Variables and records

inference.py

@@ -99,8 +99,8 @@ def main():
 
     if args.service:
         args.cwd = agent_name
-        service_act_save_path = f'{args.cwd}/actor.pth'
-        agent.act.load_state_dict(torch.load(service_act_save_path))
+        act_save_path = f'{args.cwd}/actor.pth'
+        agent.act.load_state_dict(torch.load(act_save_path))
 
         # 创建一个队列用于线程间通信
         data_queue = queue.Queue()

models/env.py

@@ -124,7 +124,7 @@ class WgzGym(gym.Env):
         reward = - self.a * demand_cost - self.b * economic_cost + self.c * eco_benifit
 
         self.unbalance = power_gap + heat_gap
-        final_step_outputs = [self.HST.current_soc, self.EC.current_power, self.grid.current_power]
+        final_step_outputs = [self.HST.current_soc, self.HST.get_power(), self.EC.current_power, self.grid.current_power]
         self.current_time += 1
         finish = (self.current_time == self.episode_length)
         if finish:

models/tools.py

@@ -14,17 +14,13 @@ def test_one_episode(env, act, 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])
+        record_system_info.append([state[1], state[2], env.HST.current_soc(), env.HST.get_power(),
+                                   env.EC.current_power, env.grid.current_power, action, 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]
+    final_step_outputs = [self.HST.current_soc, self.HST.get_power(), self.EC.current_power, self.grid.current_power]
+    record_system_info[-1][2:6] = [env.final_step_outputs[0], env.final_step_outputs[1], env.final_step_outputs[2],
+                                   env.final_step_outputs[3]]
     record = {'init_info': record_init_info, 'system_info': record_system_info}
     return record
 
@@ -40,7 +36,7 @@ def get_episode_return(env, act, device):
         state, next_state, reward, done, = env.step(action)
         state = next_state
         episode_reward += reward
-        episode_unbalance += env.real_unbalance
+        episode_unbalance += env.unbalance
         if done:
             break
     return episode_reward, episode_unbalance

train.py

@@ -236,8 +236,6 @@ if __name__ == '__main__':
         '''init training params'''
         # args.train = False
         # args.save_network = False
-        # args.test_network = False
-        # args.save_test_data = False
         if args.train:
             for i_episode in range(num_episode):
                 with torch.no_grad():
@@ -266,14 +264,3 @@ if __name__ == '__main__':
             pickle.dump(reward_record, tf)
         torch.save(agent.act.state_dict(), act_save_path)
         print('actor params have been saved')
-
-    if args.test_network:
-        args.cwd = agent_name
-        agent.act.load_state_dict(torch.load(act_save_path))
-        record = test_one_episode(env, agent.act, agent.device)
-
-    if args.save_test_data:
-        test_data_save_path = f'{args.cwd}/test.pkl'
-        with open(test_data_save_path, 'wb') as tf:
-            pickle.dump(record, tf)
-        print('test data have been saved')