Abstract: Various systems and methods for content adaptation based on seat position or occupant position in a vehicle are described herein. An example implementation for content adaptation based on seat position in a vehicle includes: obtaining sensor data, the sensor data including a seat position of a seat in the vehicle; identifying audiovisual content for output to a human occupant in the vehicle; identifying an occupant position of the human occupant, based on the seat position, for a user experience of the output of the audiovisual content; and cause one or more adjustments to the output of the audiovisual content in the vehicle, via an output device, based on the identified position of the human occupant.

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed for in-network computation and control of network congestion based on in-network computation delays. An example device includes interface circuitry to access a packet including a header having (1) a destination address field to identify a first network address of a destination device capable of performing an action and (2) a workload class field to identify a workload class associated with the action. The example device also includes programmable circuitry to utilize machine-readable instructions to perform the action at the device based on the workload class field, the device having a second network address that is different than the first network address. Additionally, the example programmable circuitry is to modify an indicator field of the packet to indicate that the action has been performed and cause the interface circuitry to forward the packet with the modified indicator field toward the destination device.

Abstract: Systems and techniques for distributed machine learning (DML) in an information centric network (ICN) are described herein. Finite message exchanges, such as those used in many DML exercises, may be efficiently implemented by treating certain data packets as interest packets to reduce overall network overhead when performing the finite message exchange. Further, network efficiency in DML may be improved achieved by using local coordinating nodes to manage devices participating in a distributed machine learning exercise. Additionally, modifying a round of DML training to accommodate available participant devices, such as by using a group quality of service metric to select the devices, or extending the round execution parameters to include additional devices, may have an impact on DML performance.

Abstract: Systems and methods of providing DMRS for a UE are generally described. The DMRS locations in a resource unit of a Physical Resource Allocation of a shared channel are randomly determined, and the DMRS sequences randomly generated before transmission from a master UE to a wearable UE. The DMRS locations are disposed on different subcarriers and symbols in the resource unit and are repeated every k subframes or m resource units within the same subframe. In situations in which the collision/contention probability is relatively small, DMRS in control channels may be used rather than in the shared data channel.

Abstract: Various approaches for deploying and controlling distributed compute operations with the use of infrastructure processing units (IPUs) and similar networked processing units are disclosed. For example, a payload may be received at a networking infrastructure device. Here, the payload is part of a workload that is routed through the networking infrastructure device from a first network node to a second network node. The networking infrastructure device may obtain a workload graph for the workload with vertices of the workload graph specifying functions. The networking infrastructure device may apply a function to the payload in accordance with the workload graph to transform the payload into a processed payload. The processed payload may be transmitted towards the second network node.

Abstract: Various approaches for deploying and controlling distributed compute operations with the use of infrastructure processing units (IPUs) and similar network-addressable processing units are disclosed.

Abstract: Systems and techniques for machine generation of content names in an information centric network (ICN) are described herein. For example, a node may obtain content. An inference engine may be invoked to produce a name for the content. Once the content is named, the node may respond to an interest packet that includes the name of the content. The response is a data packet that includes the content.

Abstract: Systems and methods for managing distributed compute resources are described herein. A system is configured to receive, from an agent operating at a first compute domain of a plurality of compute domains, a request for compute resources; broadcast the request for compute resources to respective agents at the plurality of compute domains; receive a plurality of offers for available compute resources from at least a portion of the plurality of compute domains; transmit, to a selected agent at a selected compute domain of the plurality of compute domains, a commit message to reserve compute resources of the selected compute domain associated with a selected offer of the plurality of offers; and transmit an indication of the commit message to the agent at the first compute domain, wherein the first compute domain is to use the compute resources reserved at the selected compute domain for workloads of the first compute domain.

Abstract: Systems and techniques for distributed machine learning (DML) in an information centric network (ICN) are described herein. Finite message exchanges, such as those used in many DML exercises, may be efficiently implemented by treating certain data packets as interest packets to reduce overall network overhead when performing the finite message exchange. Further, network efficiency in DML may be improved achieved by using local coordinating nodes to manage devices participating in a distributed machine learning exercise. Additionally, modifying a round of DML training to accommodate available participant devices, such as by using a group quality of service metric to select the devices, or extending the round execution parameters to include additional devices, may have an impact on DML performance.

Abstract: A computing node includes interface circuitry and processing circuitry. To implement a spectrum harvesting entity in a wireless network configured for crowdsource-based unlicensed spectrum harvesting, the processing circuitry is configured to select a set of crowdsourcing nodes from a plurality of crowdsourcing nodes available in the wireless network. A plurality of spectrum occupancy reports (SORs) is received from the set of crowdsourcing. Each of the plurality of SORs indicates a channel occupancy status of a communication channel in the unlicensed spectrum sensed by a corresponding crowdsourcing node of the set and geolocation associated with the corresponding crowdsourcing node. A spectrum occupancy map of the unlicensed spectrum is generated based on the channel occupancy status and the geolocation provided in the plurality of SORs by each crowdsourcing node of the set of crowdsourcing nodes.

