Microsoft Technology Licensing, LLC

Laszlo Lovasz

Jeffrey Bruce Parham

William Birkin Lees

Mark Robbin Brown

Nicholas J A Harvey

Katalin Vesztergombi

Van H Vu

Philip Andrew Chou

Kamal Jain

Nicholas J Harvey

An overlay network and scheme for building and using the overlay network are described. As the overlay network is built, new nodes joining the network are connected randomly with other nodes which results in a random graph as the network topology. The network is fully scalable, with each new node providing the same number of network connections for output to other nodes as it consumes when it joins the network. In addition, network coding is implemented at each node to mix packets of data entering each node using random linear functions. The network coding at each node generates new packets that are independent combinations of original data packets entering the node. The new coded packets make the distribution of data to other nodes more efficient and robust.

Scalable overlay network

A method for designating communication paths in a computer network is provided, in which communication paths are designated for the transmission of data throughout a network. The network may have both recipient computers, which are the intended recipients of the data, and intermediary computers, which are not the intended recipients, but merely relay the data. Each intermediary computer is grouped with the 'closest' recipient computer (i.e. the recipient computer with whom it is 'least expensive' to communicate). Communication paths between the resulting groups are then identified. A representation of the network is then created. The representation replaces the intermediary computers with the inter-group communication paths, so that the inter-group communication paths appear to pass directly through the locations occupied by the intermediary computers. The created representation is then further processed so that the &#x201c;least expensive&#x201d; communication paths may be designated.

Method for designating communication paths in a network

A method of finding an optimal match between clients and servers under given matching constraints utilizes a bipartite diagram in which the clients are presented as vertices on one side, the servers as vertices on the other side, and each possible client-server pairing allowed under the matching constraints as an edge connecting the vertices representing the client and the server. After an initial round of assignments is performed, the assignments are optimized by an optimization operation that iteratively applies a reassignment process. The reassignment process searches for a chain of servers starting with a server having a highest number of clients and ends with another server with a client number less than that of the first server by at least two, with each server in the chain except the end server having a client reassignable to the next server in the chain. Those reassignable clients are then reassigned along the chain such that the first server's client number is reduced by one and the end server's client number is reduced by one. The reassignment process is repeated until an optimal match is reached.

Method and system for matching network clients and servers under matching constraints

Growing community of inventors

Sammamish, WA, United States of America

Laszlo Lovasz