On the Transformative Potential of Energy Data Analytics
Duke expert Kyle Bradbury touts transformative potential of energy data analytics in new book on digital decarbonization
This week the Council on Foreign Relations released Digital Decarbonization, an anthology of 13 experts’ perspectives on how the unfolding of the digital revolution could help to drive a transition toward clean energy. The volume, edited by Varun Sivaram, includes an article by Duke University researcher Dr. Kyle Bradbury (ECE MS’08, PhD’13), who outlines the transformative potential of the emerging field of energy data analytics.
Bradbury was among more than 40 energy experts convened by the Council on Foreign Relations at a February 2018 workshop supported by the Alfred P. Sloan Foundation.
Bradbury, who is managing director of Duke University’s Energy Data Analytics Lab and a lecturing fellow at the Pratt School of Engineering, argues in his article (pp. 73-81) that “data science could enable the decentralization of the centralized energy systems that have existed since the beginning of the twentieth century.”
The article launches with an account of the confluence of trends that have led to the emergence of this new field of inquiry: new energy data sources as well as parallel advances in data science techniques and the computational power necessary to perform them.
Bradbury explains how data science is already shaping (and could further transform) the electric power sector, offering examples of how machine learning techniques have the potential to enhance system operation, forecasting, and planning.
The article points to additional applications beyond the electricity sector, offering examples of how data science is already changing how energy is produced, delivered, and consumed in, say, the transportation and oil and gas sectors.
And Bradbury argues that data science could also be leveraged to tackle a particularly formidable problem: the overall complexity and scale of energy systems, which often get in the way of effective planning. The emerging field of energy data analytics “could fundamentally change how societies generate, manage, and consume energy, by increasing system efficiency and optimizing planning to reduce system costs and environmental damage,” Bradbury writes.
Finally, Bradbury reflects on challenges facing those in the field, particularly the availability and the ease of access to data. “Establishing policies that enable streamlined data sharing for approved R&D purposes is a prerequisite for more democratized access to data,” he observes.
“This article is by no means comprehensive,” cautions Bradbury. “But it does spotlight some intriguing possibilities for productive collisions between data scientists in search of problems and energy system stakeholders in search of solutions.”
Experts affiliated with Duke’s Energy Data Analytics Lab—including engineers, data scientists, and social scientists—are positioning Duke University as an international leader in the emerging area of energy data analytics.
Bradbury’s invitation to present at the Council on Foreign Relations workshop was predicated on the lab’s achievements. Among other projects, the lab has pioneered the application of visual object identification and machine learning techniques to satellite imagery for energy resource detection and mapping. One of the lab's long-term objectives is to create a map of global energy infrastructure that can be automatically updated.
Founded in 2014, Duke's Energy Data Analytics Lab is also creating a pipeline of talented innovators. Projects connected with Duke’s unique Data+ and Bass Connections programs accomplish lab research objectives while deepening undergraduate and graduate students’ research, project management, and communications skills. Thanks to grants from the Alfred P. Sloan Foundation, the lab is launching programs for doctoral student fellows and postdoctoral fellows this fall.
The Energy Data Analytics Lab is a collaborative effort of the Duke University Energy Initiative (which houses it), the Information Initiative at Duke (iiD), and the Social Science Research Institute (SSRI).
Bradbury holds Ph.D. and M.S. degrees in electrical engineering from the Pratt School of Engineering at Duke University and a B.S. in Electrical Engineering from Tufts University. He has worked for ISO New England, MIT Lincoln Laboratories, and Dominion.