Abstract: A 3GPP LTE protocol enhancement realizes the full benefit of discontinuous reception (DRX) in Long Term Evolution networks by coordinating and aligning DRX operations for conserving power and timing overhead. A dual connectivity enabled User Equipment (UE) comprising a processor and transceiver is configured to align DRX configuration between counterpart Evolved Node Bs (eNB)s, wherein counterpart eNBs are a Master eNB (MeNB) and a Secondary eNB (SeNB) simultaneously connected to the UE, communicate system frame timing and system frame number (SFN) information between the counterpart eNBs, align DRX start offset (drxStartOffset) values for the counterpart eNBs according to the communicated system frame timing and SFN information to compensate for offsets in system frame timing, and allow the start of a DRX ON duration at specific frame or sub-frame times determined by the drxStartOffset values, after the expiration of a DRX inactivity timer.

Abstract: Systems and techniques for quality-of-service (QoS) in cellular information centric network (ICN) are described herein. An example system includes processing circuitry, and a memory that includes instructions, the instructions, when executed by the processing circuitry, cause the processing circuitry to obtain QoS characteristics for an ICN packet, apply the QoS characteristics to the ICN packet, and transmit the ICN packet over the cellular ICN in accordance with the QoS characteristics.

Abstract: Systems and techniques for an information centric network (ICN) distributed search with approximate cache and forwarding information lookup. For example, a search interest packet may be received. Here, the search interest packet includes search criteria and a signal indicating that it is a search interest packet. A search for content—including content in a local content store—that meets the search criteria may then be performed. Once complete, a data packet that includes the results of the search may be transmitted towards an author of the search interest packet.

Abstract: A 3GPP LTE protocol enhancement realizes the full benefit of discontinuous reception (DRX) in Long Term Evolution networks by coordinating and aligning DRX operations for conserving power and timing overhead. A dual connectivity enabled User Equipment (UE) comprising a processor and transceiver is configured to align DRX configuration between counterpart Evolved Node Bs (eNB)s, wherein counterpart eNBs are a Master eNB (MeNB) and a Secondary eNB (SeNB) simultaneously connected to the UE, communicate system frame timing and system frame number (SFN) information between the counterpart eNBs, align DRX start offset (drxStartOffset) values for the counterpart eNBs according to the communicated system frame timing and SFN information to compensate for offsets in system frame timing, and allow the start of a DRX ON duration at specific frame or sub-frame times determined by the drxStartOffset values, after the expiration of a DRX inactivity timer.

Abstract: System and techniques for an environmental control loop are described herein. A device for an environmental control loop can include a memory including instructions and processing circuitry that when in operation, can be configured by the instructions to receive environmental sensor data from a first component in a set of heterogeneous components installed in an environment with a controller. The environmental sensor data can indicate a service level value sensed by the first component. The controller can also measure a violation of a service level objective based on comparing the environmental sensor data to a threshold. The controller can also transmit an adjustment to an operating parameter of a second component of the set of heterogeneous components. The adjustment can be operative to attenuate the violation of the service level objective when implemented by the second component.

Abstract: Systems and techniques for efficient remote function execution in an information centric network (ICN) are described herein. For example, a requestor node may transmit an admission probe interest packet. Here, the admission probe interest packet includes a name that includes a function. The admission probe interest packet also includes a metric of a parameter of the function. In response, the requestor node may receive a manifest data packet. The manifest includes a metric of function execution at a node that created the manifest data packet. The manifest also includes a name of an implementation of the function. The requestor node may then determine that the metric of function execution meets a threshold and transmit an interest packet that includes the name of the implementation of the function.

Abstract: Various systems and methods for providing opportunistic placement of compute in an edge network are described herein. A node in an edge network may be configured to access a service level agreement related to a workload, the workload to be orchestrated for a user equipment by the node; modify a machine learning model based on the service level agreement; implement the machine learning model to identify resource requirements to execute the workload in a manner to satisfy the service level agreement; initiate resource assignments from a resource provider, the resource assignments to satisfy the resource requirements; construct a resource hierarchy from the resource assignments; initiate execution of the workload using resources from the resource hierarchy; and monitor and adapt execution of the workload based on the resource hierarchy in response to the execution of the workload.

Abstract: Disclosed are systems and methods for adaptive resilient network communication. A system may monitor network traffic on multiple pathways between user equipment and an application or a service at a network destination, gather network telemetry data from the monitored network traffic, input the network telemetry data into a trained artificial intelligence model, and classify the network telemetry data using the model. The system may further determine, using the model, an anomaly condition in at least a portion of the multiple pathways, and in response to the determination of an anomaly, select a mitigation technique for the at least a portion of the multiple pathways.

Abstract: Systems and techniques for distributed machine learning (DML) in an information centric network (ICN) are described herein. Finite message exchanges, such as those used in many DML exercises, may be efficiently implemented by treating certain data packets as interest packets to reduce overall network overhead when performing the finite message exchange. Further, network efficiency in DML may be improved achieved by using local coordinating nodes to manage devices participating in a distributed machine learning exercise. Additionally, modifying a round of DML training to accommodate available participant devices, such as by using a group quality of service metric to select the devices, or extending the round execution parameters to include additional devices, may have an impact on DML performance.

Abstract: A resource management framework may be used to improve performance of dominant and non-dominant resources for edge multi-tenant applications. The resource management framework may include an admission control mechanism, which may be used to balance disproportionate resource allocations by controlling allocation of unconstrained resources proportional to the requested dominant resources based on resource availability. The admission control mechanism may provide ongoing monitoring of dominant and non-dominant resource utilization, such as using a hybrid centralized-distributed telemetry collection approach. The resource management framework may also include a lightweight resource monitoring and policy enforcement mechanism on distributed networking elements to reduce or eliminate the exploitations of non-dominant resources.