Issue155 v070

.github/workflows/github-actions.yml

@@ -16,8 +16,6 @@ jobs:
         uses: actions/checkout@v3
       - name: Pull boptestgym image from registry
         run: make pull-boptestgym
-      - name: Pull boptest_base image from registry
-        run: make pull-boptestbase
       - name: Install Docker Compose
         run: |
           sudo apt-get update

README.md

@@ -1,7 +1,9 @@
-# BOPTEST-Gym
+# BOPTEST-Gym-service
 
 BOPTESTS-Gym is the [OpenAI-Gym](https://gym.openai.com/) environment for the [BOPTEST](https://github.com/ibpsa/project1-boptest) framework. This repository accommodates the BOPTEST API to the OpenAI-Gym convention in order to facilitate the implementation, assessment and benchmarking of reinforcement learning (RL) algorithms for their application in building energy management. RL algorithms from the [Stable-Baselines 3](https://github.com/DLR-RM/stable-baselines3) repository are used to exemplify and test this framework. 
 
+This is the service version of BOPTEST-Gym, meaning that it has been adapted to use BOPTEST test cases that can be run in a server instead of just locally. 
+
 The environment is described in [this paper](https://www.researchgate.net/publication/354386346_An_OpenAI-Gym_environment_for_the_Building_Optimization_Testing_BOPTEST_framework). 
 
 ## Structure
@@ -73,7 +75,7 @@ Running BOPTEST locally is substantially faster
 
 1) Create a conda environment from the `environment.yml` file provided (instructions [here](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html#creating-an-environment-from-an-environment-yml-file)). 
 2) Run a BOPTEST case with the building emulator model to be controlled (instructions [here](https://github.com/ibpsa/project1-boptest/blob/master/README.md)).  
-3) Check out the `master` branch of this repository and run the example above replacing the url to be `url = 'http://127.0.0.1:5000'` and avoiding the `testcase` argument to the `BoptestGymEnv` class. 
+3) Check out the `master` branch of this repository and run the example above replacing the url to be `url = 'http://127.0.0.1:80'` and avoiding the `testcase` argument to the `BoptestGymEnv` class. 
 
 ## Quick-Start (running BOPTEST locally in a vectorized environment)
 

boptestGymEnv.py

@@ -36,7 +36,8 @@ class BoptestGymEnv(gym.Env):
     metadata = {'render.modes': ['console']}
 
     def __init__(self, 
-                 url                = 'http://127.0.0.1:5000',
+                 url                = 'http://127.0.0.1',
+                 testcase           = 'bestest_hydronic_heat_pump',
                  actions            = ['oveHeaPumY_u'],
                  observations       = {'reaTZon_y':(280.,310.)}, 
                  reward             = ['reward'],
@@ -56,6 +57,8 @@ def __init__(self,
         ----------
         url: string
             Rest API url for communication with the BOPTEST interface
+        testcase: string
+            The string identifier of the testcase
         actions: list
             List of strings indicating the action space. The bounds of 
             each variable from the action space the are retrieved from 
@@ -134,6 +137,7 @@ def __init__(self,
         super(BoptestGymEnv, self).__init__()
 
         self.url                = url
+        self.testcase           = testcase
         self.actions            = actions
         self.observations       = list(observations.keys())
         self.max_episode_length = max_episode_length
@@ -160,18 +164,26 @@ def __init__(self,
         #=============================================================
         # Get test information
         #=============================================================
+        # Get testid for the particular testcase
+        # Check if already started a test case and stop it if so before starting another
+        try:
+            requests.put('{0}/stop/{1}'.format(url, self.testid))
+        except:
+            pass
+        # Select and start a new test case
+        self.testid = requests.post('{0}/testcases/{1}/select'.format(url, testcase)).json()['testid']
         # Test case name
-        self.name = requests.get('{0}/name'.format(url)).json()['payload']
+        self.name = requests.get('{0}/name/{1}'.format(url, self.testid)).json()['payload']
         # Measurements available
-        self.all_measurement_vars = requests.get('{0}/measurements'.format(url)).json()['payload']
+        self.all_measurement_vars = requests.get('{0}/measurements/{1}'.format(url, self.testid)).json()['payload']
         # Predictive variables available
-        self.all_predictive_vars = requests.get('{0}/forecast_points'.format(url)).json()['payload']
+        self.all_predictive_vars = requests.get('{0}/forecast_points/{1}'.format(url, self.testid)).json()['payload']
         # Inputs available
-        self.all_input_vars = requests.get('{0}/inputs'.format(url)).json()['payload']
+        self.all_input_vars = requests.get('{0}/inputs/{1}'.format(url, self.testid)).json()['payload']
         # Default simulation step
-        self.step_def = requests.get('{0}/step'.format(url)).json()['payload']
+        self.step_def = requests.get('{0}/step/{1}'.format(url, self.testid)).json()['payload']
         # Default scenario
-        self.scenario_def = requests.get('{0}/scenario'.format(url)).json()['payload']
+        self.scenario_def = requests.get('{0}/scenario/{1}'.format(url, self.testid)).json()['payload']
 
