Abstract: Methods and systems for model discovery include forming a mathematical program based on a set of observational data to generate an objective function and one or more constraints. The mathematical program represents a model space as an expression tree comprising operators and operands. The mathematical program is solved by optimizing the objective function subject to the one or more constraints to determine a model in the model space that best fits the set of observational data.

Abstract: A thermal behavior model of a building may be constructed based on time series data. Based on the constructed thermal behavior model, forecasted zone temperature and energy usage for a next control time period may be predicted. An objective function may be constructed based on at least a dynamically priced grid energy cost, occupant comfort matrix, and one or more of: energy storage system cost and associated operational cost, and energy generation system cost and associated green house emission cost and associated operational cost. Constraints may be constructed based on at least the forecasted zone temperature values and energy usage values for the next control time period. A control profile of the HVAC system and sourcing decision of energy load of the HVAC system may be determined simultaneously based on the objective function and the plurality of constraints.

Abstract: Methods and systems for model discovery include forming a mathematical program based on a set of observational data to generate an objective function and one or more constraints. The mathematical program represents a model space as an expression tree comprising operators and operands. The mathematical program is solved by optimizing the objective function subject to the one or more constraints to determine a model in the model space that best fits the set of observational data.

Abstract: A thermal behavior model of a building may be constructed based on time series data. Based on the constructed thermal behavior model, forecasted zone temperature and energy usage for a next control time period may be predicted. An objective function may be constructed based on at least a dynamically priced grid energy cost, occupant comfort matrix, and one or more of: energy storage system cost and associated operational cost, and energy generation system cost and associated green house emission cost and associated operational cost. Constraints may be constructed based on at least the forecasted zone temperature values and energy usage values for the next control time period. A control profile of the HVAC system and sourcing decision of energy load of the HVAC system may be determined simultaneously based on the objective function and the plurality of constraints.