Spatio-temporal wind speed prediction of multiple wind farms using capsule network

Spatio-temporal wind speed prediction is of great significance to the grid-connected operation of multiple wind farms in smart grid. This paper proposes a spatio-temporal wind speed prediction method based on capsule network (CapsNet) for geographically dispersed wind farms over a region. In the proposed method, the historical wind speed data from the wind farms are originally converted into chronological images in a 3D space, and the spatial features implicit in the images are extracted by the convolutional operation. Then, the temporal information of wind speed spatial properties is encapsu-lated in multi-dimensional time-capsules and learned by the dynamic routing mechanism, thus capturing the nonlinear temporal dependencies based on the extracted spatial features. A regression layer activated by the leaky rectified linear unit (Leaky ReLU) function integrates the spatio-temporal features and generates the final prediction results. Furthermore, a two-layer iterative training approach is employed to well-tune the model parameters and accelerate the convergence speed. Finally, the real data of multiple wind farms from Ohio are collected in the case studies to demonstrate the superior performance of the proposed method compared with other forecasting methods. (c) 2021 Elsevier Ltd. All rights reserved.

Automated summary

This paper proposes a spatio-temporal wind speed prediction method based on Capsule Network, which converts historical wind speed data into chronological images to extract spatial features and encapsulate temporal information using multi-dimensional time capsules and dynamic routing mechanism, capturing nonlinear temporal dependencies. Further integration of spatio-temporal features with a regression layer activated by Leaky ReLU, employing a two-layer iterative training approach, and demonstrating superior performance compared to other forecasting methods through case studies on multiple wind farms in Ohio.