Funded Projects

A Controls Approach to Improve How Society Interacts with Electricity

This CRISP project addresses the rapid evolution of the electricity grid, from one based on few centralized generators providing power to millions of users to one where many distributed energy resources, such as small rooftop photovoltaic systems and electric cars but also thermostats and ventilation systems, play a vital role in the management of energy flows. The keystone of this research is the transformation of power distribution feeders, from relatively passive channels that deliver electricity from the transmission grid to customers, to distribution microgrids, highly intelligent entities that actively manage production, storage and use of electricity. The project studies how the telecommunications infrastructure delivers information to human and artificial stakeholders to enable rational decision-making on various aspects of energy utilization.
More details ...

National Science Foundation
Funded by: National Science Foundation, Award #: 1541000
Project Center: Center for Agile and Interconnected Microgrids

Collaboration with:

Framework for linking project teams and components

Adaptive Memory Resource Management in a Data Center - A Transfer Learning Approach

This project is focused on the management of memory resources in a data center. The project has four main tasks: an investigation on the use of transfer learning within resource management problems, the development of cache predictor using in-situ virtual machine measurements, the creation of a memory predictor using runtime characteristics of a virtual machine, and the development of a resource management scheme.
More details ...

National Science Foundation
Funded by: National Science Foundation, Award #: 1422342
Collaboration with: Western Michigan University

Memory Resource-Aware Scheduler

Distributed Agent-Based Management of Agile Microgrids

The project aims to investigate the creation and control of a microgrid with the following properties: services diverse loads, employs distributed generation with renewable resources, and requires on-line control and optimization to maintain stability and power flow. This project researches a microgrid that should be both agile and autonomous, accommodating rapid changes in generation and load resources with minimal intervention on the part of human operators. The control architecture uses a hierarchical approach. The control strategy relies on multi-agent systems using artificial intelligence and machine learning techniques.
More details ...

Funded by: US Army Research Laboratory
Project Center: Center for Agile and Interconnected Microgrids

Example Load Forecasts

Other Projects

Bayesian Networks and Feature Selection

The research creates methods for learning the structure of Bayesian networks and feature selection. Methods for learning the structure of Bayesian networks rely on ideas from local learning, contraint-based, and search-and-score techniques.

Bayesian network from Dexheimer, 2007

Persistence in Engineering and Computer Science

This on-going project looks at local and national surveys to understand student persistence. The local survey was designed to investigate aspects of persistence and the reasons behind switching majors. An analysis was performed to determine what impacts student persistence including factors such as major, gender, student-student and student-faculty interactions, and career opportunities. The project focuses on engineering and computer science undergraduate students.
More details ...