pymgrid.modules.GridModule

class pymgrid.modules.GridModule(max_import, max_export, time_series, forecaster=None, forecast_horizon=23, forecaster_increase_uncertainty=False, forecaster_relative_noise=False, initial_step=0, final_step=-1, cost_per_unit_co2=0.0, normalized_action_bounds=(0, 1), raise_errors=False)

An electrical grid module.

By default, GridModule is a fixed module; it can be transformed to a flex module with GridModule.as_flex. GridModule is the only built-in module that can be both a fixed and flex module.

Parameters

max_importfloat

Maximum import at any time step.

max_exportfloat

Maximum export at any time step.

time_seriesarray-like, shape (n_features, n_steps), n_features = {3, 4}

If n_features=3, time series of (import_price, export_price, co2_per_kwH) in each column, respectively. Grid is assumed to have no outages. If n_features=4, time series of (import_price, export_price, co2_per_kwH, grid_status) in each column, respectively. time_series[:, -1] – the grid status – must be binary.

forecastercallable, float, “oracle”, None, default None.

Function that gives a forecast n-steps ahead.

• If callable, must take as arguments (val_c: float, val_{c+n}: float, n: int), where

  • val_c is the current value in the time series: self.time_series[self.current_step]

  • val_{c+n} is the value in the time series n steps in the future

  • n is the number of steps in the future at which we are forecasting.

  The output forecast = forecaster(val_c, val_{c+n}, n) must have the same sign as the inputs val_c and val_{c+n}.

• If float, serves as a standard deviation for a mean-zero gaussian noise function that is added to the true value.

• If "oracle", gives a perfect forecast.

• If None, no forecast.

forecast_horizonint.

Number of steps in the future to forecast. If forecaster is None, ignored and 0 is returned.

forecaster_increase_uncertaintybool, default False

Whether to increase uncertainty for farther-out dates if using a GaussianNoiseForecaster. Ignored otherwise.

cost_per_unit_co2float, default 0.0

Marginal cost of grid co2 production.

normalized_action_boundstuple of int or float, default (0, 1).

Bounds of normalized actions. Change to (-1, 1) for e.g. an RL policy with a Tanh output activation.

raise_errorsbool, default False

Whether to raise errors if bounds are exceeded in an action. If False, actions are clipped to the limit possible.

Methods

as_fixed()	Convert the module to a fixed module.
as_flex()	Convert the module to a flex module.
as_sink(energy_excess)	Act as an energy sink to the microgrid.
as_source(energy_demand)	Act as an energy source to the microgrid.
dump([stream])	Save a module to a YAML buffer.
dynamic_action_space()	An action space bounded by the current step's maximum consumption and production.
forecast()	Forecast the module's time series from the current state.
from_normalized(value[, act, obs])	Un-normalize an action or observation.
get_co2_cost(import_export, as_source, as_sink)	Current cost of the carbon dioxide production of the grid's usage.
get_co2_production(import_export, as_source, ...)	Current carbon dioxide production of the grid's usage.
get_cost(import_export, as_source, as_sink)	Current cost of the grid's usage.
load(stream)	Load a module from yaml representation.
log_dict()	Module's log as a dict.
log_frame()	Module's log as a DataFrame.
reset()	Reset the module to step zero and flush the log.
sample_action([strict_bound])	Sample an action from the module's action space.
serializable_state_attributes()	Return the attributes of the module that represent the module's current state for serialization.
serialize(dumper_stream)	Serialize module.
set_forecaster(forecaster[, ...])	Set the forecaster for this module.
state_dict([normalized])	Current state of the module as a dictionary.
step(action[, normalized])	Take one step in the module, attempting to draw or send action amount of energy.
to_normalized(value[, act, obs])	Normalize an action or observation.
update(external_energy_change[, as_source, ...])	Update the state of the module given an energy request.
verbose_eq(other[, indent])

Attributes

absorption_marginal_cost	Expected marginal cost of energy absorption.
action_space	Action spaces of the module.
co2_per_kwh	Current and forecasted carbon dioxide production per kWh.
current_obs	Current observation.
current_status	Current status of the grid.
current_step	Current step of the module.
export_price	Current and forecasted export prices.
final_step
forecast_horizon	The number of steps until which the module forecasts.
forecaster	View of the forecaster.
forecaster_increase_uncertainty	View of GaussianNoiseForecaster.increase_uncertainty.
forecaster_relative_noise	View of GaussianNoiseForecaster.relative_noise.
grid_status	Current and forecasted grid status.
import_price	Current and forecasted import prices.
is_sink	Whether the module is a sink.
is_source	Whether the module is a source.
log	Module's log as a DataFrame.
logger	The module's logger.
logger_last	The most recent entry in the log.
marginal_cost	Average marginal cost of producing with the module.
max_act	Maximum action that the module allows.
max_consumption	Maximum amount of consumption at the current time step.
max_obs	Maximum observation that the module gives.
max_production	Maximum amount of production at the current time step.
min_act	Minimum action that the module allows.
min_obs	Minimum observation that the module gives.
min_production	Minimum amount of production at the current time step.
module_type	Type of the module.
observation_space	Observation space of the module.
production_marginal_cost	Expected marginal cost of energy production.
state	Current state of the module as a vector.
state_components	Labels of the components of each entry in the module's time series.
time_series	View of the module's time series.
weak_grid	Whether the grid has outages or not.
yaml_tag	Tag used for yaml serialization.