Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 2 of 2

Full-Text Articles in Computer Engineering

Investigation Of Lstm Based Prediction For Dynamic Energy Management In Chip Multiprocessors, Milad Ghorbani Moghaddam, Wenkai Guan, Cristinel Ababei Mar 2018

Investigation Of Lstm Based Prediction For Dynamic Energy Management In Chip Multiprocessors, Milad Ghorbani Moghaddam, Wenkai Guan, Cristinel Ababei

Electrical and Computer Engineering Faculty Research and Publications

In this paper, we investigate the effectiveness of using long short-term memory (LSTM) instead of Kalman filtering to do prediction for the purpose of constructing dynamic energy management (DEM) algorithms in chip multi-processors (CMPs). Either of the two prediction methods is employed to estimate the workload in the next control period for each of the processor cores. These estimates are then used to select voltage-frequency (VF) pairs for each core of the CMP during the next control period as part of a dynamic voltage and frequency scaling (DVFS) technique. The objective of the DVFS technique is to reduce energy consumption …


Optimal Energy Scheduling For A Smart Entity, Amin Fakhrazari, Hamid Vakilzadian, F. Fred Choobineh Jan 2014

Optimal Energy Scheduling For A Smart Entity, Amin Fakhrazari, Hamid Vakilzadian, F. Fred Choobineh

Department of Electrical and Computer Engineering: Faculty Publications

Real-time availability of electricity prices via a smart power grid has a potential bilateral benefit to electricity users and suppliers. The users can reduce their costs by consuming energy during low-price hours and balancing their energy usage during other hours. This in turn benefits energy utility companies by reducing their peak power demand. This article describes an optimal shrinking horizon model for electricity-consuming units based on user preferences. The proposed model optimizes the end user’s electricity cost while meeting preferred comfort levels. The user can set preferences in the model using a tristate flexibility parameter for each electric-power-consuming unit. The …