Automatic selection of tuning parameters in wind power prediction  Lasse Engbo Christiansen, Henrik Aalborg Nielsen, Torben Skov Nielsen, Henrik Madsen
 Abstract  This document presents frameworks for online tuning of adaptive estimation procedures. First, introducing unbounded optimization of variable forgetting factor recursive least squares (RLS) using steepest descent and GaussNewton methods. Second, adaptive optimization of the bandwidth in conditional parametric ARXmodels.
It was found that the steepest descent approach was more suitable in the examples considered. Further a large increase in the stability when using the proposed transformation of the forgetting factor as compared to the standard approach using a clipper function is observed. This becomes increasingly important when the optimal forgetting factor approaches unity.
Adaptive estimation in conditional parametric models are also considered. A similar approach is used to develop a procedure for online tuning of the bandwidth independently for each fitting point. Both Gaussian and tricube weight functions have been used and for many applications the tricube weight function with a lower bound on the bandwidth is preferred.
Overall this work documents that automatic tuning of adaptiveness of tuning parameters is indeed feasible and makes it easier to initialize these classes of systems, e.g. when predicting the power production from new wind farms.  Type  Technical report  Year  2007  Publisher  Informatics and Mathematical Modelling, Technical University of Denmark, DTU  Address  Richard Petersens Plads, Building 321, DK2800 Kgs. Lyngby  Series  IMMTechnical Report200712  Electronic version(s)  [pdf]  BibTeX data  [bibtex]  IMM Group(s)  Mathematical Statistics 
