Theodoros Konstantinou, N. Savvopoulos, N. Hatziargyriou
{"title":"Post-processing Numerical Weather Prediction for Probabilistic Wind Forecasting","authors":"Theodoros Konstantinou, N. Savvopoulos, N. Hatziargyriou","doi":"10.1109/PMAPS47429.2020.9183641","DOIUrl":null,"url":null,"abstract":"Weather variables are commonly used in many applications in power systems. One of the most common weather variables is the wind speed. Wind speed is used mainly in renewable energy forecasting, thermal rating of transmission lines and extreme events estimation. Unfortunately, wind is a very volatile physical phenomenon. The prediction of wind speed is a very difficult procedure with low accuracy, while all the errors are incorporated in the final functions that use this variable. A way to tackle this issue is to post-process the wind predictions with data driven methods to estimate the probabilistic density function of the wind speed. In this paper we propose a probabilistic wind speed forecasting method based on the use of artificial neural networks.","PeriodicalId":126918,"journal":{"name":"2020 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PMAPS47429.2020.9183641","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Weather variables are commonly used in many applications in power systems. One of the most common weather variables is the wind speed. Wind speed is used mainly in renewable energy forecasting, thermal rating of transmission lines and extreme events estimation. Unfortunately, wind is a very volatile physical phenomenon. The prediction of wind speed is a very difficult procedure with low accuracy, while all the errors are incorporated in the final functions that use this variable. A way to tackle this issue is to post-process the wind predictions with data driven methods to estimate the probabilistic density function of the wind speed. In this paper we propose a probabilistic wind speed forecasting method based on the use of artificial neural networks.