Studies of packet switching networks under dynamic topological conditions and changing network loads has resulted in the development of a new routing algorithm and a new routing protocol for bringing nodes and links into service. An adaptive distributed algorithm is described which uses least-hop and least-hop-plus-1 routes in a table of routing vectors, as opposed to the usual table of routing scalars. Current delays are passed backwards and forwards with the packets to allow development of expected delays to each node via all acceptable routes. The route then selected is the acceptable route with the least expected delay. For speedier recovery, a node returning to service receives the current network status from an adjoining node as soon as the link connecting them is operational. The resultant algorithms show far greater than the marginal improvements originally expected over ARPANET simulations.
ASJC Scopus subject areas
- Electrical and Electronic Engineering