New solution for e

This is according to a press release from the institution published last week.

A spectacular amount of energy

“It takes a spectacular amount of energy to manufacture modern, high-performance computer technology. The paper explores how to make computing more sustainable by finding new uses for devices society has already paid the carbon cost to manufacture,” said Pannuto.

The authors argue that traditional recycling options are energy-intensive causing much pollution and do not reuse the main body of the phone. Therefore, the researchers offer a more eco-friendly option.

Their plan: redeploy the discarded devices as working processors. “Their approach avoids a carbon intensive manufacturing process while conceivably harnessing the unspent 75 percent of a smartphone processor’s lifespan,” states the press statement.

The new study takes into account both the “practicality and environmental benefits of reusing processors for non-consumer applications.” More specifically, the researchers give new life to old wasted processors as cloudlets for microservices for social media websites and as wildlife monitoring sensors. 

This is especially handy considering that smartphone processors on average have a lifetime of more than 10 years after being discarded and are often retired after using up just 25 percent of their functional lifespan.

To assess their efforts, the researchers have conceived of a new metric; the Computational Carbon Intensity (CCI) that evaluates and compares the true lifetime impact of computing of a specific device. 

Gathering dust

After applying this new metric to old servers, laptops and smartphones, the team discovered that smartphones offered the best potential for carbon impact reduction due to their vast array of valuable components. These components provide repurposed processors with a robust power supply, valuable networking hardware and plenty of utility remaining to be used.

“For devices with shorter lifespans, such as smartphones, 80 percent or more of the lifetime carbon footprint comes from the energy expended to make the device, not the energy it used while it ran,” said Pannuto. “How many old phones, laptops, and desktops are gathering dust? Let’s see if we can find a useful second life for them!”

The research is garnering attention for its potential to deal with a long-standing significant problem. The authors have already been awarded a Distinguished Paper Award at the 2023 Architectural Support for Programming Languages and Operating Systems (ASPLOS) conference and their work has been downloaded over 50,000 times, a record amount in the conference’s 28-year history.

Considering the growing problem of e-waste, the researchers' new study could not come at a better time as recycling simply isn’t making enough leeway in addressing the issue. 

Study abstract:

1.5 billion smartphones are sold annually, and most are decommissioned less than two years later. Most of these unwanted smartphones are neither discarded nor recycled but languish in junk drawers and storage units. This computational stockpile represents a substantial wasted potential: modern smartphones have increasingly performant and energy-efficient processors, extensive networking capabilities, and reliable built-in power supplies. This project studies the ability to repurpose these unwanted smartphones as “junkyard computers.” Junkyard computers grow global compute capacity by extending device lifetimes, and save carbon by supplanting the manufacture of new devices. We show that the capabilities of even decade-old smartphones are within those demanded by modern cloud microservices, and discuss how to combine phones to perform increasingly complex tasks. We describe how current operation-focused metrics do not capture the actual carbon costs of compute. To address this, we propose Computational Carbon Intensity—a performance metric that balances the continued service of older devices with the super linear run time improvements of newer machines. We use this metric to redefine device service lifetime in terms of carbon efficiency. We develop a cloudlet of reused Pixel 3A phones and analyze the carbon benefits of deploying large, end-to-end microservice-based applications on these smartphones. Finally, we describe system architectures and associated challenges to scale to cloudlets with hundreds and thousands of smartphones