Weather dependent estimation of continent-wide wind power generation based on spatio-temporal clustering

Europe is facing the challenge of increasing shares of energy from variable renewable sources. Furthermore, it is heading towards a fully integrated electricity market, i.e. a Europe-wide electricity system. The stable operation of this large-scale renewable power system requires detailed informatio...

Full description

Saved in:
Bibliographic Details
Published in:Advances in science and research 2017-05, Vol.14, p.131-138
Main Authors: Schyska, Bruno U, Couto, António, von Bremen, Lueder, Estanqueiro, Ana, Heinemann, Detlev
Format: Article
Language:English
Subjects:
Algorithms
Alternative energy sources
Climatology
Clustering
Electric power generation
Electric power systems
Electric utilities
Electricity
Energy industry
Environmental aspects
Markets
Methods
Rain
Regression analysis
Renewable energy
Site selection
Time series
Training
Weather
Wind power
Wind power generation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Europe is facing the challenge of increasing shares of energy from variable renewable sources. Furthermore, it is heading towards a fully integrated electricity market, i.e. a Europe-wide electricity system. The stable operation of this large-scale renewable power system requires detailed information on the amount of electricity being transmitted now and in the future. To estimate the actual amount of electricity, upscaling algorithms are applied. Those algorithms – until now – however, only exist for smaller regions (e.g. transmission zones and single wind farms). The aim of this study is to introduce a new approach to estimate Europe-wide wind power generation based on spatio-temporal clustering. We furthermore show that training the upscaling model for different prevailing weather situations allows to further reduce the number of reference sites without losing accuracy.
ISSN:1992-0636
1992-0628
1992-0636
DOI:10.5194/asr-14-131-2017