The method of some embodiments samples data flows. The method samples a first set of flows during a first time interval using a first logical port window for the first time interval. The first logical port window identifies a first set of non-contiguous layer 4 (L4) values in an L4 port range that are candidate values for sampling the flows during the first time interval. The method also samples a second set of flows during a second time interval using a second logical port window for the second time interval. The second logical port window identifies a second set of non-contiguous L4 values in an L4 port range that are candidate values for sampling the flows during the second time interval.

In a method for configuring and managing a Time Sensitive Networking (TSN) network, a network packet is regularly captured and parameters are extracted. The parameters are submitted to a distributed learning model for matching an application according to the parameters, and a network requirement of the application is obtained. Such obtained network requirements are uploaded to a centralized network configuration (CNC) through a message transmission protocol, and a configuration of the network requirement is calculated through the CNC. The configuration calculated by the CNC is received and delivered to a TSN switch, causing the TSN switch to dynamically update the network configuration accordingly.

In various embodiments, the techniques and supporting systems implement a recursive routing mechanism in hierarchical topological addressed environments to analyze and determine the presence of packet-forwarding errors within an IP network comprising a plurality of network-connected devices. This includes receiving, at a software defined network device, an indication of a potential packet-forwarding error between a first and second device of the plurality of network-connected devices and injecting, by the software defined network device, a test packet at an ingress to the first device. The test packet includes an initial ingress interface location identifying the first device, an alternate ingress interface location identifying the software defined network device and an egress interface location identifying the second device. A determination may then be made as to whether the test packet is received at the second device, thus indicating the existence or lack of routing errors.

A network element includes multiple ports configured to communicate over a network, a buffer memory, a snapshot memory, and circuitry. The circuitry is configured to forward packets between the ports, to temporarily store information associated with the packets in the buffer memory, to continuously write at least part of the information to the snapshot memory concurrently with storage of the information in the buffer memory, and, in response to at least one predefined diagnostic event, to stop writing of the information to the snapshot memory, so as to create in the snapshot memory a coherent snapshot corresponding to a time of the diagnostic event.

A network element includes multiple ports configured to communicate over a network, a buffer memory, a snapshot memory, and circuitry. The circuitry is configured to forward packets between the ports, to temporarily store information associated with the packets in the buffer memory, to continuously write at least part of the information to the snapshot memory concurrently with storage of the information in the buffer memory, and, in response to at least one predefined diagnostic event, to stop writing of the information to the snapshot memory, so as to create in the snapshot memory a coherent snapshot corresponding to a time of the diagnostic event.

A method is provided for identifying operating conditions of a system. Input data relating to operation of the system is applied to a multi-class model for classification, where the multi-class model is configured for classifying the data into one of a plurality of predefined classes, and each class corresponds to a respective operating condition of the system. A confidence level of the classification by the multi-class model is determined. If the confidence level is below a threshold confidence level, the input data is applied to a plurality of binary models, where each binary model is configured for determining whether the data is or is not in a respective one of the predefined classes. If the plurality of binary models determine that the data is not in any of the respective predefined classes, the data can be taken into consideration when updating the multi-class model.

Aspects of the subject disclosure may include, for example, obtaining, over an uplink (UL) using an aggregation of modular antenna arrays, a modulated signal that includes feedback transmitted by a user equipment (UE), wherein the aggregation of modular antenna arrays comprises multiple groups of antenna elements, after the obtaining the modulated signal, performing a demodulation of the modulated signal, determining demodulator constellation errors from the demodulation of the modulated signal, performing an error gradient weight adaptation responsive to the determining the demodulator constellation errors to derive revised weights for various antenna elements of the multiple groups of antenna elements, and applying the revised weights to the various antenna elements of the multiple groups of antenna elements to adjust signals received over the UL. Other embodiments are disclosed.

Disclosed herein are systems, methods, and devices for time of arrival estimation in wireless systems and devices. Devices include a packet detector configured to identify a data packet included in a received signal having a symbol frequency. Devices also include a time stamping unit configured to generate an initial time stamp in response to the packet detector identifying the data packet. Devices further include an IQ capture unit configured to acquire a plurality of IQ samples representing phase features of the received signal. Devices additionally include a processing unit that includes one or more processors configured to generate an estimated time of arrival based on the initial time stamp and the plurality of IQ samples.

Disclosed herein are systems, methods, and devices for time of arrival estimation in wireless systems and devices. Devices include a packet detector configured to identify a data packet included in a received signal having a symbol frequency. Devices also include a time stamping unit configured to generate an initial time stamp in response to the packet detector identifying the data packet. Devices further include an IQ capture unit configured to acquire a plurality of IQ samples representing phase features of the received signal. Devices additionally include a processing unit that includes one or more processors configured to generate an estimated time of arrival based on the initial time stamp and the plurality of IQ samples.

This application provides a method, device, and system for determining a bandwidth for service flow transmission. The method includes: A first device obtains a first traffic sampling set of a service flow, where the first traffic sampling set includes one or more pieces of traffic sampling information. The first device obtains a service level parameter corresponding to the service flow and a reliability probability of meeting the service level parameter. The first device determines, based on the first traffic sampling set, the service level parameter, and the reliability probability, a bandwidth for transmitting the service flow.