         #=============================================================
         # Define observation space
@@ -470,15 +482,15 @@ def find_start_time():
             self.start_time = find_start_time()
 
         # Initialize the building simulation
-        res = requests.put('{0}/initialize'.format(self.url), 
+        res = requests.put('{0}/initialize/{1}'.format(self.url,self.testid),
                            json={'start_time':int(self.start_time),
                                  'warmup_period':int(self.warmup_period)}).json()['payload']
 
         # Set simulation step
-        requests.put('{0}/step'.format(self.url), json={'step':int(self.step_period)})
+        requests.put('{0}/step/{1}'.format(self.url,self.testid), json={'step':int(self.step_period)})
 
         # Set BOPTEST scenario
-        requests.put('{0}/scenario'.format(self.url), json=self.scenario)
+        requests.put('{0}/scenario/{1}'.format(self.url,self.testid), json=self.scenario)
 
         # Initialize objective integrand
         self.objective_integrand = 0.
@@ -493,6 +505,22 @@ def find_start_time():
 
         return observations, info
 
+    def stop(self):
+        '''
+        Stop the test case
+
+        '''
+
+        requests.put('{0}/stop/{1}'.format(self.url, self.testid))
+
+    def stop(self):
+        '''
+        Stop the test case
+
+        '''
+
+        requests.put('{0}/stop/{1}'.format(self.url, self.testid))
+
     def step(self, action):
         '''
         Advance the simulation one time step
@@ -543,7 +571,7 @@ def step(self, action):
             u[act.replace('_u','_activate')] = float(1)
 
         # Advance a BOPTEST simulation
-        res = requests.post('{0}/advance'.format(self.url), json=u).json()['payload']
+        res = requests.post('{0}/advance/{1}'.format(self.url,self.testid), json=u).json()['payload']
 
         # Compute reward of this (state-action-state') tuple
         reward = self.get_reward()
@@ -618,7 +646,7 @@ def get_reward(self):
         w = 1
 
         # Compute BOPTEST core kpis
-        kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+        kpis = requests.get('{0}/kpi/{1}'.format(self.url,self.testid)).json()['payload']
 
         # Calculate objective integrand function at this point
         objective_integrand = kpis['cost_tot'] + w*kpis['tdis_tot']
@@ -716,7 +744,7 @@ def get_observations(self, res):
         if self.is_regressive:
             regr_index = res['time']-self.step_period*np.arange(1,self.regr_n+1)
             for var in self.regressive_vars:
-                res_var = requests.put('{0}/results'.format(self.url), 
+                res_var = requests.put('{0}/results/{1}'.format(self.url, self.testid), 
                                        json={'point_names':[var],
                                              'start_time':int(regr_index[-1]), 
                                              'final_time':int(regr_index[0])}).json()['payload']
@@ -732,7 +760,7 @@ def get_observations(self, res):
 
         # Get predictions if this is a predictive agent. 
         if self.is_predictive:
-            predictions = requests.put('{0}/forecast'.format(self.url), 
+            predictions = requests.put('{0}/forecast/{1}'.format(self.url, self.testid), 
                                        json={'point_names': self.predictive_vars,
                                              'horizon':     int(self.predictive_period),
                                              'interval':    int(self.step_period)}).json()['payload']
@@ -753,7 +781,7 @@ def get_kpis(self):
         '''
 
         # Compute BOPTEST core kpis
-        kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+        kpis = requests.get('{0}/kpi/{1}'.format(self.url, self.testid)).json()['payload']
 
         return kpis
 
@@ -1246,7 +1274,7 @@ def get_reward(self):
         '''
 
         # Compute BOPTEST core kpis
-        kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+        kpis = requests.get('{0}/kpi/{1}'.format(self.url, self.testid)).json()['payload']
 
         # Calculate objective integrand function at this point
         objective_integrand = kpis['cost_tot'] + kpis['tdis_tot']
@@ -1283,7 +1311,7 @@ def get_reward(self):
         w = 0.1
 
         # Compute BOPTEST core kpis
-        kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+        kpis = requests.get('{0}/kpi/{1}'.format(self.url, self.testid)).json()['payload']
 
         # Calculate objective integrand function at this point
         objective_integrand = kpis['cost_tot'] + w*kpis['tdis_tot']
@@ -1317,7 +1345,7 @@ def get_reward(self):
         w = 10
 
