nothing

.idea/csv-editor.xml

@@ -24,6 +24,13 @@
             </Attribute>
           </value>
         </entry>
+        <entry key="\data\station.csv">
+          <value>
+            <Attribute>
+              <option name="separator" value="," />
+            </Attribute>
+          </value>
+        </entry>
         <entry key="\data\temper.csv">
           <value>
             <Attribute>

DDPG.py

@@ -7,22 +7,9 @@ from environment import ESSEnv
 from tools import *
 
 
-def update_buffer(_trajectory):
-    ten_state = torch.as_tensor([item[0] for item in _trajectory], dtype=torch.float32)
-    ary_other = torch.as_tensor([item[1] for item in _trajectory])
-    ary_other[:, 0] = ary_other[:, 0]  # ten_reward
-    ary_other[:, 1] = (1.0 - ary_other[:, 1]) * gamma  # ten_mask = (1.0 - ary_done) * gamma
-
-    buffer.extend_buffer(ten_state, ary_other)
-
-    _steps = ten_state.shape[0]
-    _r_exp = ary_other[:, 0].mean()  # other = (reward, mask, action)
-    return _steps, _r_exp
-
-
 if __name__ == '__main__':
     args = Arguments()
-    '''here record real unbalance'''
+    '''record real unbalance'''
     reward_record = {'episode': [], 'steps': [], 'mean_episode_reward': [], 'unbalance': []}
     loss_record = {'episode': [], 'steps': [], 'critic_loss': [], 'actor_loss': [], 'entropy_loss': []}
     args.visible_gpu = '0'
@@ -32,7 +19,6 @@ if __name__ == '__main__':
         agent_name = f'{args.agent.__class__.__name__}'
         args.agent.cri_target = True
         args.env = ESSEnv()
-        # creat lists of lists/or creat a long list?
         args.init_before_training(if_main=True)
         '''init agent and environment'''
         agent = args.agent
@@ -57,7 +43,7 @@ if __name__ == '__main__':
         # args.save_network=False
         # args.test_network=False
         # args.save_test_data=False
-        # args.compare_with_pyomo=False
+        # args.compare_with_gurobi=False
 
         if args.train:
             collect_data = True
@@ -111,8 +97,8 @@ if __name__ == '__main__':
         with open(test_data_save_path, 'wb') as tf:
             pickle.dump(record, tf)
 
-    '''compare with pyomo data and results'''
-    if args.compare_with_pyomo:
+    '''compare with gurobi data and results'''
+    if args.compare_with_gurobi:
         month = record['init_info'][0][0]
         day = record['init_info'][0][1]
         initial_soc = record['init_info'][0][3]
@@ -126,7 +112,7 @@ if __name__ == '__main__':
         plot_dir = make_dir(args.cwd, plot_args.feature_change)
         plot_optimization_result(base_result, plot_dir)
         plot_evaluation_information(args.cwd + '/' + 'test_data.pkl', plot_dir)
-    '''compare the different cost get from pyomo and DDPG'''
+    '''compare the different cost get from gurobi and DDPG'''
     ration = sum(eval_data['operation_cost']) / sum(base_result['step_cost'])
     print('operation_cost_sum:', sum(eval_data['operation_cost']))
     print('step_cost_sum:', sum(base_result['step_cost']))

PPO.py

@@ -241,7 +241,7 @@ class Arguments:
         self.num_threads = 32  # cpu_num for evaluate model, torch.set_num_threads(self.num_threads)
 
         '''Arguments for training'''
-        self.num_episode = 2000  # to control the train episodes for PPO
+        self.num_episode = 1000  # to control the train episodes for PPO
         self.gamma = 0.995  # discount factor of future rewards
         self.learning_rate = 2 ** -14  # 2e-4
         self.soft_update_tau = 2 ** -8  # 2 ** -8 ~= 5e-3
@@ -261,7 +261,7 @@ class Arguments:
         self.save_network = True
         self.test_network = True
         self.save_test_data = True
-        self.compare_with_pyomo = True
+        self.compare_with_gurobi = True
         self.plot_on = True
 
     def init_before_training(self, if_main):
@@ -336,7 +336,7 @@ if __name__ == '__main__':
         # args.save_network=False
         # args.test_network=False
         # args.save_test_data=False
-        # args.compare_with_pyomo=False
+        # args.compare_with_gurobi=False
         if args.train:
             for i_episode in range(num_episode):
                 with torch.no_grad():
@@ -379,8 +379,8 @@ if __name__ == '__main__':
         with open(test_data_save_path, 'wb') as tf:
             pickle.dump(record, tf)
 
