Microsoft Technology Licensing, LLC

Bozidar Radunovic

Xenofon Foukas

Dinan Srilal Gunawardena

Peter Bernard Key

Paramvir Bahl

Sanjeev Mehrotra

Yongguang Zhang

Christos Gkantsidis

Matthew John Balkwill

Thomas Karagiannis

Noel Andrew Bainbridge

Ramachandran Ramjee

Antonios Katsarakis

Alexandre Proutiere

Ranveer Chandra

Landon Prentice Cox

Krishna Kant Chintalapudi

Binh Quang Nguyen

Parisa Jalili Marandi

Jincao Zhu

Jitendra Dattatraya Padhye

Kun Tan

Richard Malcolm Banks

Ganesh Ananthanarayanan

Bernard D Aboba

Abigail Jane Sellen

Richard Harper

Vishnu Navda

Daehyeok Kim

Apurv Bhartia

Miguel Oom Temudo De Castro

Milan Vojnovic

Gopala Srihari Narlanka

Pablo Rodriguez Rodriguez

Dan Alistarh

Timothy Regan

Horia Vlad Balan

Wenjun Hu

Michael Buettner

Deeparnab Chakrabarty

Ilias Raftopoulos

Dharmaiah Manjunath

Nikhil Singh

Ghufran Baig

Zhenming Liu

Arun Bhamidimarri

Zhaowei Tan

Zhehui Zhang

A reliable network function virtualization (rVNF) system includes a virtualized network function (VNF) application instance that includes a plurality of physical VNF instances. A load balancer provides an interface between a client and the VNF application instance. A load balancer interface facilitates delivery of packets related to a particular user context to the same physical VNF instance. A communication interface facilitates communication between the client and the VNF application instance. Application storage stores session data associated with the VNF application instance.

Reliable virtualized network function system for a cloud computing system

The systems and methods relate to virtual radio access networks (vRANs). The systems and methods may offload a signal processing task of a physical layer from a vRAN server located at the far edge of a network nearby a base station to a remote location further away from the base station. The remote location may include higher level edge deployments of servers or a cloud deployment of servers. The system and methods may scale the vRAN server capacity by offloading the signal processing task to the remote location without compromising quality of service requirements or latency requirements of the user equipment or the applications.

Virtualized radio access network (vRAN) decoding as a service

Described are examples for providing radio access network (RAN) analytics for a virtualized base station. An analytics engine includes a memory storing one or more parameters or instructions for operating the virtualized RAN and at least one processor coupled to the memory. The analytics engine is configured to perform multiple protocol layers of RAN processing for at least one cell at the virtualized base station. The analytics engine is configured to determine a time series of real-time metrics at two or more layers of the multiple protocol layers for the at least one cell or a user equipment (UE) connected to the at least one cell. The analytics engine is configured to correlate a time series for each of the two or more layers to detect a network condition. The analytics engine is configured to modify a configuration of the at least one cell based on the detected network condition.

Real-time radio access network analytics

A real-time radio intelligent controller (RIC) executes in parallel with one or more virtual radio access network functions to provide real-time analytics and control of the virtual radio access network functions. At least a first processor core is configured to execute a radio network virtual function. The radio network virtual function is configured with a codelet to output selected operational data to a first stream associated with a first stream ID and receive control information from a control stream associated with a second stream ID. At least a second processor core is configured to execute the real-time RIC isolated from the at least the first processor core. The real-time RIC includes one or more dynamically loaded programs configured to: access the first stream; perform processing on the operational data; and write commands for the radio network virtual function to the control stream.

Real-time radio intelligent controller

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

The present disclosure relates to systems and methods for sharing compute resources. The systems and methods may include identifying a plurality of workloads to complete by a deadline. The systems and methods may include generating a performance prediction for each workload of the plurality of workloads. The systems and methods may use the performance prediction to calculate a number of compute resources required for the plurality of workloads to complete by the deadline. The systems and methods may schedule the plurality of workloads across the number of compute resources.

Sharing of compute resources between the virtualized radio access network (vRAN) and other workloads

To meet the stringent 5G radio access network (RAN) service requirements, layers one and two need to be processed in essentially real time. Thus, prompt anomaly detection is important to prevent negative impacts on customer experience, which is critical for mobile networks to meet the stringent service requirements. However, monitoring networks for anomalies is difficult due at least to (1) the resource constrained edge deployments in which the vRAN resides, (2) the variety of anomaly types and fault locations making anomalies difficult to detect, and (3) the low frequency of anomalies leading to unbalanced data sets for training, among others. The present application addresses these issues by decoupling anomaly detection at the infrastructure layer (servers, NICs, switches, etc.) from anomaly detection at the VNF layer (L1, high-DU, CU). This enables different techniques for identifying anomalies and for reducing the monitoring overhead that is tailored to each layer.

Anomaly detection for virtualized rans

Described are examples for providing fine-grained real-time pre-emption of codelets based on a runtime threshold. A controller inserts checkpoints into extended Berkeley packet filter (eBPF) bytecode of a third-party codelet prior to verification of the third-party codelet. A device executes the codelet at a hook point of an application. The inserted checkpoints determine a runtime of the codelet. The device terminates the codelet in response to the runtime exceeding a threshold. The application can be a virtualized radio access network (vRAN) network function and the codelet can control the vRAN function or export network metrics. The application may be executed in a container management system that modifies a container for the application to mount code including a function associated with the hook point of the application to the container; detect an annotation for the container that identifies the codelet; and symbolically links the codelet to the hook point.

Fine-grained real-time pre-emption of codelets based on runtime threshold

Described are examples for receiving, from one or more second virtual radio access network (vRAN) workloads operating one or more second cells, an indication of a measurement of at least a first signal transmitted by a first vRAN workload operating a first cell, computing, based on measurements of at least the first signal as received from the one or more second vRAN workloads, a boundary of the first cell, and adjusting, based on the boundary of the first cell, a transmit parameter of the first vRAN workload for transmitting signals in the first cell.

Techniques for adaptively determining cell boundary in wireless communications

Described are examples for using codelets executing within applications to use machine-learning (ML) models to infer a result based on application data. The codelets may be dynamically loaded into the applications during execution. A controller verifies, based on extended Berkeley packet filter (eBPF) bytecode of the codelet, that the codelet satisfies safety requirements for execution within the application. A computing device executing the application loads the verified codelet into a library of the application. The application executes the verified codelet to apply application data to the machine-learning model to infer a result. The ML model may be implemented by the eBPF code of the codelet or the codelet may include a call to a machine-learning model of a type supported by a controller of the application and a map for a serial representation of the machine-learning model. The computing device may reconstruct the ML model based on the serial representation.

Inference with inline real-time ML models in applications

A method for adjusting discontinuous reception (DRX) behavior of a user equipment (UE) to conserve energy use includes exposing a DRX application programming interface (API) that enables DRX parameters to be changed and defining a conflict resolution policy that controls when requests to change the DRX parameters should be granted. The method also includes receiving, via the DRX API, a request from an application to change a DRX parameter for the UE. The UE is in wireless communication with a base station, and the application is configured to send data to the UE via a mobile network that comprises the base station. The method also includes determining, based at least in part on the conflict resolution policy, that the request should be granted and sending a command to the base station that causes the base station to communicate a new value of the DRX parameter to the UE.

Adjusting discontinuous reception behavior of a user equipment to conserve energy use

Growing community of inventors

Cambridge, United Kingdom

Bozidar Radunovic