TY - GEN

T1 - Demand-aware network designs of bounded degree

AU - Avin, Chen

AU - Mondal, Kaushik

AU - Schmid, Stefan

N1 - Funding Information:
∗ This work was supported by the German-Israeli Foundation for Scientific Research (GIF) Grant I-1245-407.6/2014
Publisher Copyright:
© Chen Avin, Kaushik Mondal, and Stefan Schmid.

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Traditionally, networks such as datacenter interconnects are designed to optimize worst-case performance under arbitrary traffic patterns. Such network designs can however be far from optimal when considering the actual workloads and traffic patterns which they serve. This insight led to the development of demand-aware datacenter interconnects which can be reconfigured depending on the workload. Motivated by these trends, this paper initiates the algorithmic study of demand-aware networks (DANs), and in particular the design of bounded-degree networks. The inputs to the network design problem are a discrete communication request distribution, D, defined over communicating pairs from the node set V, and a bound, Δ, on the maximum degree. In turn, our objective is to design an (undirected) demand-aware network N = (V, E) of bounded-degree Δ, which provides short routing paths between frequently communicating nodes distributed across N. In particular, the designed network should minimize the expected path length on N (with respect to D), which is a basic measure of the efficiency of the network. We show that this fundamental network design problem exhibits interesting connections to several classic combinatorial problems and to information theory. We derive a general lower bound based on the entropy of the communication pattern D, and present asymptotically optimal network-aware design algorithms for important distribution families, such as sparse distributions and distributions of locally bounded doubling dimensions.

AB - Traditionally, networks such as datacenter interconnects are designed to optimize worst-case performance under arbitrary traffic patterns. Such network designs can however be far from optimal when considering the actual workloads and traffic patterns which they serve. This insight led to the development of demand-aware datacenter interconnects which can be reconfigured depending on the workload. Motivated by these trends, this paper initiates the algorithmic study of demand-aware networks (DANs), and in particular the design of bounded-degree networks. The inputs to the network design problem are a discrete communication request distribution, D, defined over communicating pairs from the node set V, and a bound, Δ, on the maximum degree. In turn, our objective is to design an (undirected) demand-aware network N = (V, E) of bounded-degree Δ, which provides short routing paths between frequently communicating nodes distributed across N. In particular, the designed network should minimize the expected path length on N (with respect to D), which is a basic measure of the efficiency of the network. We show that this fundamental network design problem exhibits interesting connections to several classic combinatorial problems and to information theory. We derive a general lower bound based on the entropy of the communication pattern D, and present asymptotically optimal network-aware design algorithms for important distribution families, such as sparse distributions and distributions of locally bounded doubling dimensions.

KW - Datacenter topology

KW - Entropy

KW - Network design

KW - Peer-topeer computing

KW - Reconfigurable networks

KW - Sparse spanners

UR - http://www.scopus.com/inward/record.url?scp=85032330832&partnerID=8YFLogxK

U2 - 10.4230/LIPIcs.DISC.2017.5

DO - 10.4230/LIPIcs.DISC.2017.5

M3 - Conference contribution

AN - SCOPUS:85032330832

T3 - Leibniz International Proceedings in Informatics, LIPIcs

BT - 31st International Symposium on Distributed Computing, DISC 2017

A2 - Richa, Andrea W.

PB - Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing

T2 - 31st International Symposium on Distributed Computing, DISC 2017

Y2 - 16 October 2017 through 20 October 2017

ER -