News

Harmonizing Energy-Autonomous Computing and Intelligence

December 30, 2019 by Paul Shepard

The Philosophical Transactions of the Royal Society published a theme issue focused on "Harmonizing energy-autonomous computing and intelligence," on 23 December, 2019. The issues compliers, Rishad Shafik and Alex Yakovlev, note; "Artificial intelligence (AI) technology will soon deliver on the pervasive penetration into the real-world at an unprecedented scale. From miniscule sensors to cloud servers, AI computing systems will be at the core of our decisions anywhere and everywhere. Empowering a vast number of these systems using portable batteries will be challenged by manual battery maintenance cycles, coupled with their energy efficiency needs.

"As such, researchers are persistently pushing the traditionally known thermodynamic energy limits with an aim to designing AI systems with energy autonomy, by harmonizing the computational intelligence with energy sourcing and management. This theme issue covers a wide spectrum of theory and practices of design, modelling and validation of the new generation of energy-autonomous computing systems, reporting contributions from pioneering researchers."

One of the articles in this theme issue is "Energy driven computing," written by Sivert T. Sliper, Oktay Cetinkaya, Alex S. Weddell, Bashir Al-Hashimi and Geoff V. Merrett. In the abstract, the authors observe; "For decades, the design of untethered devices has been focused on delivering a fixed quality of service with minimum power consumption, to enable battery-powered devices with reasonably long deployment lifetime.

Recommended for you: NGK Extends Li-ion Offering to include Coin Cells and Cells Rated for 85°C

"However, to realize the promised tens of billions of connected devices in the Internet of Things, computers must operate autonomously and harvest ambient energy to avoid the cost and maintenance requirements imposed by mains- or battery-powered operation. But harvested power typically fluctuates, often unpredictably, and with large temporal and spatial variability.

"Energy-driven computers are designed to treat energy-availability as a first-class citizen, in order to gracefully adapt to the dynamics of energy harvesting. They may sleep through periods of no energy, endure periods of scarce energy, and capitalize on periods of ample energy. In this paper, we describe the promise and limitations of energy-driven computing, with an emphasis on intermittent operation."

Potential of energy-driven computers in the context of low-power computing devices. From "Energy driven computing." (click on image to enlarge)