Abstract: The present disclosure is related to managing a caching system based on object fetch costs, where the fetch cost are based on the access latency, cache misses, and time to reuse of individual objects. The caching system may be a multi-tiered caching system that includes multiple storage tiers, where an object management system determines whether to retain or evict an object from a cache of a particular storage tier based on the object's fetch cost. Additionally, eviction can include moving objects from a current storage tier to another storage tier based on the current storage tier and fetch costs.

Abstract: Technologies for collecting metrics associated with a processing resource (e.g., central processing unit (CPU) resources, accelerator device resources, and the like) over a time window are disclosed. According to an embodiment presented herein, a network device receives, in an edge network, a request to provide one or more metrics associated with a processing resource, the request specifying a window indicative of a time period to capture the one or more metrics. The network device obtains the one or more metrics from the processing resource for the specified window and provides the obtained one or more metrics in response to the request.

Abstract: There is disclosed in one example a network device, including: a hardware platform including at least a processor and a memory; a communication interface; and stored instructions on the memory to instruct the processor to provide a health monitoring engine (HME) configured to: communicatively couple to a network via the network interface; construct a reference template during a training period; observe watchdog behavior on the network during an observation period; identify an abnormality in the watchdog behavior including a substantial variance from the reference template; and trigger a resilience response to the substantial variance.

Abstract: Methods and systems are provided for a contextual authentication of an electronic wallet (e-wallet). An example apparatus includes a wallet application configured to confirm a context for use of an e-wallet, wherein the context is defined by a multifactor authentication (MFA) policy. A multifactor authentication application is configured to access a context sensor to provide input to the wallet application for the MFA policy.

Abstract: Various approaches for deployment and use of configurable edge computing platforms are described. In an edge computing system, an edge computing device includes hardware resources that can be composed from a configuration of chiplets, as the chiplets are disaggregated for selective use and deployment (for compute, acceleration, memory, storage, or other resources). In an example, configuration operations are performed to: identify a condition for use of the hardware resource, based on an edge computing workload received at the edge computing device; obtain, determine, or identify properties of a configuration for the hardware resource that are available to be implemented with the chiplets, with the configuration enabling the hardware resource to satisfy the condition for use of the hardware resource; and compose the chiplets into the configuration, according to the properties of the configuration, to enable the use of the hardware resource for the edge computing workload.

Abstract: In one embodiment, an apparatus comprises a processor to execute instructions and having at least a first logic to execute in a trusted execution environment, a secure storage to store a platform group credential, and a first logical device comprising at least one hardware logic. The platform group credential may be dynamically provisioned into the apparatus and corresponding to an enhanced privacy identifier associated with the apparatus. The first logical device may have a first platform group private key dynamically provisioned into the first logical device and corresponding to an enhanced privacy identifier associated with the first logical device, to bind the first logical device to the apparatus. Other embodiments are described and claimed.

Abstract: Technologies for load balancing on a network device in an edge network are disclosed. An example network device includes circuitry to receive, in an edge network, a request to access a function, the request including one or more performance requirements, identify, as a function of an evaluation of the performance requirements and on monitored properties of each of a plurality of devices associated with the network device, one or more of the plurality of devices to service the request, select one of the identified devices according to a load balancing policy, and send the request to the selected device.

Abstract: This disclosure is directed to privacy enforcement via localized personalization. An example device may comprise at least a user interface to present content. A message may be received into a trusted execution environment (TEE) situated within the device or remotely, the message including at least metadata and content. The TEE may determine relevance of the content to a user based on the metadata and user data. Based on the relevance, the TEE may cause the content to be presented to the user via the user interface. In one embodiment, the TEE may be able to personalize the content based on the user data prior to presentation. If the content includes an offer, the TEE may also be able to present counteroffers to the user based on user interaction with the content. The TEE may also be able to cause feedback data to be transmitted to at least the content provider.

Abstract: Technologies for hybrid acceleration of code include a computing device (100) having a processor (120), a field-programmable gate array (FPGA) (130), and an application-specific integrated circuit (ASIC) (132). The computing device (100) offloads a service request, such as a cryptographic request or a packet processing request, to the FPGA (130). The FPGA (130) performs one or more algorithmic tasks of an algorithm to perform the service request. The FPGA (130) determines one or more primitive tasks associated with an algorithm task and encapsulates each primitive task in a buffer that is accessible by the ASIC (132). The ASIC (132) performs the primitive tasks in response to encapsulation in the buffer, and the FPGA (130) returns results of the algorithm. The primitive operations may include cryptographic primitives such as modular exponentiation, modular multiplicative inverse, and modular multiplication.

Abstract: Systems and techniques for adaptive dataflow transformation in edge computing environments are described herein. A transformation compatibility indication may be received from a device. A set of transformations available for use by the device connected to the network may be determined based on the transformation compatibility indicator. The set of transformations may be transmitted to the device. A value may be determined for an operating metric for an edge computing node of the network. The edge computing node may provide a service to the device via the network. A transformation request may be transmitted to the device based on the value. The transformation request may cause the device to execute a transformation of the set of transformations to transform a dataflow of the service. The adaptive dataflow transformations may be continuous with changing predicted values of operating metrics.

