Skip to main content

Reduced data accuracy to boost energy efficiency – young researchers to develop approximated computing in a European project

Published on 28.10.2021
Tampere University
Kuvituskuva piirilevysuunnittelusta
Illustration: Pixabay
Young researchers are starting to develop new approximate computing solutions for optimizing power and energy. The EU-funded project APROPOS, coordinated by Tampere University, aims to improve energy efficiency of global data usage up to 50-fold by reducing data accuracy.

The Approximate Computing for Power and Energy Optimisation (APROPOS) will train 15 junior researchers around Europe to tackle the challenges of future embedded and high-performance computing energy efficiency by using disruptive methodologies.The project is coordinated by Tampere University.

It’s estimated that by 2040, computers will need more electricity than the world energy resources can generate. On the communications side, energy consumption in mobile broadband networks is comparable to datacenters. The Internet of Things paradigm will soon connect up to 50 billion devices through wireless networks. The APROPOS project aims at decreasing energy consumption in both distributed computing and communications for cloud-based cyber-physical systems.

“Luckily, in many parts of the global data acquisition, transfer, computation, and storage systems, it’s possible to reduce accuracy to allow consuming of less energy and time. By introducing accuracy to the design optimization, the energy efficiency can be improved by even 50-fold,” says Professor Jari Nurmi from Electrical Engineering Unit at Tampere University.

Professor Jari Nurmi points out that, for example, numerous sensors are measuring noisy or inexact inputs, and the algorithms processing the acquired signals can be stochastic.

”The applications using data may not need completely correct results; an acceptable accuracy may be sufficient. This means that system can be resilient against random errors and, for example, a coarse classification may be enough for a data mining system.”

New solutions needed to tackle the increasing energy consumption

The APROPOS project will train fifteen research fellows in a multisectoral, international environment to form the basis of enhanced features in the products and services in various information and communications technology domains and the IoT. According to Jari Nurmi, the overall energy consumption of computing and communication systems is rapidly growing despite the recent advances in semiconductor technology and energy-aware system design.

“The early-stage researchers of APROPOS will be trained in both entrepreneurial and academic directions. Thus, they will be able to develop the commercial potential of their research and come up with innovative product and service ideas,” Nurmi adds.

The training is to a large extent done by researching energy-accuracy trade-offs on the circuit, architecture, software, and system-level solutions. The researchers will be supervised by professors and senior research fellows at Tampere University, the participating universities, and industrial partners. The young researchers attached to the project are coming from all around the world to work in Finland, Sweden, Netherlands, Austria, Italy, Spain, Switzerland, Spain, France, and the UK.

APROPOS is a four-year project funded by the European Union’s Horizon 2020 Marie Sklodowska Curie Innovative Training Networks.

Read more on http://www.apropos-itn.eu

Contact

Jari Nurmi
tel. +358 40 506 4460

jari.nurmi [at] tuni.fi