REAM - AI-Driven Renewable Energy Applications and Integration for Smart Cities

The REAM (AI-Driven Renewable Energy Applications and Integration for Smart Cities) project addresses fundamental limitations in the large-scale integration of renewable energy within urban systems, including variability of generation, limited forecasting accuracy, inefficient coordination between supply and demand, and the absence of scalable mechanisms to manage distributed energy resources. These challenges constrain system reliability, increase operational costs, and slow the transition toward low-carbon urban energy systems. To overcome these barriers, REAM develops an integrated AI-driven framework that combines advanced forecasting, optimization, and decentralized coordination. Machine learning models are designed to accurately predict renewable energy generation and consumption patterns under dynamic environmental and operational conditions. Optimization algorithms enhance energy efficiency, demand flexibility, and resource allocation across interconnected systems such as buildings, cooling networks, and distributed generation assets. The project further introduces digital architectures for decentralized energy management and exchange, enabling efficient interaction among producers, consumers, and prosumers. In parallel, resilience modeling evaluates system performance under stress scenarios, supporting robust and adaptive operation. REAM is aligned with the BeSolar initiative by embedding market-oriented intelligence and enabling data-driven valuation, coordination, and optimization of distributed solar resources within emerging energy ecosystems. Overall, REAM delivers a scalable and data-centric solution that enhances renewable energy utilization, improves system flexibility and resilience, and enables intelligent, market-aware energy management, supporting the development of sustainable and economically viable smart cities.

Hamad Bin Khalifa University (HBKU)