Abstract: In one embodiment, an apparatus comprises processing circuitry to: receive, via a network interface, a video stream comprising a plurality of video frames; identify a plurality of dependencies among the plurality of video frames; identify, based on the plurality of dependencies, a first subset of video frames to be transmitted using a first transmission method and a second subset of video frames to be transmitted using a second transmission method, wherein the first subset of video frames and the second subset of video frames are identified from the plurality of video frames, and wherein the first transmission method provides a higher quality of service than the second transmission method; transmit, via the network interface, the first subset of video frames to a corresponding destination using the first transmission method; and transmit, via the network interface, the second subset of video frames to the corresponding destination using the second transmission method.

Abstract: Various systems and methods of artificial intelligence (AI) processing using hardware acceleration within edge computing settings are described herein. In an example, processing performed at an edge computing device includes: obtaining a request for an AI operation using an AI model; identifying, based on the request, an AI hardware platform for execution of an instance of the AI model; and causing execution of the AI model instance using the AI hardware platform. Further operations to analyze input data, perform an inference operation with the AI model, and coordinate selection and operation of the hardware platform for execution of the AI model, is also described.

Abstract: Technologies for accelerated key caching in an edge hierarchy include multiple edge appliance devices organized in tiers. An edge appliance device receives a request for a key, such as a private key. The edge appliance device determines whether the key is included in a local key cache and, if not, requests the key from an edge appliance device included in an inner tier of the edge hierarchy. The edge appliance device may request the key from an edge appliance device included in a peer tier of the edge hierarchy. The edge appliance device may activate per-tenant accelerated logic to identify one or more keys in the key cache for eviction. The edge appliance device may activate per-tenant accelerated logic to identify one or more keys for pre-fetching. Those functions of the edge appliance device may be performed by an accelerator such as an FPGA. Other embodiments are described and claimed.

Abstract: An Internet of Things (IoT) network includes an IoT device with a communicator to send a communication including egress frame, protocol library builder to determine available protocols, frame analyzer to analyze an ingress frame, and frame builder to build the egress frame from the ingress frame. An IoT network includes an IoT device with network discoverer to identify available parallel communication channels between the IoT device and target device, payload, payload fragmenter/packager to fragment the payload into sub-objects for transmission, and packet communicator to send sub-objects to the target device over parallel communication channels. An IoT network includes a plurality of IoT devices, which each include a communication channel to an upstream device, a network link to another one of the plurality of IoT devices, a hash calculator to identify a neighbor IoT device, and a communicator to send out a message to the neighbor IoT device.

Abstract: A method, apparatus, system, and computer program product for domain-authenticated control of platform resources. Resources under the control of the platform are managed in accordance with access control rules that are centrally managed by a directory service. Security policies are uniformly applied by requiring authorization of the user's access to platform resources including hard drives, flash memory, sensors, network controllers and power state controllers.

Abstract: Various systems and methods of establishing data model visibility in IoT network implementations, through an internal data model and external data model and associated data representations are described herein. In an example, a data representation is defined for a data set that corresponds to an internal (a not externally visible data model), where there is a permutation or change of the data that is applied before it is revealed or made visible externally. Such data permutations and state changes may be used to qualify some aspect of the internal model to be made visible to the external model, for a variety of IoT network use cases.

Abstract: Systems and techniques for digital twin framework for next generation networks are described herein. A digital twin model may be generated for physical nodes of an edge network. The digital twin model may include a digital twin for a physical node of the physical nodes. An error may be identified of the physical node or the digital twin for the physical node. The digital twin model may be updated to halt communication with the physical node or the digital twin of the physical node. A path may be created to another physical node or a digital twin of the another physical node in the digital twin model.

Abstract: An architecture to allow Multi-Access Edge Computing (MEC) billing and charge tracking, is disclosed. In an example, a tracking process, such as is performed by an edge computing apparatus, includes: receiving a computational processing request for a service operated with computing resources of the edge computing apparatus from a connected edge device within the first access network, wherein the computational processing request includes an identification of the connected edge device; identifying a processing device, within the first access network, for performing the computational processing request; and storing the identification of the connected edge device, a processing device identification, and data describing the computational processes completed by the processing device in association with the computational processing request.

Abstract: Various systems and methods for discovery and onboarding in an interconnected network framework of Internet of Things (IoT) devices are described. In an example, a technique for onboarding and provisioning a device onto an interconnected network framework includes operations to: receive a unique temporary device identifier from a device instance, the device instance indicating availability for onboarding onto a network; onboard the device instance onto the network; establish a secure session with the device instance via the network; receive, in the secure session, a secure device identifier; and initiate provisioning of the device instance in a secure directory based on the secure device identifier. In a further example, techniques are provided to securely identify and provision a second device instance (a doppelganger device instance) operating on a physical device that hosts both the first device instance and the second device instance.

Abstract: Systems and techniques for end-to-end quality of service in edge computing environments are described herein. A set of telemetry measurements may be obtained for an ongoing dataflow between a device and a node of an edge computing system. A current key performance indicator (KPI) may be calculated for the ongoing dataflow. The current KPI may be compared to a target KPI to determine an urgency value. A set of resource quality metrics may be collected for resources of the network. The set of resource quality metrics may be evaluated with a resource adjustment model to determine available resource adjustments. A resource adjustment may be selected from the available resource adjustments based on an expected minimization of the urgency value. Delivery of the ongoing dataflow may be modified using the selected resource adjustment.