Edge computing is a method of optimizing cloud computing systems by performing data processing at the edge of the network, closer to the users and sources of data. As data processing is traditionally done in large data centers, typically located at the center of the network, the edge computing paradigm will reduce the communication bottleneck to the data centers, thereby improving overall performance. This becomes more important as the number of Internet-of-Things (IoT) devices increases.
Our research focuses on how to coordinate the computational nodes at the edge of the network in a distributed way to collaboratively process incoming data. Our current plan is to use a distributed constraint optimization (DCOP) formulation and to develop DCOP algorithms that are tailored to this specific application.
Sponsors
Mission-oriented Adaptive Placement of Task and Data (MAP).
Defense Advanced Research Projects Agency (2017 – 2021).
Representative Publications
- Khoi D. Hoang, Christabel Wayllace, William Yeoh, Jacob Beal, Soura Dasgupta, Yuanqiu Mo, Aaron Paulos, and Jon Schewe. “New Distributed Constraint Reasoning Algorithms for Load Balancing in Edge Computing.” In Proceedings of the International Conference on Principles and Practice of Multi-Agent Systems (PRIMA), pages 69-86, 2019.