Microsoft Technology Licensing, LLC

Elwha LLC

Paramvir Bahl

Ranveer Chandra

Lin Zhong

Tim Paek

Alastair Wolman

Sharad Agarwal

Craig J Mundie

Lowell L Wood, Jr

Roderick A Hyde

Clarence T Tegreene

Jordin T Kare

Nathan P Myhrvold

Robert W Lord

Muriel Y Ishikawa

Victoria Y H Wood

Charles Whitmer

Richard T Lord

William Henry Gates, Iii

Douglas Christopher Burger

Desney S Tan

Matthew Graham Dyor

Jitendra Dattatraya Padhye

Atul Adya

Thomas Moscibroda

Ganesh Ananthanarayanan

Rachee Singh

Srinivasan Venkatachary

Anand Balachandran

Pablos Holman

Ryan Andrew Beckett

Manikanta Kotaru

Mark A Malamud

Royce A Levien

John D Rinaldo, Jr

Ming Zhang

Paul D Holman

Lili Qiu

Abhishek Udupa

Sanjeev Mehrotra

Pradeep Bahl

Stefan Saroiu

Srikanth Kandula

Landon Prentice Cox

Timothy S Paek

Lidong Zhou

Peter Bodik

Venkata N Padmanabhan

Bozidar Radunovic

David Chiyuan Chu

Matthai Philipose

Kun Tan

Yunnan Wu

Brian Don Zill

Xenofon Foukas

Yongguang Zhang

Kevin A Chin

Amer A Hassan

Michael Jack Sinclair

Ivan Jelev Tashev

David A Maltz

Paul Nathan Bennett

Ratul Mahajan

Lenin Ravindranath Sivalingam

Joshua Glenn Broch

Daehyeok Kim

Jie Jerry Liu

Stephen Edward Hodges

Albert Gordon Greenberg

James William Scott

Yi-Min Wang

Daniel Ron Simon

Ramachandran Ramjee

Aman Kansal

Bernard D Aboba

Jiansong Zhang

Yong He

Eduardo Alberto Cuervo Laffaye

Jonathan Bernard Lester

Anoop Gupta

Thomas W Kuehnel

Timothy Mark Moore

William Jefferson Westerinen

Li Erran Li

Abhishek Abhishek

John David Dunagan

Kamal Jain

Nissanka Arachchige Bodhi Priyantha

Bongshin Lee

Warren Vincent Barkley

Edward Charles Giaimo, Iii

Alice Jane Bernheim Brush

Barry Clayton Bond

Sasa Junuzovic

Ying Zhang

Romit Roy Choudhury

Xu Chen

Jean Pierre De Vries

Hariharan Rahul

Poovanpilli G Madhavan

Aspects of the present disclosure relate to determining reference symbol transmission times. In some examples, a method for determining reference symbol transmission times for cellular communications includes receiving signal feedback based on a wireless communication channel between a wireless communication device and a base station, identifying a periodic exchange of reference symbols that are used to adjust beamforming between the wireless communication device and the base station, generating a vector based on the signal feedback, and providing the vector as an input to a trained machine learning model. A training of the trained machine learning model includes calculating a plurality of rewards for a respective plurality of transmission time delays. The plurality of rewards are each calculated based on a function of downlink throughput and uplink overhead. The function of downlink throughput and uplink overhead are based upon a priority level of the wireless communication device.

Determining reference signal transmission times

A context analysis system receives a query from a user. The context analysis system generates one or multiple context profiles and generates a prompt for a foundation model for each of the context profiles. The context analysis system analyzes each of the context profiles and generates a relevancy score. The context analysis system selects one of the context profiles based on the relevancy score. In some examples, the context analysis system iteratively determines predicted latencies and relevancies of processing a query in conjunction with a generated context and, based on the predicted latencies and/or relevancies, processes the query using a foundation model, such as a large language model (LLM).

