Archives—January 2017

Power Grids and People

Today’s infrastructure is connected in ways not always known until problems like extreme weather, diseases, major accidents, terror, or cyber threats arise.

Say fuel delivery will be delayed. What can be done?

Sixteen critical infrastructure sectors—including water, gas, energy, communications, and transportation—are linked and interdependent. The National Science Foundation is supporting new fundamental research to transform infrastructure from physical structures to responsive systems. The Critical Resilient Interdependent Infrastructure Systems and Processes (CRISP) program supports a collaborative project for Laura Brown, along with Wayne Weaver, and Chee-Wooi Ten, associate professors of electrical and computer engineering at Michigan Tech, and colleagues from the University of New Mexico, Texas Tech University, University of Tennessee–Knoxville, and Fraunhofer USA Center for Sustainable Energy Systems.


Motivated by distributed renewable resources like solar panels and wind turbines, Brown and her research partners seek to ensure the resiliency of three interdependent networks: the electrical grid, telecommunications, and related socio-economic behavior. The team will look at how people react to power management in extreme conditions. Understanding and modeling human responses is necessary in the design of intelligent systems and programs embedded in devices that control and consume power.

Tiny Microgrids, Fiercely Important

A microgrid is a standalone power grid requiring generation capabilities (often generators, batteries, or renewable resources) plus control methods to maintain power flow. Electronics, appliances, and heating or cooling are all responsible for consuming that power. In this project, Laura Brown and other Michigan Tech researchers are investigating a control system for such microgrids that are autonomous—able to work in isolation—and agile, flexible to rapid changes in the configuration of the electric grid to incoming sources and consumers of power.


The world of microgrids is layered, each layer with a different purpose and speed. For stable power, the controls for the microgrid are considered hierarchically: low-level control responds to fastest events, and maintains regulation of stable voltages and currents in the system; the upper layer of control is responsible for power distribution, optimization, and long-term planning and prediction of resource availability and use. Brown’s work focuses on this high-level analysis in resource prediction at several timescales—in the next few minutes, next hours, next days. What if a generator is out of service for maintenance—what can be done? Brown uses artificial intelligence, machine learning, and experts in other domains to turn off non-critical resources or add new power sources.

The United States Department of Defense and the Army Research Lab seek the expertise of interdisciplinary Michigan Tech researchers to solve, prevent, and adapt to these potential real-world scenarios.

Associate Professor Nilufer Onder receives high marks on student evaluations

Michigan_Tech_Nilufer_Onder_smallAssociate Professor, Dr. Nilufer Onder has been identified as one of only 91 instructors on campus who received an exceptional “Average of 7 dimensions” from student evaluations this fall.  Students in Nilufer’s classes felt she deserved a 4.95 (out of 5.0) on the question, ‘Taking everything into account, I consider this instructor to be an excellent teacher’.

This achievement reflects the tremendous efforts that Nilufer has devoted to teaching and the excellence of her teaching performance.  Way to go, Nilufer!

Transfer Learning in Data Centers

Faster apps. More memory. Laura Brown and Zhenlin Wang bring efficiency to Big Data.

What memory resources will be available if applications A, B, and C all run together?

Big companies like Amazon and Google have even bigger data centers. Think 30 data centers each with 50,000 to 80,000 servers. And the underlying computer processors are not all identical; each year new improvements are integrated and added. Brown, Wang, and computer science colleagues from Western Michigan University are digging deep into the management of memory resources in these larger-than-life data centers.

The researchers use machine-learning techniques to create models that predict the cache and memory requirements of an application.


The challenge is how to make accurate predictions with such a massive variety of applications using the data center, and the different computers the application runs on. Applications might include Netflix streaming a movie, Airbnb running database queries, or NASA processing satellite images. Each app is not run in isolation with a dedicated machine. To maximize resources, data centers may have two or more applications all running on a single machine.

“If we learn the memory requirements of application A on computer X, what if the same app runs on machine Y or machine Z? Or, what memory resources will be available if A, B, and C all run together?” Brown asks.

Computational Intelligence Aids in Explosive Hazard Detection

To detect buried explosive hazards in places like Afghanistan, and to save the lives of civilians and US soldiers, Michigan Tech researcher Tim Havens realizes it requires a team—a team
of sensors.

This technology has the potential to not only save lives, but also to advance the basic science of how to combine sensors and information together to get a whole better than the sum of its parts.

A new $983,000 research project, “Heterogeneous Multisensor Buried Target Detection Using Spatiotemporal Feature Learning,” will look at how forward-looking ground-penetrating radar, LiDAR, and video sensors can be combined synergistically to see into the ground, capture high-quality images, and then automatically notify the operator of threats. With funding from the US Army Research Office, Havens and Tim Schulz, professor of electrical and computer engineering at Michigan Tech, will work with three PhD students to create a high probability-of-detection/low false-alarm rate solution.

“It’s a very difficult problem to solve because most of the radar energy bounces right off the surface of the earth,” says Havens, the William and Gloria Jackson Assistant Professor of Computer Systems at Michigan Tech. “This technology has the potential to not only save lives, but also to advance the basic science of how to combine sensors and information together to get a whole better than the sum of its parts.”


This new project will advance additional sensor-related work Havens and collaborators completed between 2013–2015. The US Army-funded project studied signal processing and computer-aided detection and classification using forward-looking, ground-penetrating, vehicle-mounted radar.
The Army currently fields ground-penetrating radars in its fleet. The problem is they cannot detect hazards until they’re right above them, putting a multi-million dollar radar—and soldiers—directly in the path of danger.

“The big ideas here were to process data to obtain better images, see into the ground in a high-fidelity manner, and develop algorithms to automatically find buried threats—notifying operators of what the possible threats actually are,” Havens adds.

Havens has partnered with the Army since 2008 when he was a PhD student.