Energy-Efficient Distributed Algorithms for Synchronous Networks

TL;DR

This paper investigates energy-efficient algorithms in distributed networks, showing that while constant energy solutions exist for all problems, constraints on round complexity in the CONGEST model lead to significant energy costs and a separation between node and edge activation complexities.

Contribution

It proves the existence of constant-energy algorithms for all problems and highlights the trade-offs and separations in energy complexity under round constraints in the CONGEST model.

Findings

Constant node-activation algorithms exist for all Turing-computable problems.

Imposing polynomial round constraints in the CONGEST model increases energy costs for some problems.

A separation exists between edge and node activation complexities in the CONGEST model under round constraints.

Abstract

We study the design of energy-efficient algorithms for the LOCAL and CONGEST models. Specifically, as a measure of complexity, we consider the maximum, taken over all the edges, or over all the nodes, of the number of rounds at which an edge, or a node, is active in the algorithm. We first show that every Turing-computable problem has a CONGEST algorithm with constant node-activation complexity, and therefore constant edge-activation complexity as well. That is, every node (resp., edge) is active in sending (resp., transmitting) messages for only $O(1)$ rounds during the whole execution of the algorithm. In other words, every Turing-computable problem can be solved by an algorithm consuming the least possible energy. In the LOCAL model, the same holds obviously, but with the additional feature that the algorithm runs in $O(\mbox{poly}(n))$ rounds in $n$-node networks. However, we show that insisting on algorithms running in $O(\mbox{poly}(n))$ rounds in the CONGEST model comes with a severe cost in terms of energy. Namely, there are problems requiring $\Omega(\mbox{poly}(n))$ edge-activations (and thus $\Omega(\mbox{poly}(n))$ node-activations as well) in the CONGEST model whenever solved by algorithms bounded to run in $O(\mbox{poly}(n))$ rounds. Finally, we demonstrate the existence of a sharp separation between the edge-activation complexity and the node-activation complexity in the CONGEST model, for algorithms bounded to run in $O(\mbox{poly}(n))$ rounds. Specifically, under this constraint, there is a problem with $O(1)$ edge-activation complexity but $\tilde{\Omega}(n^{1/4})$ node-activation complexity.