Extending the Service Lifetime of a Battery-Powered System Supporting Multiple Active Modes
Journal Title: IOSR Journals (IOSR Journal of Electrical and Electronics Engineering) - Year 2017, Vol 12, Issue 3
Abstract
Dynamic power management (DPM) is a well known power optimization technique that aims at reducing the power consumption of a system while maintaining an acceptable performance degradation level. This paper presents a Reinforcement Learning-based dynamic power management framework for extending the battery service lifetime of a system with multiple active modes. In the proposed framework, a Power Manager adapts the system operating mode to the actual battery state of charge based on the observation of the battery output voltage. Moreover, it uses the reinforcement learning technique to accurately define the optimal battery voltage threshold value and use it to control the system active mode. Additionally, the power management policy is automatically adapted to the optimal timeout value. The proposed algorithms are experimented on both single and dual-battery powered systems and the obtained results confirm their excellent performance for defining the optimal power management policy particularly for high latency constrained systems. Experimental results show an improvement in battery State of Charge (SoC) savings up to 42.83% and 55.38 % respectively for single battery and dual battery systems in comparison with classic pre-specified timeout policies using a given preset battery threshold voltage
Authors and Affiliations
Maryam Triki, Ahmed Chiheb Ammari
Keywords
Related Articles
- EP ID EP387190
- DOI 10.9790/1676-1203023446.
- Views 193
- Downloads 0
Vertical-Edge-Based Car-License-Plate Detection Method
Vehicle plate recognition is a successful image processing technique used to recognize vehicles' plate numbers. There are several applications for this method which enlarge through many fields and attention groups. Vehic...
Branding Strategy in Fact Segment Global and Indian Perspective
In a global economy subject to changing dynamics and ever increasing competition, the role of brands has never been greater. They serve as a route map for purchasing behaviour and when managed well, are able to accrue si...
Sepic Topology Based High Step-Up Step down Soft Switching Bidirectional DC-DC Converter for Energy Storage Applications
SEPIC topology based bidirectional DC-DC Converter is proposed for interfacing energy storage elements such as batteries & super capacitors with various power systems. This proposed bidirectional DC-DC converter acts as...
Implication of EBOT Kit in Kuwait’s Robotics Technology Learning and Innovation
Despite being one of the highest ranking countries with respect to GDP per capita, Kuwait has not yet made its mark in the world of technology and research. Researchers suggest that due to its diverse nature, Robotics ed...
Applying Parametric Functional Approximations for Teaching Electromechanical Systems
In this paper functional approximations for the parameters of a DC machine are proposed. These nonlinear algebraic approximations are based on the experimental data that are obtained by carrying out several steady state...