Generating and implementing context profiles in processing queries using foundation models

Described are examples for monitoring performance metrics of one or more workloads in a cloud-computing environment and reallocating compute resources based on the monitoring. Reallocating compute resources can include migrating workloads among nodes or other resources in the cloud-computing environment, reallocating hardware accelerator resources, adjusting transmit power for virtual radio access network (vRAN) workloads, and/or the like.

Techniques for adaptively allocating resources in a cloud-computing environment

Methods and systems for dynamically re-routing layer traffic between different servers with little user-visible disruption and without modifications to the vRAN software stack are provided. For instance, transformations on messages between the L2 and PHY, such as duplication and filtering, enable the system to maintain one or more low-overhead 'hot, inactive' PHY clones. A hot, inactive PHY clone may be a duplicate of an operational PHY, where the PHY clone is primed to process a PHY workload of the operational PHY (e.g., “hot”) but is not currently responsible for processing the PHY workload (e.g., low-overhead, inactive). In this way, a PHY workload may be automatically and seamlessly migrated to the hot PHY clone in response to planned downtime (e.g., scheduled maintenance, software upgrades) or unexpected events (e.g., server failures) within the strict transmission time intervals (TTIs) required for processing the PHY workload.

Creating elasticity and resiliency in virtualized RANs

Systems and methods are provided for continuous learning of models across hierarchies under a multi-access edge computing. In particular, an on-premises edge server, using a model, generates inference data associated with captured stream data. A data drift determiner determines a data drift in the inference data by comparing the data against reference data generated using a golden model. The data drift indicates a loss of accuracy in the inference data. A gateway model maintains one or more models in a model cache for update the model. The gateway model instructs the one or more servers to train the new model. The gateway model transmits the trained model to update the model in the on-premises edge server. Training the new model includes determining an on-premises edge server with computing resources available to train the new model while generating other inference data for incoming stream data in the data analytic pipeline.

Continuous learning models across edge hierarchies

Systems and methods are provided for performing privacy transformation of data to protect privacy in data analytics under the multi-access edge computing environment. In particular, a policy receiver in an edge server receives privacy instructions. Inference determiner in the edge server in a data analytics pipeline receives data from an IoT device and evaluates the data to recognize data associated with personally identifiable information. Privacy data transformer transforms the received data with inference for protecting data privacy by preventing exposure of private information from the edge server. In particular, the privacy data transformer dynamically selects a technique among techniques for removing information that is subject to privacy protection and transforms the received data using the technique. The techniques includes reducing resolution of image data such that inference enables object recognition without sufficient details to prevent other servers in the data analytics pipeline to determine identifies of the object deeper inferences.

Privacy transformations in data analytics

Described are examples for calculating and exposing network capacity and congestion to applications. A network entity such as a radio access network (RAN) intelligent controller (RIC) or virtual base station component receives measurements of a signal quality for a plurality of user devices connected to a RAN. The network entity estimates a deliverable throughput of a wireless link for a user device of the plurality of user devices based on at least the measurements. The network entity can consider other factors such as a number of competing users, queue sizes of the user device and of the competing users, or a scheduling policy. The network entity provides the deliverable throughput to an application server for an application of the user device communicating with the application server via the RAN. The application server can adapt a data rate for the application and the user device based on the deliverable throughput.

Calculating and exposing network capacity and congestion to applications

The devices and methods leverage harmonics to resolve, separate, and identify devices. The devices and methods use the harmonic patterns associated with a frequency modulating (FM) signal to discern and extract information from the FM signal using correlation learning in a crowded spectrum space where the nodes are transmitting simultaneously on multiple channels. The methods and devices leverage harmonics to resolve, separate, and/or identify wireless communication devices.

