The Wind Watcher
The search for the ultimate wind forecasting model got a boost at the end of 2008 when DOE’s Argonne National Laboratory (ANL) began collaborating with a Portuguese research institute, INESC Porto (Institute for Systems and Computer Engineering of Porto) to develop a new platform for making such predictions.
14 maio 2009
The increasing reliance by the United States on renewable energy, especially variable wind, is giving the power industry a new set of hurdles to overcome. It makes sense for the DOE to turn to Europe, which meets about 4.2 percent of EU electricity demand via wind. The ANL project is led by Vladimiro Miranda, PhD, a full professor at the University of Porto, Portugal, and also one of the directors of INESC Porto since 2000. He is an IEEE Fellow and author of more than 200 publications.
“Vladimiro Miranda is a wind forecasting expert and we have worked with Portugal for the last seven years and we knew Portugal has up to 12 to 13% of electricity produced from wind, while in the United States it is only one percent,” says Guenter Conzelmann, director of ANL’s Center for Energy, Environmental and Economic Systems Analysis.
Other partners in the project include Horizon Wind Energy, one of the largest wind power developers in the United States, which has a connection to Portugal as it was bought by the Portuguese power company, Energias de Portugal, S.A. The Midwest Independent System Operator also supports the project as an adviser. With the United States headed toward the aggressive goal of 20 percent or more of the country’s electric supply coming from wind in the next 20 years or so, forecasting must be improved and so must be the way the information is used.
Because of DOE funding, the information that results from the study will be made available in the public domain. The study is slated to end in September 2010, but Miranda will be presenting a paper at the American Wind Energy Conference (AWEA) Windpower 2009 conference in Chicago on May 5 providing initial findings on current predictive models and possible improvements.
“SELF-ADAPTIVE PREDICTION MODELS CAN INTELLIGENTLY RECOGNIZE THE WIND HAS CHANGED.”
Fortnightly: What does INESC Porto bring to this this research project?
Miranda: We have worked in windpower integration for more than 15 years at the international level, in Europe, Africa and South America, in projects financed by research agencies, by governments and by the European Union, or in direct research and consulting contracts with companies, utilities, system operators and regulators. We have over a decade of experience producing advanced software solutions that have been integrated in commercial packages for DMS (distribution management systems) used throughout the world by a number of utilities. During this period, we have developed a consistent scientific [approach], translated into theses, journal publications and the organization of conferences that made us known in the research and academic community, namely in the United States. I am proud that we form a respected center of knowledge in power systems and especially in systems with renewables and smart grids. Furthermore, we are an independent, private non-profit institute, with a link to the University of Porto, that acts in consortium in projects both in the European Union and in Brazil. INESC Porto is not specialized in power systems—we also have strong research activity in other areas from telecommunications to optical sensors, and from computer science to manufacturing systems engineering. The crossarea links we are able to establish add strength to our projects related with wind power. For example, we have been called to study problems of interference of wind farms and generators with radar (civil or military), cell phone or television broadcasting processes. Argonne National Laboratory has had experience developing projects in Portugal and I believe the American researchers had good grounds to evaluate the robustness of teaming up with a Portuguese R&D institution. The international visibility of Portugal in the field of renewable energies is very positive, which may have added to the sense of confidence in establishing a relationship.
Fortnightly: Why is this project important to the United States?
Miranda: We are excited with the project because it means the United States is quickly closing a gap that we felt existed. For a long time, Europe has been the leader in wind generation, but we all shared the view that it was of the utmost importance to the planet that we could have the United States on board of this warship fighting for environmentally responsible energy generation. Wind generation creates many jobs, as we have learned in Europe, and opens the opportunity for the existence of new industries—such as the wind power prediction industry. Having stable high-quality standards and benchmarking procedures is very important to stimulate a market. For the United States, I believe the project means the recognition that know-how must be internalized and that wind power prediction has enormous economic value. The objective of 20 percent wind set by the United States can only be achieved by strongly improving the forecasting techniques and their quality and robustness, to guarantee system safety and reliability at high penetration percentages. Wind power: First we tolerate it, then we integrate it. The United States —industry and public opinion—has gone beyond the threshold of tolerance. Integration requires science, skill and good industry. We hope to give a contribution to this goal by sharing our experience with ANL in this project.
Fortnightly: What is it about your work on wind forecasting that makes it cutting edge?
Miranda: At INESC Porto we are seen as experts in the area of computational intelligence and we have applied many concepts of this scientific discipline to wind power. It is perhaps this combination of computational intelligence with power systems that is our strength. We have consistently added the best science from many fields to generate the best models to serve our purposes. In the wind power prediction problem, I can give three examples of innovation out of a few more that could be listed. We are applying new concepts from a field denoted “data streaming” to build new online self-adaptive prediction models. These can intelligently recognize that the characteristics of wind behavior have changed and therefore the model not only learns the new patterns of behavior but also forgets knowledge previously learned, whose consideration may now be more harmful than good. We are also applying new concepts related to information entropy in the training process of our intelligent systems, instead of using a classic approach based on the variance of the prediction errors. And we are using the full power of information gathered from individual wind turbines instead of trying to predict the behavior of a wind farm as a whole, having built up a process of naturally taking into account unit outages or unit additions of any distinct rated power.
Fortnightly: What is the role of Horizon Wind Energy in the project?
Miranda: Horizon Wind Energy is an extremely important partner that will help in validating our work. We already have the experience of working with the parent company of Horizon Wind Energy, EdP. In this country, we have worked in a consortium, EPREV, of companies and research institutions to build up a dispatch center for wind energy, to serve the interests of wind energy producers. This has certainly created a link of confidence and also of responsibility that will allow ANL and also INESC Porto to submit and discuss the work with business actors. Horizon may also serve as a source of data and as test bed for the models to be developed. ANL has made sure there would be one such partner in the project and this is a good thing. I would like also to make a reference to another important partner, with a distinct yet no less important point of view, which is the Midwest ISO.
Fortnightly: Will the resulting wind forecasting system that is developed be proprietary?
Miranda: The policy will be defined by Argonne National Laboratory and I am not entitled to issue an opinion on this matter. But it is my understanding, and we are working with this motivation, that we are building not only a demonstrator but also a robust tool that may be used as an independent benchmarking platform. In Europe there is no such independent platform. This will provide for wind generation companies and also for system operators, a means to independently assess the quality of the prediction models and processes they have, or will, adopt. Hopefully, this will also be seen as an incentive for actors in a wind power prediction industry to improve the quality of the models they offer.
Revista Public Utilities Fortnightly (EUA), Maio 2009