Abstract: In some embodiments, there may be provided a method that includes receiving, as a first input to a first machine learning model, at least a first traffic matrix indicative of an amount of traffic routed among at least one node pair of an overlay network; receiving, as a second input to the first machine learning model, information indicative of overlay network routing among the at least one node pair of the overlay network; receiving, as a third input to the first machine learning model, measured delay between the at least one node pair of the overlay network; and learning, by the first machine learning model, a representation of an underlay network, the learning using a minimization of a difference between an average delay in the underlay network and the measured delay between the at least one node pair of the overlay network.

Abstract: A method managing multipath communication includes acquiring a plurality of network addresses respectively corresponding to a plurality of servers associated with a domain, sending a data request to at least one server of the plurality of servers based on the acquired plurality of network addresses, receiving a first data packet transmitted from a first server of the plurality of servers in response to the data request, the first data packet being received first in order among a plurality of data packets received from the plurality of servers in response to the data request, accepting the first data packet, and rejecting data packets transmitted from each server of the plurality of servers other than the first server.

Abstract: In one embodiment, a device obtains browser waterfall data from a web browser of a client that is used to access an online application via a network. The device obtains user feedback from the client indicative of whether a user of the client is satisfied with their experience with the online application. The device trains, using the browser waterfall data and user feedback as training data, a prediction model to predict a quality of experience metric for the online application. The device causes an adjustment to the network based on a prediction by the prediction model.

Abstract: A route generation method, performed in an SRv6 network and including: receiving, by a first network device, a first notification packet from a second network device; where the first notification packet includes a network slice identifier, the first notification packet indicates an association relationship between information of the network slice identifier and an IPv6 address prefix of the second network device, and the network slice identifier is used to identify one network slice; and generating, by the first network device, a route forwarding entry for the IPv6 address prefix of the second network device based on an association relationship between the network slice identifier and the IPv6 address prefix of the second network device. This helps implement a network slice and resource isolation in the SRv6.

Abstract: A method and video decoder system using the method are provided for identifying video frames in an encoded or encrypted video stream without performing decoding or decryption. The method includes: receiving a video data stream comprised of a plurality of transport stream (TS) packets; detecting a first video frame in the video data stream, wherein detection of the first video frame includes registering a last checked position at the start of the video data stream, examining bytes in a next TS packet to identify a predetermined pattern indicating a network abstraction layer (NAL) unit, repeating the examining step until two TS packets have been identified that include an NAL unit, wherein the last checked position is updated after each examining step, and identifying a video frame based on a position of the NAL unit identified in the two TS packets; and repeating the detecting step for a plurality of additional video frames in the video data stream.

Abstract: A method of identifying a hidden anomaly in a stream of time-series data. The stream of time-series data is parsed into a number of sub-streams. Each sub-stream in the number of sub-streams includes a parameter in a number of parameters. A number of policies are executed on the number of sub-streams. Executing outputs a first set of values in a current time window for each of the number of sub-streams. For the each sub-stream, a corresponding difference determination is generated by comparing, for the each sub-stream, the first set of values in the current time window to a second set of values in a past time window for the each sub-stream. When, for a sub-stream, a difference determination satisfies a threshold, an alert is returned that the hidden anomaly occurred with respect to the parameter for the selected sub-stream.

Abstract: A method including: determining whether the receiving terminal has received a second data packet when a first data packet in a plurality of data packets continuously sent by a sending terminal at an interval in a preset sending sequence is received, the second data packet comprises the data packet preceding the first data packet in the preset sending sequence; determining whether the second data packet is expired when the second data packet is not received; acquiring a consumption importance level of the second data packet when the second data packet is expired; and consuming the first data packet when the consumption importance level of the second data packet is a preset consumption importance level. Through the present disclosure, an application corresponding to the plurality of data packets is responded timely to avoid a delayed response to the applications. For example, the smoothness of the application is improved.

Abstract: An information processing system is provided. This information processing system includes: a controller; and a memory. The controller accepts a transmission request for transmitting a file stored in the memory. The controller acquires a first timestamp based on the file when accepting the transmission request. The first timestamp includes a first hash value which is a random letter string acquired from the file. The controller allows the memory to store the first timestamp to be linked with the file, and transmits the file to a destination that has sent the transmission request.

Abstract: A method of providing at least one Network Service (NS) to a Network Slice (NwS) during a design phase of the NwS based on a NwS Forwarding Graph (NwS FG) which comprises Network Functions (NFs) at a functional level, Virtual Network Functions (VNFs) and/or Physical Network Functions (PNFs) at a resource level, and embedding information for embedding the VNFs and/or PNFs (VNFs/PNFs) across more than one domain. The method determines, based on the NwS FG, Network Slice Subnets (NwSSs) for the NwS, wherein NFs comprising the NwS FG are grouped into respective groups to be managed by a respective NwSS manager. The method further maps the NwSSs to NSs based on Network Function Virtualization Orchestrator (NFVO) assigned to a domain, wherein at least some of the VNFs/PNFs managed by respective NFVOs are mapped to sites across the multiple domains determined by the embedding information.

