Balancing Forecast Accuracy and Emissions for Hourly Wind Power at Dumat Al-Jandal: Sustainable AI for Zero-Carbon Transitions

This paper develops a Sustainable Artificial Intelligence-Driven Wind Power Forecasting System (SAI-WPFS) to enhance the integration of renewable energy while minimizing the environmental footprint of deep learning computations. Although deep learning models such as CNN, LSTM, and GRU have achieved high accuracy in wind power forecasting, existing research rarely considers the computational energy cost and associated carbon emissions, creating a gap between predictive performance and sustainability objectives. Moreover, limited studies have addressed the need for a balanced framework that jointly evaluates forecast precision and eco-efficiency in the context of large-scale renewable deployment. Using real-time data from the Dumat Al-Jandal Wind Farm, Saudi Arabia’s first utility-scale wind project, this study evaluates multiple deep learning architectures, including CNN-LSTM-AM and GRU, under a dual assessment framework combining accuracy metrics (MAE, RMSE, R²) and carbon efficiency indicators (CO₂ emissions per computational hour). Results show that the CNN-LSTM-AM model achieves the highest forecasting accuracy (MAE = 29.37, RMSE = 144.99, R² = 0.74), while the GRU model offers the best trade-off between performance and emissions (320 g CO₂/h). These findings demonstrate the feasibility of integrating sustainable AI into wind energy forecasting, aligning technical innovation with Saudi Vision 2030 goals for zero-carbon cities and carbon-efficient energy systems.