Article

A Ubiquitous Power Management System to Balance Energy Savings and Response Time Based on Device- level Usage Prediction.

Journal of Information Processing 01/2010; 18:147-163. DOI: 10.2197/ipsjjip.18.147
Source: DBLP

ABSTRACT Power conservation has become a serious concern during people's daily life. Ubiquitous computing technologies clearly provide a potential way to help us realizing a more environment-friendly lifestyle. In this paper, we propose a ubiquitous power management system called Gynapse, which uses multi-modal sensors to predict the exact usage of each device, and then switches their power modes based on predicted usage to maximize the total energy saving under the constraint of user required response time. We build a three-level Hierarchical Hidden Markov Model (HHMM) to represent and learn the device level usage patterns from multi-modal sensors. Based on the learned HHMM, we develop our predictive mechanism in Dynamic Bayesian Network (DBN) scheme to pre- cisely predict the usage of each device, with user required response time under consideration. Based on the predicted usage, we follow a four-step process to balance the total energy saving and response time of devices by switching their power modes accordingly. We use PlaceLab data set to evaluate Gynapse, and the preliminary results demonstrate that Gynapse has the capability to reduce power consumption while keeping the response time not exceed user require- ment, which provides a complementary approach to previous power manage- ment systems.

0 Followers
 · 
117 Views
  • Source
    • "We implement Gynapse on eight student desks in our laboratory based on the system design in [3]. Figure 3 depicts its architecture. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Context-aware computing technologies provide great potential to help us adaptively reducing power consumption. We have proposed a context-aware power management system called Gynapse, which builds a three-level Hierarchical Hidden Markov Model (HHMM) to predict the exact usage of each device from multi-modal sensors, and then switches their power modes based on prediction to maximize the total energy saving under the constraint of user required response time. In this paper, we will discuss Gynapse's implementation in our laboratory and experimental results.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Energy consumption has increased considerably in the last years. The way to reduce and make energy consumption more efficient has become of great interest for researchers. One of the research areas is the reduction of energy consumption in users' residences. In order to reduce energy consumption in home environments, researches have been designing Home Energy Management Systems (HEMS). Efficiently managing and distributing electricity in the grid will also help to reduce the increase of energy consumption in the future. The power grid is evolving into the Smart Grid, which is being developed to distribute and produce electricity more efficiently. This paper presents the high level goals and requirements of HEMS and the Smart Grid. Additionally, it provides an overview on how Information and Communication Technologies (ICT) is involved in the Smart Grid and how they help to achieve the emerging functionalities that the Smart Grid can provide.

Preview

Download
0 Downloads
Available from