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

Abstract

Wind energy is an attractive alternative to conventional sources of electricity generation due to its effectively zero carbon emissions. 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 timescales and signify offshore weather conditions. In contrast to onshore wind, offshore wind requires improved forecasting since unfavourable weather prevents repair and maintenance activities. Delayed repair results in increased downtime and reduced wind farm availability and energy yield. This paper proposes two data-driven models for long-term weather conditions forecasting to improve the wind farm availability and 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. A LSTM is an artificial recurrent neural network (RNN), 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 datasets are obtained from FINO3 database to train and validate the performance of these data-driven 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 full paper outlines the weakness and strength associated with proposed models in relations to offshore wind farms operational activities.

A Review on Wind Power Forecasting Regarding Impacts on the System Operation, Technical Challenges, and Applications

“…[ 240 ] The wind power prediction for maintenance planning is crucial for backup power systems, exploration after severe climate circumstances, smooth weather prediction during the process, and selection of suitable control system architecture. [ 241,242 ]…”

“…[240] The wind power prediction for maintenance planning is crucial for backup power systems, exploration after severe climate circumstances, smooth weather prediction during the process, and selection of suitable control system architecture. [241,242] The sitting of a wind farm is a crucial factor affecting the generated power by wind turbines. [243] Evaluations regarding the area's energy potential where the wind farm will be established are significant to ensure maximum efficiency from the installed plant.…”

The Game of Guwarra: A game theory-based decision-making framework for site selection of offshore wind farms in Australia

“…Various techniques to forecast wind speed and wave height have been proposed, including data-driven and physical models. Pandit et al (2020) proposed a data-driven model for weather forecasting in offshore environments and found that more accurate weather forecasts can decrease O&M costs by up to 3%. As presented in Fig.…”

Demystifying the use of ERA5‐land and machine learning for wind power forecasting

“…The chaining of customisable cells makes the LSTM model especially useful for working with data that include cyclical events over long time intervals, such as climate data sets. Moreover, LSTM models work well even with long delays between significant events in the input data and are also suitable for long‐term forecasting [43].…”