chenxiaodong
/
building-agents
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

plot

This commit is contained in:
chenxiaodong 2024-06-25 14:07:04 +08:00
parent 80344bd10a
commit 9d0b220b54
3 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
PPO.py
View File

@ -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

37
plotDRL.py
View File

@ -62,7 +62,7 @@ def plot_optimization_result(datasource, directory): # data source is dataframe
axs[1, 0].plot(T, datasource['netload'], label='Netload', drawstyle='steps-mid', alpha=0.7)
axs[1, 0].legend(loc='upper right', fontsize=12, frameon=False, labelspacing=0.3)
# axs[1,0].set_xticks([i for i in range(24)],[i for i in range(1,25)])
# plt.show()
fig.savefig(f"{directory}/optimization_information.svg", format='svg', dpi=600, bbox_inches='tight')
print('optimization results have been ploted and saved')
@ -78,9 +78,9 @@ def plot_evaluation_information(datasource, directory):
plt.autoscale(tight=True)
# prepare data for evaluation the environment here
eval_data = pd.DataFrame(test_data['information'])
eval_data = pd.DataFrame(test_data['system_info'])
eval_data.columns = ['time_step', 'price', 'netload', 'action', 'real_action', 'soc', 'battery', 'gen1', 'gen2',
'gen3', 'unbalance', 'operation_cost']
'gen3', 'temperature', 'irradiance', 'unbalance', 'operation_cost']
# plot unbalance in axs[0]
axs[0, 0].cla()
@ -90,10 +90,17 @@ def plot_evaluation_information(datasource, directory):
axs[0, 0].legend(loc='upper right', fontsize=12, frameon=False, labelspacing=0.5)
# axs[0,0].set_xticks([i for i in range(24)],[i for i in range(1,25)])
# plot reward in axs[1]
axs[1, 1].cla()
axs[1, 1].set_ylabel('Costs')
axs[1, 1].bar(eval_data['time_step'], eval_data['operation_cost'])
# plot energy charge/discharge with price in ax[1]
axs[0, 1].cla()
axs[0, 1].set_ylabel('Price')
axs[0, 1].set_xlabel('Time Steps')
axs[0, 1].plot(eval_data['time_step'], eval_data['price'], drawstyle='steps-mid', label='Price', color='pink')
axs[0, 1] = axs[0, 1].twinx()
axs[0, 1].set_ylabel('SOC')
# axs[0,1].set_xticks([i for i in range(24)], [i for i in range(1, 25)])
axs[0, 1].plot(eval_data['time_step'], eval_data['soc'], drawstyle='steps-mid', label='SOC', color='grey')
axs[0, 1].legend(loc='upper right', fontsize=12, frameon=False, labelspacing=0.3)
# plot generation and netload in ax[2]
axs[1, 0].cla()
@ -121,18 +128,10 @@ def plot_evaluation_information(datasource, directory):
axs[1, 0].plot(x, eval_data['netload'], drawstyle='steps-mid', label='Netload')
axs[1, 0].legend(loc='upper right', fontsize=12, frameon=False, labelspacing=0.3)
# plot energy charge/discharge with price in ax[3].
axs[0, 1].cla()
axs[0, 1].set_ylabel('Price')
axs[0, 1].set_xlabel('Time Steps')
axs[0, 1].plot(eval_data['time_step'], eval_data['price'], drawstyle='steps-mid', label='Price', color='pink')
axs[0, 1] = axs[0, 1].twinx()
axs[0, 1].set_ylabel('SOC')
# axs[0,1].set_xticks([i for i in range(24)], [i for i in range(1, 25)])
axs[0, 1].plot(eval_data['time_step'], eval_data['soc'], drawstyle='steps-mid', label='SOC', color='grey')
axs[0, 1].legend(loc='upper right', fontsize=12, frameon=False, labelspacing=0.3)
# plt.show()
# plot reward in axs[3]
axs[1, 1].cla()
axs[1, 1].set_ylabel('Costs')
axs[1, 1].bar(eval_data['time_step'], eval_data['operation_cost'])
fig.savefig(f"{directory}/Evoluation Information.svg", format='svg', dpi=600, bbox_inches='tight')
print('evaluation figure have been plot and saved')

2
tools.py
View File

@ -7,7 +7,7 @@ import torch
from gurobipy import GRB
def optimization_base_result(env,month,day,initial_soc):
def optimization_base_result(env, month, day, initial_soc):
price = env.data_manager.get_series_price_data(month, day)
load = env.data_manager.get_series_load_cons_data(month, day)
temperature = env.data_manager.get_series_temperature_data(month, day)