This disclosure describes systems, methods, and apparatuses related to network function virtualization infrastructure (NFVI) performance. An apparatus may receive performance data from a network function virtualization infrastructure (NFVI) associated with one or more virtualized resources (VRs) of the NFVI. The apparatus may determine a collection method based on the received performance data. The apparatus may determine a performance measurement associated with the collection method. The apparatus may perform the performance measurement using the received performance data and the collection method. The apparatus may generate one or more outputs based on the performance measurement. The apparatus may cause to send the one or more outputs to a VNF manager (VNFM).

It is disclosed a method for performing a time measurement on a packet flow transmitted through a communication network. The transmitting node divides the packets into first and second packets transmitted in alternating periods. At each period, transmitting node also marks each packet by setting a feature thereof to a first value indicating that the packet shall undergo time measurement or a second value indicating that the packet shall not undergo time measurement. The transmission times of two packets marked by the first value are reciprocally delayed by a predefined inter-transmission time shorter than a period duration. For each packet marked by the first value, the transmitting node generates a transmission time stamp and the receiving node generates a reception time stamp. Then, after the end of each period, a time measurement is performed based on transmission and reception timestamps of packets marked by the first value transmitted during the preceding period.

A method including selecting multiple dedicated radios on a transmission channel and programming multiple association identifiers on each dedicated radio is provided. Each of the association identifiers is configured to detect a resource unit assigned to one of multiple stations. The method includes providing multiple packets collected from the dedicated radios to a server and merging the packets from the dedicated radios to identify at least one station. Merging the packets includes identifying a preamble in the packets from the dedicated radios, matching the preamble from different dedicated radios, combining a data portion of the packets from different dedicated radios whose preamble match, selecting a time-stamp from one of the dedicated radios, and associating the time-stamp with the data portion. A system and a non-transitory, computer readable medium storing instructions to perform the above method are also provided.

The present invention presents a network apparatus and a selective information monitoring method using the network apparatus, which allow a user to monitor only required information (the field information of packets) from all received packets. The network apparatus one or more physical interfaces connected to a monitoring target host and configured to receive network packets from the monitoring target host, and a switch fabric module including a configurable monitoring module configured to perform filtering so that selective information is extracted from the network packets collected through the one or more physical interfaces.

The subject matter described herein includes methods, systems, and computer program products for performing deep packet inspection at an endpoint. According to one method, a data portion of a data packet is examined at an inspection point located at an endpoint or mobile terminal of a communications network. A user profile associated with the endpoint or mobile terminal is provided that defines one or more actions or criteria to be applied to the data packet. An action related to the data packet is performed based on the examined data portion and the user profile.

In a method of identifying matching packets at different locations in a network, a first plurality of packets is received at a first location in the network, and a first subset thereof is selected in accordance with a filter. A second plurality of packets is received at a second location in the network, and a second subset thereof is selected in accordance with the same filter. Each packet in the first and second subsets is parsed to extract invariant header fields from an outermost IP header inwards, until a minimal set of invariant header fields is obtained for that packet, or until it is determined that a minimal set is not obtainable for that packet. A packet signature is computed from the minimal set for each packet having a minimal set, and the packet signatures arc compared to identify matching packets in the first and second subsets.

A relay device directly connected to end nodes in an in-vehicle network transmits a failure detection packet to each end node. When each end node can receive the failure detection packet, each end node transmits a response to the relay device. When the relay device receives the response, the relay device transmits another failure detection packet. The end node determines that the in-vehicle network is normal when the value of the previous failure detection packet does not match the value of the other failure detection packet, and determines that the in-vehicle network is not normal when the value of the previous failure detection packet matches the value of the other failure detection packet.

Provided herein are systems and methods for determining relationships between events occurring in networks. Notifications describing events occurring in networks can be received and processed to determine groups of network event types. A root-cause network can be generated based on the events, with the nodes of the root-cause network representing different event types and the edges of the root-cause network indicating directional, causal relationships between the nodes. A received network event can be processed to determine potential causes of the received network event based on the root-cause network and other events received by the network.

Aspects of the subject disclosure may include, for example, a device in which a processing system instantiates a data collector agent at an edge of a communication network. The data collector agent determines a type of data to be collected for executing an application, determines a data collection procedure including a data collection algorithm selected in accordance with the application, and performs the data collection procedure, resulting in collected data. The system can also configure a data processing module to process the collected data in accordance with the application; the data processing module is connected to the data collector agent and a database, and includes a data streaming system. The system can also configure a monitoring module connected to the controller for monitoring performance of the data processing module and a status of the database, and store the collected data in near real time. Other embodiments are disclosed.

A sampling node in a SDN and a method performed thereby for handling flows through the SDN between client(s) and origin server(s) of a communication network connected to the SDN are provided. The method comprising receiving (110) a fraction of a total amount of traffic flows originating at client(s) served by the SDN, and destined for the origin server(s); identifying (120) which of the received traffic flows that benefit from being routed via a service optimising node, capable of providing value added services, VAS, to the traffic flows, by fulfilling predetermined conditions; and determining (130), for each individual traffic flow, a capacity demand of the flow. The method further comprises selecting (150) which traffic flows that shall be routed via the service optimising node on the basis of their capacity demand considering a capacity of the service optimising node; and informing (160) a flow switch of the SDN about which traffic flows should bypass the service optimising node and which traffic flows that should be routed via the service optimising node.