Deploying deep reinforcement learning (DRL) in safety-critical nuclear control is limited less by raw performance than by the absence of licensable, audit-ready evidence. We introduce a Deterministic Assurance Framework (DTAF) that converts controller behavior into licensing-grade proof by combining the following: (i) deterministic licensing gates tied to formal safety and performance limits (e.g., Total Time Unsafe (TTU) = 0; bounded Transient Severity Score (TSS); and minimum Grid Load-Following Index (GLFI)); (ii) a portfolio of adversarial stress tests representative of off-nominal operation; and (iii) a traceability and explainability package that renders every evaluated action auditable. The DTAF is demonstrated on a high-fidelity pressurized-water-reactor (PWR) simulation model used as a software-in-the-loop testbed. Three governor architectures are evaluated under identical, fixed scenarios: a curriculum-trained Soft Actor–Critic (SAC) agent, and Differential-Evolution-optimized Proportional–Integral–Derivative (PID-DE) and Fuzzy-Logic (FLC-DE) Controllers. Performance is assessed deterministically via gate-aligned metrics—TTU, TSS, GLFI, cumulative control effort (CE_sum), valve-reversal count (V_rev), and speed overshoot (OS_ω). Across the adversarial portfolio, the SAC controller meets the predeclared licensing gates in single-run evaluations, whereas the strong conventional baselines violate gates in specific high-severity cases; where all methods remain within the safe envelope, the SAC delivers a higher GLFI and lower CE_sum, with fewer reversals and reduced overshoot. All licensing conclusions derive from deterministic single-run tests; a small, fixed-seed check (three seeds with descriptive intervals) is reported separately as non-licensing supplementary analysis. By producing transparent, reproducible artifacts, the DTAF offers a regulator-oriented pathway for qualifying DRL controllers in grid-interactive nuclear operations.
Indonesia is currently revising some Government Regulations regarding the licensing process of the nuclear power plant. In the current revision process, the latest technology such as small modular reactors and floating nuclear power plants are also considered to be regulated specifically. In current regulations, regardless of the type and technology, the licensing for nuclear power plants is regulated generally. Considering its unique nature and character, the floating nuclear power plant should have more specific requirements for the licensing process. This paper is carried out to analyze the specific requirements that should be considered for the licensing process of the floating nuclear power plant in Indonesia. The results of this study are expected to be a suggestion for the Government Regulations revision.
This study presents a time-dependent probabilistic risk assessment of Station Blackout (SBO) for a newcomer nuclear program, in this case Uganda’s prospective first nuclear power plant, with emphasis on the role of Flexible and Diverse Coping Strategies (FLEX) in mitigating AC power loss. The model developed incorporates exponentially distributed fail-to-run rates for Emergency Diesel Generators (EDGs) and Alternate AC (AAC) sources and applies a Weibull distribution to model offsite power recovery, reflecting the country’s infrastructural constraints and grid reliability challenges. Two operational scenarios are analyzed: (1) reliance solely on AC-based power sources and (2) inclusion of a Turbine-Driven Pump (TDP) as a non-AC coping mechanism. In both cases, FLEX is assumed to be integrated after initial commercial operation and functions as a portable AC supply. Results indicate that timely FLEX deployment substantially reduces SBO risk, with the largest benefit at longer mission times. Sensitivity analysis reveals that equipment reliability dominates deployment timing effects, with high-reliability systems achieving up to 75% risk reduction, while low-reliability equipment provides limited improvement below 25%. These findings provide a quantified risk perspective for Uganda’s nuclear safety planning and support evidence-based decisions on post-startup integration, infrastructure investment, and emergency preparedness.