Transfer learning for short-term wind speed prediction with deep neural networks |
| |
| Affiliation: | 1. Department of Chemical Engineering, National Taiwan University of Science and Technology, 43, Keelung Rd., Sec. 4, Taipei 106-07, Taiwan;2. Department of Chemical Engineering, Institut Teknologi Sepuluh Nopember, Kampus ITS Keputih Sukolilo, Surabaya 60111, Indonesia;3. Department of Chemical Engineering, Widya Mandala Surabaya Catholic University, Kalijudan 37, Surabaya 60114, Indonesia;4. Department of Chemical Engineering, University of San Carlos – Talamban Campus, Nasipit, Talamban, Cebu City 6000, Philippines;1. Andalusian Institute for Earth System Research, Universidad de Granada, Av. del Mediterráneo s/n., 18006 Granada, Spain;2. Universidad de Málaga, Escuela Técnica Superior de Ingeniería Industrial, Campus de Teatinos, 29071 Málaga, Spain;1. Department of Architecture, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8505, Japan;2. Institute of Industrial Science, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8505, Japan;1. National Kaohsiung University of Applied Sciences, 415 Jiangong Road, Sanmin District, Kaohsiung 80778, Taiwan;2. National Kaohsiung Marine University, 142 Hai-Jhuan Road, Nanzih District, Kaohsiung 81143, Taiwan |
| |
| Abstract: | As a type of clean and renewable energy source, wind power is widely used. However, owing to the uncertainty of wind speed, it is essential to build an accurate forecasting model for large-scale wind power penetration. Numerical weather prediction (NWP) and data-driven modeling are two typical paradigms. NWP is usually unavailable or spatially insufficient. Data-driven modeling is an effective candidate. As to some newly-built wind farms, sufficient historical data is not available for training an accurate model, while some older wind farms may have long-term wind speed records. A question arises regarding whether the prediction model trained by data coming from older farms is also effective for a newly-built farm. In this paper, we propose an interesting trial of transferring the information obtained from data-rich farms to a newly-built farm. It is well known that deep learning can extract a high-level representation of raw data. We introduce deep neural networks, trained by data from data-rich farms, to extract wind speed patterns, and then finely tune the mapping with data coming from newly-built farms. In this way, the trained network transfers information from one farm to another. The experimental results show that prediction errors are significantly reduced using the proposed technique. |
| |
| Keywords: | Wind speed prediction Transfer learning Deep neural networks Stacked denoising autoencoder |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
