
Location
Badges
Activity
Challenge Categories
Challenges Entered
Detecting Energy Flexibility in Buildings
Latest submissions
See All| graded | 294152 | ||
| graded | 294148 | ||
| graded | 294103 |
Automating Building Data Classification
Latest submissions
Advanced Building Control & Grid-Resilience
Latest submissions
See All| failed | 239488 | ||
| failed | 239469 | ||
| failed | 239466 |
Audio Source Separation using AI
Latest submissions
Using AI For Buildingโs Energy Management
Latest submissions
See All| graded | 200299 | ||
| graded | 200290 | ||
| graded | 200282 |
Interactive embodied agents for Human-AI collaboration
Latest submissions
A dataset and open-ended challenge for music recommendation research
Latest submissions
Latest submissions
Latest submissions
| Participant | Rating |
|---|---|
felipe_b
|
0 |
ChunFu
|
0 |
student
|
271 |
| Participant | Rating |
|---|---|
felipe_b
|
0 |
ChunFu
|
0 |
NeurIPS 2023 Citylearn Challenge
Observations data structure and indexing
About 2 years agoGot it, very clear and this makes life easier. Thanks
Observations data structure and indexing
About 2 years agoThis is a suggestion on the observation data structure. The observations at every time step is given by as the observation of all building in one array. Would have been nice to have a list of list with each sublist holding the specific observation for a building. It could make it easier to work on individual building observation rather than getting into indexing.
Getting building level features
About 2 years agofor a given building at a given time step, i can get the electrical load using the method env.buildings[0].energy_simulation.solar_generation[env.time_step]. How can i do the same for carbon intensity from the environment since i cannot access it in the building.
Additionally, how do i get the following features for a given building Vintage, Area (ft2), Heat pump (kW), Heater (kW), DHW storage (kWh), Battery (kWh), PV (kW)
Control Track: CityLearn Challenge
Accessing carbon intensity at a given point in time
About 2 years agoI want to access the carbon intensity of a building at a given point in time the same way i do for solar generation e.g I can get solar generation using env.buildings[0].energy_simulation.solar_generation[env.time_step]. I am unable to do the same for carbon_intensity which i though would be follow the same syntax using ``env.buildings[0].energy_simulation.carbon_intensity[env.time_step]`.
My Question is how do i access carbon intensity. I want to get the true values of the carbon intensity for the next 48 steps inorder to use it for training my regression model.
NeurIPS 2022: CityLearn Challenge
Dynamic normalization inside the env
Over 3 years agoThank for the explanation @kingsley_nweye. Problem Solved
Looking for a way to map observations to the schema
Over 3 years agoI had the same issue and made a similar assumption. Here is my take.
{โmonthโ: True,
โday_typeโ: True,
โhourโ: True,
โoutdoor_dry_bulb_temperatureโ: True,
โoutdoor_dry_bulb_temperature_predicted_6hโ: True,
โoutdoor_dry_bulb_temperature_predicted_12hโ: True,
โoutdoor_dry_bulb_temperature_predicted_24hโ: True,
โoutdoor_relative_humidityโ: True,
โoutdoor_relative_humidity_predicted_6hโ: True,
โoutdoor_relative_humidity_predicted_12hโ: True,
โoutdoor_relative_humidity_predicted_24hโ: True,
โdiffuse_solar_irradianceโ: True,
โdiffuse_solar_irradiance_predicted_6hโ: True,
โdiffuse_solar_irradiance_predicted_12hโ: True,
โdiffuse_solar_irradiance_predicted_24hโ: True,
โdirect_solar_irradianceโ: True,
โdirect_solar_irradiance_predicted_6hโ: True,
โdirect_solar_irradiance_predicted_12hโ: True,
โdirect_solar_irradiance_predicted_24hโ: True,
โcarbon_intensityโ: True,
โnon_shiftable_loadโ: True,
โsolar_generationโ: True,
โelectrical_storage_socโ: True,
โnet_electricity_consumptionโ: True,
โelectricity_pricingโ: True,
โelectricity_pricing_predicted_6hโ: True,
โelectricity_pricing_predicted_12hโ: True,
โelectricity_pricing_predicted_24hโ: True}
This in order of states with value true in the schema.json file. I generated this while preparing a state_action_schema json file for MARLISA. I also donโt know if this is correct but I know the month and day_type index are. Though i know this, I would also like some clarifications/corrections/.
Dynamic normalization inside the env
Over 3 years agoThanks for pointing it out @joseph_amigo. I was having the same problem with an error " storage capacity cannot be less than zero".
Additionally i was trying to randomly sample a buildingโs observation for a given day to return the hour as is used in the ruled based agent(env.observation_space[0].sample()[2]). I noticed the hours were in float with the values were in the range [0,24]. Seems some kind of normalization took place coz the number were not just integers converted to floats but some had numbers like 1.23 etc. Same applies to day in index 1.
Iโm trying to use this random sample to train a rule based controller with charging and discharge rate optimized by an evolutionary algorithm. @kingsley_nweye could you please clarify with the normalization or how the floats can be converted to their original hour.
What iโm trying to do is start my training at a random day and not the env.reset() day. For instance in episode 1 i want to train my agent only on day 30, in episode 2, i want to train my agent only on day 55. Is it possible to achieve this in the current env, if so how @kingsley_nweye. I understand i can train for day 1 after the env is reset.
Notebooks
-
MARLISA 2022: Adopting MARLISA for CityLearn2022 Adopting MARLISA for CityLearn2022. A GuideBook and a BaselineChemagoยท Over 3 years ago -
CityLearn-2-EvolveCity: A Swarm and Evolutionary Approach Getting Started with Genetic Algorithm and Particle Swarm Optimization for CityLearnChemagoยท Over 3 years ago
Getting building level features
About 2 years agoGot it thnks.
A followup question.
Given that these features are not in observations, if they are used for training, can they be used during online evaluation (asking because the function compute_forecast only takes observations as input and the environment is not accessible to the ExamplePredictor class).