A master thesis from Aalborg University
IDE Extension for Reasoning About Energy Consumption
Term
4. term
Education
Publication year
2021
Submitted on
2021-06-11
Pages
87 pages
Abstract
This project explains the process of creating an IDE extension for Visual Studio Code. This extension is used to reason about the energy consumption at both the program and function level. We implement three approaches for obtaining energy consumption estimates, being statically using machine learning and an energy model and dynamically using RAPL. For the static analysis we create an interpreter for CIL code to count the number of times each CIL instruction encountered during interpretation. To evaluate the accuracy of the static approaches we use the dynamically measured values as the ground truth and compares the statically obtained values to this. Based on these results, the non-linear machine learning creates better estimates than the energy model and the linear machine learning models. The energy model creates better estimates than the linear models, except for lasso regression. The estimation approach with the least error is the random forest machine learning model.
Keywords
Documents
Colophon: This page is part of the AAU Student Projects portal, which is run by Aalborg University. Here, you can find and download publicly available bachelor's theses and master's projects from across the university dating from 2008 onwards. Student projects from before 2008 are available in printed form at Aalborg University Library.
If you have any questions about AAU Student Projects or the research registration, dissemination and analysis at Aalborg University, please feel free to contact the VBN team. You can also find more information in the AAU Student Projects FAQs.