IBM / rl-testbed-for-energyplus

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

Program exits starting episode 1 run #17

Closed myndtrust closed 5 years ago

myndtrust commented 5 years ago

I am running the program without any modifications. I had a successful run right after install, but then undated to Ubuntu 18.0.02 from 18.04.01 and the behavior of the program changed. I have cloned the repo in another directory by following the installation instruction, but the problem persists.

I am running the program with time python3 -m baselines_energyplus.trpo_mpi.run_energyplus --num-timesteps 10 The error file also does not contain much information neither. The error file for the 1 episode is Program Version,EnergyPlus, Version 8.8.0-7c3bbe4830, YMD=2019.05.01 19:17,IDD_Version 8.8.0 ************* Beginning Zone Sizing Calculations

Episode 0 had a more detailed err file, but it appears irrelevant to the exist when starting episode 1.

`Program Version,EnergyPlus, Version 8.8.0-7c3bbe4830, YMD=2019.05.01 19:09,IDD_Version 8.8.0 Beginning Zone Sizing Calculations Warning Calculated design heating load for zone=WEST ZONE is zero. ~~~ Check Sizing:Zone and ZoneControl:Thermostat inputs. Warning Calculated design heating load for zone=EAST ZONE is zero. ~~~ Check Sizing:Zone and ZoneControl:Thermostat inputs. Beginning System Sizing Calculations Warning ManageSizing: Calculated Heating Design Air Flow Rate for System=WEST ZONE AIR SYSTEM is zero. ~~~ Check Sizing:Zone and ZoneControl:Thermostat inputs. Warning ManageSizing: Calculated Heating Design Air Flow Rate for System=EAST ZONE AIR SYSTEM is zero. ~~~ Check Sizing:Zone and ZoneControl:Thermostat inputs. Beginning Plant Sizing Calculations Testing Individual Branch Integrity All Branches passed integrity testing Testing Individual Supply Air Path Integrity All Supply Air Paths passed integrity testing Testing Individual Return Air Path Integrity All Return Air Paths passed integrity testing No node connection errors were found. Beginning Simulation Severe CalcIndirectResearchSpecialEvapCooler: calculate secondary air mass flow failed for Indirect Evaporative Cooler Research Special = EAST DATA CENTER IEC ~~~ Environment=WHOLEYEARDAY, at Simulation time=01/01 17:42 - 17:43 ~~~ Iteration limit [1000] exceeded in calculating secondary air mass flow rate ~~~ Simulation continues Severe CalcIndirectResearchSpecialEvapCooler: calculate secondary air mass flow failed for Indirect Evaporative Cooler Research Special = WEST DATA CENTER IEC ~~~ Environment=WHOLEYEARDAY, at Simulation time=01/01 19:38 - 19:39 ~~~ Iteration limit [1000] exceeded in calculating secondary air mass flow rate ~~~ Simulation continues Warning CalcDoe2DXCoil: Coil:Cooling:DX:SingleSpeed="WEST DX COOLING COIL" - Air volume flow rate per watt of rated total cooling capacity is out of range at 1.100E-005 m3/s/W. ~~~ Environment=WHOLEYEARDAY, at Simulation time=01/01 19:38 - 19:39 ~~~ Expected range for VolumeFlowPerRatedTotalCapacity=[2.684E-005--6.713E-005] ~~~ Possible causes include inconsistent air flow rates in system components, ~~~ or variable air volume [VAV] system using incorrect coil type. Warning CalcDoe2DXCoil: Coil:Cooling:DX:SingleSpeed "WEST DX COOLING COIL" - Air-cooled condenser inlet dry-bulb temperature below 0 C. Outdoor dry-bulb temperature = -1.38 ~~~ ... Occurrence info = WHOLEYEARDAY, 01/01 19:38 - 19:39 ~~~ ... Operation at low ambient temperatures may require special performance curves. Warning CalcDoe2DXCoil: Coil:Cooling:DX:SingleSpeed "WEST DX COOLING COIL" - Full load outlet air dry-bulb temperature < 2C. This indicates the possibility of coil frost/freeze. Outlet temperature = -37.94 C. ~~~ ...Occurrence info = WHOLEYEARDAY, 01/01 19:38 - 19:39 ~~~ ... Possible reasons for low outlet air dry-bulb temperatures are: This DX coil ~~~ 1) may have a low inlet air dry-bulb temperature. Inlet air temperature = 10.263 C. ~~~ 2) may have a low air flow rate per watt of cooling capacity. Check inputs. ~~~ 3) is used as part of a HX assisted cooling coil which uses a high sensible effectiveness. Check inputs. Warning CoolingTower:VariableSpeed "COOLING TOWER" - Tower range temperature is outside model boundaries at 2.06E-002. ~~~ ...Valid range = 1.11 to 22.22. Occurrence info = WHOLEYEARDAY, 01/07 20:17 - 20:18 ~~~ ...Tower range temperature passed to the model = 2.05947E-002 ~~~ ...Range temperatures outside model boundaries may not adversely affect tower performance. ~~~ ...This is not an unexpected occurrence when simulating actual conditions. Warning CoolingTower:VariableSpeed "COOLING TOWER" - Tower approach temperature is outside model boundaries at 0.44. ~~~ ...Valid range = 1.11 to 40.00. Occurrence info = WHOLEYEARDAY, 02/23 07:48 - 07:49 ~~~ ...Tower approach temperature passed to the model = 0.43596 ~~~ ...Approach temperatures outside model boundaries may not adversely affect tower performance. ~~~ ...This is not an unexpected occurrence when simulating actual conditions. Warning CoolingTower:VariableSpeed "COOLING TOWER" - Inlet air wet-bulb temperature is outside model boundaries at 26.68. ~~~ ...Valid range = -34.40 to 26.67. Occurrence info = WHOLEYEARDAY, 07/19 16:15 - 16:16 ~~~ ...Inlet air wet-bulb temperature passed to the model = 26.666700 ~~~ ...Wet-bulb temperatures outside model boundaries may not adversely affect tower performance. Warning CoolingTower:VariableSpeed "COOLING TOWER" - Inlet air wet-bulb temperature is outside model boundaries at 26.68. ~~~ ...Valid range = -34.40 to 26.67. Occurrence info = WHOLEYEARDAY, 07/19 16:17 - 16:18 ~~~ ...Inlet air wet-bulb temperature passed to the model = 26.666700 ~~~ ...Wet-bulb temperatures outside model boundaries may not adversely affect tower performance. Warning CoolingTower:VariableSpeed "COOLING TOWER" - Inlet air wet-bulb temperature is outside model boundaries at 26.68. ~~~ ...Valid range = -34.40 to 26.67. Occurrence info = WHOLEYEARDAY, 07/19 16:18 - 16:19 ~~~ ...Inlet air wet-bulb temperature passed to the model = 26.666700 ~~~ ...Wet-bulb temperatures outside model boundaries may not adversely affect tower performance. Warning CoolingTower:VariableSpeed "COOLING TOWER" - Inlet air wet-bulb temperature is outside model boundaries at 26.68. ~~~ ...Valid range = -34.40 to 26.67. Occurrence info = WHOLEYEARDAY, 07/19 16:20 - 16:21 ~~~ ...Inlet air wet-bulb temperature passed to the model = 26.666700 ~~~ ...Wet-bulb temperatures outside model boundaries may not adversely affect tower performance. Warning CoolingTower:VariableSpeed "COOLING TOWER" - Inlet air wet-bulb temperature is outside model boundaries at 26.68. ~~~ ...Valid range = -34.40 to 26.67. Occurrence info = WHOLEYEARDAY, 07/19 16:21 - 16:22 ~~~ ...Inlet air wet-bulb temperature passed to the model = 26.666700 ~~~ ...Wet-bulb temperatures outside model boundaries may not adversely affect tower performance. Simulation Error Summary There are 1 unused schedules in input. ***** Use Output:Diagnostics,DisplayUnusedSchedules; to see them.


