Short-Term Wind-Speed Forecasting Using Kernel Spectral Hidden Markov\n Models

2018/11/15 by Shunsuke Tsuzuki, Tsuzuki, Shunsuke, Yu Nishiyama +1
Computer Science · Engineering · Environmental Science · #Energy Load and Power Forecasting #FOS: Computer and information sciences #Hydrological Forecasting Using AI #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Solar Radiation and Photovoltaics

paper · pdf · doi:10.48550/arxiv.1811.06210

openalex publication_date 2018/11/15 · openalex created_date 2022/08/02 · openalex updated_date 2026/07/28

Abstract

In machine learning, a nonparametric forecasting algorithm for time series\ndata has been proposed, called the kernel spectral hidden Markov model (KSHMM).\nIn this paper, we propose a technique for short-term wind-speed prediction\nbased on KSHMM. We numerically compared the performance of our KSHMM-based\nforecasting technique to other techniques with machine learning, using\nwind-speed data offered by the National Renewable Energy Laboratory. Our\nresults demonstrate that, compared to these methods, the proposed technique\noffers comparable or better performance.\n

Citations

• A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains

Related

• Wind Speed Prediction and Visualization Using Long Short-Term Memory\n Networks (LSTM)
• Wind power predictions from nowcasts to 4-hour forecasts: a learning approach with variable selection
• A Multi-variable Stacked Long-Short Term Memory Network for Wind Speed Forecasting
• Short-term wind speed forecasting model based on an attention-gated recurrent neural network and error correction strategy
• Leveraging data from nearby stations to improve short-term wind speed forecasts