belongs, dividing the administrative region into a plurality of reference regions, determining a related flow type of each reference area in the plurality of flow types based on the usage amount of the user for each flow type in each reference area, and determining a resource planning result based on the related flow type of the target area and a predetermined resource planning strategy; according to the invention, the rationality and scientificity of the determined resource planning result can be improved.

The invention provides a network traffic detection method, device and equipment, a storage medium and a program product, and belongs to the technical field of artificial intelligence, and the method comprises the steps: determining an input tensor based on the network traffic characteristics of network traffic data; inputting the input tensor into a pre-trained type detection model to obtain a traffic type result output by the type detection model; the type detection model comprises a convolutional network module and an open set detection module; the open set detection module is used for determining a traffic type result based on each first distance value between the first output vector of the convolutional network module and each first interchange point vector; each first interchange point vector corresponds to one known flow type; the traffic type result comprises a known traffic type or an unknown traffic type. According to the method, the classification of known traffic types and finer granularity and the identification of unknown traffic types can be realized.

Methods, computer program products and apparatus are provided for determining which protocol data unit (PDU) sessions have a high or highest (end-to-end) energy consumption (EC) impact on a mobile network, as well as signaling for sharing such information between a radio access network node and a network function of a mobile network. High EC PDU sessions may be defined as, for example, PDU sessions that exceed a threshold (which may be per traffic type, energy credit or QoS type, etc.) relative to the remaining PDU sessions. A network function of a radio access network node (e.g., a gNB) or a core network may determine, store and process energy-related information for a PDU session with a high EC, indicate that the PDU is a high energy consumption PDU session or a UE, and share the information with each other. The radio access network node may also include time information, such as observing or anticipating and / or predicting a time period of a high energy consumption PDU session in the future.

The present application relates to a kind of malicious encrypted traffic detection method based on variational autoencoder, belong to computer network security technical field, solve the problem that existing technology is difficult to generalize and migrate in malicious encrypted traffic detection method, and the detection ability of unknown malicious encrypted traffic type is poor.Method includes collecting and processing network encrypted traffic data to obtain feature vector data, add class label for the feature vector data, obtain total sample data, wherein the class label includes normal flow data and each malicious category flow data;Normal flow sample data is input into variational autoencoder and is trained, learns the feature distribution of normal flow data, obtains trained variational autoencoder;Total sample data is input into trained variational autoencoder, obtains the reconstruction error of each detection category sample data, determines the recognition threshold interval of each detection category based on reconstruction error;Wherein, each detection category includes normal and each malicious category.

The invention belongs to the field of information communication, and discloses a data center network flow resource allocation method and a related device, and the method comprises the steps: obtaining the state information of each current network flow of a data center; and calling a preset data center resource allocation model according to the state information of each current network flow of the data center to obtain a path of each network flow type of each current communication host pair of the data center and the bandwidth of each hop of the path. The preset data center resource allocation model can dynamically allocate corresponding paths and bandwidths to different network traffic types of each communication host pair of the data center, so that differentiated resource scheduling for dynamically adjusting differentiated demands of different network traffic types, such as mouse flow and elephant flow, is realized. Network congestion caused by disordered resource occupation of elephant flow in a traditional method is avoided, meanwhile, the low-delay requirement of mouse flow is guaranteed, and the transmission efficiency, the network throughput, the link utilization rate and the overall service quality of data center network flow are improved on the whole.

This disclosure provides a system, device, apparatus, and method comprising a computer program encoded on a storage medium for beam management for beam switching acceleration. A UE receives multiple beams from a network entity for signal quality measurement (408, 908). The UE communicates with the network entity via a first beam of the multiple beams. Based on the fact that the signal quality of the second beam is higher than that of the first beam and that the signal quality of the first beam exceeds a traffic type threshold, the UE sends a message to the network entity indicating that it will accelerate beam switching from the first beam to the second beam of the multiple beams (424, 524, 624, 724, 824, 924).

