JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.advisor | Casarin, Roberto | it_IT |
| dc.contributor.author | Zaetta, Paul <1995> | it_IT |
| dc.date.accessioned | 2018-06-19 | it_IT |
| dc.date.accessioned | 2018-12-03T06:23:45Z | |
| dc.date.available | 2018-12-03T06:23:45Z | |
| dc.date.issued | 2018-07-03 | it_IT |
| dc.identifier.uri | http://hdl.handle.net/10579/13440 | |
| dc.description.abstract | The assumption of a proper distribution in order to account for the nonlinear and double-bounded nature of wind power generation in short-term probabilistic forecasting is an essential feature. The aim of this study is to show the superiority of the logit-Normal distribution over classical assumptions (Normal and Beta distributions). | it_IT |
| dc.language.iso | en | it_IT |
| dc.publisher | Università Ca' Foscari Venezia | it_IT |
| dc.rights | © Paul Zaetta, 2018 | it_IT |
| dc.title | Very short-term probabilistic forecasting of wind power | it_IT |
| dc.title.alternative | Very short-term analysis of wind power generation in a probabilistic forecasting framework | it_IT |
| dc.type | Master's Degree Thesis | it_IT |
| dc.degree.name | Economia e finanza | it_IT |
| dc.degree.level | Laurea magistrale | it_IT |
| dc.degree.grantor | Dipartimento di Economia | it_IT |
| dc.description.academicyear | 2017/2018, sessione estiva | it_IT |
| dc.rights.accessrights | openAccess | it_IT |
| dc.thesis.matricno | 872113 | it_IT |
| dc.subject.miur | SECS-P/05 ECONOMETRIA | it_IT |
| dc.description.note | Nowadays, generating very-short term energy power forecasts is a crucial challenge. In particular, wind generation, which exhibits large fluctuations, is not easy to predict. This study is based on a probabilistic forecasting framework and ought to account for the nonlinear and double-bounded nature of that stochastic process. Discrete and continuous mixtures of generalised logit-Normal distributions and probability masses at the bounds serve to provide probabilistic forecasts. Pinson (2012) showed that this framework is superior to classical models for wind power production, which assume that the shape of predictive densities follow (censored) Normal and Beta distributions. Both simple autoregressive and autoregressive moving average models are designed in order to estimate the location and the scale parameters. The first aim of this study is to extend the Pinson (2012) model by introducing a dynamic structure for the location of the wind generation. The second aim is to analyse the predictive ability of the proposed model. The theory approach concerning the different methods is illustrated by assessment and ranking of probabilistic forecasts of wind generation at Galicia in the Spain Northwest (on 10-minute ahead point). | it_IT |
| dc.degree.discipline | it_IT | |
| dc.contributor.co-advisor | it_IT | |
| dc.date.embargoend | it_IT | |
| dc.provenance.upload | Paul Zaetta (872113@stud.unive.it), 2018-06-19 | it_IT |
| dc.provenance.plagiarycheck | Roberto Casarin (r.casarin@unive.it), 2018-07-02 | it_IT |
