DARC: A Constraint-Diagnostic LLM Agent Framework for Day-Ahead Dispatch of Campus-Level Integrated Energy Microgrids Under Natural-Language Preferences and Forecast Uncertainty
Day-ahead dispatch of integrated energy systems (IESs) is commonly solved by mixed-integer linear programming when objectives, constraints, and forecasts are fully specified. In practice, however, operators often express temporary preferences in natural language, and day-ahead forecasts inevitably deviate from realized...