Artifact: Voltaire: Precise Energy-Aware Code Offloading Decisions with Machine Learning

In this guide, we describe how to reproduce the results of the evaluation from [1]. Voltaire is a novel scheduler for sophisticated energy-aware code offloading decisions. It applies machine learning on crowd-sourced data about past executions to accurately predict the complexity and the result data size of an upcoming task. Combining these predictions with device-specific energy profiles and context knowledge allows Voltaire to estimate the energy consumption on the mobile device. Thus, Voltaire makes well-informed offloading decisions and carefully selects local or remote execution based on the expected energy consumption. We run experiments with the Tasklet distributed computing system. This guide contains two steps. First, it describes how to deploy the Tasklet System and how to perform energy measurements. Second, the article guides the reader through the data analysis process up to the creation of the paper figures based on either self-collected data or provided raw data.