===== Recurring Error Summary ===== The following recurring error messages occurred.


Warning Secondary air mass flow Iteration limit exceeded in Indirect Evaporative Cooler Research Special = EAST DATA CENTER IEC ~~~ This error occurred 4 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times.


Warning Secondary air mass flow Iteration limit exceeded in Indirect Evaporative Cooler Research Special = WEST DATA CENTER IEC ~~~ This error occurred 4 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times.


Warning CalcDoe2DXCoil: Coil:Cooling:DX:SingleSpeed="WEST DX COOLING COIL" - Air volume flow rate per watt of rated total cooling capacity is out of range error continues... ~~~ This error occurred 125600 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times. ***** ~~~ Max=2.683985E-005 Min=1.081167E-005


Warning CalcDoe2DXCoil: Coil:Cooling:DX:SingleSpeed="WEST DX COOLING COIL" - Low condenser dry-bulb temperature error continues... ~~~ This error occurred 3 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times. ***** ~~~ Max=-0.15 [C] Min=-1.375 [C]


Warning CalcDoe2DXCoil: Coil:Cooling:DX:SingleSpeed="WEST DX COOLING COIL" - Full load outlet temperature indicates a possibility of frost/freeze error continues. Outlet air temperature statistics follow: ~~~ This error occurred 45192 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times. ***** ~~~ Max=1.999938 Min=-48.246852


Warning CoolingTower:VariableSpeed "COOLING TOWER" - Tower range temperature is out of range error continues... ~~~ This error occurred 18760 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times. ***** ~~~ Max=1.110626 Min=1.215599E-005


Warning CoolingTower:VariableSpeed "COOLING TOWER" - Tower approach temperature is out of range error continues... ~~~ This error occurred 135282 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times. ***** ~~~ Max=1.10822 Min=0.


Warning CoolingTower:VariableSpeed "COOLING TOWER" - Inlet air wet-bulb temperature is out of range error continues... ~~~ This error occurred 34 total times; ~~~ during Warmup 0 times; ~~~ during Sizing 0 times. ***** ~~~ Max=26.940529 Min=26.679421


EnergyPlus Warmup Error Summary. During Warmup: 0 Warning; 0 Severe Errors. EnergyPlus Sizing Error Summary. During Sizing: 4 Warning; 0 Severe Errors. ***** EnergyPlus Completed Successfully-- 324890 Warning; 2 Severe Errors; Elapsed Time=00hr 07min 54.86sec`

I am not certain if the problem is the Ubuntu update or something else.

https://wiki.ubuntu.com/BionicBeaver/ReleaseNotes/ChangeSummary/18.04.2

myndtrust commented 5 years ago

Update: Assuming that the issues was with the Ubuntu update, I deployed on GCP with a 16.04 Ubuntu VM. The problem persisted, so this is not an OS issue.

I then commented out the single weather epw (Chicago) file and un-commented the the comma separated set of weather files in the .bashrc.

Run appears to be working - but this root cause is puzzling. The IDF has Chicago noted, the README notes the San Francisco, and in practice this only works with the the set of weather files. I am doing this right?

myndtrust commented 5 years ago

Closing this issue. The solution was to un-comment the set of epw files. The run_energyplus.py script iterates over the epws file in each episode of the simulation. The epw file is copied into the respective output directory.