Time-Series Prediction of the Offshore and Onshore Wind Profiles using the Autoencoding Models: Lidar and Meteorological Measurements Based

The development of a reliable wind forecast model plays a vital role in describing the variability and analyzing the time-series of the offshore and onshore wind profiles. In this paper, the analysis of the offshore and onshore wind profiles from the lidar and meteorological measurements based on two autoencoding architectures are presented.The historical datasets of the selected station variables from the:1lidar measurements and 2meteorological masts at 5–min and 10–min intervals are obtained. Two autoencoding model architectures (Conv2D and GRU encoding-decoding networks) in an unsupervised predictive operation are used for the time-series multivariable forecasting (1-288 horizons) and analysis of the:wind speed and wind direction, sectorwise windrose, CNR and prevailing air temperature. At the sampling period of 48 timesteps, the time-series wind speed and direction variations are analyzed in determining the measurement height with the steadiest wind flows for optimal loading of the large-scale wind turbine. Studied finding results of the offshore wind profiles at different heights revealed that the steadiest wind flow above 128.8 m height prevails but driven by the atmospheric effects. Also, the experimental findings revealed that the dominant wind flows of the onshore (10-20m height) are impacted by the local surface irregularitiesand atmospheric effects. Finally, the autoencoders performance is reported for the experimental offshore and onshore wind flowfor different station heights with and without the feature noise removal. Upon the validation and evaluation of the autoencoders with actual models, the proposed model architectures proved to be a fundamental forecast tool