47 lines
2.3 KiB
Python
47 lines
2.3 KiB
Python
import torch
|
|
|
|
|
|
def test_one_episode(env, act, device):
|
|
"""get evaluate information, record the unbalance of after taking action"""
|
|
record_system_info = [] # same as observation
|
|
record_init_info = [] # include month,day,time
|
|
env.TRAIN = False
|
|
state = env.reset()
|
|
record_init_info.append([env.month, env.day, env.current_time])
|
|
print(f'current testing month is {env.month}, day is {env.day}')
|
|
for i in range(24):
|
|
s_tensor = torch.as_tensor((state,), device=device)
|
|
a_tensor = act(s_tensor)
|
|
action = a_tensor.detach().cpu().numpy()[0]
|
|
state, next_state, reward, done = env.step(action)
|
|
obs = np.concatenate((np.float32(time_step), np.float32(price), np.float32(temper),
|
|
np.float32(solar), np.float32(load), np.float32(heat),
|
|
np.float32(people), np.float32(ec_out), np.float32(hst_soc), np.float32(wind)), axis=None)
|
|
record_system_info.append([state[0], state[1], state[2], action, EC.current_power(),
|
|
env.HST.current_soc(), env.HST.get_power(), next_state[4], next_state[5],
|
|
next_state[6], env.solar.current_power, env.power_demand, env.heat_demand, reward])
|
|
state = next_state
|
|
# add information of last step EC, HST.current_soc, HST.power, grid
|
|
record_system_info[-1][7:12] = [env.final_step_outputs[0], env.final_step_outputs[1], env.final_step_outputs[2],
|
|
env.final_step_outputs[4], env.final_step_outputs[5]]
|
|
record_system_info[-1][5] = env.final_step_outputs[3]
|
|
record = {'init_info': record_init_info, 'system_info': record_system_info}
|
|
return record
|
|
|
|
|
|
def get_episode_return(env, act, device):
|
|
episode_reward = 0.0 # sum of rewards in an episode
|
|
episode_unbalance = 0.0
|
|
state = env.reset()
|
|
for i in range(24):
|
|
s_tensor = torch.as_tensor((state,), device=device)
|
|
a_tensor = act(s_tensor)
|
|
action = a_tensor.detach().cpu().numpy()[0] # not need detach(), because with torch.no_grad() outside
|
|
state, next_state, reward, done, = env.step(action)
|
|
state = next_state
|
|
episode_reward += reward
|
|
episode_unbalance += env.real_unbalance
|
|
if done:
|
|
break
|
|
return episode_reward, episode_unbalance
|