Abstract: Described herein is a client device, configured to provide a user service and to establish communication with a server device for providing a Digital Twin Machine Learning, ML, Model training service for said client device, comprising: at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the client device at least to: receive, from the server device, a plurality of models for providing estimation for at least one parameter associated with the user service; apply, for each of the received plurality of models, data at the client device associated with the user service to a model evaluation function, and determine, for the each model, a corresponding model evaluation value for indicating performance of the each model in providing estimation for said at least one parameter associated with the user service; obtain, from the server device, an indicator for indicating a model selected by the server device for the client device among the receive

Abstract: A segment routing (SR) network has a plurality of interconnected SR gateways, where each of a plurality of local networks is connectable to an SR gateway at an edge router of the local network. An SR network control plane maintains a locator database that maps (i) a global IP (GIP) address for user equipment (UE) to (ii) an IP address of a downstream node associated with the UE along a path from the SR network to the UE. An SR gateway (i) receives a message for the UE and (ii) addresses the message to the IP address of the downstream node. The SR network control plane updates the locator database to map (i) the GIP address for the UE to (ii) a different IP address of a downstream node upon the SR network control plane determining that the association of the UE has changed to the different IP address.

Abstract: Various example embodiments for supporting packet replication and deduplication are presented. Various example embodiments may be configured to support packet replication and deduplication within the context of application flows utilizing multiple communication paths which may be based on multiple access technologies. Various example embodiments may be configured to support packet replication and deduplication based on support for application-based policy control for enabling applications to control selection and application of packet replication and deduplication to application traffic flows based on considerations such as the needs of the application traffic flows, network conditions, and so forth. Various example embodiments may be configured to support packet replication and deduplication based on packet hashes, packet sequence numbers, or the like, as well as various combinations thereof.

Abstract: A device for communicating within a network includes at least one processor and at least one memory storing instructions that, when executed by the processor, cause the device to receive, from a network gateway, a connectivity policy for the device and facilitate communication between the device and the network gateway according to the connectivity policy. The device includes a kernel with at least a first kernel tunnel and a second kernel tunnel. The connectivity policy specifies at least one of the first kernel tunnel or the second kernel tunnel for uplink transmission of packets from the device. The device includes a kernel virtual switch configured to switch between the first kernel tunnel and the second kernel tunnel to facilitate the communication between the device and the network gateway based on the connectivity policy.

Abstract: A segment routing (SR) network has a plurality of interconnected SR gateways, where each of a plurality of local networks is connectable to an SR gateway at an edge router of the local network. An SR network control plane maintains a locator database that maps (i) a global IP (GIP) address for user equipment (UE) to (ii) an IP address of a downstream node associated with the UE along a path from the SR network to the UE. An SR gateway (i) receives a message for the UE and (ii) addresses the message to the IP address of the downstream node. The SR network control plane updates the locator database to map (i) the GIP address for the UE to (ii) a different IP address of a downstream node upon the SR network control plane determining that the association of the UE has changed to the different IP address.

Abstract: Leaf nodes of a tree structure, also having a root node and intermediate nodes, communicate with endpoints via access networks and store mappings from permanent virtual IP (VIP) addresses for the endpoints to physical IP (PIP) addresses for the endpoints on the access networks. The root node and intermediate nodes store pointers for the endpoints' leaf nodes and associated access networks. When a connection setup request (CSR) for a destination endpoint is received from a corresponding node, the receiving leaf node passes the CSR up through the tree structure to a lowest common ancestor (LCA) node for the receiving leaf node and one or more destination leaf nodes associated with the destination endpoint. The LCA node uses its pointers to pass the CSR down towards the one or more destination leaf nodes, which use the corresponding VIP-to-PIP mappings to forward the CSR to the destination endpoint.

Abstract: Network-based, unsupervised classifiers are provided. The classifiers identify both known and unknown attacks aimed at industrial networks without the need to have a priori knowledge of known malicious attack patterns.

Abstract: Various example embodiments for supporting scheduling of deterministic flows in time synchronized networks are presented. Various example embodiments for supporting scheduling of deterministic flows in a time synchronized network may be configured to support scheduling of deterministic flows in the time synchronized network based on assignment of transmission start times to data flows of communication devices such that the communication devices may transmit data of the data flows at the transmission start times in a manner tending to reduce or eliminate collisions in the time synchronized network.

Abstract: Various example embodiments for supporting scheduling of deterministic flows in time synchronized networks are presented. Various example embodiments for supporting scheduling of deterministic flows in a time synchronized network may be configured to support scheduling of deterministic flows in the time synchronized network based on assignment of transmission start times to data flows of communication devices such that the communication devices may transmit data of the data flows at the transmission start times in a manner tending to reduce or eliminate collisions in the time synchronized network.

Abstract: Network-based, unsupervised classifiers are provided. The classifiers identify both known and unknown attacks aimed at industrial networks without the need to have a priori knowledge of known malicious attack patterns.

