Data-driven weather forecasting models performance comparison for improving offshore wind turbine availability and maintenance

Wind power is highly dependent on wind speed and operations offshore are affected by wave height; these together called turbine weather datasets that are variable and intermittent over various time-scales and signify offshore weather conditions. In contrast to onshore wind, offshore wind requires improved forecasting since unfavorable weather prevents repair and maintenance activities. This study proposes two data-driven models for long-term weather conditions forecasting to support operation and maintenance (O&M) decision-making process. These two data-driven approaches are long short-term memory network, abbreviated as LSTM, and Markov chain. An LSTM is an artificial recurrent neural network, capable of learning long-term dependencies within a sequence of data and is typically used to avoid the long-term dependency problem. While, Markov is another data-driven stochastic model, which assumes that, the future states depend only on the current states, not on the events that occurred before. The readily available weather FINO3 datasets are used to train and validate the performance of these models. A performance comparison between these weather forecasted models would be carried out to determine which approach is most accurate and suitable for improving offshore wind turbine availability and support maintenance activities. The entire study outlines the weakness and strength associated with proposed models in relations to offshore wind farms operational activities.