Microsoft Technology Licensing, LLC

Tsu-wang Hsieh

Behnaz Arzani

Paramvir Bahl

Ranveer Chandra

Srikanth Kandula

Ganesh Ananthanarayanan

Daniel Sebastian Berger

Yuanchao Shu

Nikolaos Karianakis

Pooria Namyar

Romil Bhardwaj

Daniel Stopol Crankshaw

Peder Andreas Olsen

Shadi Abdollahian Noghabi

Jin Hyun So

Chenning Li

A computing device including a processor configured to receive satellite status data from satellites included in a satellite constellation. The processor is further configured to determine a link topology of the satellites. Based at least in part on the satellite status data and the link topology, the processor is further configured to identify a first satellite constellation subset including one or more selected satellite pairs. Identifying the one or more selected satellite pairs includes computing respective link utility values associated with a plurality of candidate pairs of satellites included in the satellite constellation based at least in part on the satellite status data and the link topology. The one or more selected satellite pairs are selected based at least in part on the link utility values. The processor is further configured to transmit, to the satellites included in the first satellite constellation subset, instructions to perform intersatellite imaging data transfer.

Intersatellite imaging data transfer

A satellite is provided, including an onboard computing device. The onboard computing device may include a processor configured to receive training data while the satellite is in orbit. The processor may be further configured to perform training at a machine learning model based at least in part on the training data. The processor may be further configured to generate model update data that specifies a modification made to the machine learning model during the training. The processor may be further configured to transmit the model update data from the satellite to an additional computing device.

Generating model update data at satellite

A computing system identifies mitigation actions in response to failures within a computer network. A service level objective is obtained by the computing system for client-resource data flows traversing the computer network between client-side and resource-side nodes. Indication of a failure event at a network location of the computer network is obtained. For each mitigation action of a set of candidate mitigation actions, an estimated impact to a distribution of the service level objective is determined for the mitigation action by applying simulated client-resource data flows to a network topology model of the computer network in combination with the mitigation action and the failure event. One or more target mitigation actions are identified by the computing system from the set of candidate mitigation actions based on a comparison of the estimated impacts of the set of candidate mitigation actions.

Impact-aware mitigation for computer networks

Provided are aspects relating to methods and computing devices for allocating computing resources and selecting hyperparameter configurations during continuous retraining and operation of a machine learning model. In one example, a computing device configured to be located at a network edge between a local network and a cloud service includes a processor and a memory storing instructions executable by the processor to operate a machine learning model. During a retraining window, a selected portion of a video stream is selected for labeling. At least a portion of a labeled retraining data set is selected for profiling a superset of hyperparameter configurations. For each configuration of the superset of hyperparameter configurations, a profiling test is performed. The profiling test is terminated, and a change in inference accuracy that resulted from the profiling test is extrapolated. Based upon the extrapolated inference accuracies, a set of selected hyperparameter configurations is output.

Allocating computing resources during continuous retraining

Methods and computing devices for allocating computing resources and selecting hyperparameter configurations during continuous retraining and operation of a machine learning model. In one example, a computing device configured to be located at a network edge between a local network and a cloud service includes a processor and a memory storing instructions executable by the processor to operate a machine learning model. During a retraining window, a selected portion of a video stream is selected for labeling. At least a portion of a labeled retraining data set is selected for profiling a superset of hyperparameter configurations. For each configuration of the superset of hyperparameter configurations, a profiling test is performed. The profiling test is terminated, and a change in inference accuracy that resulted from the profiling test is extrapolated. Based upon the extrapolated inference accuracies, a set of selected hyperparameter configurations is output.

Growing community of inventors

Redmond, WA, United States of America

Tsu-wang Hsieh