NAL

We are the Network Architecture Lab, and we work on fundamental questions regarding network system design: 

  • Can we infer network behavior from external observations? We proved the feasibility of network neutrality inference [ paper ]. Zeinab is exploring how to use it to localize traffic differentiation
    [ project page, paper ].
      
  • Can we leverage streaming footage to improve Internet transparency? Catalina is developing Tero, which creates a near-real-time Internet latency map by extracting latency numbers from gaming footage [ project page, paper ].
  • Is there a definition of network neutrality that is meaningful for the current Internet? Today, most content is served through edge caches, so, by design, more popular services enjoy better performance. Abdullah is exploring the magnitude of the resulting performance differences, and whether such a thing as neutral caching may exist [ paper ].   
  • How should we write software network functions (NFs), such that we can reason about their performance? Rishabh is exploring the idea of performance interfaces and how to extract such interfaces from software NFs [ code, paper ]. He won the Dennis M. Ritchie Award for his thesis on this topic.