How to Save the World from Big Data: Tactics for Making Cloud Computing Massively Greener

Data That Matters
Location: King's Suite Level: Intermediate
Average rating: ***..
(3.00, 2 ratings)

Main idea:

Cloud computing is a powerful tool which enables massive-scale data analysis and machine learning, but also has a very large carbon footprint, especially since many public cloud providers are powered by coal-fired grids (annual data centre emissions are currently ~75 million tonnes and growing). This talk aims to give developers a feel for the total scale of the issue, and to share tactics and devops approaches which hugely reduce carbon without reductions in performance.

Subtopics:

1. Overall scale of cloud carbon footprint and some regular-world comparisons – e.g. how does a big map/reduce job compare in footprint to your household personal emissions

2. The physical and technical factors which determine footprint of any given compute job – physical design, climate, timing, power grid

3. Interesting current projects in the field – Facebook’s OpenCompute, renewables-powered computing, etc

4. Practical considerations for developers: data mobility; getting accurate info easily; latency; price; building footprint considerations into processing workflows

Conclusion:

As developers, we orchestrate massive amounts of computing power, and that has an ugly carbon footprint. It’s possible to make choices in the development process which significantly reduce this footprint, and I encourage the audience to do so.

Photo of Francine Bennett

Francine Bennett

Mastodon C

Francine Bennett is co-founder and CEO of Mastodon C [link: www.mastodonc.com], which offers managed Hadoop and data science services in the cloud in the greenest possible way. She started carbon footprinting cloud providers in 2012 after realising that it was possible to make huge reductions in CO2 emissions by putting together some straightforward data, and that nobody else was doing it.

She previously worked at extracting insight from Big Data at Google and at Ask.com. She is a former mathematician and a massive data nerd, who feels very strongly about bad data visualisations and Comic Sans.

Sponsors

Sponsorship Opportunities

For information on exhibition and sponsorship opportunities, contact Susan Stewart at sstewart@oreilly.com or +1 (707) 827-7148

Media Partner Opportunities

For information on trade opportunities contact Kathy Yu at mediapartners
@oreilly.com

Press and Media

For media-related inquiries, contact Maureen Jennings at maureen@oreilly.com

Contact Us

View a complete list of Strata contacts.