FOREWER: Forecasting and Risk Evaluation of Wind Energy Production

"The wind died down, sad, mourning in the high trees, passing away; going back out to the sea, to the Celebes, to the Ivory Coast, to Sumatra and Cape Horn, to Cornwall and the Philippines. Fading, fading, fading."
R. Bradbury, The Wind

The generation of electricity from wind is intermittent by nature, yet most methods for forecasting wind energy production provide a single expected value per timescale and fail to take into account the non-stationarity due to the evolution of climatic variables. 

FOREWER will address these critical issues via a synergy between modern statistical and meteorological models. This multidisciplinary partnership brings together statisticians and meteorologists from the academia with engineers from energy industry. 

We aim to develop reliable models and scenario generators for resource distribution and power output at various scales with focus on medium to long term, to be used to solve planning and risk management problems relevant for the industrial partners of the project.

Project at a Glance:

  • FOREWER is a collaborative public-private project funded by the French National Research Agency (ANR). The project started on October 1st, 2014 and will operate for 3.5 years.

Project Consortium

    Project Objectives

    • Develop reliable theoretical and numerical models and scenario generators for the wind resource distribution and power output at various spatial and temporal scales with a focus on medium to long term. 
    • Evaluate the potential of these tools for solving the forecasting and risk management problems relevant for the industrial partners of the project, such as the evaluation of the sensitivity of a proposed wind farm to climate variability and optimal placement of wind farms, determination of the required capacity of back-up generators and optimal operation of these assets, and integration of renewable power sources into the grid.
    • Apply state of the art statistical and probabilistic modeling tools (wavelets, stochastic processes) to the historical weather simulations in order to understand the multiscale behavior of the wind resource, analyze its variability modes and identify the predictable components of the distribution. 
    • Adapt the powerful statistical learning methods, developed by the statistics group at LPMA to identify the salient predicting features as well as the connections between renewable power production and the meteorological variables. 
    • Apply the statistical forecasting methodology to obtain seasonal and decadal projections of these relationships and produce reliable probabilistic forecasts of the renewable power production taking into account the climate non-stationarity.


    Rolling Updates

    • Forecasting and Risk Management for Renewable Energy, Paris June 7-9, 2017 This workshop aims to bring together statisticians, probabilists, meteorologists, economists and engineers working on various aspects of renewable energy, from production forecasting to optimal storage management. The particular focus will ...
      Posted Apr 4, 2017, 4:52 AM by Lucie M
    • Forewer seminar - February 22nd The first session of Forewer seminar will take place on February 22nd, in room 1016 of Sophie Germain building at 17:30 pm. We will have the pleasure to attend ...
      Posted Feb 11, 2016, 10:31 AM by Lucie M
    • Project meeting of 26 November 2015 On November 26, 2015, the project members met at Paris Diderot to discuss the current affairs of the project and listen to the presentations of Lucie Montuelle, Bénédicte Jourdier and ...
      Posted Jan 26, 2016, 8:02 AM by Peter Tankov
    • Welcome to Bastien Alonzo Bastien Alonzo joined the project team as a PhD student starting from October 1st, 2015. He splits his time between LMD and LPMA and works on seasonal forecasting of wind ...
      Posted Jan 26, 2016, 7:59 AM by Peter Tankov
    • Welcome to Lucie Montuelle Lucie Montuelle (post-doctoral researcher) has jointed the project team starting from September 1st, 2015. She works on short term wind power forecasting using statistical learning methods. 
      Posted Jan 26, 2016, 7:57 AM by Peter Tankov
    Showing posts 1 - 5 of 9. View more »

    Recent publications

    • Statistical learning for wind power: A modeling and stability study towards forecasting   0k - Sep 8, 2017, 1:34 AM by Lucie M (v1)
      ‎We focus on wind power modeling using machine learning techniques. We show on real data provided by the wind energy company Maïa Eolis that parametric models even following closely the physical equation relating wind production to wind speed are outperformed by intelligent learning algorithms. In particular, the CART-Bagging algorithm gives very stable and promising results. Besides, as a step towards forecast, we quantify the impact of using deteriorated wind measures on the performances. We show also on this application that the default methodology to select a subset of predictors provided in the standard random forest package can be refined, especially when there exists among the predictors one variable, which has a major impact.‎
    • Modelling the Variability of the Wind Energy Resource on Monthly and Seasonal Timescales   0k - Sep 7, 2016, 7:28 AM by Peter Tankov (v1)
      ‎We study the variability of the wind energy resource in France on monthly to seasonal timescales. On such long‑term timescales, the variability of the surface wind speed is strongly influenced by the large‑scale situation of the atmosphere. We investigate the relationship between the large scale circulation and the surface wind speed, summarizing the former by a principal component analysis, so that the large‑scale mass distribution is described by a small set of coefficients. We then apply a multi polynomial relationship to model the monthly and seasonal distribution of surface wind speeds given the knowledge of these few coefficients. We finally apply this model to seasonal forecasts from the European Center for Medium‑range Weather Forecasts (ECMWF) in an attempt of forecasting the monthly and seasonal distribution of the surface wind speed. For one month time‑horizon, the forecasting performance is superior to climatology.‎
    • Optimal trading policies for wind energy producer   0k - Sep 7, 2016, 7:17 AM by Peter Tankov (v1)
      ‎We study the optimal trading policies for a wind energy producer who aims to sell the future production in the open forward, spot, intraday and adjustment markets, and who has access to imperfect dynamically updated forecasts of the future production. We construct a stochastic model for the forecast evolution and determine the optimal trading policies which are updated dynamically as new forecast information becomes available. Our results allow to quantify the expected future gain of the wind producer and to determine the economic value of the forecasts. ‎
    • Tails_of_weakly_dependent_random_vectors.pdf   0k - Jan 26, 2016, 8:13 AM by Peter Tankov (v1)
      ‎Article "Tails of Weakly Dependent Random Vectors" by P. Tankov, published in Journal of Multivariate Analysis (Volume 145, March 2016, Pages 73–86). This article presents methods for quantifying the tail behavior of random vectors which can be used, for example, to evaluate risks due to spatial dependency in wind power production.  ‎
    Showing 4 files from page Publications.

    Upcoming events