Abstract: The present disclosure generally discloses improvements in computer performance for supporting various capabilities for enabling Internet-of-Things (IoT) devices to communicate via communication networks. The capabilities for enabling IoT devices to communicate via communication networks may include IoT device connectivity capabilities, IoT device discovery capabilities, IoT device networking capabilities, or the like.

Abstract: Various exemplary embodiments relate to a method of offline traffic matrix aware segment routing. The method may include receiving a traffic matrix based upon all the traffic between nodes i and j that is routed in the network; and determining the amount of traffic between nodes i and j will be routed through node k, based on minimizing a maximum link utilization for the traffic matrix by determining that the total amount of flow on a link e in the network is less than the link's capacity.

Abstract: The present disclosure generally discloses a data plane configured for processing function scalability. The processing functions for which scalability is supported may include charging functions, monitoring functions, security functions, or the like.

Abstract: Various exemplary embodiments relate to a method of offline traffic matrix unaware segment routing. The method may include determining the fraction of traffic between a node i and a node j is routed though node k, by minimizing the maximum value of any link e carrying traffic between node i and node j based upon the following constraints: using a dual variable ?(e,e?) where e? is an alternate link to e? for comparison, the fraction of traffic from i to j that is routed through intermediate node k is greater than or equal to zero; the total traffic from i to j that is routed through intermediate node k is equal to 1 for all (i,j) pairs; and determining when the total capacity for link e as constrained by the dual variable is less than or equal to the capacity, c of link e? for all e?.

Abstract: Various exemplary embodiments relate to a method of online segment routing in a network having an ingress node, an egress node, and a plurality of links, l. The method may include determining for a plurality of links l dual weights ?(l); receiving a new flow; determining an intermediate node k providing a minimum weight two segment path from the ingress node to egress node for the new flow based upon the flow that results on link l from the new flow through intermediate node k and the dual weight values ?(l) for the links l; and routing the new flow to the intermediate node k along the minimum weight path when the minimum weight path has a weight less than or equal to one.

Abstract: Various exemplary embodiments relate to a method of offline traffic matrix aware segment routing. The method may include receiving a traffic matrix based upon all the traffic between nodes i and j that is routed in the network; and determining the amount of traffic between nodes i and j will be routed through node k, based on minimizing a maximum link utilization for the traffic matrix by determining that the total amount of flow on a link e in the network is less than the link's capacity.

Abstract: A method and a system are disclosed for making available telecommunication network resources associated with network subscribers and exposed by a Network Service Gateway (NSG) to clients of the NSG services based on stored subscriber availability preferences. The method and system can be implemented using an availability Policy Server that sits next to or inside of the NSG. The Policy Server interprets the stored availability preferences of subscribers in response to requests for subscriber information. These availability preferences are translated into a low-level policy rule language. The Policy Server implements a policy rule evaluator to evaluate policies written in this language. Policies written in the low-level language are referred to as aPolicies (availability policies). An aPolicy receives as input a stream of events. Based on these events, the aPolicy may decide to take one or more actions. The NSG or clients of the NSG will carry out the execution of the actions.

Abstract: A method and a system for supporting rendezvous based instant group conferencing among mobile users allows a conference originator to initiate and setup instant group conferencing to a set of participants even when the participants may not be immediately available to commit to the conference call at the time of its initiation. All negotiations for obtaining commitments from the participants are performed by the system, thus relieving the originator of the time consuming task of negotiating with the participants. The system automatically decides as to when to actually dial out to the participants to setup the conference call after obtaining commitment from all (or a quorum of) required participants.

Abstract: A system and related method for supporting non-intrusive and effective voice communication among mobile users in which voice calls between mobile users are managed based on callee availability, caller-callee relationships, and non-intrusive information exchange, including interactive exchange at the time of call setup but prior to the call being answered. Callee availability can be based on callee device status, calendar activities, location, past behavior and other factors. The caller-callee relationships specify whether the callee is available, unavailable or on restricted availability relative to the caller. The interactive exchange can be implemented using voice and/or text/graphic displays on caller and callee mobile device. Callees are provided with options for handling the call. Callers are provided with information regarding the callee's current and future availability and willingness to receive a voice call from the caller, thus maximizing the chance of caller reaching the callee on every voice call.

Abstract: A system and related method for supporting non-intrusive and effective voice communication among mobile users in which voice calls between mobile users are managed based on callee availability, caller-callee relationships, and non-intrusive information exchange, including interactive exchange at the time of call setup but prior to the call being answered. Callee availability can be based on callee device status, calendar activities, location, past behavior and other factors. The caller-callee relationships specify whether the callee is available, unavailable or on restricted availability relative to the caller. The interactive exchange can be implemented using voice and/or text/graphic displays on caller and callee mobile device. Callees are provided with options for handling the call. Callers are provided with information regarding the callee's current and future availability and willingness to receive a voice call from the caller, thus maximizing the chance of caller reaching the callee on every voice call.