Scientists in China have proposed a new microgrid planning framework based on hybrid PV and small modular nuclear reactors. The framework uses multi-objective, distributionally robust optimization with a real-time reinforcement learning mechanism and is reportedly capable of reducing operational costs by 18.7%.
Researchers from China’s Guangdong Power Grid have proposed integrating solar energy with a small modular nuclear reactor (SMR) to increase the short-term dispatch capacity of microgrids while improving their long-term economic viability.
To combine the two energy sources, the research team used a scheduling framework that integrates a multi-objective distributionally robust optimization (DRO) with a real-time reinforcement learning (RL)-assisted mechanism.
“Unlike previous studies that focus on the use of renewable microgrids or nuclear-based energy systems, this paper presents a holistic framework for hybrid energy management that integrates multiple energy sources under a single optimization paradigm,” the team explains. “The novelty of this research lies in the co-optimization of photovoltaic and small modular reactor generation, combined with a robust, uncertainty-aware dispatch mechanism that takes into account both short- and long-term storage dynamics.”
In the proposed system, PV and SMR provide complementary energy sources, while a generator and battery act as resources. Hydrogen is produced by electrolyzers during excess periods and stored for later use, while an energy management system (EMS) acts as the brain of the entire system, making decisions and integrating predictions and real-time data.
The DRO is used within the EMS to generate basic planning strategies that can withstand forecast uncertainty, while the RL modules continuously adjust the control signals to improve adaptability and reduce real-world performance degradation. The optimization model was implemented in Python using Pyomo for mathematical programming, with Gurobi 10.0 as the solver for mixed integer programming formulations.
The system simulated as a case study included a 100 MW hybrid microgrid serving an industrial load with an average demand of 85 MW, exhibiting daily fluctuations in peak demand of up to 25%, and a residential demand component with an average load of 15 MW and a peak-to-average ratio of 1.6.
It has an installed PV capacity of 40 MW, with solar radiation data obtained from historical weather records over a period of one year. Solar energy variability is modeled using a normal distribution with a mean of 80% of nominal irradiance and a standard deviation of 12%, capturing seasonal and daily variations.
The SMR has a minimum stable power of 10 MW and a slope limit of 5 MW per hour. The system also includes a 20 MWh lithium-ion battery storage system, with a charge-discharge efficiency of 92%, and a hydrogen storage unit with a maximum capacity of 15 tons.
The analysis found that over a one-year operational horizon, the proposed optimization framework achieves an average operational cost reduction of approximately 18.7% while reducing CO2 emissions intensity by almost 37.1% compared to a conventional fossil fuel-dominated microgrid. Resilience indicators, such as the reliability of the critical load supply, have reportedly improved to more than 98% across all uncertainty scenarios, “underlining the framework’s ability to maintain safe operation during both regular and extreme conditions.”
The academics claim that, by combining DRO with learning-assisted adaptive planning, the microgrid operational strategy dynamically evolves based on real-time changes in the environment, ensuring flexibility even in the face of previously unseen conditions.
“Additionally, the coordination between short-term battery storage and long-term hydrogen storage allows the system to manage both daily and seasonal energy imbalances, creating a dual-layer storage strategy that simultaneously improves cost-effectiveness and reliability,” they concluded. “DR further supports this flexibility by dynamically reshaping consumption profiles to better align with sustainable generation patterns, reducing reliance on carbon-intensive backup generation.”
Their findings are available in the study “Coordinated operation and multi-layer optimization of hybrid photovoltaic microgrids with small modular reactors”, published in Scientific reports.
This content is copyrighted and may not be reused. If you would like to collaborate with us and reuse some of our content, please contact: editors@pv-magazine.com.
