COMPARATIVE ANALYSIS OF LSTM, RF AND SVM ARCHITECTURES FOR PREDICTING WIND NATURE FOR SMART CITY PLANNING

Abstract. Meteorological data and its effect have been the attention of the researchers of the smart city planning for thorough utilization and management of resources, that help in effective government management, convenient public services and sustainable industrial development. Renewable sources of energy like wind, solar, are being integrated into city planning to improve environmental quality. Wind energy is utilized through wind turbines and requires foreknowledge of wind parameters like speed and direction. The aim of this paper is to predict dominant wind speed and direction for time-series wind dataset, that can be incorporated into city planning for selecting suitable sites for wind turbines. This paper proposes three one-dimensional (1D) algorithms using Long Short Term Memory (LSTM), Random Forest (RF) and Support Vector Machine (SVM) for dominant wind speed and direction prediction. The proposed 1D LSTM (1DLSTM), RF (1DRF) and SVM (1DSVM) take successive time values in terms of wind speed and direction as input and predict the future dominant speed and direction, separately. The proposed algorithms are trained and tested using historical wind dataset of Stuttgart and Netherlands respectively. Prediction using 1DLSTM results in total accuracies reaching up to 93.9% and 94.7%, up to 92.8% and 93.8% using 1DSVM and up to 88.7% and 89.3% using 1DRF for speed and direction, respectively. Thus, prediction of wind nature using the proposed algorithms, will give city planners advanced knowledge of wind conditions.

[1]  Seref Sagiroglu,et al.  A novel implementation of kNN classifier based on multi-tupled meteorological input data for wind power prediction , 2017 .

[2]  Oliver Kramer,et al.  Wind Power Prediction with Machine Learning , 2016, Computational Sustainability.

[3]  Yanbin Yuan,et al.  Short-Term Wind Speed Prediction Using EEMD-LSSVM Model , 2017 .

[4]  Luis Vargas,et al.  Data mining techniques for very short term prediction of wind power , 2010, 2010 IREP Symposium Bulk Power System Dynamics and Control - VIII (IREP).

[5]  Zijun Zhang,et al.  Short-Horizon Prediction of Wind Power: A Data-Driven Approach , 2010, IEEE Transactions on Energy Conversion.

[6]  Georges Kariniotakis,et al.  Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering. , 2005 .

[7]  Richard J. Cant,et al.  Characterisation of Large Changes in Wind Power for the Day-Ahead Market Using a Fuzzy Logic Approach , 2014, KI - Künstliche Intelligenz.

[8]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[9]  Geoffrey E. Hinton,et al.  Gated Softmax Classification , 2010, NIPS.

[10]  Chao Liu,et al.  Energy prediction using spatiotemporal pattern networks , 2017 .

[11]  Mohammad Monfared,et al.  A new strategy for wind speed forecasting using artificial intelligent methods , 2009 .

[12]  Manish Pandey,et al.  Modeling approaches for time series forecasting and anomaly detection , 2017 .

[13]  Tansu Filik,et al.  Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir , 2017 .

[14]  Maria Grazia De Giorgi,et al.  Comparison Between Wind Power Prediction Models Based on Wavelet Decomposition with Least-Squares Support Vector Machine (LS-SVM) and Artificial Neural Network (ANN) , 2014 .

[15]  E.F. El-Saadany,et al.  One Day Ahead Prediction of Wind Speed and Direction , 2008, IEEE Transactions on Energy Conversion.

[16]  Andrew Kusiak,et al.  Models for monitoring wind farm power , 2009 .

[17]  Borhan Molazem Sanandaji,et al.  Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting , 2017, ArXiv.

[18]  M. M. Ardehali,et al.  Very short-term wind speed prediction: A new artificial neural network–Markov chain model , 2011 .

[19]  Raúl Zurita-Milla,et al.  Mapping frequent spatio-temporal wind profile patterns using multi-dimensional sequential pattern mining , 2017, Int. J. Digit. Earth.

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

[21]  Ali Daraeepour,et al.  Day-ahead wind speed prediction by a Neural Network-based model , 2014, ISGT 2014.

[22]  Yuehua Huang,et al.  Short-term wind power prediction based on LSSVM–GSA model , 2015 .

[23]  R.W. Dunn,et al.  One-hour-ahead wind speed prediction using a Bayesian methodology , 2006, 2006 IEEE Power Engineering Society General Meeting.

[24]  Markus Wagner,et al.  Predicting the Energy Output of Wind Farms Based on Weather Data: Important Variables and their Correlation , 2011, ArXiv.

[25]  H. Zhou,et al.  Short-term wind power prediction based on statistical clustering , 2011, 2011 IEEE Power and Energy Society General Meeting.

[26]  Seddik Bacha,et al.  Modeling and control of hybrid photovoltaic wind power system with battery storage , 2015 .

[27]  M. G. De Giorgi,et al.  Short-term wind forecasting using artificial neural networks ( ANNs ) , 2009 .

[28]  Yongqian Liu,et al.  Genetic algorithm-piecewise support vector machine model for short term wind power prediction , 2010, 2010 8th World Congress on Intelligent Control and Automation.

[29]  Seref Sagiroglu,et al.  A new approach to very short term wind speed prediction using k-nearest neighbor classification , 2013 .

[30]  A. Kusiak,et al.  Short-Term Prediction of Wind Farm Power: A Data Mining Approach , 2009, IEEE Transactions on Energy Conversion.