Harmonic-enhanced identification (ID) and device resolution for frequency modulating communication

Resistance to vulnerabilities from timing-based side-channel attacks on 5G network slices that share underlying physical infrastructure and resources may be enhanced by selectively imposing time-based constraints on service provisioning and data handling to obscure data-driven time variations that occur during workload execution in a slice that can leak secret information. By preventing timing leakage from the 5G network slices, an attacker cannot observe execution latencies to thereby infer the constituency of workload characteristics. In addition, the attacker cannot create contention for shared resources on its own slice to observe an extent to which the shared resources are utilized by a targeted slice.

Resistance to side-channel attacks on 5G network slices

A method for utilizing computing resources in a vRAN is described. A predicted resource load is determined for data traffic processing of wireless communication channels served by the vRAN using a trained neural network model. The data traffic processing comprises at least one of PHY data processing or MAC processing for a 5G RAN. Computing resources are allocated for the data traffic processing based on the predicted resource load. Wireless parameter limits are determined for the wireless communication channels that constrain utilization of the allocated computing resources using the trained neural network model, including setting one or more of a maximum number of radio resource units per timeslot or a maximum MCS index for the wireless parameter limits. The data traffic processing is performed using the wireless parameter limits to reduce load spikes that cause a violation of real-time deadlines for the data traffic processing.

Wireless parameter limits for predicted vRAN resource loads

Methods and systems for dynamically re-routing layer traffic between different servers with little user-visible disruption and without modifications to the vRAN software stack are provided. This approach enables operators to initiate a PHY migration either on demand (e.g., during planned maintenances) or to set up automatic migration on unexpected events (e.g., server failures). It is recognized that PHY processing in cellular networks has no hard state that must be migrated. As a result, layer traffic such as the PHY-L2 traffic or L2-PHY traffic can be simply re-routed to a different server. This re-routing mechanism is realized by interposing one or more message controllers (e.g., middlebox) in a communication channel between the PHY and L2.

Dynamic re-routing and modification of layer traffic in virtualized RANs

A method for improving efficiency of routing edge compute traffic from a user equipment (UE) to an edge compute server at a far edge of a cellular network includes provisioning a near edge control unit (CU) and a near edge user plane function (UPF) at a near edge of the cellular network. The method also includes provisioning a far edge CU, a far edge UPF, and an edge compute workload at the far edge. The method also includes receiving UE traffic at one or more distributed units located at the far edge. The UE traffic includes the edge compute traffic and non-edge compute traffic. The method also includes identifying the edge compute traffic among the UE traffic, routing the edge compute traffic to the edge compute workload at the far edge, and routing the non-edge compute traffic to the near edge UPF at the near edge.

Efficiency of routing traffic to an edge compute server at the far edge of a cellular network

Described are examples for providing a distributed fault-tolerant state store for a virtualized base station. In an aspect, a first server at a datacenter may perform physical layer processing for at least one virtualized base station. While performing the physical layer processing, the first server may generate inter-slot physical layer state data during a first slot. The inter-slot physical layer state data is to be used in a subsequent slot. The first server may periodically transmit the inter-slot physical layer state data to one or more other servers of the plurality of servers within the datacenter. One of the other servers may take over the physical layer processing for the at least one virtualized base station based on the inter-slot physical layer state data, for example, in response to a fault at the first server or a migration of the at least one virtualized base station.

Distributed fault-tolerant state store for virtualized radio access networks

Aspects include a machine learning based resource block scheduler configured to meet service level requirements of applications. Aspects include receiving a plurality of scheduling requests each associated with a respective application of a plurality of applications on a plurality of wireless devices, identifying a plurality of current channel state information each associated with one of the plurality of wireless devices, and identifying a plurality of different types of service level requirements each associated with one of the plurality of applications. Further, the aspects include determining, by a machine learning based scheduler based on each of the plurality of current channel state information, a sequence of resource assignments expected to meet the plurality of different types of service level requirements, the sequence of resource assignments including a plurality of grants of a scheduled assignment of a resource, and transmitting respective grants for the respective applications to the wireless devices.

Learned scheduler for flexible radio resource allocation to applications

Growing community of inventors

Bellevue, WA, United States of America

Paramvir Bahl