This disclosure provides a system, device, apparatus, and method for beam management for beam switching deferral, including a computer program encoded on a storage medium. A UE receives multiple beams from a network entity for signal quality measurement (408, 708). The UE communicates with the network entity via a first beam of the multiple beams. Based on the fact that the signal quality of the second beam is higher than that of the first beam and the signal quality of the first beam is below a traffic type threshold, the UE sends a message to the network entity indicating a request to defer beam switching from the first beam to the second beam of the multiple beams for at least a subset of the communication channels (416, 516, 616, 716).

The invention discloses a protection method and system, a product, equipment and a storage medium, and the method comprises the steps: obtaining an exit IP address set of a cooperation CDN service provider and a minimum credible threat IP address set of a threat intelligence service provider, and judging whether a request is a direct connection request or a CDN forwarding request according to four layers of source IP addresses; the direct connection request directly compares four layers of source IPs with a minimum trusted threat IP address set, the CDN forwards the request to analyze an X-Forwarded-For field at the head of an HTTP message and check whether any IP in the threat IP set is included, and if yes, interception is executed; the method has the main technical effects that traffic types are accurately distinguished, interference caused by X-Forwarded-For field counterfeiting and CDN equipment record rule difference is avoided, the calculation overhead of a protection system is reduced, meanwhile, mistaken blocking and missing blocking conditions are reduced, and the accuracy and efficiency of enterprise network protection are remarkably improved.

The present disclosure provides a communication apparatus and a communication method for prioritized traffic. The communication apparatus, comprising: a receiver, which, in operation, receives from another communication apparatus a notification of one or more priority service periods (SPs), each SP being a time period in which only frames belonging to a traffic type designated by the other communication apparatus are allowed to be transmitted; and circuitry, which, in operation, determines if at least one frame of the designated traffic type is to be transmitted in one of the one or more SPs, and refrains from transmitting during the one of the one of more SPs in response to the determination that there are no frames of the designated traffic type to be transmitted.

The application provides a multi-feature fusion network traffic classification method, system, device and storage medium, the method comprising: obtaining target traffic, the target traffic comprising multiple different types of traffic; inputting the target traffic into a network traffic classification model to obtain the traffic type in the target traffic; wherein the network traffic classification model comprises a multi-core convolutional neural network, a bidirectional long short-term memory network and a Transformer model, the multi-core convolutional neural network is used for extracting local features of the target traffic, the bidirectional long short-term memory network is used for extracting time sequence dynamic features according to the local features, and the Transformer model is used for obtaining attention features according to the time sequence dynamic features. The network traffic classification method in the embodiment of the application can effectively distinguish similar types of traffic, is effective in encrypted and obfuscated traffic classification, and has application potential in enhancing a network security system.

This invention relates to a load balancing method, apparatus, computer device, and readable storage medium. The method includes: splitting received traffic and configuring a load balancing strategy, which is a method for evenly distributing traffic across nodes; forwarding the split traffic to a public cloud and / or a private cloud according to the load balancing strategy; acquiring and updating various resource information of the traffic in the public and private clouds for analysis to determine the type of traffic and recording it, including storage cloud type, memory, CPU information, IP address, disk space, and bandwidth; and reconfiguring a traffic scheduling strategy based on the recorded traffic type, adjusting the load balancing strategy, which is a method for combining and forwarding different types of traffic. This method can comprehensively consider security and cost in a hybrid cloud environment, analyze and plan user traffic, thereby improving resource utilization and reducing user costs.

Aspects of the subject disclosure may include, for example, acquiring data traffic from an open radio unit network (ORAN) with respect to user equipment (UE) resulting in acquired data traffic; analyzing the acquired data traffic using a rApp deployed therein, the rApp configured as a traffic classification application operable to classify the acquired data traffic into one or more service types; based on the classification of the one or more service types, determining allocation of one or more RAN slices to be optimized for the one or more service types; and transmitting the determined allocation to a near-real-time radio access network intelligent controller (near-RT RIC) to implement the allocation of the one or more RAN slices in one or more open distributed units (O-DUs) and one or more open radio units (O-RUs) in the ORAN. Other embodiments are disclosed.

