Abstract: A method includes operating equipment to affect a variable state or condition of a space and training weights of a neural network by outputting control dispatches from the neural network based on simulated inputs, simulating costs associated with operating the equipment in accordance with control dispatches, and adjusting the weights to reduce the costs. The method also includes generating a control dispatch for the equipment by applying an actual measurement relating to the space as an input to the neural network, and controlling the equipment in accordance with the control dispatch.

Abstract: A method includes operating equipment to affect a variable state or condition of a space and determining a set of learned weights for a neural network by modeling an estimated cost of operating the equipment over a plurality of simulated scenarios. Each simulated scenario includes simulated measurements relating to the space. The neural network is configured to generate simulated control dispatches for the equipment based on the simulated measurements. The method also includes configuring the neural network for online control by applying the set of learned weights, applying actual measurements relating to the space to the neural network to generate a control dispatch for the equipment, and controlling the equipment in accordance with the control dispatch.

Abstract: A building cooling system includes a controller and a cooling device operable to affect indoor air temperature of a building. The controller is configured to obtain a cost function that characterizes a cost of operating the cooling device over a future time period, obtain a dataset relating to the building, determine a current state of the building by applying the dataset to a neural network, select a temperature bound associated with the current state, augment the cost function to include a penalty term that increases the cost when the indoor air temperature violates the temperature bound, and determine a temperature setpoint for each of a plurality of time steps in the future time period. The temperature setpoints achieve a target value of the cost function over the future time period. The controller is configured to control the cooling device to drive the indoor air temperature towards the temperature setpoint.

Abstract: A method includes operating equipment to affect a variable state or condition of a space and determining a set of learned weights for a neural network by modeling an estimated cost of operating the equipment over a plurality of simulated scenarios. Each simulated scenario includes simulated measurements relating to the space. The neural network is configured to generate simulated control dispatches for the equipment based on the simulated measurements. The method also includes configuring the neural network for online control by applying the set of learned weights, applying actual measurements relating to the space to the neural network to generate a control dispatch for the equipment, and controlling the equipment in accordance with the control dispatch.

Abstract: A building cooling system includes a controller and a cooling device operable to affect indoor air temperature of a building. The controller is configured to obtain a cost function that characterizes a cost of operating the cooling device over a future time period, obtain a dataset relating to the building, determine a current state of the building by applying the dataset to a neural network, select a temperature bound associated with the current state, augment the cost function to include a penalty term that increases the cost when the indoor air temperature violates the temperature bound, and determine a temperature setpoint for each of a plurality of time steps in the future time period. The temperature setpoints achieve a target value of the cost function over the future time period. The controller is configured to control the cooling device to drive the indoor air temperature towards the temperature setpoint.