CAREER: Problem Solving in Dynamic, Distributed Environments

University Of Tulsa, Tulsa OK

Investigators

Abstract

Computers are increasingly used to monitor and manage many aspects of our daily lives. These systems are often required to work together to solve complex problems that are rapidly changing. Current approaches to addressing these situations develop tailored distributed protocols that are verified through empirical testing. This project increases the practical applicability of distributed problem solving techniques by developing a theoretical model of these problems based on thermodynamic theory. Using this model, a protocol's performance can, for the first time ever, be predicted under previously untested conditions. This theoretical model is validated through extensive empirical evaluation and this project develops a new protocol that alters its problem solving strategy to maximize the trade-off between deliberate and reactive decision making based on environmental dynamics. This protocol is applied to address a pressing practical problem: allocating telescopes for tracking objects in Low Earth Orbit (LEO). With nearly all of our manned space missions and satellites in LEO, effectively monitoring space debris has broad implications to society at large and scientific progress along numerous directions. This transformative research combines cross-disciplinary ideas from artificial intelligence, distributed systems, and statistical physics. The educational initiatives in this project directly address the recruitment and retention of students, especially focusing on women and minorities, into Computer Science by generating excitement through the Heartland Gaming Expo and by utilizing a new peer outreach program, called Engineering Ambassadors.