Cheaper computing can mean more computing.
Efficiency makes computing cheaper, and cheaper computing invites more use. Without a limit, the saving is spent on more load and emissions don't fall: the rebound effect.
Researchers led by Lancaster University, with Mike Berners-Lee, argue that savings only count when total use is capped. GreenCode's climate case builds on this work.
GreenCode helps tackle this by measuring reductions in absolute terms, not only per task. Its climate case shows owners where capacity can be retired, so a saving can be banked rather than spent. More on this.
Cheaper computing can mean more computing. Efficiency makes each task cheaper to run. And cheaper computing invites more use. Without a limit, the saving is spent on more load. Total emissions do not fall. This is called the rebound effect. Here is the fix you can use today. Pair every efficiency project with an energy or carbon budget. Retire the servers and capacity that an optimisation frees up. Report total energy, not only energy per task. Researchers led by Lancaster University worked on this with Mike Berners-Lee. They argue that savings only count when total use is capped. GreenCode's climate case builds on this work. The Software Carbon Intensity method scores carbon per unit of work. Add the totals from your cloud bills, using tools like Cloud Carbon Footprint. GreenCode helps tackle this by measuring cuts in total, not only per task. It shows where freed capacity can be retired, so the saving is banked. That was GreenCode Tech Tip number twenty-six. Follow for the next tip, and find more on greencode.ai/tech-tips.
Share this
