After a long period when networking research seemed to be focused mainly on making the existing Internet work better, interest in "clean slate" approaches to network architecture seems to be growing. Beginning with the DARPA program in the mid-1990's, researchers working on active networks explored such an approach, based on the idea of a programming interface as the basic interoperability mechanism of the network. This note draws on the author's experiences in that effort and attempts to extract some observations or "lessons learned" that may be relevant to more general network architecture research. Categories and Subject Descriptors C.2.1 [Network Architecture and Design]: Packet-switching networks; C.2.2 [Network Protocols]: Protocol Architecture General Terms Design, Experimentation
Kenneth L. Calvert