Feature Engineering and Forecasting via Derivative-free Optimization and Ensemble of Sequence-to-sequence Networks with Applications in Renewable Energy

Abstract

This study introduces a framework for the forecasting, reconstruction and feature engineering of multivariate processes along with its renewable energy applications. We integrate derivative-free optimization with an ensemble of sequence-to-sequence networks and design a new resampling technique called additive resampling, which, along with Bootstrap aggregating (bagging) resampling, are applied to initialize the ensemble structure. Moreover, we explore the proposed framework performance on three renewable energy sources---wind, solar and ocean wave---and conduct several short- to long-term forecasts showing the superiority of the proposed method compared to numerous machine learning techniques. The findings indicate that the introduced method performs more accurately when the forecasting horizon becomes longer. In addition, we modify the framework for automated feature selection. The model represents a clear interpretation of the selected features. Furthermore, we investigate the effects of different environmental and marine factors on the wind speed and ocean output power, respectively, and report the selected features. Finally, we explore the online forecasting setting and illustrate that the model outperforms alternatives through different measurement errors.

References in corpus (12)

• Sequence to Sequence Learning with Neural Networks
• LSTM: A Search Space Odyssey
• Learning to Diagnose with LSTM Recurrent Neural Networks
• The Microsoft 2017 Conversational Speech Recognition System
• The Microsoft 2016 Conversational Speech Recognition System
• Climate change impacts on wind energy potential in the European domain
• Text-based LSTM networks for Automatic Music Composition
• Black-Box Optimization in Machine Learning with Trust Region Based Derivative Free Algorithm
• Lung Cancer Screening Using Adaptive Memory-Augmented Recurrent Networks
• Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks
• Text-Independent Speaker Verification Using Long Short-Term Memory Networks
• Algebraic multigrid support vector machines

Cited by in corpus (3)

• A Deep-learning Real-time Bias Correction Method for Significant Wave Height Forecasts in the Western North Pacific
• Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks
• Simultaneous Decision Making for Stochastic Multi-echelon Inventory Optimization with Deep Neural Networks as Decision Makers