Feature selection in machine learning prediction systems for renewable energy applications

Abstract This paper focuses on feature selection problems that arise in renewable energy applications. Feature selection is an important problem in machine learning, both in classification and regression problems. In renewable energy systems, feature selection appears related to prediction systems in the most important sources such as wind, solar and marine resources. The objective of the paper is twofold: first, a review of the most important prediction systems for renewable energy applications involving feature selection is carried out. Analysis and discussion of different feature selection problems in prediction systems are considered. We show that wrapper FSP approaches are those mostly used due to their higher performance. They include a diversity of algorithms, prevailing fast-training approaches. The lack of an uniform framework for FSP and the diversity of tackled problems impede a systematic assessment of the performance and properties of the applied methods. Thus, the simultaneously use of several global search mechanisms should be the preferred option. In a second part of the paper, we explore this possibility, by introducing a novel approach for feature selection based on a novel meta-heuristic, the Coral Reefs Optimization algorithm with Substrate Layer. This approach is able to combine different search mechanisms into a single algorithm, providing a global search procedure of high quality. We use an Extreme Learning Machine for prediction within this novel approach. The performance of the system is evaluated in a problem of wind speed prediction from numerical models input, using real data from a wind farm in Spain, where comparison with alternative regression algorithms is carried out. Improvements up to 20% in hourly and daily wind speed prediction are obtained with the proposed system versus the algorithms without the feature selection process considered.

[1]  I. Ozturk,et al.  Impacts of renewable energy consumption on the German economic growth: Evidence from combined cointegration test , 2017 .

[2]  Ashu Verma,et al.  Economic and environmental effectiveness of renewable energy policy instruments: Best practices from India , 2016 .

[3]  Mário A. T. Figueiredo,et al.  Incremental filter and wrapper approaches for feature discretization , 2014, Neurocomputing.

[4]  Jie Zhang,et al.  A data-driven multi-model methodology with deep feature selection for short-term wind forecasting , 2017 .

[5]  Irena Koprinska,et al.  Univariate and multivariate methods for very short-term solar photovoltaic power forecasting , 2016 .

[6]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[7]  S. Chandel,et al.  Selection of most relevant input parameters using WEKA for artificial neural network based solar radiation prediction models , 2014 .

[8]  Jihoon Yang,et al.  Feature Subset Selection Using a Genetic Algorithm , 1998, IEEE Intell. Syst..

[9]  V. Sadasivam,et al.  An integrated PSO for parameter determination and feature selection of ELM and its application in classification of power system disturbances , 2015, Appl. Soft Comput..

[10]  Tingting Zhu,et al.  Short-term wind speed forecasting using empirical mode decomposition and feature selection , 2016 .

[11]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[12]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[14]  Hsu-Yung Cheng,et al.  Predicting solar irradiance with all-sky image features via regression , 2013 .

[15]  Sancho Salcedo-Sanz,et al.  Feature selection in wind speed prediction systems based on a hybrid coral reefs optimization – Extreme learning machine approach , 2014 .

[16]  Jaesung Jung,et al.  Optimal planning and design of hybrid renewable energy systems for microgrids , 2017 .

[17]  Ajay Kumar Bansal,et al.  Selection of Input Variables for the Prediction of Wind Speed in Wind Farms Based on Genetic Algorithm , 2011 .

[18]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[19]  Dan Zhang,et al.  Composite quantile regression extreme learning machine with feature selection for short-term wind speed forecasting: A new approach , 2017 .

[20]  Amit Kumar Yadav,et al.  Solar radiation prediction using Artificial Neural Network techniques: A review , 2014 .

[21]  A. Will,et al.  On the use of niching genetic algorithms for variable selection in solar radiation estimation , 2013 .

[22]  Chu Zhang,et al.  A compound structure of ELM based on feature selection and parameter optimization using hybrid backtracking search algorithm for wind speed forecasting , 2017 .

[23]  René Jursa,et al.  Short-term wind power forecasting using evolutionary algorithms for the automated specification of artificial intelligence models , 2008 .

[24]  Bohumil Frantál,et al.  Renewable energy investment and job creation; a cross-sectoral assessment for the Czech Republic with reference to EU benchmarks , 2017 .

[25]  J. Sanz-Justo,et al.  A CRO-species optimization scheme for robust global solar radiation statistical downscaling , 2017 .

