Abstract: The present disclosure relates to a device for use in a wireless network, the device including: a processor configured to: provide input data to a trained machine learning model, the input data representative of a network environment of the wireless network, wherein the trained machine learning model is configured to provide, based on the input data, output data representative of an expected performance of a plurality of configurations of network components with respect to power consumption and performance of the wireless network; select a configuration of a network component from the plurality of configurations based on the output data of the trained machine learning model; and instruct an operation of the network component according to the selected configuration; and a memory coupled with the processor, the memory storing the input data provided to the trained machine learning model and/or the output data from the trained machine learning model.

Abstract: A circuit arrangement includes a preprocessing circuit configured to obtain context information related to a user location, a learning circuit configured to determine a predicted user movement based on context information related to a user location to obtain a predicted route and to determine predicted radio conditions along the predicted route, and a decision circuit configured to, based on the predicted radio conditions, identify one or more first areas expected to have a first type of radio conditions and one or more second areas expected to have a second type of radio conditions different from the first type of radio conditions and to control radio activity while traveling on the predicted route according to the one or more first areas and the one or more second areas.

Abstract: In one embodiment, a road side unit (RSU) establishes a data offload session with a vehicle in the vicinity of the RSU based on a session establishment request sent by the vehicle, and stores data received from the vehicle during the data offload session in its memory. The RSU generates storage record information (including identifying information for the RSU) for the stored data, and transmits the storage record information to the vehicle.

Abstract: A circuit arrangement includes a preprocessing circuit configured to obtain context information related to a user location, a learning circuit configured to determine a predicted user movement based on context information related to a user location to obtain a predicted route and to determine predicted radio conditions along the predicted route, and a decision circuit configured to, based on the predicted radio conditions, identify one or more first areas expected to have a first type of radio conditions and one or more second areas expected to have a second type of radio conditions different from the first type of radio conditions and to control radio activity while traveling on the predicted route according to the one or more first areas and the one or more second areas.

Abstract: An apparatus and system of providing energy saving in a network are described. A target node receives, from a source node, a handover request to handover a UE due to at least one of entry of the source node into a power saving state or mobility optimization. In response, the target node transmits a relative energy efficiency value of Bits per Joule and periodic feedback related to a status of the UE for training an AI/ML energy saving model and stops the feedback in response to a stop parameter being met. The stop parameter is a first of: a predicted period of the source node to stay in the power saving state or time for a UE to connect to the target node, a percentage of UEs handed over that enter an idle or inactive state, and a percentage of UEs handed over that are further handed to another node.

Abstract: Edge devices utilizing personalized machine learning and methods of operating the same are disclosed. An example edge device includes a model accessor to access a first machine learning model from a cloud service provider. A local data interface is to collect local user data. A model trainer is to train the first machine learning model to create a second machine learning model using the local user data. A local permissions data store is to store permissions indicating constraints on the local user data with respect to sharing outside of the edge device. A permissions enforcer is to apply permissions to the local user data to create a sub-set of the local user data to be shared outside of the edge device. A transmitter is to provide the sub-set of the local user data to a public data repository.

Abstract: An apparatus of a computing node of a communication network, a system, a machine-readable storage medium, and a method. One or more processing circuitries of the apparatus are to: receive a plurality of service data flows (SDFs) associated with respective applications to be executed, the SDFs including data packets; determine first Quality of Service (QoS) flows corresponding to a plurality of first QoS requirements for the SDFs, wherein SDFs associated with a same application correspond to a same QoS requirement of the plurality of first QoS requirements; change the first QoS flows to second QoS flows different from the first QoS flows, the second QoS flows corresponding to a plurality of second QoS requirements for respective ones of the SDFs, the second QoS flows based on the respective applications and further based on respective ones of the data packets; and send for transmission from the output the plurality of SDFs based on the second QoS flows.

Abstract: Systems and techniques for service roaming between edge computing platforms are described herein. A service executing on a first edge computing platform may be identified to be migrated to a second edge computing platform. A first service component may be determined that is being executed by the first edge computing platform. Transmission of the service to the second edge platform may be initiated to execute a second service component for execution of the service.

Abstract: System and techniques for base station assisted Information Centric Network (ICN) are described herein. A mobile network base station receives an ICN packet from a user equipment (UE). The mobile network base station identifies an aggregate packet data unit (PDU) session with a user plane function (UPF) ICN gateway (ICN-GW) hosted in a mobile network core network (CN) for the ICN packet. Then, the mobile network base station transmits the ICN packet via the aggregate PDU session.

Abstract: Devices and techniques for Information Centric Network (ICN) packet transmission control are described herein. An interest (or data) packet may be received at an ICN router. Here, the packet includes quality of service (QoS) information. For an interest packet, the ICN router creates a pending interest table (PIT) entry for the packet. The ICN router determines that it does not have a route for the packet. Thus, if it is an interest packet, there is no forward route in a forwarding information base (FIB). If it is a data packet, there is no corresponding PIT entry. However, after extracting the QoS information from the packet, the ICN router broadcasts the packet in accordance with the QoS information.