-    '''compare with pyomo data and results'''
-    if args.compare_with_pyomo:
+    '''compare with gurobi data and results'''
+    if args.compare_with_gurobi:
         month = record['init_info'][0][0]
         day = record['init_info'][0][1]
         initial_soc = record['init_info'][0][3]
@@ -394,7 +394,7 @@ if __name__ == '__main__':
         plot_dir = make_dir(args.cwd, plot_args.feature_change)
         plot_optimization_result(base_result, plot_dir)
         plot_evaluation_information(args.cwd + '/' + 'test_data.pkl', plot_dir)
-    '''compare the different cost get from pyomo and PPO'''
+    '''compare the different cost get from gurobi and PPO'''
     ration = sum(eval_data['operation_cost']) / sum(base_result['step_cost'])
     print('operation_cost_sum:', sum(eval_data['operation_cost']))
     print('step_cost_sum:', sum(base_result['step_cost']))

SAC.py

@@ -7,19 +7,6 @@ from environment import ESSEnv
 from tools import *
 
 
-def update_buffer(_trajectory):
-    ten_state = torch.as_tensor([item[0] for item in _trajectory], dtype=torch.float32)
-    ary_other = torch.as_tensor([item[1] for item in _trajectory])
-    ary_other[:, 0] = ary_other[:, 0]  # ten_reward
-    ary_other[:, 1] = (1.0 - ary_other[:, 1]) * gamma  # ten_mask = (1.0 - ary_done) * gamma
-
-    buffer.extend_buffer(ten_state, ary_other)
-
-    _steps = ten_state.shape[0]
-    _r_exp = ary_other[:, 0].mean()  # other = (reward, mask, action)
-    return _steps, _r_exp
-
-
 if __name__ == '__main__':
     args = Arguments()
     reward_record = {'episode': [], 'steps': [], 'mean_episode_reward': [], 'unbalance': []}
@@ -59,7 +46,7 @@ if __name__ == '__main__':
         # args.save_network=False
         # args.test_network=False
         # args.save_test_data=False
-        # args.compare_with_pyomo=False
+        # args.compare_with_gurobi=False
         #
         if args.train:
             collect_data = True
@@ -115,8 +102,8 @@ if __name__ == '__main__':
         with open(test_data_save_path, 'wb') as tf:
             pickle.dump(record, tf)
 
-    '''compare with pyomo data and results'''
-    if args.compare_with_pyomo:
+    '''compare with gurobi data and results'''
+    if args.compare_with_gurobi:
         month = record['init_info'][0][0]
         day = record['init_info'][0][1]
         initial_soc = record['init_info'][0][3]
@@ -130,7 +117,7 @@ if __name__ == '__main__':
         plot_dir = make_dir(args.cwd, plot_args.feature_change)
         plot_optimization_result(base_result, plot_dir)
         plot_evaluation_information(args.cwd + '/' + 'test_data.pkl', plot_dir)
-    '''compare the different cost get from pyomo and SAC'''
+    '''compare the different cost get from gurobi and SAC'''
     ration = sum(eval_data['operation_cost']) / sum(base_result['step_cost'])
     print('operation_cost_sum:', sum(eval_data['operation_cost']))
     print('step_cost_sum:', sum(base_result['step_cost']))

TD3.py

@@ -7,19 +7,6 @@ from environment import ESSEnv
 from tools import *
 
 
-def update_buffer(_trajectory):
-    ten_state = torch.as_tensor([item[0] for item in _trajectory], dtype=torch.float32)
-    ary_other = torch.as_tensor([item[1] for item in _trajectory])
-    ary_other[:, 0] = ary_other[:, 0]  # ten_reward
-    ary_other[:, 1] = (1.0 - ary_other[:, 1]) * gamma  # ten_mask = (1.0 - ary_done) * gamma
-
-    buffer.extend_buffer(ten_state, ary_other)
-
-    _steps = ten_state.shape[0]
-    _r_exp = ary_other[:, 0].mean()  # other = (reward, mask, action)
-    return _steps, _r_exp
-
-
 if __name__ == '__main__':
     args = Arguments()
     reward_record = {'episode': [], 'steps': [], 'mean_episode_reward': [], 'unbalance': []}
@@ -56,7 +43,7 @@ if __name__ == '__main__':
         # args.save_network=False
         # args.test_network=False
         # args.save_test_data=False
-        # args.compare_with_pyomo=False
+        # args.compare_with_gurobi=False
 
         if args.train:
             collect_data = True
@@ -111,8 +98,8 @@ if __name__ == '__main__':
         with open(test_data_save_path, 'wb') as tf:
             pickle.dump(record, tf)
 
