Research Article
IoT-Based Data Driven Prediction of Offshore Wind Power in a Short-Term Interval Span
@INPROCEEDINGS{10.1007/978-3-030-95987-6_17, author={Muhammad Khalid and Mir Bilal Khan and Imam Dad and Shayhaq Fateh}, title={IoT-Based Data Driven Prediction of Offshore Wind Power in a Short-Term Interval Span}, proceedings={IoT as a Service. 7th EAI International Conference, IoTaaS 2021, Sydney, Australia, December 13--14, 2021, Proceedings}, proceedings_a={IOTAAS}, year={2022}, month={7}, keywords={Big data Wind power SGD SVM}, doi={10.1007/978-3-030-95987-6_17} }- Muhammad Khalid
Mir Bilal Khan
Imam Dad
Shayhaq Fateh
Year: 2022
IoT-Based Data Driven Prediction of Offshore Wind Power in a Short-Term Interval Span
IOTAAS
Springer
DOI: 10.1007/978-3-030-95987-6_17
Abstract
Wind energy is becoming one of the most important suppliers of renewable energy but due to its reliance on weather conditions it is highly inconsistent and its integration into electricity grids is a challenge. In this research we present a comparative analysis of the performance of several prominent data mining techniques in prediction of wind energy generation. Data from the Big Data Challenge Bremen 2018 was used for short term forecasting. Of basic models, a decision tree produced the best performing model. It performed marginally better than SGD, OLS, LASSO and Bayesian ridge regression. Whereas, SVM, nearest neighbor and Gaussian NB performed very poorly. A further analysis using ensemble methods was performed where a Gradient Boosting was the best model. Further improvements of the IoT model are performed and limitations of this are discussed in detail.
