def test_global_finite_horizon_optimal_management():
management = Finite_horizon_optimal_management(resource.index,
config=config)
b3 = battery.copy()
env = Dynamic_environment(b3, resource, management)
env.set_demand(result_df)
env.step_over_time()
env.simulation_result()
def test_reactive_follow_management():
management = Reactive_follow_management(demand)
b2 = battery.copy()
env = Dynamic_environment(b2, resource, management)
env.set_demand(result_df)
env.step_over_time()
env.simulation_result()
def test_absolute_follow_managemet():
management = Absolute_follow_management()
b1 = battery.copy()
env = Dynamic_environment(b1, resource, management)
env.set_demand(result_df)
env.step_over_time()
env.simulation_result()
def __init__(self, task_name, config=None):
"""
Initialise simulation environment by task name.
:param task_name: str name of the task e.g. 'Route-3-2013-01-01-3.pkl'
"""
with open(task_name, 'rb') as f:
env_pack = cloudpickle.load(f)
battery, result_df, resource = env_pack
battery_copy = battery.copy()
self.env = Dynamic_environment(battery_copy, resource, None, config=config)
self.resource = resource
self.env.set_demand(result_df)
self.def_space()
def test_ewm_management():
management = EWMA_management()
b4 = battery.copy()
env = Dynamic_environment(b4, resource, management)
env.set_demand(result_df)
env.step_over_time()
print(env.simulation_result())
print(env.total_reward)
class EnergyEnv(gym.Env):
metadata = {'render.modes': ['human']}
def __init__(self, task_name, config=None):
"""
Initialise simulation environment by task name.
:param task_name: str name of the task e.g. 'Route-3-2013-01-01-3.pkl'
"""
with open(task_name, 'rb') as f:
env_pack = cloudpickle.load(f)
battery, result_df, resource = env_pack
battery_copy = battery.copy()
self.env = Dynamic_environment(battery_copy, resource, None, config=config)
self.resource = resource
self.env.set_demand(result_df)
self.def_space()
def step(self, action):
"""
Parameters
----------
action :
Returns
-------
ob, reward, episode_over, info : tuple
ob (object) :
an environment-specific object representing your observation of
the environment.
reward (float) :
amount of reward achieved by the previous action. The scale
varies between environments, but the goal is always to increase
your total reward.
episode_over (bool) :
whether it'rlenergy time to reset the environment again. Most (but not
all) tasks are divided up into well-defined episodes, and done
being True indicates the episode has terminated. (For example,
perhaps the pole tipped too far, or you lost your last life.)
info (dict) :
diagnostic information useful for debugging. It can sometimes
be useful for learning (for example, it might contain the raw
probabilities behind the environment'rlenergy last state change).
However, official evaluations of your agent are not allowed to
use this for learning.
"""
ob, reward, done, info = self.env.gym_step(action)
self.done = done
if isinstance(reward, np.ndarray):
reward = reward[0][0]
return ob, reward, done, info
def reset(self):
init_state = self.env.reset()
# Also return initial state
return init_state
def render(self, mode='human', close=False):
if self.done:
return self.env.simulation_result()
else:
pass
def def_space(self):
self.action_space = Box(-1., 1., shape=(1,))
self.observation_space = Box(-1., 1., shape=(4,))
def scaler(self):
return self.env.get_scaler()