Big data and machine learning for applied weather forecasts: Forecasting solar power for utility operations

Sue Ellen Haupt, Branko Kosovic

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

35 Scopus citations

Abstract

To blend growing amounts of renewable energy into utility grids requires accurate estimate of the power from those resources for both day ahead planning and real-Time operations. This requires predicting the wind and solar resource on those timescales. Accurate prediction of these meteorological variables is a big data problem that requires a multitude of disparate data, multiple models that are each applicable to a specific time frame, and application of computational intelligence techniques to successfully blend all of the model and observational information in real-Time and deliver it to the decision-makers at utilities and grid operators. Considering that the capacity of renewable energy continues to grow an additional challenge includes selecting and archiving data for continuous retraining of machine learning algorithms.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages496-501
Number of pages6
ISBN (Electronic)9781479975600
DOIs
StatePublished - 2015
EventIEEE Symposium Series on Computational Intelligence, SSCI 2015 - Cape Town, South Africa
Duration: Dec 8 2015Dec 10 2015

Publication series

NameProceedings - 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015

Conference

ConferenceIEEE Symposium Series on Computational Intelligence, SSCI 2015
Country/TerritorySouth Africa
CityCape Town
Period12/8/1512/10/15

Fingerprint

Dive into the research topics of 'Big data and machine learning for applied weather forecasts: Forecasting solar power for utility operations'. Together they form a unique fingerprint.

Cite this