sinergym.utils.rewards.MultiZoneReward
- class sinergym.utils.rewards.MultiZoneReward(energy_variables: List[str], temperature_and_setpoints_conf: Dict[str, str], comfort_threshold: float = 0.5, energy_weight: float = 0.5, lambda_energy: float = 1.0, lambda_temperature: float = 1.0)
- __init__(energy_variables: List[str], temperature_and_setpoints_conf: Dict[str, str], comfort_threshold: float = 0.5, energy_weight: float = 0.5, lambda_energy: float = 1.0, lambda_temperature: float = 1.0)
A linear reward function for environments with different comfort ranges in each zone. Instead of having a fixed and common comfort range for the entire building, each zone has its own comfort range, which is directly obtained from the setpoints established in the building. This function is designed for buildings where temperature setpoints are not controlled directly but rather used as targets to be achieved, while other actuators are controlled to reach these setpoints. A setpoint observation variable can be assigned per zone if it is available in the specific building. It is also possible to assign the same setpoint variable to multiple air temperature zones.
- Parameters:
energy_variables (List[str]) – Name(s) of the energy/power variable(s).
temperature_and_setpoints_conf (Dict[str, str]) – Dictionary with the temperature variable name (key) and the setpoint variable name (value) of the observation space.
comfort_threshold (float, optional) – Comfort threshold for temperature range (+/-). Defaults to 0.5.
energy_weight (float, optional) – Weight given to the energy term. Defaults to 0.5.
lambda_energy (float, optional) – Constant for removing dimensions from power(1/W). Defaults to 1e-4.
lambda_temperature (float, optional) – Constant for removing dimensions from temperature(1/C). Defaults to 1.0.
Methods
__init__(energy_variables, ...[, ...])A linear reward function for environments with different comfort ranges in each zone.
Attributes
logger