The invention relates to the technical field of road emergency evacuation, in particular to a partition progressive signal control method and system for emergency evacuation, and the method comprises the steps: extracting the traffic flow characteristic information of historical image data and historical monitoring data, extracting the initial traffic information of a traffic junction of each road section, classifying the traffic types based on a preset classification standard; performing feature extraction on the traffic flow feature information of each type to obtain traffic flow feature values, constructing a traffic flow feature value set, performing traffic intensity evaluation according to the change condition of the traffic flow feature values of each group along with time, and generating an evacuation type; carrying out regional management and control importance evaluation, and dividing a road network region according to an evaluation result; and matching the evacuation type with the preset evacuation strategy of the corresponding road network region, and sending the dynamic evacuation information to the traffic hub of the corresponding road section, thereby solving the problem that in the prior art, regional management and control strategies cannot be effectively divided and traffic flow and crowd cannot be guided for traffic evacuation.

Provided herein is a unified Quality of Experience (QoE) framework for determining QoE metrics for a plurality of mobile services based, in part, on the Key Performance Indicators (KPIs) that are collected for the services. The QoE metrics are scalar values, fall on a unified scale, and eliminate any dependencies that may exist between the KPIs used in determining the QoE metrics. The unified QoE framework includes a generic QoE calculation module having a loss model component, a KPI coupling calculation component, and a machine learning (ML) parameter optimization component. The QoE calculation module correlates network event information and calculates various resource and / or network KPIs. Additionally, the QoE calculation module calculates service KPIs for a predetermined number of traffic types, and estimates factors due to losses, drops, and soft drops. Additionally, the internal functional parameters of the underlying KPI are determined and / or optimized without requiring external intervention or the initial setting of parameters.

Apparatuses and methods for traffic type based quality of experience (QoE) maintenance for mobile devices. A user equipment (UE) includes a transceiver. The transceiver is configured to receive and transmit traffic over a link with a wireless network. The UE further includes a processor operably coupled to the transceiver. The processor is configured to classify the traffic into at least one of real time (RT) traffic or non-real-time (NRT) traffic, generate a link deterioration prediction, select, based on the link deterioration prediction and the traffic class, a QoE maintenance action, and perform the QoE maintenance action.

Systems and methods for integrating multi-path communication networks to provide In-Flight Connectivity (IFC) for users, by augmenting data streams from multi-path satellite networks are disclosed. The system includes IFC system and IAT to provide wireless network connectivity to user devices. The system includes SD-WAN router communicatively coupled to IFC system and IAT. The SD-WAN router receives request for accessing WAN from user devices, and determines parameters associated with data packets based on received request. The SD-WAN router classifies data packets into traffic types based on parameters. Furthermore, SD-WAN router prioritizes data packets based on traffic types and available network capacity for upstream transmission of data packets across IFC system and IAT. Additionally, SD-WAN router determines appropriate WAN transport path associated with SD-WAN tunnel for upstream transmission based on traffic types and performance parameters. Further, SD-WAN router transmits data packets to WAN over determined WAN transport path.

This invention relates to the field of traffic data processing and classification, and proposes a mobile traffic classification method and system based on spatiotemporal hybrid representation learning. Through a preprocessing mechanism of feature hierarchical screening and dynamic noise filtering, the quality of the original traffic feature input is optimized. Subsequently, attention-guided feature interaction is added in the micro-fusion stage to strengthen the nonlinear correlation of spatiotemporal features within a single time step. Furthermore, in the macro-fusion stage, a cross-scale feature alignment and temporal-spatial attention interaction mechanism is designed to avoid the limitations of traditional independent modeling. Finally, the classification module is optimized by combining a class-adaptive loss adjustment strategy to adapt to the sample distribution differences of different traffic types. This invention achieves deep spatiotemporal feature fusion and improves the accuracy of mobile traffic classification.