meeting

PPO.py

@@ -100,7 +100,6 @@ class AgentPPO:
 
         self.ratio_clip = 0.2  # ratio.clamp(1 - clip, 1 + clip)
         self.lambda_entropy = 0.02  # could be 0.01~0.05
-        self.gamma = 0.99
         self.lambda_gae_adv = 0.98  # could be 0.95~0.99, GAE (Generalized Advantage Estimation. ICLR.2016.)
         self.get_reward_sum = None  # self.get_reward_sum_gae if if_use_gae else self.get_reward_sum_raw
         self.trajectory_list = None
@@ -211,10 +210,10 @@ class AgentPPO:
         pre_r_sum = 0
         pre_advantage = 0  # advantage value of previous step
         for i in range(buf_len - 1, -1, -1):
-            buf_r_sum[i] = ten_reward[i] + ten_mask[i] * self.gamma * pre_r_sum
+            buf_r_sum[i] = ten_reward[i] + ten_mask[i] * gamma * pre_r_sum
             pre_r_sum = buf_r_sum[i]
-            delta = ten_reward[i] + ten_mask[i] * self.gamma * ten_value[i + 1] - ten_value[i]
-            buf_advantage[i] = delta + ten_mask[i] * self.gamma * self.lambda_gae_adv * pre_advantage
+            delta = ten_reward[i] + ten_mask[i] * gamma * ten_value[i + 1] - ten_value[i]
+            buf_advantage[i] = delta + ten_mask[i] * gamma * self.lambda_gae_adv * pre_advantage
             pre_advantage = buf_advantage[i]
         return buf_r_sum, buf_advantage
 

parameters.py

@@ -1,5 +1,5 @@
 solar_parameters = {
-    'I_sc0': 10.0,  # 参考条件下的短路电流 (A)
+    'I_sc0': 8.0,  # 参考条件下的短路电流 (A)
     'V_b': 25,  # 基准电压
     'V_oc0': 36.0,  # 参考条件下的开路电压 (V)
     'R_s': 0.1,  # 串联电阻 (Ω)

tools.py

@@ -61,7 +61,7 @@ def optimization_base_result(env, month, day, initial_soc):
     pv_voltage = m.addVars(period, vtype=GRB.CONTINUOUS, lb=-1, ub=1, name='pv_voltage')
 
     # 计算光伏和风力发电量
-    pv = [(0.25 * irradiance[t] + 0.05 * temperature[t] - 9.25) * (1 + pv_voltage[t]) for t in range(period)]
+    pv = [(0.2 * irradiance[t] + 0.05 * temperature[t] - 9.25) * (1 + pv_voltage[t]) for t in range(period)]
     wind = [172.265625 * wind_speed[t] ** 3 / 1e3 if 3 <= wind_speed[t] < 8
             else (172.265625 * 8 ** 3 / 1e3 if 8 <= wind_speed[t] < 12 else 0) for t in range(period)]