An ultra-fast way of searching weather analogs for renewable energy forecasting

Abstract Analogs—weather patterns that highly resemble each other—have been widely adopted by the meteorology and renewable energy communities for predictive applications. It has been repeatedly demonstrated that by searching for and using past analogs, an analog ensemble (AnEn) can be constructed, circumventing or complementing computationally expensive dynamical ensemble systems. Of course, the pattern matching required by the AnEn benefits from larger historical datasets. However, brute-force analog searches become impractical with larger training datasets. To overcome this challenge, this paper introduces a rapid method for finding analogs. This method is referred to as Mueen’s algorithm for similarity search (MASS). MASS has many desirable properties in that it is exact, non-parametric, scalable, parallelizable and most notably, free from the curse of dimensionality. MASS can also be easily extended to multivariate cases. In a case study, 20 years of 1-h averaged ground-based multivariate weather data are used to exemplify a typical AnEn setup. It is found that MASS is about 100 times faster than the brute-force algorithm. MASS is suitable for all Euclidean distance-based pattern-matching tasks.

[1]  Eamonn J. Keogh,et al.  Searching and Mining Trillions of Time Series Subsequences under Dynamic Time Warping , 2012, KDD.

[2]  Lionel M. Ni,et al.  Efficient Similarity Joins on Massive High-Dimensional Datasets Using MapReduce , 2012, 2012 IEEE 13th International Conference on Mobile Data Management.

[3]  Stefano Alessandrini,et al.  A novel application of an analog ensemble for short-term wind power forecasting , 2015 .

[4]  J. Sanz,et al.  Analysis of wind power productions by means of an analog model , 2014 .

[5]  Stefano Alessandrini,et al.  A comparison between the ECMWF and COSMO Ensemble Prediction Systems applied to short-term wind power forecasting on real data , 2013 .

[6]  Dazhi Yang,et al.  SolarData: An R package for easy access of publicly available solar datasets , 2018, Solar Energy.

[7]  Luca Delle Monache,et al.  Post-processing techniques and principal component analysis for regional wind power and solar irradiance forecasting , 2016 .

[8]  F. Woodcock.  On the Use of Analogues to Improve Regression Forecasts , 1980 .

[9]  H. M. van den Dool,et al.  A New Look at Weather Forecasting through Analogues , 1989 .

[10]  S. E. Haupt,et al.  A Wind Power Forecasting System to Optimize Grid Integration , 2012, IEEE Transactions on Sustainable Energy.

[11]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[12]  R. Hilborn.  Sea gulls, butterflies, and grasshoppers: A brief history of the butterfly effect in nonlinear dynamics , 2004 .

[13]  Luca Delle Monache,et al.  Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble , 2017 .

[14]  Constantin Junk,et al.  Analog-Based Ensemble Model Output Statistics , 2015 .

[15]  Zheng Wang,et al.  Solar Power Forecasting Using Pattern Sequences , 2017, ICANN.

[16]  Olivier Mestre,et al.  Calibrated Ensemble Forecasts Using Quantile Regression Forests and Ensemble Model Output Statistics , 2016 .

[17]  Xiaofeng Meng,et al.  Parallel similarity joins on massive high‐dimensional data using MapReduce , 2016, Concurr. Comput. Pract. Exp..

[18]  Francisco Martinez Alvarez,et al.  Energy Time Series Forecasting Based on Pattern Sequence Similarity , 2011, IEEE Transactions on Knowledge and Data Engineering.

[19]  Eamonn J. Keogh,et al.  On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration , 2002, Data Mining and Knowledge Discovery.

[20]  David Huard,et al.  An Assessment of Six Dissimilarity Metrics for Climate Analogs , 2013 .

[21]  Eamonn J. Keogh,et al.  Clustering Time Series Using Unsupervised-Shapelets , 2012, 2012 IEEE 12th International Conference on Data Mining.

[22]  Pierre Tandeo,et al.  Nowcasting solar irradiance using an analog method and geostationary satellite images , 2018 .

[23]  L. D. Monache,et al.  An analog ensemble for short-term probabilistic solar power forecast , 2015 .

[24]  E. Lorenz.  Atmospheric Predictability as Revealed by Naturally Occurring Analogues , 1969 .

[25]  Jakob W. Messner,et al.  Probabilistic Forecasts Using Analogs in the Idealized Lorenz96 Setting , 2011 .

[26]  L. D. Monache,et al.  An application of the ECMWF Ensemble Prediction System for short-term solar power forecasting , 2016 .

[27]  Michael K. Tippett,et al.  Constructed Analogs and Linear Regression , 2013 .

[28]  Luca Delle Monache,et al.  Probabilistic Weather Prediction with an Analog Ensemble , 2013 .