Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products for distributed Artificial Intelligence, AI. A first device receives a representation of at least part of a machine learning model and information representing a plurality of split points, a split point representing a layer at which an intermediate result of execution of the machine learning model may be output to a second device, the intermediate result enabling execution of the machine learning model from the split point, determines a selected split point from the plurality of split points, processes input data using the AI/ML model up to the selected split point to obtain an intermediate result corresponding to the selected split point, and outputs, to the second device, information corresponding to the intermediate result corresponding to the selected split point and information indicating the selected split point.

Abstract: Methods, apparatuses, systems, etc., directed to quality of experience (QoE) data analytics for multiple wireless transmit and receive units (WTRUs) in 5G networks are disclosed herein. In an embodiment, a method may comprise receiving a request message requesting a quality of service (QoS) configuration related to at least one WTRU involved in an application for obtaining a target QoE of the application. The first method may further comprise transmitting the QoS configuration obtained based on the target QoE. In an embodiment, a method may comprise transmitting a first request signal for subscribing to a service data from an application and receiving a first response signal comprising at least one identifier of at least one WTRU involved in the application, the first response signal may comprise at least one indication of at least one individual contribution of the at least one WTRU to a QoE of the application.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products for distributed Artificial Intelligence, AI. A first device partitions a unit of media data corresponding to a media content item into a plurality of media segments, and, for each media segment, determines a machine learning model, a machine learning part, and whether inference using the machine learning part is to be performed externally to the first device or by an inference unit of the first device, transmits content data corresponding to the media segment and information indicative of the determined machine learning model and machine learning part for inference, and obtains processed data resulting from processing of the content data using at least the machine learning part.

Abstract: A method performed by a wireless transmit/receive unit (WTRU) may comprise: receiving, from a base station, configuration information; receiving, from an application layer, one or more uplink protocol data units (PDUs); determining a buffering delay for transmitting the one or more uplink PDUs in resources associated with configured grant (CG) physical uplink shared channel (PUSCH) occasions; and on a condition that the buffering delay is greater than a delay threshold and that there are no available resources associated with semi-persistent scheduling (SPS) physical downlink shared channel (PDSCH)occasions within a time window, transmitting an indication of a time offset for the time window. The method may further comprise transmitting, to the base station, in a CG PUSCH occasion, the one or more uplink PDUs.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products for distributed Artificial Intelligence, AI. A first device receives from a second device information indicative of a plurality of distributed Artificial Intelligence, AI, models, wherein each model of the plurality of distributed AI models corresponds to a same AI service, transmits, to the second device, a message including information indicative of a selected distributed AI model from among the plurality of distributed AI models, wherein the selected distributed AI model includes a plurality of model subsets making up the AI service, receives information corresponding to a model subset of the selected distributed AI model, and runs the model subset of the selected distributed AI model based on the information corresponding to the model subset.

Abstract: A first network analysis node in a network receives, from a device, a first message comprising information indicative of a subscription, for the device, to network analytics information, and sends, to a second network node, a second message comprising information indicative of a request for a transfer of at least part of the subscription to network analytics information to a second network analysis node.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products of machine learning using a first machine learning (ML) module implementing a first ML model and a second ML module implementing a second ML model, the method comprising: receiving, by the second ML module, first prediction results of the first ML model, the first prediction results being based on input data; generating, by the second ML module, second prediction results using the second ML model based on the input data; determining, by the second ML module, an accuracy metric based on a comparison of the first prediction results of the first ML model and the second prediction results of the second ML model; and sending, by the second ML module, the determined accuracy metric and an accuracy condition.

Abstract: A first network analysis node in a network receives, from a device, a first message comprising information indicative of a subscription, for the device, to network analytics information, and sends, to a second network node, a second message comprising information indicative of a request for a transfer of at least part of the subscription to network analytics information to a second network analysis node.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products comprising: sending, by a first Wireless Transmit/Receive Unit (WTRU) to a network entity, a subscription request for downloading an AI/ML model, the AI/ML model comprising a first model portion, and one or more further model portions; determining a second WTRU storing at least the first model portion of the AI/ML model; sending, to the network entity, first information comprising an indication of the second WTRU; receiving, from the network entity, second information indicating a schedule for downloading at least the first model portion of the AI/ML model from the second WTRU; and downloading, from the second WTRU via a device-to-device communication between the first WTRU and the second WTRU, at least the first model portion of the AI/ML model at a scheduled time using the second information.

Abstract: A first network analysis node in a network receives, from a device, a first message comprising information indicative of a subscription, for the device, to network analytics information, and sends, to a second network node, a second message comprising information indicative of a request for a transfer of at least part of the subscription to network analytics information to a second network analysis node.

