Sustainable AI-driven wind energy forecasting: advancing zero-carbon cities and environmental computation

Abstract

Accurate forecasting of wind speed and power is transforming renewable wind farm management, facilitating efficient energy supply for smart and zero-energy cities. This paper introduces a novel low-carbon Sustainable AI-Driven Wind Energy Forecasting System (SAI-WEFS) developed from a promising real-world case study in MENA region. The SAI-WEFS evaluates twelve machine learning algorithms, utilizing both single and ensemble models for forecasting wind speed (WSF) and wind power (WPF) across multiple timeframes (10 min, 30 min, 6 h, 24 h, and 36 h). The system integrates multi-time horizon predictions, where the WSF output is input for the WPF model. The environmental impact of each algorithm is assessed based on CO2 emissions for each computational hour. Predictive accuracy is assessed using mean square error (MSE) and mean absolute percentage error (MAPE). Results indicate that ensemble algorithms consistently outperform single ML models, with tree-based models demonstrating a lower environmental impact, emitting approximately 60 g of CO2 per computational hour compared to deep learning models, which emit up to 500 g per hour. This system enhances the Urban Energy Supply Decarbonization Framework (UESDF) by predicting the Urban Carbon Emission Index (UCEI) to illustrate the Urban Carbon Transition Curve.