APEX: Automated Parameter Exploration for Low-Power Wireless Protocols

TL;DR

APEX is an automated framework that efficiently explores parameters for low-power wireless protocols, significantly reducing testbed trials needed to find optimal configurations compared to traditional methods.

Contribution

The paper introduces APEX, a novel Gaussian process-based tool for automated, informed parameter exploration in low-power wireless protocols, minimizing experimental trials.

Findings

APEX reduces testbed trials by up to 10.6x compared to exhaustive search.

APEX effectively finds optimal parameters across diverse application requirements.

The framework demonstrates significant efficiency improvements over greedy and reinforcement learning approaches.

Abstract

Careful parametrization of networking protocols is crucial to maximize the performance of low-power wireless systems and ensure that stringent application requirements can be met. This is a non-trivial task involving thorough characterization on testbeds and requiring expert knowledge. Unfortunately, the community still lacks a tool to facilitate parameter exploration while minimizing the necessary experimentation time on testbeds. Such a tool would be invaluable, as exhaustive parameter searches can be time-prohibitive or unfeasible given the limited availability of testbeds, whereas non-exhaustive unguided searches rarely deliver satisfactory results. In this paper, we present APEX, a framework enabling an automated and informed parameter exploration for low-power wireless protocols and allowing to converge to an optimal parameter set within a limited number of testbed trials. We design APEX using Gaussian processes to effectively handle noisy experimental data and estimate the optimality of a certain parameter combination. After developing a prototype of APEX, we demonstrate its effectiveness by parametrizing two IEEE 802.15.4 protocols for a wide range of application requirements. Our results show that APEX can return the best parameter set with up to 10.6x, 4.5x and 3.25x less testbed trials than traditional solutions based on exhaustive search, greedy approaches, and reinforcement learning, respectively.