Getting building level features

Got 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).

View post 1

Observations data structure and indexing

Got it, very clear and this makes life easier. Thanks

View post 0

Observations data structure and indexing

This 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.

View post 0

Getting building level features

for 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)

View post 0

Accessing carbon intensity at a given point in time

I 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.

View post 0

Evaluation phase failing

Got it, Thnks @mohanty

View post 0

Evaluation phase failing

I had the same error @nicolas_cuadrado

View post 0

Dynamic normalization inside the env

Thank for the explanation @kingsley_nweye. Problem Solved

View post 1

Looking for a way to map observations to the schema

I had the same issue and made a similar assumption. Here is my take.

{‘month’: True,
‘day_type’: True,
‘hour’: True,
‘outdoor_dry_bulb_temperature’: True,
‘outdoor_dry_bulb_temperature_predicted_6h’: True,
‘outdoor_dry_bulb_temperature_predicted_12h’: True,
‘outdoor_dry_bulb_temperature_predicted_24h’: True,
‘outdoor_relative_humidity’: True,
‘outdoor_relative_humidity_predicted_6h’: True,
‘outdoor_relative_humidity_predicted_12h’: True,
‘outdoor_relative_humidity_predicted_24h’: True,
‘diffuse_solar_irradiance’: True,
‘diffuse_solar_irradiance_predicted_6h’: True,
‘diffuse_solar_irradiance_predicted_12h’: True,
‘diffuse_solar_irradiance_predicted_24h’: True,
‘direct_solar_irradiance’: True,
‘direct_solar_irradiance_predicted_6h’: True,
‘direct_solar_irradiance_predicted_12h’: True,
‘direct_solar_irradiance_predicted_24h’: True,
‘carbon_intensity’: True,
‘non_shiftable_load’: True,
‘solar_generation’: True,
‘electrical_storage_soc’: True,
‘net_electricity_consumption’: True,
‘electricity_pricing’: True,
‘electricity_pricing_predicted_6h’: True,
‘electricity_pricing_predicted_12h’: True,
‘electricity_pricing_predicted_24h’: 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 don’t 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/.

View post 0

Dynamic normalization inside the env

Thanks 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 building’s 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.

I’m 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 i’m 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.

View post 0