Project Description:

Pervasive Architecture for Object Tracking using RFID tags:

A completely visible Pervasive Transaction Environment where it is possible to link all related distributions of physical objects and trace their mobility through their entire life process, has been elusive. We propose an architecture for pervasive real-time tracking of object distribution and subsequently present an efficient mechanism for performing Recall of RFID tagged objects that were previously distributed but turned out defective. We mathematically model the distribution and recall process and get a stochastic estimate of the average spread of object distributions and the number of recall messages required. Currently we are extending on our architecture and trying to develop a prototype of the architecture and the application layer protocol to manage the mobility of the tagged objects in a multi-organization scenario.

Game Theoretic Pricing Policies and Job Allocation Strategies on Mobile Grid:

The goal of this project is to develop a solid mathematical foundation for the development of integrated Mobile Grid Computing by proposing a fair pricing strategy and an optimal, static job allocation scheme. Mobile devices have not yet been integrated into Grid computing platforms mainly due to their inherent limitations in processing and storage capacity, power and bandwidth shortages. Here, we propose a game theoretic pricing model, to address load balancing issues in mobile grids. In particular, by drawing upon the Nash Bargaining Solution (NBS), we show that we can obtain a unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing.

Ubiquitous Computing and Access to Grid Services:

The goal of this project is to establish a fundamental understanding of exploiting the Grid as an integrated infrastructure that can play the dual roles of a coordinated resource consumer as well as a donator in distributed computing environments. We investigate the use of the Grid as a candidate for provisioning computational services to applications in ubiquitous computing environments. In particular, we present a competitive model that describes the possible interaction between the competing resources in the Grid infrastructure as service providers and ubiquitous applications as subscribers.

Distributed Scheduling and Mapping strategies for   Heterogeneous  Computing:

The ultimate goal of this project is to develop a heuristic for mapping a set of interacting tasks of a parallel application onto a heterogeneous computing platform such as a computational grid. Our novel approach is based on the Cross-Entropy (CE) method, which is a new and extremely robust rare event simulation (RES) technique. We tailor the CE method to the requirements of the problem at hand, develop a mathematical framework, and present our algorithm, called MaTCH.

Mobility-Aware Resource Management in Multi-Inhabitant Smart Home:

This project aims at developing a smart space. In order to extract the best performance and efficacy of smart computing environments, one needs a technology-independent, context-aware platform spanning over multiple inhabitants. In this project we have developed a framework for mobility-aware resource management in multi-inhabitant smart home, based on a dynamic, cooperative reinforcement learning technique. This results in adaptive control of automated devices and temperature of the house, thus providing an amicable environment and sufficient comfort to the inhabitants.