Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Ratul Mahajan

Ming Zhang

Sharad Agarwal

Jitendra Dattatraya Padhye

Srikanth Kandula

Paramvir Bahl

Bongshin Lee

Alice Jane Bernheim Brush

Lenin Ravindranath Sivalingam

Shahin Shayandeh

Hongqiang Liu

Jaeyeon Jung

Ian Obermiller

Ranveer Chandra

Stephen Edward Hodges

Zicheng Liu

James William Scott

Amar Phanishayee

Sumit Garg

Chun-Te Chu

Xin Jin

Saurabh Kumar

Giacomo Bernardi

Blaine S Christian

Albert Gordon Greenberg

Alastair Wolman

Thomas Moscibroda

Zheng Zhang

Stefan Saroiu

Ashish Kapoor

Lihua Yuan

Antony Ian Taylor Rowstron

Christos Gkantsidis

Brian Don Zill

Ronnie Chaiken

Yongqiang Xiong

Saleema Amin Amershi

Alice Zheng

Vijay Gill

Vivek Pai

Aruna Balasubramanian

Xuan Zou

Trinabh Gupta

Sirius Kuttiyan

Chi-Yao Hong

Ramya Raghavendra

Monia Ghobadi

Christopher M Moore

Peng Sun

Zhicheng Liu

Mohan Nanduri

Roger Peter Wattenhofer

Colin Kimm Dixon

Patrick D Verkaik

Paramivir Bahl

Lindsey Philip Poole

Rayman Preet Singh

Danyang Zhuo

Amar Panishayee

Stephen Hodges

James Scott

A computer network organized in a logical grid having rows and columns can include network nodes coupled according to harmonics. Each network node can be coupled to network nodes of the same row using a set of horizontal strands according to a set of horizontal harmonics. Each of the horizontal harmonics specifies a node distance along the row between adjacent connection points on the corresponding horizontal strand. Each network node can also be coupled to network nodes of the same column using a set of vertical strands according to a set of vertical harmonics. Each of the vertical harmonics specifies a node distance along the column between adjacent connection points on the corresponding vertical strand.

Network architecture with harmonic connections

Network traffic between a source node and a destination node in a network fabric can be routed by distributing the network traffic from the source node to a set of one-hop neighbors of the source node. Each one-hop neighbor of the source node can be set as a first waypoint. A one-hop neighbor of the destination node mapped to the corresponding one-hop neighbor of the source node is identified and set as a second waypoint. The distributed traffic is then routed from the first waypoint to the second waypoint via a network fabric having network nodes connected according to harmonics.

Multipath routing in network fabrics with harmonic connections

The techniques and/or systems described herein are configured to determine a set of update operations to transition a network from an observed network state to a target network state and to generate an update dependency graph used to dynamically schedule the set of update operations based on constraint(s) defined to ensure reliability of the network during the transition. The techniques and/or systems dynamically schedule the set of update operations based on feedback. For example, the feedback may include an indication that a previously scheduled update operation has been delayed, has failed, or has been successfully completed.

Dynamic scheduling of network updates

Techniques and architectures may be used to generate data center network topologies that use less reliable and less expensive links mixed with links of higher reliability. Such topologies may be categorized into reliability classes, where each class corresponds to a bound(s) on reliability of paths that include the links. A topology class may be selected for use by an application based, at least in part, on the degree of reliability demanded by the application.

Data center topology having multiple classes of reliability

A technique for multi-camera object tracking is disclosed that preserves privacy of imagery from each camera or group of cameras. This technique uses secure multi-party computation to compute a distance metric across data from multiple cameras without revealing any information to operators of the cameras except whether or not an object was observed by both cameras. This is achieved by a distance metric learning technique that reduces the computing complexity of secure computation while maintaining object identification accuracy.

Secure and private tracking across multiple cameras

Techniques and constructs to facilitate data management can provide improved response time and space efficiency for time-series data such as from connected devices. The constructs may enable receiving a stream of time-series data comprising a plurality of objects and a time identification associated with each of the objects. One or more tags are associated with the objects. The constructs may also chunk the stream into a plurality of contiguous chunks, each including a plurality of objects, create an index associating the time identification and the one or more tags, transmit the chunks to a first, remote storage, and then store the index.

Data management for connected devices

Aspects of the subject disclosure are directed towards monitoring application performance during actual use, particularly mobile application performance. Described is instrumenting mobile application binaries to automatically identify a critical path in user transactions, including across asynchronous-call boundaries. Trace data is logged by the instrumented application to capture UI manipulations, thread execution, asynchronous calls and callbacks, UI updates and/or thread synchronization. The trace data is analyzed to assist developers in improving application performance.

Monitoring mobile application performance

An analysis management system (AMS) is described that analyzes the in-field behavior of a program resource installed on a collection of computing devices, such as mobile telephone devices or the like. In operation, the AMS can instruct different devices to collect data regarding different observation points associated with the program resource, thus spreading the reporting load among the devices. Based on the data that is collected, the AMS can update a dependency graph that describes dependencies among the observation points associated with the program resource. The AMS can then generate new directives based on the updated dependency graph. The AMS can also use the dependency graph and the collected data to infer information regarding observation points that is not directly supplied by the collected data.

Generating dependency graphs for analyzing program behavior

The techniques and/or systems described herein implement a fault handling service that is able to ensure that at least part of a network can avoid congestion (e.g., a link exceeding capacity) as long as a predetermined maximum number of faults is not exceeded. The fault handling service models different combinations of possible faults based on network topology and then computes an amount of traffic to be communicated via individual paths such that congestion is avoided as long as a number of actual faults that occur is less than or equal to the predetermined maximum number of faults.

Proactive handling of network faults

Methods and systems for dynamically providing application analytic information are provided herein. The method includes inserting instrumentation points into an application file via an application analytic service and dynamically determining desired instrumentation points from which to collect application analytic data. The method also includes receiving, at the application analytic service, the application analytic data corresponding to the desired instrumentation points and analyzing the application analytic data to generate application analytic information. The method further includes sending the application analytic information to a client computing device.

Dynamically providing application analytic information

The techniques and/or systems described herein implement a network management service configured to read and write a state of a network for various applications (e.g., network management applications) so that the applications can operate independently. The network management service is configured to read an observed network state and provide the observed network state to the applications. Subsequently, the network management service receives proposed network states from the applications and uses a state dependency graph to determine whether state conflicts exist between the proposed network states. The network management service also determined whether defined policies are violated by the proposed network states. Finally, the network management service is configured to generate a target network state by merging non-conflicting proposed network states that comply with defined policies and to update (e.g., write) the network state based on the generated target network state.

Network-state management service

Securely joining a secure wireless communications network is described, for example, where a printer or other device is securely added to a home wireless network. In various embodiments, a temporary wireless network is established between a new joiner device and a second wireless communications device which is already a member of a secure home wireless network. In an example, the temporary wireless network is set up using a secret key known to the new joiner device and the second wireless communications device by virtue of physical proximity. In various examples, the secure, temporary wireless network is used to transfer credentials of the secure home network to the new joiner device which then joins the home network. In an example the temporary wireless network is cancelled once the new joiner device becomes a member of the secure home (or other) wireless network.

Securely joining a secure wireless communications network

Growing community of inventors

Seattle, WA, United States of America

Ratul Mahajan