Merge pull request #94 from intelligent-environments-lab/citylearn-ch…

…allenge-2023-power-outage-env

Citylearn challenge 2023 power outage env

citylearn/building.py

@@ -759,6 +759,10 @@ def observations(self, include_all: bool = None, normalize: bool = None, periodi
             'cooling_electricity_consumption': self.cooling_electricity_consumption[self.time_step],
             'heating_electricity_consumption': self.heating_electricity_consumption[self.time_step],
             'dhw_electricity_consumption': self.dhw_electricity_consumption[self.time_step],
+            'cooling_storage_electricity_consumption': self.cooling_storage_electricity_consumption[self.time_step],
+            'heating_storage_electricity_consumption': self.heating_storage_electricity_consumption[self.time_step],
+            'dhw_storage_electricity_consumption': self.dhw_storage_electricity_consumption[self.time_step],
+            'electrical_storage_electricity_consumption': self.electrical_storage_electricity_consumption[self.time_step],
             'cooling_device_cop': self.cooling_device.get_cop(self.weather.outdoor_dry_bulb_temperature[self.time_step], heating=False),
             'heating_device_cop': self.heating_device.get_cop(
                 self.weather.outdoor_dry_bulb_temperature[self.time_step], heating=True
@@ -770,7 +774,7 @@ def observations(self, include_all: bool = None, normalize: bool = None, periodi
         }
 
         if include_all:
-            valid_observations = list(self.observation_metadata.keys())
+            valid_observations = list(data.keys())
         else:
             valid_observations = self.active_observations
 
@@ -1151,16 +1155,16 @@ def estimate_observation_space_limits(self, include_all: bool = None, periodic_n
 
         # Use entire dataset length for space limit estimation
         data = {
-            'solar_generation':np.array(self.pv.get_generation(self.energy_simulation.__getattr__(
-                'solar_generation', 
-                start_time_step=self.episode_tracker.simulation_start_time_step, 
-                end_time_step=self.episode_tracker.simulation_end_time_step
-            ))),
             **{k.lstrip('_'): self.energy_simulation.__getattr__(
                 k.lstrip('_'), 
                 start_time_step=self.episode_tracker.simulation_start_time_step, 
                 end_time_step=self.episode_tracker.simulation_end_time_step
             ) for k in vars(self.energy_simulation)},
+            'solar_generation':np.array(self.pv.get_generation(self.energy_simulation.__getattr__(
+                'solar_generation', 
+                start_time_step=self.episode_tracker.simulation_start_time_step, 
+                end_time_step=self.episode_tracker.simulation_end_time_step
+            ))),
             **{k.lstrip('_'): self.weather.__getattr__(
                 k.lstrip('_'), 
                 start_time_step=self.episode_tracker.simulation_start_time_step, 
@@ -1253,6 +1257,42 @@ def estimate_observation_space_limits(self, include_all: bool = None, periodic_n
                 low_limit[key] = 0.0
                 high_limit[key] = self.dhw_device.nominal_power
 
+            elif key == 'cooling_storage_electricity_consumption':
+                demand = self.energy_simulation.__getattr__(
+                   f'cooling_demand', 
+                    start_time_step=self.episode_tracker.simulation_start_time_step, 
+                    end_time_step=self.episode_tracker.simulation_end_time_step
+                )
+                electricity_consumption = self.cooling_device.get_input_power(demand, data['outdoor_dry_bulb_temperature'], False)
+                low_limit[key] = -max(electricity_consumption)
+                high_limit[key] = self.cooling_device.nominal_power
+
+            elif key == 'heating_storage_electricity_consumption':
+                demand = self.energy_simulation.__getattr__(
+                   f'heating_demand', 
+                    start_time_step=self.episode_tracker.simulation_start_time_step, 
+                    end_time_step=self.episode_tracker.simulation_end_time_step
+                )
+                electricity_consumption = self.heating_device.get_input_power(demand, data['outdoor_dry_bulb_temperature'], True)\
+                    if isinstance(self.heating_device, HeatPump) else self.heating_device.get_input_power(demand)
+                low_limit[key] = -max(electricity_consumption)
+                high_limit[key] = self.heating_device.nominal_power
+
+            elif key == 'dhw_storage_electricity_consumption':
+                demand = self.energy_simulation.__getattr__(
+                   f'dhw_demand', 
+                    start_time_step=self.episode_tracker.simulation_start_time_step, 
+                    end_time_step=self.episode_tracker.simulation_end_time_step
+                )
+                electricity_consumption = self.dhw_device.get_input_power(demand, data['outdoor_dry_bulb_temperature'], True)\
+                    if isinstance(self.dhw_device, HeatPump) else self.dhw_device.get_input_power(demand)
+                low_limit[key] = -max(electricity_consumption)
+                high_limit[key] = self.dhw_device.nominal_power
+
+            elif key == 'electrical_storage_electricity_consumption':
+                low_limit[key] = -self.electrical_storage.nominal_power
+                high_limit[key] = self.electrical_storage.nominal_power
+
             elif key == 'power_outage':
                 low_limit[key] = 0.0
                 high_limit[key] = 1.0

citylearn/citylearn.py

@@ -1,5 +1,5 @@
 from copy import deepcopy
-from enum import Enum, unique
+from enum import Enum
 import importlib
 import logging
 import os
@@ -128,14 +128,16 @@ def __init__(self,
         self.central_agent = central_agent
         self.shared_observations = shared_observations
 
+        # set reward function
+        self.reward_function = reward_function
+
         # reset environment and initializes episode time steps
         self.reset()
 
         # reset episode tracker to start after initializing episode time steps during reset
         self.episode_tracker.reset_episode_index()
 
-        # set reward function
-        self.reward_function = reward_function
+        # set reward metadata
         self.reward_function.env_metadata = self.get_metadata()
 
         # reward history tracker
@@ -1141,6 +1143,9 @@ def reset(self) -> List[List[float]]:
         for building in self.buildings:
             building.reset()
 
+        # reset reward function (does nothing by default)
+        self.reward_function.reset()
+
         # variable reset
         self.__rewards = [[]]
         self.__net_electricity_consumption = []

citylearn/reward_function.py

@@ -34,6 +34,11 @@ def central_agent(self) -> bool:
     def env_metadata(self, env_metadata: Mapping[str, Any]):
         self.__env_metadata = env_metadata
 
+    def reset(self):
+        """Use to reset variables at the start of an episode."""
+
+        pass
+
     def calculate(self, observations: List[Mapping[str, Union[int, float]]]) -> List[float]:
         r"""Calculates reward.