Florjan Bartol (2014) Estimating energy consumption of web pages mith machine learning. EngD thesis.
Abstract
Verify the hypothesis that it is feasible to predict web page's energy consumption based on their structural properties by utilizing machine learning methods. For this purpose develop an automated measuring system for measuring electric current and voltage on the mobile phone while web pages are loading. Use the system for collecting data on energy consumption for a set of popular web pages and combine the measurements with pages' structural properties into a learning set. On the acquired dataset experiment with various machine learning methods and qualitatively and quantitatively asses the results.
Actions (login required)