Abstract
This research introduces a creative strategy for addressing the challenges of wind power predicting, crucial for effective renewable energy integration into the power grid. We propose a dual-stage attention-based Temporal Convolutional Network and Gated Recurrent Units (ATCN-AGRU) method for predicting wind energy over the medium term. In the first stage, a local attention mechanism captures fine-grained details and local dependencies, while the second stage employs a global attention mechanism to emphasize broader context and long-range dependencies within the data sequence. Our experimentation employs wind turbine data at 1-hr resolution, examining various time horizons from 24 hr to 1 week to assess multi-step forecasting precision and computational efficiency. Through rigorous statistical assessments, we demonstrate the model’s validity, with the mean absolute percentage errors (MAPE) consistently below 9% for week-ahead forecasting. Model parameters were fine-tuned using white shark optimization (WSO), enhancing convergence and overall performance. The proposed hybrid model significantly outperforms standard forecasting methods, achieving a maximum MAPE of 8.07% for week-ahead forecasting and a minimal 4.44% for day-ahead forecasting. To test the model’s stability, we extend the experiment to month-ahead forecasting, with the mean absolute error (MAE) ranging from 2.42 to 6.2% for weekly predictions.
ACKNOWLEDGMENTS
The authors express their sincere gratitude to National Institute of Wind Energy (NIWE), Chennai and the technical guidance provided by Dr. K. Boopathi, Director, Dr. A. G. Rangaraj, Deputy Director, and Mr. Yeluchuri Srinath, Assistant Director, National Institute of Wind Energy (NIWE), Chennai to carry out this research work.
ETHICS APPROVAL AND CONSENT TO PARTICIPATE
No participation of humans takes place in this implementation process.
HUMAN AND ANIMAL RIGHTS
No violation of Human and Animal Rights is involved.
DISCLOSURE STATEMENT
Conflict of Interest is not applicable in this work.
AUTHORSHIP CONTRIBUTIONS
All authors are contributed equally to this work.
FUNDING
No funding is involved in this work.
DATA AVAILABILITY STATEMENT
Data sharing not applicable to this article as no datasets were generated or analyzed during this study.
Additional information
Notes on contributors
C. Bharathi Priya
C. Bharathi Priya is an Assistant Professor, has two decade of teaching and industry experience. She has worked in several projects in medical image processing and IoT. Her research interests include Renewable Energy Analytics, Wireless Sensor Networks, Internet of Things, Medical Image Processing and Vehicular Adhoc Networks (VANETs). She published several research papers on Wind Energy Analytics, Internet of Things, Localization techniques in Wireless Sensor Networks, Vehicular Adhoc Networks and Cloud Security.
N. Arulanand
N. Arulanand is a professor who has a diverse background of industry experience, teaching experience, and research publications. He has experience in Embedded Systems, IoT, Machine Learning and Image Processing. He has a strong track record of publishing research papers in these fields, which demonstrates his expertise and knowledge in the area. Dr. Arulanand N has spent a significant amount of time researching and developing new technologies and techniques related to embedded systems, IoT, machine learning, and image processing, which can be applied to various industries. With his industry experience, he brings a unique perspective to teaching, with a focus on practical applications of these technologies.