The AWPPS - The ARMINES Wind Power Prediction System

WELCOME TO THE AWPPS HOME PAGE

		*The AWPPS System*
		The AWPPS provides short-term forecasts for the power output of onshore and offshore wind farms: for the next 48/72 hours with a time step of 1 hour (updates every hour), for the next 4-6 hours with a time step of 10-15 min (updates every 10-15 min), on-line uncertainty assessment for these forecasts.

		*Why wind power forecasts*
		Accurate short-term wind power forecasts permit to operate wind farms, maximise wind power penetration, plan reserves & storage, maximise revenues when participating in the electricity market, plan maintenance etc. For all these purposes, the AWPPS can be used by end-users such as Transmission or Distribution System Operators, Independent Power Producers, Energy Service providers, wind farm operators, energy traders, etc.

		The Software


		*Power Prediction*
		The Power Prediction Module provides forecasts for the output of each considered wind farm. The core Module is based on state-of-the-art adaptive fuzzy neural networks. This approach provides strong advantages compared to classical neural networks or other statistical or physical techniques. The module is enhanced with on-line adaptation capabilities for optimal performance.

		*Uncertainty Evaluation*
		The AWPPS is the only available tool that provides confidence intervals for wind power forecasts with a predefined level of confidence (i.e. 85, 90, 95%). The intervals are produced based on an advanced approach appropriate to the wind prediction problem.

		*Prediction Risk*
		The Prediction Risk Module permits to «forecast» the uncertainty based on the expected weather stability for the next 24 hours. The on-line use of this module permits to develop appropriate strategies for maximising the value from the use of power forecasts.

		Regional Forecasting
		The AWPPS includes a module for forecasting regional or national wind power based on a sample of reference wind farms.

		*Performance :*
		The AWPPS was successfully adapted and validated for more than 35 onshore and offshore wind farms in Denmark, Germany, Greece, Ireland, Portugal, Spain and UK situated in different terrain types (flat, semi~, complex). The performance for single wind farm forecasting ranges between 2-5% (of the nominal wind farm power) for one-hour ahead predictions and 10-15% for 48 hours ahead. The performance for regional forecasting is 8-10% for 24 hours ahead.

		*Input :*
		Numerical Weather Predictions by meteorological services (i.e. Aladin, Hirlam, Skiron etc.). If available: on-line measurements of power and meteorological variables. The user may insert information on scheduled maintenance of the wind farms. Advanced processes are used for automatic selection of the most relevant input.

		*Implementations*
		The AWPPS is provided as an independent software able to run locally at the end-user or via internet (via secured access). It can be also provided through the More-Care Energy Management System (EMS) or finally through the e-terra SCADA system of AREVA T&D.

		*References :*
		The development of AWPPS started in 1995. The prediction modules of AWPPS have been installed for on-line operation in Ireland for the prediction of 11 wind farms, in Crete for 6 wind farms and in Madeira for 2 farms. An installation at Azores is under development (4/2004).

		*Related papers and reports:*
		ARMINES has carried out research considerable research in the area of short-term wind power prediction during the last 12 years. A number of papers has been published in Journals and Conferences presenting the methods developped and also results from various applications. For a list of references click here.

		*Developped by :*


	...	*Contact information :*
		Dr. George Kariniotakis, Project Manager, Ecole des Mines de Paris, Centre Energétique et Procédés, B. P. No 207, 6904 Sophia Antipolis, France. Tel: +33-(0)493957501, (~99) Fax: +33-(0)493957535 Email: georges.kariniotakis_AT_cep.cma.fr

Download information leaflet on AWPPS

2004.06.01