Evolvable network architectures: what can we learn from biology?

  • Authors:
  • Constantine Dovrolis;J. Todd Streelman

  • Affiliations:
  • Georgia Tech, Atlanta, GA, USA;Georgia Tech, Atlanta, GA, USA

  • Venue:
  • ACM SIGCOMM Computer Communication Review
  • Year:
  • 2010

Quantified Score

Hi-index 0.02

Visualization

Abstract

There is significant research interest recently to understand the evolution of the current Internet, as well as to design clean-slate Future Internet architectures. Clearly, even when network architectures are designed from scratch, they have to evolve as their environment (i.e., technological constraints, service requirements, applications, economic conditions, etc) always changes. A key question then is: what makes a network architecture evolvable? What determines the ability of a network architecture to evolve as its environment changes? In this paper, we review some relevant ideas about evolvability from the biological literature. We examine the role of robustness and modularity in evolution, and their relation with evolvability. We also discuss evolutionary kernels and punctuated equilibria, two important concepts that may be relevant to the so-called ossification of the core Internet protocols. Finally, we examine optimality, a design objective that is often of primary interest in engineering but that does not seem to be abundant in biology.