Data Stream Mining Applied to Maximum Wind Forecasting in the Canary Islands

The Canary Islands are a well known tourist destination with generally stable and clement weather conditions. However, occasionally extreme weather conditions occur, which although very unusual, may cause severe damage to the local economy. The ViMetRi-MAC EU funded project has among its goals, managing climate-change-associated risks. The Spanish National Meteorology Agency (AEMET) has a network of weather stations across the eight Canary Islands. Using data from those stations, we propose a novel methodology for the prediction of maximum wind speed in order to trigger an early alert for extreme weather conditions. The methodology proposed has the added value of using an innovative kind of machine learning that is based on the data stream mining paradigm. This type of machine learning system relies on two important features: models are learned incrementally and adaptively. That means the learner tunes the models gradually and endlessly as new observations are received and also modifies it when there is concept drift (statistical instability), in the modeled phenomenon. The results presented seem to prove that this data stream mining approach is a good fit for this kind of problem, clearly improving the results obtained with the accumulative non-adaptive version of the methodology.

[1]  Ricardo García-Herrera,et al.  Precipitation trends in the Canary Islands , 2003 .

[2]  J. C. Schlimmer,et al.  Incremental learning from noisy data , 2004, Machine Learning.

[3]  A. P. Dawid,et al.  Present position and potential developments: some personal views , 1984 .

[4]  Ali Lahouar,et al.  Hour-ahead wind power forecast based on random forests , 2017 .

[5]  Ping-Huan Kuo,et al.  A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities , 2018, Sensors.

[6]  J. Torres,et al.  Forecast of hourly average wind speed with ARMA models in Navarre (Spain) , 2005 .

[7]  Gerhard Widmer,et al.  Learning in the Presence of Concept Drift and Hidden Contexts , 1996, Machine Learning.

[8]  F. Cassola,et al.  Wind speed and wind energy forecast through Kalman filtering of Numerical Weather Prediction model output , 2012 .

[9]  A. Testa,et al.  Markov chain modeling for very-short-term wind power forecasting , 2015 .

[10]  R. Tibshirani,et al.  Generalized Additive Models , 1986 .

[11]  Zhijian Jin,et al.  Probabilistic Wind Power Forecasting Approach via Instance-Based Transfer Learning Embedded Gradient Boosting Decision Trees , 2019, Energies.

[12]  F. Ramírez,et al.  GPS Monitoring of the Tropical Storm Delta along the Canary Islands Track, November 28-29, 2005 , 2009 .

[13]  Edward Hanna,et al.  An analysis of the climate of Macaronesia, 1865–2012 , 2014 .

[14]  Jing Shi,et al.  On comparing three artificial neural networks for wind speed forecasting , 2010 .

[15]  Benjamin Bechtel,et al.  THE CLIMATE OF THE CANARY ISLANDS BY ANNUAL CYCLE PARAMETERS , 2016 .

[16]  Michael F. Wehner,et al.  Anthropogenic influences on major tropical cyclone events , 2018, Nature.

[17]  Francisco Martín León,et al.  La inusual y anómala tormenta tropical "Delta" , 2006 .

[18]  Ishwarappa,et al.  A Brief Introduction on Big Data 5Vs Characteristics and Hadoop Technology , 2015 .

[19]  Hadley Wickham,et al.  ggplot2 - Elegant Graphics for Data Analysis (2nd Edition) , 2017 .

[20]  Albert Bifet,et al.  DATA STREAM MINING A Practical Approach , 2009 .

[21]  Oriol Jorba,et al.  Sensitivity study of surface wind flow of a limited area model simulating the extratropical storm Delta affecting the Canary Islands , 2009 .

[22]  D. Woolley.  The White Paper. , 1972, British medical journal.

[23]  Venkata Dinavahi,et al.  Direct Interval Forecast of Uncertain Wind Power Based on Recurrent Neural Networks , 2018, IEEE Transactions on Sustainable Energy.

[24]  Jonay Neris,et al.  Soil Temperature Regimes from Different Latitudes on a Subtropical Island (Tenerife, Spain) , 2010 .

[25]  Cees T. A. M. de Laat,et al.  Addressing big data issues in Scientific Data Infrastructure , 2013, 2013 International Conference on Collaboration Technologies and Systems (CTS).

[26]  Andrew Kusiak,et al.  Very short-term wind speed forecasting with Bayesian structural break model , 2013 .

[27]  Mario Vasak,et al.  Deep neural networks for ultra-short-term wind forecasting , 2015, 2015 IEEE International Conference on Industrial Technology (ICIT).

[28]  Weisheng Wang,et al.  Probabilistic Forecast for Multiple Wind Farms Based on Regular Vine Copulas , 2018, IEEE Transactions on Power Systems.

[29]  João Gama,et al.  Ensemble learning for data stream analysis: A survey , 2017, Inf. Fusion.

[30]  Ángel M. Pérez-Bellido,et al.  Hybridizing the fifth generation mesoscale model with artificial neural networks for short-term wind speed prediction , 2009 .

[31]  Zong Woo Geem,et al.  A Coral Reefs Optimization algorithm with Harmony Search operators for accurate wind speed prediction , 2015 .

[32]  Mohamed Mohandes,et al.  Support vector machines for wind speed prediction , 2004 .

[33]  Mohamed Medhat Gaber,et al.  Learning from Data Streams: Processing Techniques in Sensor Networks , 2007 .

[34]  Xiaofu Xiong,et al.  Estimating wind speed probability distribution using kernel density method , 2011 .