-    '''compare with pyomo data and results'''
-    if args.compare_with_pyomo:
+    '''compare with gurobi data and results'''
+    if args.compare_with_gurobi:
         month = record['init_info'][0][0]
         day = record['init_info'][0][1]
         initial_soc = record['init_info'][0][3]
@@ -126,7 +113,7 @@ if __name__ == '__main__':
         plot_dir = make_dir(args.cwd, plot_args.feature_change)
         plot_optimization_result(base_result, plot_dir)
         plot_evaluation_information(args.cwd + '/' + 'test_data.pkl', plot_dir)
-    '''compare the different cost get from pyomo and TD3'''
+    '''compare the different cost get from gurobi and TD3'''
     ration = sum(eval_data['operation_cost']) / sum(base_result['step_cost'])
     print('operation_cost_sum:', sum(eval_data['operation_cost']))
     print('step_cost_sum:', sum(base_result['step_cost']))

data_manager.py

@@ -5,15 +5,12 @@ class Constant:
 
 class DataManager:
     def __init__(self) -> None:
-        self.Pv = []
         self.Prices = []
         self.Load_Consumption = []
         self.Temperature = []
         self.Irradiance = []
         self.Wind = []
 
-    def add_pv_element(self, element): self.Pv.append(element)
-
     def add_price_element(self, element): self.Prices.append(element)
 
     def add_load_element(self, element): self.Load_Consumption.append(element)
@@ -25,9 +22,6 @@ class DataManager:
     def add_wind_element(self, element): self.Wind.append(element)
 
     # get current time data based on given month day, and day_time
-    def get_pv_data(self, month, day, day_time):
-        return self.Pv[(sum(Constant.MONTHS_LEN[:month - 1]) + day - 1) * 24 + day_time]
-
     def get_price_data(self, month, day, day_time):
         return self.Prices[(sum(Constant.MONTHS_LEN[:month - 1]) + day - 1) * 24 + day_time]
 
@@ -44,10 +38,6 @@ class DataManager:
         return self.Wind[(sum(Constant.MONTHS_LEN[:month - 1]) + day - 1) * 24 + day_time]
 
     # get series data for one episode
-    def get_series_pv_data(self, month, day):
-        return self.Pv[(sum(Constant.MONTHS_LEN[:month - 1]) + day - 1) * 24:
-                       (sum(Constant.MONTHS_LEN[:month - 1]) + day - 1) * 24 + 24]
-
     def get_series_price_data(self, month, day):
         return self.Prices[(sum(Constant.MONTHS_LEN[:month - 1]) + day - 1) * 24:
                            (sum(Constant.MONTHS_LEN[:month - 1]) + day - 1) * 24 + 24]

environment.py

@@ -11,8 +11,8 @@ class ESSEnv(gym.Env):
     def __init__(self, **kwargs):
         super(ESSEnv, self).__init__()
         self.excess = None
-        self.unbalance = None
         self.shedding = None
+        self.unbalance = None
         self.real_unbalance = None
         self.operation_cost = None
         self.current_output = None
@@ -113,7 +113,7 @@ class ESSEnv(gym.Env):
                 sell_benefit = self.grid.get_cost(price, unbalance) * self.sell_coefficient
             else:
                 sell_benefit = self.grid.get_cost(price, self.grid.exchange_ability) * self.sell_coefficient
-                # real unbalance that even grid could not meet
+                # real unbalance that grid could not meet
                 self.excess = unbalance - self.grid.exchange_ability
                 excess_penalty = self.excess * self.penalty_coefficient
         else:  # unbalance <0, its load shedding model, deficient penalty is used
@@ -153,14 +153,12 @@ class ESSEnv(gym.Env):
     #           format(self.day, self.current_time, current_obs, next_obs, reward, finish))
 
     def _load_year_data(self):
-        # pv_df = pd.read_csv('data/pv.csv', sep=',')
         price_df = pd.read_csv('data/prices.csv', sep=';')
         load_df = pd.read_csv('data/houseload.csv', sep=',')
         irradiance_df = pd.read_csv('data/irradiance.csv', sep=',')
         temperature_df = pd.read_csv('data/temper.csv', sep=',')
         wind_df = pd.read_csv('data/wind.csv', sep=',')
 
-        # pv = pv_df['pv'].to_numpy(dtype=float)
         price = price_df['Price'].apply(lambda x: x.replace(',', '.')).to_numpy(dtype=float)
         load = load_df['houseload'].to_numpy(dtype=float)
         irradiance = irradiance_df['irradiance'].to_numpy(dtype=float)
@@ -173,7 +171,6 @@ class ESSEnv(gym.Env):
                 transformed_element = transform_function(element)
                 add_function(transformed_element)
 
