Dynamic power management by reinforcement learning

This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Electrical and Electronic Engineering, 2016.

Detaylı Bibliyografya
Asıl Yazarlar:	Hossain, Safayet, Ibn-Ismail, Muhammad Adnan
Diğer Yazarlar:	Khan, Dr. Md. Muhidul Islam
Materyal Türü:	Tez
Dil:	English
Baskı/Yayın Bilgisi:	BRAC University 2016
Konular:	Power management Reinforcement learning
Online Erişim:	http://hdl.handle.net/10361/6434

id	10361-6434
record_format	dspace
spelling	10361-64342019-09-30T03:11:07Z Dynamic power management by reinforcement learning Hossain, Safayet Ibn-Ismail, Muhammad Adnan Khan, Dr. Md. Muhidul Islam Department of Electrical and Electronic Engineering, BRAC University Power management Reinforcement learning This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Electrical and Electronic Engineering, 2016. Cataloged from PDF version of thesis report. Includes bibliographical references (page 57-60). Optimization in design and utilization of both hardware and software is needed in order to achieve more energy efficient systems. In this paper we presented a Reinforcement learning based DPM approaches for our LAN card power management system. The presented approaches do not require priori model of the system as an Opposite to the existing DPM approaches. Thesis outcomes also show that sleeping is indeed feasible in the LAN and in some cases, with very little impact on other protocols. Moreover, reinforcement learning is a machine intelligence approach that has been applied in many different areas whereas Qlearning is one of the most popular algorithms that perform reinforcement learning. At last, with the desired outcomes of this thesis work, power management issues of LAN card system were solved effectively. In future we aim to compare DPM problem with mission learning problem. The RL based learning algorithm can then be implemented to find the right value of power constraint. Safayet Hossain Muhammad Adnan Ibn-Ismail B. Electrical and Electronic Engineering 2016-09-21T08:12:04Z 2016-09-21T08:12:04Z 2016 2016 Thesis ID 12121111 ID 11321059 http://hdl.handle.net/10361/6434 en BRAC University thesis are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 60 pages application/pdf BRAC University
institution	Brac University
collection	Institutional Repository
language	English
topic	Power management Reinforcement learning
spellingShingle	Power management Reinforcement learning Hossain, Safayet Ibn-Ismail, Muhammad Adnan Dynamic power management by reinforcement learning
description	This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Electrical and Electronic Engineering, 2016.
author2	Khan, Dr. Md. Muhidul Islam
author_facet	Khan, Dr. Md. Muhidul Islam Hossain, Safayet Ibn-Ismail, Muhammad Adnan
format	Thesis
author	Hossain, Safayet Ibn-Ismail, Muhammad Adnan
author_sort	Hossain, Safayet
title	Dynamic power management by reinforcement learning
title_short	Dynamic power management by reinforcement learning
title_full	Dynamic power management by reinforcement learning
title_fullStr	Dynamic power management by reinforcement learning
title_full_unstemmed	Dynamic power management by reinforcement learning
title_sort	dynamic power management by reinforcement learning
publisher	BRAC University
publishDate	2016
url	http://hdl.handle.net/10361/6434
work_keys_str_mv	AT hossainsafayet dynamicpowermanagementbyreinforcementlearning AT ibnismailmuhammadadnan dynamicpowermanagementbyreinforcementlearning
_version_	1814307528684601344

Dynamic power management by reinforcement learning

Benzer Materyaller