Case Study: For Ultra Low Power, the Right Algorithms Are Key

Submitted by BDTI on Mon, 08/31/2015 - 22:00

When engineers set out to design a system (such as a wearable or handheld device) for minimum power consumption, there's a tendency to focus on selecting the most energy efficient processor and on optimizing the software for maximum efficiency. These are important steps, to be sure, but when the application is based on digital signal processing, choosing the right algorithms can be even more important.

Digital signal processing is, of course, fundamentally the application of math to signals, whether for wireless communications, audio, motor control or other purposes. There are usually multiple ways to solve a given math problem, and in digital signal processing this means that there are usually several algorithms that can produce the same functional result. But the alternative algorithms may have very different computational requirements.

In a recent project, a client engaged BDTI to develop a new frequency-domain algorithm to replace an existing time-domain algorithm used in a low-power wearable device. The motivation for creating a new algorithm was twofold: first, a frequency-domain algorithm would integrate more naturally into the rest of the client's system; next, in addition, it was hoped that a frequency-domain algorithm would reduce power consumption by reducing computation load.

BDTI engineers studied the client's existing time-domain algorithm in detail, working with the client's engineers to understand which of the algorithm's behaviors were useful and which were undesired artifacts. BDTI then designed and tested a new frequency-domain algorithm that replicated the desired behaviors of the original algorithm while slashing its computation requirements by more than 50%.

The project was completed in under four months and gave BDTI's client a valuable opportunity to simplify its software architecture and free up precious battery power needed for the implementation of new features.

Find out how BDTI can help you select, evaluate, or design digital signal processing algorithms to meet your challenging functional requirements while minimizing power consumption. Contact Jeremy Giddings at +1 (925) 954 1411 or giddings@BDTI.com.

Add new comment

Log in or register to post comments