Smart Grid, Smart FiT: A data-driven approach to optimize microgrid energy market

The dynamic nature of renewable energy production and customer demand necessitates a flexible approach for designing Feed-in Tariff (FiT) schemes to ensure equity and fairness. This research presents a comprehensive data-driven framework for determining FiT rates by analyzing trends in demand, renewable energy generation, and temperature over time. The proposed method calculates FiT rates that adapt dynamically to evolving scenarios by incorporating both historical and projected trends. To optimize FiT values and offer affordable tariffs beneficial to both energy providers and customers, the proposed approach employs Sequential Model-Based Optimization (SMBO). Case studies using real-world microgrid data showcase the model’s adaptability and confirm its reliability by ensuring that the optimized FiT values remain within Australian government-set tariff limits. The SMBO method can decrease computational time by as much as 90%, achieving a Root Mean Square Error of 2.839. Additionally, the dynamic FiT model enhances financial sustainability by shortening the payback period for various prosumers by 17%–22% compared to a fixed FiT. The dynamic FiT adjusts rates based on previous historical and projected trends, incentivizing prosumers to export energy during peak demand. This method supports sustainable energy usage and offers a flexible, efficient pricing mechanism that adapts to the changing energy landscape. • A flexible and adaptive FiT framework to account for multiple uncertainties. • A new dynamic FiT model incorporating generation, consumption, and environmental patterns. • The FiT model includes a volatility control mechanism to manage real-time demand fluctuations. • The resulting export rate remains unaffected by geographic zones and seasonal variations. • A computation-driven FiT for future time frames, ensuring timely results.