S. R.

Explainable Deep Learning for Sustainable Solar and Wind Power Forecasting

Solar PV and wind energy development in ongoing power systems is a means of achieving sustainability in power generation. Climatic uncertainty and renewables' variability, however, add to power forecasting volatility, which impacts energy management and reliability. Most existing deep learning models are hard to interpret and are trained to make the best prediction, limiting their ability in operational decisionmaking. For that, propose a novel Explainable Deep Learning (XDL) framework for Sustainable Solar and Wind Power Forecasting (SWPF) in this paper that addresses these drawbacks. The proposed framework integrates the multimodal extraction of meteorological features, the temporal attention-enhanced deep learning model, the explainable feature attribution, the uncertainty-aware prediction, and the reliability calibration to achieve accurate and explainable predictions of renewable energy resources. The extensive experiments demonstrate that XForecastNet is the most accurate, robust, and interpretable forecasting solution compared to traditional machine learning and state-of-the-art deep- learning approaches. The suggested framework would be beneficial for better prediction of the renewable energy sources, for a more stable grid, for more utilization of renewable energy sources, and for the possibility to operate the power system more sustainably.

AI-Native Deep Learning Framework for Ultra-Reliable Low-Latency IoT Networks with Federated Edge Intelligence

Intelligent Energy Optimization for Sustainable Green Buildings Using Artificial Intelligence

Buildings use a lot of energy and generate carbon emissions, so there is a need for an energy-management system that is intelligent enough to optimize energy use, save energy, and maintain the comfort of the people who inhabit the building while reducing carbon emissions. Building-management strategies currently operate in a static manner, with separate optimization for HVAC, lighting, appliances, and renewable resources. This paper suggests an AI-based framework called GreenOptNet, which incorporates multimodal sensor fusion, occupancy determination, HVAC and lighting control adaptation, appliance scheduling, coordinating renewable energy, and sustainability evaluation. This framework was tested with smart building energy, occupancy, environmental, solar-generation, and battery data. GreenOptNet was successful in energy savings of 43.68%, energy use of 84.72 kWh, HVAC efficiency of 98.53%, and occupant comfort of 98.84%. It also recorded a 96.74% renewable energy use and a 46.85% reduction in carbon emissions and operational cost savings of 44.36%. Ablation analyses confirmed that each module of the frameworks contributed, and statistical testing showed significant improvement over the compared models. The results have indicated that GreenOptNet is an effective, reliable, and sustainable solution for intelligent energy management in nextgeneration green buildings.