Slide 1.pngSlide 2.pngSlide 3.pngSlide 4.pngSlide 5.pngSlide 6.png

    

International Conference on Innovative Applied Energy    

E-Proceedings ISBN: 978-1-912532-05-6

St Cross College, University of Oxford, United Kingdom

  


 

On the historical predictability of the diffusion ofrenewable energy

 


 

Rita Maria del Rio Chanona (1), Berke Vow Ricketti (2), Francois Lafond (1), Rupert Way (1) and Doyne Farmer (1)

1. Institute for New Economic Thinking at the Oxford Martin, School Eagle House, Oxford, United Kingdom

2. Institute of Photonics and Quantum Sciences, Hariot-Watt University Edinburgh, United Kingdom

 

Paper Abstract

It is well-known that past forecasts of the diffusion of renewable energy technologies have been too pessimistic. However, these prediction failures are seldom evaluated in light of the underlying predictability of the historical time series. Here we compare the projections made by the EIA to the forecasts that would have been made by the simplest time series model. We make this comparison for the forecast of different renewable sources. For each source we fit a geometric random walk with drift and compare the forecast errors of the time series models and the experts. Because some renewable energy time series are intrinsically more volatile than others, we acknowledge that they are also harder to predict, and so we can give a fairer assessment of the forecasts made by the EIA.

Paper Keywords
Forecast, time series, renewable energy.
Corresponding author Biography

Rita María is currently doing her Dphil in Mathematics under the supervision of Prof. Doyne Farmer. She obtained her BSc in Physics at Universidad Nacional Autónoma de México (UNAM) 2011-2016. During this period she did two summer research internships, one at Imperial College London under the supervision of Prof. Henrik Jensen and another at Ryerson University with Prof. Anthony Bonato. Her research topics involved networks and graph theory. Rita Maria worked in two consulting firms Inno-ba and Pondera, where she did time series prediction, epidemiology analysis and information gathering. She is currently interested in complex systems, combining agent-based modelling, networks, renewable energies and economics.

The International Conference on Innovative Applied Energy (IAPE’18)