AI-driven predictive models for sustainability
Year: 2024
Type: article
Abstract: This research presents an AI-driven, explainable energy management model that aligns with Net Zero sustainability objectives by optimizing energy consumption, enhancing predictive accuracy, and ensuring transparency. The model integrates machine learning algorithms, like Gradient Boosting Machines (GBM) and Random Forests, and utilizes techniques like SHAP and LIME for interpretability. Data was split 70/30 for training and validation, with 10-times validation to avoid overfitting, achieving a Mean Absolute Error (MAE) of 1.26–1.53 and Root Mean Squared Error (RMSE) of 1.97–2.06. The model's predictive accuracy reached an R 2 of 0.92, with precision and recall scores of 85–90% and 80–88%, respectively, demonstrating significant improvements over traditional methods. Sensitivity analysis revealed high influence from temperature and historical consumption data, requiring careful monitoring. This model performed robustly across diverse scenarios, reducing CO₂ emissions by 30% and cutting costs by 18%, highlighting its adaptability in real-world applications. Conclusions affirm that the explainable AI model advances sustainable energy management by providing reliable, actionable insights, aligning with Net Zero goals, and supporting informed decision-making through enhanced transparency and accuracy. • AI model outperforms traditional systems with 20% higher accuracy in energy prediction. • Explainable AI ensures transparency, boosting stakeholder trust and facilitating regulatory compliance. • Energy consumption was reduced by up to 35% across sectors, enhancing sustainability efforts. • Advanced AI techniques enable precise feature selection, optimizing model efficiency. • Research validates AI's role in achieving Net Zero goals through effective energy management.
Authors: Mattew A. Olawumi, Bankole I. Oladapo
Institutions: De Montfort University, University of Dundee
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,850
OpenAlex ID: W4404798080