For an innovative insight into using cellphone data to plan energy infrastructure in the developing world, SFI Postdoctoral Fellow Markus Schlӓpfer and his team have won the $5,000 First Prize and the $2,000 Energy Prize in the 2014-15 'Data for Development' Challenge Senegal.
A big data open innovation competition, the D4D Challenge Senegal made anonymized cellphone data from Sonatel’s mobile network available to international researchers for the purpose of advancing development and welfare in the country’s general population. The competition drew registrations from 250 universities globally but the data was made available only to the 150 that worked on it, including Schlӓpfer’s entry with his collaborators from the University of Manchester, UK, and the Université Cheikh Anta Diop, Senegal.
Schlӓpfer’s team proposed that cellphone data be used to ‘electrify’ developing countries by helping them plan electrical infrastructure based on population distribution and projected energy consumption. Over 70% of Senegal's rural population lacks access to electricity, and the difficulty of predicting their potential electricity consumption discourages costly infrastructure investments. Nearly all Senegalese carry cellphones, however, and the country has become sprinkled with cell towers - many of them running on their own diesel generators.
As a first step toward predicting power needs, the researchers measured the cellphone activity at each tower, gaining unprecedented knowledge into where and when human activity takes place. "This new, data-driven insight into the population dynamics allows us to predict local infrastructure needs with an accuracy that has never been possible before," says Schläpfer. The metric is of particular relevance for regions where census data is outdated or lacking.
Schlӓpfer’s team used their predictions to inform different planning scenarios for electrification options such as new power lines or photovoltaics-based microgrids. Schläpfer points out that their awarded work is a preliminary investigation, and several technical questions remain to be tackled before the proposed framework can become fully operational. "Nevertheless, we believe that analyzing cellphone data has an immense potential for building and operating more sustainable infrastructures, not only in the developing world" he concludes.
The framework for combining mobile data analysis and energy-infrastructure engineering techniques appears in the research paper the team submitted for the competition.