Reduced Data Accuracy Helps Save Energy – Tampere University, Finland, Is Coordinating a Project That Trains Young Scientists From Around the World to Develop Solutions

Computers use more and more energy. APROPOS – an international EU-funded project coordinated by the University of Tampere, Finland – aims to improve the energy efficiency of global data use by up to 50 times by reducing data accuracy. The young researchers involved in the project come from all over the world to work in Finland, Sweden, the Netherlands, Austria, Italy, Spain, Switzerland, France and the United Kingdom.

TAMPERE, Finland, 11 November 2021— (BUSINESS CHP) – It is estimated that by 2040, computers will need more electricity than the world’s energy resources can generate. The Approximate Computing for Power and Energy Optimization (APROPOS) project will train 15 junior researchers from across Europe to address the challenges of future built-in and high-performance computational energy effects using destructive methodologies.

This press release includes multimedia. See the full edition here: https://www.businesswire.com/news/home/20211111005657/en/

Professor Jari Nurmi coordinates the APROPOS project and co-leads four of its researchers. His current research interests include approximate and reconfigurable calculations, software-defined radio and networks, and wireless positioning hardware. Photo: Sari Laapotti

The power consumption of mobile broadband networks is comparable to that of data centers. The Internet of Things paradigm will soon connect up to 50 billion devices via wireless networks. The APROPOS project aims to reduce energy consumption in both distributed computing and communications for cloud-based cyber-physical systems.

“Fortunately, in many parts of global data collection, transfer, calculation and storage systems, it is possible to reduce accuracy to allow for reduced energy and time consumption. By introducing precision in design optimization, energy efficiency can be improved up to 50 times, ”says the professor. Jari Nurmi from the Electrical Engineering Unit of the University of Tampere.

Nurmi points out that, for example, multiple sensors measure noisy or inaccurate inputs, and the algorithms that process the received signals can be stochastic. Swarms of sensors measuring the natural environment produce very noisy and inaccurate data that can be transferred and processed with less accuracy without losing the main trends of the observed phenomena.

“Applications that use data may not need completely correct results; acceptable accuracy may be sufficient. This means that the system can be resistant to accidental errors and, for example, a rough classification may be sufficient for a data retrieval system. “

New solutions are needed to tackle growing energy consumption

The overall energy consumption of computing and communication systems is growing rapidly, despite the latest advances in semiconductor technology and the design of energy-friendly systems. The APROPOS project will train fifteen research associates in a multisectoral, international environment to form the basis for improved performance in products and the design of energy-aware systems.

“APROPOS start-up researchers will be trained in both entrepreneurship and academia. In this way, they will be able to develop the commercial potential of their research and come up with innovative ideas for products and services, “adds Nurmi.

APROPOS is a four-year project funded by the innovative training networks of Marie Skłodowska Curie of the European Union Horizon 2020. Coordinated by University of Tampere, Finland. Many young researchers come from outside the EU to work in Finland, Sweden, the Netherlands, Austria, Italy, Spain, Switzerland, France and the United Kingdom.