Microsoft Technology Licensing, LLC

Ayalvadi Jagannathan Ganesh

Ming Zhang

Guobin Shen

Sandeep Singhal

Peter Bernard Key

Thomas Karagiannis

Laurent Massoulie

Anne-Marie Kermarrec

Using location-independent names to identify content, a service for mapping endpoint requests to requested content. Content requested by an endpoint of the network is mapped to a dynamic 'swarm' of server, peer, or other endpoints capable of supporting the content download. Content names are mapped to a dynamically generated content swarm, presenting a current set of hosts, which can provide the requested content. Optionally, varying degrees of explicit visibility into routing paths and the performance tradeoffs between those routing paths is supported. Based on a set of class of service parameters for a given request for content, a host can initiate route selection based on class of service parameters, predicated on routing metrics maintained by the network by cooperating endpoints and/or network routers.

Network routing of endpoints to content based on content swarms

A service for facilitating a determination of path quality between a first endpoint node and a second endpoint node in a network of nodes is provided. Path quality information is aggregated from across network internet service providers (ISPs), giving authorized endpoints access to path quality information for specified path segments of a path to another endpoint. Path quality information includes one or more metrics that measure available bandwidth, loss rate and/or latency.

Characterization of network path quality for network applications and services

In an unstructured overlay network, each node in the network periodically tests logical network links among neighboring nodes to determine whether the links should be reorganized. A Metropolis scheme is used to determine the probability with which the links are reorganized. This probability is computed based on the change in link costs and/or node degrees that would be effected by a proposed reorganization. The Metropolis scheme tends to maintain a consistency among the degrees of the nodes, thereby providing strong failure resilience.

Self-organizing overlay networks

Growing community of inventors

Bristol, United Kingdom

Ayalvadi Jagannathan Ganesh