nothing

PPO.py

@@ -331,8 +331,8 @@ if __name__ == '__main__':
         buffer = list()
         '''init training parameters'''
         num_episode = args.num_episode
-        args.train = False
-        args.save_network = False
+        # args.train = False
+        # args.save_network = False
         # args.test_network = False
         # args.save_test_data = False
         # args.compare_with_gurobi = False

environment.py

@@ -1,7 +1,7 @@
 import gym
 import numpy as np
 import pandas as pd
-from gym import spaces
+
 from module import *
 from parameters import *
 from data_manager import *
@@ -39,8 +39,8 @@ class ESSEnv(gym.Env):
         self.solar = Solar(self.solar_parameters)
         self.wind = Wind(self.wind_parameters)
 
-        self.action_space = spaces.Box(low=-1, high=1, shape=(5,), dtype=np.float32)  # 已增加调节电压动作
-        self.state_space = spaces.Box(low=-np.inf, high=np.inf, shape=(10,), dtype=np.float32)
+        self.action_space = gym.spaces.Box(low=-1, high=1, shape=(5,), dtype=np.float32)  # 已增加调节电压动作
+        self.state_space = gym.spaces.Box(low=0, high=1, shape=(10,), dtype=np.float32)
 
     def reset(self, *args):
         self.month = np.random.randint(1, 13)  # choose 12 month
@@ -69,7 +69,7 @@ class ESSEnv(gym.Env):
         temperature = self.data_manager.get_temperature_data(self.month, self.day, self.current_time)
         irradiance = self.data_manager.get_irradiance_data(self.month, self.day, self.current_time)
         wind_speed = self.data_manager.get_wind_data(self.month, self.day, self.current_time)
-        # print('house_load:', house_load)
+
         pv_generation = self.solar.step(temperature, irradiance)
         wd_generation = self.wind.step(wind_speed)
         generation = pv_generation + wd_generation
@@ -129,10 +129,9 @@ class ESSEnv(gym.Env):
         solar_cost = self.solar.get_cost(self.solar.current_power)
         wind_cost = self.wind.gen_cost(self.wind.current_power)
 
-        reward -= (battery_cost + dg1_cost + dg2_cost + dg3_cost + solar_cost + wind_cost + excess_penalty +
-                   deficient_penalty - sell_benefit + buy_cost) / 1e3
         self.operation_cost = (battery_cost + dg1_cost + dg2_cost + dg3_cost + solar_cost + wind_cost + excess_penalty +
                                deficient_penalty - sell_benefit + buy_cost)
+        reward -= self.operation_cost / 1e3
         self.unbalance = unbalance
         self.real_unbalance = self.shedding + self.excess
         final_step_outputs = [self.dg1.current_output, self.dg2.current_output, self.dg3.current_output,

plotDRL.py

@@ -134,7 +134,7 @@ def plot_evaluation_information(datasource, directory):
     axs[1, 1].set_ylabel('Costs')
     axs[1, 1].bar(eval_data['time_step'], eval_data['operation_cost'])
     fig.savefig(f"{directory}/evaluation_information.svg", format='svg', dpi=600, bbox_inches='tight')
-    print('evaluation figure have been plot and saved')
+    print('evaluation figure have been ploted and saved')
 
 
 def make_dir(directory, feature_change):