-        # process_elements(pv, lambda x: x, self.data_manager.add_pv_element)
         process_elements(price, lambda x: max(x / 10, 0.5), self.data_manager.add_price_element)
         process_elements(load, lambda x: x * 3, self.data_manager.add_load_element)
         process_elements(irradiance, lambda x: x, self.data_manager.add_irradiance_element)

module.py

@@ -78,9 +78,9 @@ class Solar:
         self.oc_voltage = parameters['V_oc0']
         self.s_resistance = parameters['R_s']
         self.sh_resistance = parameters['R_sh']
-        self.temper_coefficient = parameters['k_v']
-        self.opex_cofficient = parameters['k_o']
-        self.refer_irradiance = parameters['G_ref']
+        self.temper_coefficient = parameters['T_c']
+        self.opex_cofficient = parameters['O_c']
+        self.refer_irradiance = parameters['I_ref']
         self.refer_temperature = parameters['T_ref']
 
     def step(self, temperature, irradiance, action_voltage=0):
@@ -126,7 +126,6 @@ class Wind:
                                   self.power_coefficient * self.generator_efficiency) / 1e3
         else:
             self.current_power = 0
-
         return self.current_power
 
     def gen_cost(self, current_power):

parameters.py

@@ -2,13 +2,13 @@ import numpy as np
 
 solar_parameters = {
     'I_sc0': 8.0,  # 参考条件下的短路电流 (A)
-    'V_b': 24,  # 基准电压
+    '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)
     'R_sh': 100.0,  # 并联电阻 (Ω)
-    'k_v': -0.2,  # 开路电压的温度系数 (V/°C)
-    'k_o': 0.001,  # 变动成本系数 (元/千瓦时)
-    'G_ref': 1000,  # 参考辐照度 (W/m²)
+    'T_c': -0.2,  # 开路电压的温度系数 (V/°C)
+    'O_c': 0.001,  # 变动成本系数 (元/千瓦时)
+    'I_ref': 1000,  # 参考辐照度 (W/m²)
     'T_ref': 25,  # 参考温度 (°C)
 }
 
@@ -35,15 +35,15 @@ battery_parameters = {
 }
 
 dg_parameters = {
-    'gen_1': {'a': 0.0034, 'b': 3, 'c': 30, 'd': 0.03, 'e': 4.2, 'f': 0.031,
+    'gen_1': {'a': 0.0034, 'b': 3, 'c': 30,
               'power_output_max': 150, 'power_output_min': 10,
               'ramping_up': 100, 'ramping_down': 100, 'min_up': 2, 'min_down': 1},
 
-    'gen_2': {'a': 0.001, 'b': 10, 'c': 40, 'd': 0.03, 'e': 4.2, 'f': 0.031,
+    'gen_2': {'a': 0.001, 'b': 10, 'c': 40,
               'power_output_max': 375, 'power_output_min': 50,
               'ramping_up': 100, 'ramping_down': 100, 'min_up': 2, 'min_down': 1},
 
-    'gen_3': {'a': 0.001, 'b': 15, 'c': 70, 'd': 0.03, 'e': 4.2, 'f': 0.031,
+    'gen_3': {'a': 0.001, 'b': 15, 'c': 70,
               'power_output_max': 500, 'power_output_min': 100,
               'ramping_up': 200, 'ramping_down': 200, 'min_up': 2, 'min_down': 1}
 }

tools.py

@@ -129,7 +129,7 @@ class Arguments:
         self.num_threads = 32  # cpu_num for evaluate model, torch.set_num_threads(self.num_threads)
 
         '''Arguments for training'''
-        self.num_episode = 2000
+        self.num_episode = 1000
         self.gamma = 0.995  # discount factor of future rewards
         # self.reward_scale = 1  # an approximate target reward usually be closed to 256
         self.learning_rate = 2 ** -14  # 2 ** -14 ~= 6e-5
@@ -152,7 +152,7 @@ class Arguments:
         self.save_network = True
         self.test_network = True
         self.save_test_data = True
-        self.compare_with_pyomo = True
+        self.compare_with_gurobi = True
         self.plot_on = True
 
     def init_before_training(self, if_main):
@@ -233,6 +233,19 @@ def get_episode_return(env, act, device):
     return episode_return, episode_unbalance
 
 
+def update_buffer(_trajectory):
+    ten_state = torch.as_tensor([item[0] for item in _trajectory], dtype=torch.float32)
+    ary_other = torch.as_tensor([item[1] for item in _trajectory])
+    ary_other[:, 0] = ary_other[:, 0]  # ten_reward
+    ary_other[:, 1] = (1.0 - ary_other[:, 1]) * gamma  # ten_mask = (1.0 - ary_done) * gamma
+
+    buffer.extend_buffer(ten_state, ary_other)
+
+    _steps = ten_state.shape[0]
+    _r_exp = ary_other[:, 0].mean()  # other = (reward, mask, action)
+    return _steps, _r_exp
+
+
 class ReplayBuffer:
     def __init__(self, max_len, state_dim, action_dim, gpu_id=0):
         self.now_len = 0