Abstract
Accurate wind power forecasting plays a critical role in the operation of wind parks and the dispatch of wind energy into the power grid. With excellent automatic pattern recognition and nonlinear mapping ability for big data, deep learning is increasingly employed in wind power forecasting. However, salient realities are that in-situ measured wind data are relatively expensive and inaccessible and correlation between steps is omitted in most multistep wind power forecasts. This paper is the first time that data augmentation is applied to wind power forecasting by systematically summarizing and proposing both physics-oriented and data-oriented time-series wind data augmentation approaches to considerably enlarge primary datasets, and develops deep encoder-decoder long short-term memory networks that enable sequential input and sequential output for wind power forecasting. The proposed augmentation techniques and forecasting algorithm are deployed on five turbines with diverse topographies in an Arctic wind park, and the outcomes are evaluated against benchmark models and different augmentations. The main findings reveal that on one side, the average improvement in RMSE of the proposed forecasting model over the benchmarks is 33.89%, 10.60%, 7.12%, and 4.27% before data augmentations, and increases to 40.63%, 17.67%, 11.74%, and 7.06%, respectively, after augmentations. The other side unveils that the effect of data augmentations on prediction is intricately varying, but for the proposed model with and without augmentations, all augmentation approaches boost the model outperformance from 7.87% to 13.36% in RMSE, 5.24% to 8.97% in MAE, and similarly over 12% in QR90. Finally, data-oriented augmentations, in general, are slightly better than physics-driven ones.
Highlights
Wind is a renewable, sustainable, and environmentally friendly en ergy resource
It was demonstrated that the seq2seq model “approaches or surpasses all currently published results” [14] in Natural Language Pro cessing (NLP), like Google Translate, and recently it has shown its promise in renewable energy forecasting. [15, 16] The Encoder-Decoder (ED) Recurrent Neural Networks (RNN) has successfully handled seq2 seq problems [17] and exhibits state-of-the-art performance in the area of text translation that is fundamentally a time-series problem
Kisvari et al [24] constructed a framework consisting of data preprocessing, anomaly detection, feature engineering, and gated recurrent deep learning models for wind power prediction and demon strated that the framework offered more effective predictions than traditional recurrent neural networks
Summary
Sustainable, and environmentally friendly en ergy resource. As wind technology has developed in recent years, wind energy has received attention from a growing number of countries for its low-cost operation and maintenance, small turbine footprint, flexibility in development scale, and rapidly decreasing electricity generation costs. [1]. Massive electricity generated by wind energy is volatile, intermittent, and with low power density. Wind power forecasting methodology is generally divided into physical, statistical, and hybrid approaches. Machine learning-based wind power forecasting methods developed in recent years are widely applied. In wind energy, it is generally challenging to acquire high-quality and long-duration meteorological and power production data. Data augmentation is a technique to make supervised machine learning, especially deep networks, more efficient. It extends the amount of available training data by adding modified versions of existing data or new data generated based on existing data. It was demonstrated that the seq2seq model “approaches or surpasses all currently published results” [14] in Natural Language Pro cessing (NLP), like Google Translate, and recently it has shown its promise in renewable energy forecasting. [15, 16] The Encoder-Decoder (ED) Recurrent Neural Networks (RNN) has successfully handled seq2 seq problems [17] and exhibits state-of-the-art performance in the area of text translation that is fundamentally a time-series problem
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have