Abstract: In one implementation, a manifest application server provides to a UE a description text file, called “manifest.” which indicates several network communication paths to download or update a particular AI/ML model adapted to the target UE capabilities. The AI/ML model is supposed to be split into chunks. The manifest file is centralized and controlled by the manifest application server for delivering the best overall network efficiency with respect to different types of UEs in the system. The manifest file includes device to device communication paths and relevant information (bandwidth, chunk IDs, etc.) provided by the UE themselves. The manifest application server publishes a set of different manifests describing different network communication paths and related expected network limitations for downloading particular model chunks.

Abstract: A first network analysis node in a network receives, from a device, a first message comprising information indicative of a subscription, for the device, to network analytics information, and sends, to a second network node, a second message comprising information indicative of a request for a transfer of at least part of the subscription to network analytics information to a second network analysis node.

Abstract: Instantiating a Network Service described by a Forwarding Graph comprising Virtual Network Functions, VNF instances, which are interconnected via communication links. This includes splitting the Forwarding Graph into n VNF Elementary Graphs, VNF EGs. Each of the VNF EGs for a VNF Instance includes routing information for forwarding, by that VNF instance and to another VNF instance, packets output by that VNF instance based on a packet class identifier included in the packet. Each of the VNF EGs is transmitted to the corresponding VNF instance for that VNF EG. Each of the VNF instances, when outputting a packet handled by it, then transmits the packet to a next VNF instance based on the packet class identifier included in the packet.

Abstract: Methods, apparatuses, systems, etc., directed to quality of experience (QoE) data analytics for multiple wireless transmit and receive units (WTRUs) in 5G networks are disclosed herein. In an embodiment, a method may comprise receiving a request message requesting a quality of service (QoS) configuration related to at least one WTRU involved in an application for obtaining a target QoE of the application. The first method may further comprise transmitting the QoS configuration obtained based on the target QoE. In an embodiment, a method may comprise transmitting a first request signal for subscribing to a service data from an application and receiving a first response signal comprising at least one identifier of at least one WTRU involved in the application, the first response signal may comprise at least one indication of at least one individual contribution of the at least one WTRU to a QoE of the application.

Abstract: The invention relates to a method for controlling access to a first network, comprising receiving, by a first network access device of the first network, an access request from a visiting user device, determining, by the first network access device, if the visiting user device was granted an access to the first network, if the visiting device has not been granted an access to the first network, determining if there is a second network access device that granted the visiting user device an access to a second network and the second network access device is linked to the first network access device, and if the second network access device exists, granting the visiting user device an access to the first network by the first network access device.

Abstract: In an Internet interface device such as a gateway managing a local network, a processor obtains a packet received from a device via a local network interface. The processor can determine whether or not the packet originates from a device in the local network deemed to be part of a particular group. The processor can also determine if the packet is addressed to an internet domain for which it stores identifying information in memory. In this case, the processor inspects the packet in search of a cookie. In case no cookie is found, the packet is output as is; if a cookie is found, the processor modifies cookie information in the packet by inserting a cookie specific to the Internet interface device, which results in a modified packet that then is output through the internet interface. Using the original cookie and the added cookie, it is possible to link cookies sent from different devices in the local network.

Abstract: A network equipment includes at least one access point interface and is configured to operate a plurality of network functions. The network equipment is configured to be in communication with at least one terminal belonging to a network. The network equipment further includes at least one classifier configured to modify a data frame, the data frame coming from the at least one terminal and being received by the access point interface. The data frame may be modified by replacing an address of the data frame with processing information.

Abstract: A Forwarder (220) in a network (200), preferably based on Information-Centric Networking (ICN), receives (S310) a first request for data, the first request comprising an identifier of requested data and a condition from a Consumer device (210) or a second Forwarder device, sends (S335) a second request for the data to a Producer device (230) or a third Forwarder device in the network (200), the second request comprising at least the identifier of the data, receives (S340) received data corresponding to requested data from the Producer device (230) or the third Forwarder device, determines (S350) whether the received data satisfy the condition and sends (S355) the requested data to the Consumer device (210) or the second Forwarder device only in case the received data satisfy the condition.

Abstract: The invention relates to a method for controlling access to a first network, comprising receiving, by a first network access device of the first network, an access request from a visiting user device, determining, by the first network access device, if the visiting user device was granted an access to the first network, if the visiting device has not been granted an access to the first network, determining if there is a second network access device that granted the visiting user device an access to a second network and the second network access device is linked to the first network access device, and if the second network access device exists, granting the visiting user device an access to the first network by the first network access device.

Abstract: A device configured to be connected to a customer premises equipment of a first type network. The first network includes at least one network apparatus in communication with the customer premises equipment and having a communication interface configured to receive capabilities information from the customer premises equipment and the at least one network apparatus, a routing application to define, based on the received capabilities information, one or several routing rules to route packets of the device. The routing rules identifying either the customer premises equipment or the at least one network apparatus to forward packets between the first type network and a second type network. The communication interface being further configured to send commands to enforce the defined routing rules either at the customer premises equipment or at the at least one network apparatus.