Abstract: The present disclosure provides a method for associating actions for Internet of things, an electronic device, and a computer-adable storage medium, the method includes: triggering a first device to execute a first action, and triggering a second device to execute a second action to obtain a feedback result of the first action and a feedback result of the second action, where each feedback result includes at least one of an execution result or an execution effect; and judging whether the first action and the second action are associable with each other based on the feedback result of the first action and the feedback result of the second action; and in response to that the first action and the second action are associable with each other, associating the first action with the second action.

Abstract: A process control system includes a plurality of field devices operating to control a process. A communication infrastructure couples the field devices to a software-defined control system (SDCS) that receives data from the field devices and transmits instructions to the field devices. A data cluster, executing the SDCS, includes a plurality of computing nodes, each of which includes a processor executing an operating system, a memory, and a communication resource coupled to one or more other computing nodes in the data cluster. First and second containers, each of which is an isolated execution environment, are instantiated on a first computing node within the operating system of the first computing node. The second container is instantiated within the first container. The first and second containers correspond to levels of a hierarchical structure of the SDCS.

Abstract: An information processing apparatus transmits, to a server, authentication information for login process on servers, and upon success of the login process, searches for a device connected to the information processing apparatus, and in response to an instruction for registering a found device, makes a request to the server for setting information including security setting information for communication between the server and a device to be registered. The information processing apparatus transmits the obtained setting information obtained to the device to be registered, and determines whether the setting information has been reflected in the device and if the setting information has been reflected in the device, transmits, to the server, identification information of the device and makes a request to the server to register the device.

Abstract: The described technology is generally directed towards implementing a cloud intelligent controller (CIC) system at the O-Cloud platform/infrastructure to enable automated and fast (e.g., near-RT) implementation/coordination between the O-Cloud CIC and radio access network (RAN) controllers. O-Cloud-applications (cApps) are configured for implementation at the CIC, such that a workload received at the O-Cloud can be accompanied with a cApp, wherein the cApp defines the respective resources, functionality, etc., required to process the workload. Hence, rather than relying on information provided by other platforms in the RAN (e.g., service management and orchestration (SMO), non-RT RAN intelligent controller (RIC), near-RT RIC, and associated rApps and xApps), implementing a CIC with cApps enables inherent processing latency of conventional RAN configurations to be reduced, further enabling improved power control, resource management, and the like, to be performed locally at the CIC/O-Cloud.

Abstract: The disclosure provides a scheduling transmission method and an apparatus. The method includes: obtaining a scheduling priority of a terminal, and transmitting a data packet of the terminal based on the scheduling priority of the terminal, where the scheduling priority of the terminal is determined based on importance of a data unit to which the data packet of the terminal belongs and a size level of the data unit to which the data packet of the terminal belongs. Solutions of this disclosure may be widely used in the fields of communication technologies, artificial intelligence, internet of vehicles, internet of smart home, and the like.

Abstract: Methods and apparatuses are described for capturing and utilizing cross-channel context data in conversation service application communication sessions. A computing device establishes a first communication session between a first conversation service application and a first remote device. The orchestration utility detects an intent to transfer the first communication session to a second remote device. The orchestration utility captures context data generated during the first communication session. The computing device establishes a second communication session between a second conversation service application and the second remote computing device. The orchestration utility configures the second communication session based upon the context data, including synchronizing a state of the second communication session to a state of the first communication session.

Abstract: Systems and methods for border gateway protocol (BGP) Segment Routing (SR) (BGP-SR) update packing include negotiating with border gateway protocol (BGP) peers for packing BGP-Segment Routing (BGP-SR) updates, receiving a plurality of prefixes for a BGP-SR update message, encoding the plurality of prefixes with associated label information in network layer reachability information (NLRI) of the BGP-SR update message, and transmitting the BGP-SR update message to any of the BGP peers.

Abstract: Disclosed herein are system, method, and computer program product embodiments for a template XSLT (extensible stylesheet language transformation) based NETCONF (network configuration protocol) data collector. An embodiment operates by sending, by a network management device, a NETCONF request to a first network element and a first network element, where the NETCONF request is generated based on a configuration file corresponding to the first network element and the first network element. The embodiment generates a stylesheet corresponding to the NETCONF configuration file. The embodiment receives a first NETCONF reply message and a second NETCONF reply message, where the first NETCONF reply message is generated by the first network element in response to receiving the NETCONF request, and the second NETCONF reply message is generated by the first network element in response to receiving the NETCONF request.

Abstract: In one embodiment, a device initiates, using a chaos engineering tool, performance of randomized actions in a network via which an online application is accessible. The device obtains telemetry data from the network. The device computes correlations between the telemetry data and the randomized actions. The device uses the correlations to determine a root cause of an event in the network with respect to the online application.

Abstract: A network entity aggregation system may obtain different information for entities of a network from various sources of network entity information. The network entity aggregation system may generate a list of unified network entities including a corresponding record for each unified network entity. Unified network entity information and/or aggregated network information of the unified network entities may be presented to a user via a web interface and/or provided to applications and/or services.

Abstract: Computer systems and computer-implemented methods are configured to assign limited resources such as cloud or other computing resources to objects such as networks of computers having demands for the resources. Efficiencies are optimized by assigning the objects based upon an intra-network score and an inter-network score, both of which may include an associated network density and/or an associated metric, and may be based on information received from electronic records. The metric may be a parameter relating to a factor or other characteristic that is desired to be optimized by the assignments. For example, the metric may be related to costs of communications between the computers of a network.