         # Compute BOPTEST core kpis
-        kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+        kpis = requests.get('{0}/kpi/{1}'.format(self.url, self.testid)).json()['payload']
 
         # Calculate objective integrand function at this point
         objective_integrand = kpis['cost_tot'] + w*kpis['tdis_tot']

docs/tutorials/CCAI_Summer_School_2022/Building_Control_with_RL_using_BOPTEST.ipynb

@@ -42,7 +42,7 @@
         "\n",
         "📌 **Note**: This tutorial is prepared for use with BOPTEST v0.6.0.\n",
         "and uses a web-based version of BOPTEST (called \"BOPTEST-Service\") as not to require installation of any BOPTEST software on a user's own device. It is also possible to use BOPTEST on a user's own (local) device. \n",
-        "Both the web-based and local versions have the same functionality, and will produce the same results, with only small changes in the API (changing the BOPTEST-service url to your localhost url, that is, to: `http://127.0.0.1:5000/<request>`). The tutorial is continuously updated to work with the latest BOPTEST versions. See [the release notes](https://github.com/ibpsa/project1-boptest-gym/blob/master/releasenotes.md) for the version history.\n",
+        "Both the web-based and local versions have the same functionality, and will produce the same results, with only small changes in the API (changing the BOPTEST-service url to your localhost url, that is, to: `http://127.0.0.1:80/<request>`). The tutorial is continuously updated to work with the latest BOPTEST versions. See [the release notes](https://github.com/ibpsa/project1-boptest-gym/blob/master/releasenotes.md) for the version history.\n",
         "\n",
         "🎥 **Video**: An explanatory video of this tutorial can be seen [here](https://drive.google.com/file/d/1lvCVQef_kctwCagA5QOVj7QljHQ1xKUQ/view?usp=sharing) for the CCAI2022 Summer School on August 18, 2022. The video starts with a one-hour lecture on the application of machine learning in buildings. The part of BOPTEST-Gym follows right after and lasts for 1.5 hours. Please note that the software version used in the video is v0.2.0. The framework and tutorial have been updated since then so you may notice slight differences in the content and interface. However, the main concepts and explanation behind remains the same. \n"
       ]

examples/run_baseline.py

@@ -11,7 +11,7 @@
 from boptestGymEnv import BoptestGymEnv, NormalizedObservationWrapper, NormalizedActionWrapper
 from examples.test_and_plot import test_agent
 
-url = 'http://127.0.0.1:5000'
+url = 'http://127.0.0.1'
 
 # Seed for random starting times of episodes
 random.seed(123456)
@@ -77,7 +77,7 @@ def get_reward(self):
             w = 0.1
 
             # Compute BOPTEST core kpis
-            kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+            kpis = requests.get('{0}/kpi/{1}'.format(self.url, self.testid)).json()['payload']
 
             # Calculate objective integrand function at this point
             objective_integrand = kpis['cost_tot']*12.*16. + w*kpis['tdis_tot']
@@ -125,7 +125,7 @@ def get_reward(self):
             '''
 
             # Compute BOPTEST core kpis
-            kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+            kpis = requests.get('{0}/kpi/{1}'.format(self.url, self.testid)).json()['payload']
 
             # Calculate objective integrand function at this point
             objective_integrand = kpis['cost_tot']*12.*16. + kpis['tdis_tot']
@@ -249,7 +249,10 @@ def run(envClass, wrapper=None, scenario={'electricity_price':'constant'},
                          episode_length=episode_length_test,
                          warmup_period=warmup_period_test,
                          plot=plot)
-
+
+    # stop the test
+    env.stop()
+
     return observations, actions, rewards
 
 class BaselineModel(object):

examples/run_sample.py

@@ -10,7 +10,7 @@
 from examples.test_and_plot import test_agent
 import random
 
-url = 'http://127.0.0.1:5000'
+url = 'http://127.0.0.1'
 
 # Seed for random starting times of episodes
 random.seed(123456)
@@ -68,6 +68,9 @@ def run(envClass, wrapper=None, plot=False):
                          episode_length=episode_length_test,
                          warmup_period=warmup_period_test,
                          plot=plot)
+
+    # stop the test
+    env.stop()
 
