Short-term wind speed interval prediction using improved quality-driven loss based gated multi-scale convolutional sequence model.

Efficient estimation of the uncertainty associated with wind speed forecast is crucial for evaluating wind farms' power quality and operation. Typically, the performance of prediction interval (PI) generating models; is restricted in terms of computational efficiency inheritably from the sequential data processing; whereas restrictions in forecast quality are derived from the PI generation techniques. This paper presents an efficient Gated Multi-Scale Convolutional Sequence Model (GMSCSM) to forecast wind speed PIs. GMSCSM while conserving the 'recurrence' of LSTMs also offers 'parallel input' advantage of CNNs for better computational efficiency which is highly desirable for short-term forecasting models. In addition, capturing features at various scales in the sequence, GMSCSM learns both local details and global context which is vital for multi-horizon forecasts. The model generates quality PIs utilizing an improved quality-driven loss which we proposed by invoking calibration assessment in its existing definition. Forecasts generated for eight different datasets obtained from two different wind farms show an improvement of 30 % and 6 % in the average coverage width criterion index while reducing the model training time to nearly half and one third of the respective values obtained from traditional and LSTM based models which showcases the proposed model's excellent prediction capability and efficiency. • An efficient wind speed interval prediction tool is developed which could prove helpful in tackling the wind power development problems. • Utilizing the parallel input advantage of CNNs and recurrence properties of RNNs, an efficient deep learning framework for wind speed interval prediction is proposed. • Combining different window sizes-based convolutions the study develops a smart and efficient multi-scale feature extraction mechanism to capture both local and long-term dependencies in the data. • Adding a calibration function, the study proposed an improved calibrated quality driven loss function (QD imp) which mitigates the threshold coverage problem specially under multi-horizon forecasting. [ABSTRACT FROM AUTHOR]