[26]  Daphne Lopez,et al.  Feature Selection used for Wind Speed Forecasting with Data Driven Approaches , 2015 .

[27]  Yan Jiang,et al.  Short-term wind speed prediction: Hybrid of ensemble empirical mode decomposition, feature selection and error correction , 2017 .

[28]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[29]  Javier Del Ser,et al.  A novel Coral Reefs Optimization algorithm with substrate layers for optimal battery scheduling optimization in micro-grids , 2016, Soft Comput..

[30]  Henrik Madsen,et al.  A review on the young history of the wind power short-term prediction , 2008 .

[31]  Fernando Castellano,et al.  Comparison of feature selection methods using ANNs in MCP-wind speed methods. A case study , 2015 .

[32]  Md. Rafiqul Islam,et al.  Hybrids of support vector machine wrapper and filter based framework for malware detection , 2016, Future Gener. Comput. Syst..

[33]  J. A. Portilla-Figueras,et al.  The Coral Reefs Optimization Algorithm: A Novel Metaheuristic for Efficiently Solving Optimization Problems , 2014, TheScientificWorldJournal.

[34]  Raymond Chiong,et al.  Mid-term interval load forecasting using multi-output support vector regression with a memetic algorithm for feature selection , 2015 .

[35]  Sancho Salcedo-Sanz,et al.  Active Vibration Control Design Using the Coral Reefs Optimization with Substrate Layer Algorithm , 2018 .

[36]  Musa A. Mammadov,et al.  A hybrid wrapper-filter approach to detect the source(s) of out-of-control signals in multivariate manufacturing process , 2014, Eur. J. Oper. Res..

[37]  Àngela Nebot,et al.  Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques , 2015 .

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

[39]  Sancho Salcedo-Sanz,et al.  A review on the coral reefs optimization algorithm: new development lines and current applications , 2017, Progress in Artificial Intelligence.

[40]  Jesús Ariel Carrasco-Ochoa,et al.  A new hybrid filter-wrapper feature selection method for clustering based on ranking , 2016, Neurocomputing.

[41]  J. Sanz-Justo,et al.  A novel Grouping Genetic Algorithm–Extreme Learning Machine approach for global solar radiation prediction from numerical weather models inputs , 2016 .

[42]  Sancho Salcedo-Sanz,et al.  Structures vibration control via Tuned Mass Dampers using a co-evolution Coral Reefs Optimization algorithm , 2017 .

[43]  Sancho Salcedo-Sanz,et al.  Significant wave height and energy flux prediction for marine energy applications: A grouping genetic algorithm – Extreme Learning Machine approach , 2016 .

[44]  Yi Qin,et al.  Feature extraction method of wind turbine based on adaptive Morlet wavelet and SVD , 2011 .

[45]  Enrique Alexandre,et al.  Computational intelligence in wave energy: Comprehensive review and case study , 2016 .

[46]  Guang Yang,et al.  Solar irradiance feature extraction and support vector machines based weather status pattern recognition model for short-term photovoltaic power forecasting , 2015 .

[47]  Dalibor Petković,et al.  Selection of climatic parameters affecting wave height prediction using an enhanced Takagi-Sugeno-based fuzzy methodology , 2016 .

[48]  Sancho Salcedo-Sanz,et al.  New coral reefs-based approaches for the model type selection problem: a novel method to predict a nation's future energy demand , 2017, Int. J. Bio Inspired Comput..

[49]  Irena Koprinska,et al.  Correlation and instance based feature selection for electricity load forecasting , 2015, Knowl. Based Syst..

[50]  Zong Woo Geem,et al.  A New Heuristic Optimization Algorithm: Harmony Search , 2001, Simul..

[51]  María Pérez-Ortiz,et al.  A Review of Classification Problems and Algorithms in Renewable Energy Applications , 2016 .

[52]  Sancho Salcedo-Sanz,et al.  Evaluation of dimensionality reduction methods applied to numerical weather models for solar radiation forecasting , 2018, Eng. Appl. Artif. Intell..

[53]  Peng Kou,et al.  Probabilistic wind power forecasting with online model selection and warped gaussian process , 2014 .

[54]  M. Vermeij.  Substrate composition and adult distribution determine recruitment patterns in a Caribbean brooding coral , 2005 .

[55]  Xiaobing Kong,et al.  Wind speed prediction using reduced support vector machines with feature selection , 2015, Neurocomputing.