search

IBM / rl-testbed-for-energyplus

Reinforcement Learning Testbed for Power Consumption Optimization using EnergyPlus
MIT License
186 stars 77 forks source link

use FlowFromSystem instead of FlowControlWithApproachTemperatures #79

Closed antoine-galataud closed 2 years ago

antoine-galataud commented 2 years ago

Fixes #78

Signed-off-by: Antoine Galataud antoine@foobot.io

antoine-galataud commented 2 years ago

Tested with:

/usr/local/EnergyPlus-9-3-0/energyplus -r \
  -d /tmp/work -w /usr/local/EnergyPlus-9-3-0/WeatherData/USA_IL_Chicago-OHare.Intl.AP.725300_TMY3.epw \
  ./EnergyPlus/Model-9-3-0/2ZoneDataCenterHVAC_wEconomizer-baseline.idf

Then

>>> import pandas as pd
>>> df = pd.read_csv("/tmp/work/eplusout.csv")
>>> df["EAST ZONE:Zone Air Temperature [C](TimeStep)"].describe()
count    35040.000000
mean        23.760994
std          0.400133
min         22.999875
25%         23.483835
50%         23.740662
75%         24.035037
max         24.592905
Name: EAST ZONE:Zone Air Temperature [C](TimeStep), dtype: float64