     return observations, actions, rewards
 

examples/run_save_callback.py

@@ -14,7 +14,7 @@
 import random
 import os
 
-url = 'http://127.0.0.1:5000'
+url = 'http://127.0.0.1'
 seed = 123456
 
 # Seed for random starting times of episodes

examples/run_variable_episode.py

@@ -14,7 +14,7 @@
 import random
 import os
 
-url = 'http://127.0.0.1:5000'
+url = 'http://127.0.0.1'
 seed = 123456
 
 # Seed for random starting times of episodes

examples/test_and_plot.py

@@ -81,7 +81,7 @@ def plot_results(env, rewards, points=['reaTZon_y','reaTSetHea_y','reaTSetCoo_y'
     # We use env.start_time+1 to ensure that we don't return the last 
     # point from the initialization period to don't confuse it with 
     # actions taken by the agent in a previous episode. 
-    res = requests.put('{0}/results'.format(env.url), 
+    res = requests.put('{0}/results/{1}'.format(env.url, env.testid), 
                         json={'point_names':points,
                               'start_time':env.start_time+1, 
                               'final_time':3.1536e7}).json()['payload']
@@ -200,4 +200,4 @@ def create_datetime_index(df):
 
     return df
 
-
+

examples/train_RL.py

@@ -22,7 +22,7 @@
 import random
 import os
 
-url = 'http://127.0.0.1:5000'
+url = 'http://127.0.0.1'
 seed = 123456
 
 # Seed for random starting times of episodes
@@ -93,7 +93,7 @@ def get_reward(self):
             '''
 
             # Compute BOPTEST core kpis
-            kpis = requests.get('{0}/kpi'.format(self.url)).json()['payload']
+            kpis = requests.get('{0}/kpi/{1}'.format(self.url, self.testid)).json()['payload']
 
             # Calculate objective integrand function at this point
             objective_integrand = kpis['cost_tot']*12.*16. + 100*kpis['tdis_tot']
@@ -108,6 +108,7 @@ def get_reward(self):
     if case == 'simple':
         env = BoptestGymEnvCustomReward(
                             url                   = url,
+                            testcase              = 'bestest_hydronic_heat_pump',
                             actions               = ['oveHeaPumY_u'],
                             observations          = OrderedDict([('reaTZon_y',(280.,310.))]), 
                             random_start_time     = True,
@@ -120,6 +121,7 @@ def get_reward(self):
     elif case == 'A':
         env = BoptestGymEnvCustomReward(
                             url                   = url,
+                            testcase              ='bestest_hydronic_heat_pump',
                             actions               = ['oveHeaPumY_u'],
                             observations          = OrderedDict([('time',(0,604800)),
                                                      ('reaTZon_y',(280.,310.)),
@@ -136,6 +138,7 @@ def get_reward(self):
     if case == 'B':
         env = BoptestGymEnvCustomReward(
                             url                   = url,
+                            testcase              ='bestest_hydronic_heat_pump',
                             actions               = ['oveHeaPumY_u'],
                             observations          = OrderedDict([('time',(0,604800)),
                                                      ('reaTZon_y',(280.,310.)),
@@ -154,6 +157,7 @@ def get_reward(self):
     if case == 'C':
         env = BoptestGymEnvCustomReward(
                             url                   = url,
+                            testcase              ='bestest_hydronic_heat_pump',
                             actions               = ['oveHeaPumY_u'],
                             observations          = OrderedDict([('time',(0,604800)),
                                                      ('reaTZon_y',(280.,310.)),
@@ -173,6 +177,7 @@ def get_reward(self):
     if case == 'D':
         env = BoptestGymEnvCustomReward(
                             url                   = url,
+                            testcase              ='bestest_hydronic_heat_pump',
                             actions               = ['oveHeaPumY_u'],
                             observations          = OrderedDict([('time',(0,604800)),
                                                      ('reaTZon_y',(280.,310.)),

generateDockerComposeYml.py

@@ -16,7 +16,7 @@
     yaml_target_dir = os.path.dirname(os.path.abspath(__file__))
 
 num_services = 2  # Total Services needed
-base_port = 5000  # Start Port number
+base_port = 80  # Start Port number
 
 
 # Function to check if a port is available
@@ -53,7 +53,7 @@ def is_port_available(port):
             "./forecast:${APP_PATH}/forecast/",
             "./kpis:${APP_PATH}/kpis/",
         ],
-        "ports": [f"127.0.0.1:{port}:5000"],
+        "ports": [f"127.0.0.1:{port}:80"],
         "networks": ["boptest-net"],
         "restart": "on-failure"  # restart on-failure
     }

testing/Dockerfile

@@ -1,7 +1,7 @@
 # Start with a base Ubuntu image
 FROM --platform=linux/x86_64 ubuntu:20.04
 # This is the Focal Fossa ubuntu version
-MAINTAINER Javier Arroyo <javier.arroyo@kuleuven.be>
+MAINTAINER Javier Arroyo <javier.arroyo@wedoco.io>
 
 # Avoid warnings while installing ubuntu
 # debconf: unable to initialize frontend: Dialog