Automated testbench for hybrid machine learning-based worst-case energy consumption analysis on batteryless IoT devices
| Autor: | Philippe Reiter, Thomas Huybrechts, Steven Latre, Siegfried Mercelis, Jeroen Famaey, Peter Hellinckx |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
batteryless devices
Schedule Technology Control and Optimization Computer science hybrid resource consumption analysis Energy Engineering and Power Technology Worst-Case Energy Consumption machine learning automated testbench Internet-of-Things 02 engineering and technology Upper and lower bounds 0202 electrical engineering electronic engineering information engineering Code (cryptography) Electrical and Electronic Engineering Engineering (miscellaneous) Renewable Energy Sustainability and the Environment Physics 020206 networking & telecommunications Energy consumption Static analysis 020202 computer hardware & architecture Task (computing) Computer engineering Energy harvesting Engineering sciences. Technology Energy (signal processing) Energy (miscellaneous) |
| Zdroj: | Energies Energies, Vol 14, Iss 3914, p 3914 (2021) Energies; Volume 14; Issue 13; Pages: 3914 |
| ISSN: | 1996-1073 |
| Popis: | Batteryless Internet-of-Things (IoT) devices need to schedule tasks on very limited energy budgets from intermittent energy harvesting. Creating an energy-aware scheduler allows the device to schedule tasks in an efficient manner to avoid power loss during execution. To achieve this, we need insight in the Worst-Case Energy Consumption (WCEC) of each schedulable task on the device. Different methodologies exist to determine or approximate the energy consumption. However, these approaches are computationally expensive and infeasible to perform on all type of devices; or are not accurate enough to acquire safe upper bounds. We propose a hybrid methodology that combines machine learning-based prediction on small code sections, called hybrid blocks, with static analysis to combine the predictions to a final upper bound estimation for the WCEC. In this paper, we present our work on an automated testbench for the Code Behaviour Framework (COBRA) that measures and profiles the upper bound energy consumption on the target device. Next, we use the upper bound measurements of the testbench to train eight different regression models that need to predict these upper bounds. The results show promising estimates for three regression models that could potentially be used for the methodology with additional tuning and training. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|