Abstract: A telecommunication network may operate to enable a wake up signals (WUSs) within the telecommunication network. A mobility management entity (MME) may estimate a coverage enhancement (CE) level of a user equipment (UE), determine, based on the CE level, a number of repetitions for a wake up signal (WUS) for the UE, and cause a WUS for UE to be transmitted to a radio access network (RAN) node corresponding to the UE. The RAN node may inform the MME that the RAN node has disabled the WUS feature, and may cause system information to be broadcast to UEs in IDLE mode, indicating that the WUS feature of the RAN node has been disabled. A UE may determine a paging occasion (PO) determine a maximum WUS duration, minimum offset, and start location of the WUS.

Abstract: Examples described herein relate to dynamically composing an application as a monolithic implementation or two or more microservices based on telemetry data. In some examples, based on composition of an application as two or more microservices, at least one connection between microservices based on telemetry data is adjusted. In some examples, a switch can be configured to perform forwarding of communications between microservices based on the adjusted at least one connection between microservices.

Abstract: Methods and apparatus to provide power management for multi-die stacks using artificial intelligence are disclosed. An example integrated circuit (IC) package includes a computer processor unit (CPU) die, a memory die, inference engine circuitry within the CPU die, the inference engine circuitry to infer, based on a first machine learning model, a workload for at least one of the CPU die or the memory die, and power management engine circuitry within the CPU die, the power management engine circuitry distinct from the inference engine circuitry, the power management engine circuitry to adjust, based on a second machine learning model different than the first machine learning model, operational parameters associated with the at least one of the CPU die or the memory die, the inferred workload to be an input to the second machine learning model.

Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store sensor data captured by one or more sensors associated with a first device. Further, the processor comprises circuitry to: access the sensor data captured by the one or more sensors associated with the first device; determine that an incident occurred within a vicinity of the first device; identify a first collection of sensor data associated with the incident, wherein the first collection of sensor data is identified from the sensor data captured by the one or more sensors; preserve, on the memory, the first collection of sensor data associated with the incident; and notify one or more second devices of the incident, wherein the one or more second devices are located within the vicinity of the first device.

Abstract: System and techniques for network slice resiliency are described herein. An indication of a fault-attack-failure-outage (FAFO) event for a network slice may be received. Here, the network slice is one of multiple network slices. A capacity in a slice segment may be estimated to determine whether there is enough capacity to meet a service level agreement (SLA) of the multiple network slices based on the FAFO event. In this case, the slice segment is a set of physical resources shared by the multiple network slices. Operation of the slice segment may then be modified based on results from estimating the capacity in the slice segment to address impacts from the FAFO event.

Abstract: In one embodiment, a node of a data centric network (DCN) may receive a first service request interest packet from another node of the DCN, the first service request interest packet indicating a set of functions to be performed on source data to implement a service. The node may determine that it can perform a particular function of the set of functions, and determine, based on a backlog information corresponding to the particular function, whether to commit to performing the particular function or to forward the service request interest packet to another node. The node may make the determination further based on service delivery information indicating, for each face of the node, a service delivery distance for implementing the set of functions.

Abstract: Systems and methods of reducing power consumption associated with paging or cDRX mode are described. A wake-up receiver (WUR) wakes up from an idle mode or cDRX state. Whether a wake-up signal (WUS) has been received by the WUR is determined. The WUS is a low-complexity signal that is less complicated than a PDCCH or PDSCH and is repeated multiple times at resource elements as indicated in a configuration from an eNB. If received, a baseband transceiver wakes up for reception of a PDCCH for the UE in a PO when the UE is in the idle mode or a PDSCH for the UE when the UE is in the cDRX state.

Abstract: In one embodiment, an apparatus comprises a network interface and a processor. The processor is to: receive, via the network interface, a plurality of data streams to be routed over a network, wherein the plurality of data streams correspond to sensor data captured by a plurality of sensors; identify, from the plurality of data streams, a set of related data streams that are contextually related; identify a convergence function to be performed on the set of related data streams, wherein the convergence function is for transforming the set of related data streams into a converged data stream that is smaller in size than the set of related data streams; perform the convergence function to transform the set of related data streams into the converged data stream; and route, via the network interface, the converged data stream to one or more corresponding destinations over the network.

Abstract: Methods and apparatus to implement efficient memory storage in multi-die packages are disclosed. An example multi-die package includes a multi-die stack including a first die and a second die. The second die is stacked on the first die. The multi-die package further includes a third die adjacent the multi-die stack. The multi-die package also includes a silicon-based connector to communicatively couple the multi-die stack and the third die. The silicon-based connector includes at least one of a logic circuit or a memory circuit.

Abstract: Methods and apparatus to provide power management for multi-die stacks using artificial intelligence are disclosed. An example multi-die package includes a computer processor unit (CPU) die, a memory die stacked in vertical alignment with the CPU die, and artificial intelligence (AI) architecture circuitry to infer a workload for at least one of the CPU die or the memory die. The AI architecture circuitry is to manage power consumption of at least one of the CPU die or the memory die based on the inferred workload.