It is recommended to have a look at the 00_Introduction, 00_SmallExample and 02_Observation notebooks before this one.
Objectives
This notebook covers the basics of how to efficienty modify the powergrid by using the Action class. Indeed, there are multiple concepts behind this class that may not be very clear at first glance.
This notebook focuses on the manipulation of Actions from an expert system point of view in order to demonstrate how a desired action is fundamentally taken in the Grid2Op environment. We will give a more detailed example later which will focus on a more automatic way to handle actions (for example using machine learning, in the notebook 04_TrainingAnAgent).
Cell will look like:
!pip install grid2op[optional] # for use with google colab (grid2Op is not installed by default)
# !pip install grid2op[optional] # for use with google colab (grid2Op is not installed by default)
import numpy as np
import grid2op
from grid2op.Action import PlayableAction
res = None
try:
from jyquickhelper import add_notebook_menu
res = add_notebook_menu()
except ModuleNotFoundError:
print("Impossible to automatically add a menu / table of content to this notebook.\nYou can download \"jyquickhelper\" package with: \n\"pip install jyquickhelper\"")
res
To modify a powergrid, we introduce two distinct (yet close) concepts that will affect the objects differently:
This is different to the previous pypownet implementation, where only the change
concept was implemented. The option of having these two types of modifying the powergrid supports our understanding of the system and the intention of the Agent, especially in the debugging phase.
Of course, it is perfectly possible to use only the change
capability and thus being closer to the original implementation.
The following is specific example to highlight the differences between these two type of methods to modify the powergrid. Suppose we have a substation with 5 elements:
Let's also assume the original configuration (before the action is applied, ie the configuration of the observation at time t) is:
Object Name | Original Bus | Original Status |
---|---|---|
$l_1$ (origin) | 1 | connected |
$l_2$ (extremity) | 2 | connected |
$l_3$ (extremity) | NA | disconnected |
$c_1$ | 1 | NA |
$g_1 $ | 2 | NA |
Let's say:
* NB Another breaking change compared to the pypownet implementation is the introduction of "ambiguous" actions. When an action can be understood in different ways or have different meanings, then it will be replaced by a "do nothing" action by the environment.
In this situation, the previous actions are equivalent to:
When some actions are "ambiguous" it means that they cannot be properly and / or univocally interpreted. These actions will be ignored if attempted to be used on the powergrid. This will be equivalent to doing nothing.
For a detailed list of ambiguous actions, the documentation is the only official source. Only some examples are presented here. The documentation is available at _check_for_ambiguity.
An action can be ambiguous in the following cases:
It affects the "injections" in an incorrect way:
It affects the "powerlines" in an incorrect manner:
It has an ambiguous behaviour concerning the topology of some substations
IMPORTANT NOTICE Each Agent has its own action space
attribute that can be accessed with self.action_space
. This is the only recommended way to create a valid Action. It is strongly recommend to NOT using its constructor, as it requires a deep knowledge of all the elements in the powergrid, as well as their names, their type, the order in which they are used in the backend, etc. For performance reasons, no sanity check are performed to make sure the action (that would be created) is compatible with the backend.
In the next cell, we retrieve the action space used by the Agent.
Two main classes are useful when dealing with Actions in Grid2Op. The Action class is the most basic one. The ActionHelper is a tool that helps create and manipulate some actions in most of our notebooks, we start by creating an Environment. We will use the case14_fromfile
provided as an example.
We will then extract the complete action space (action_space
, that is, the actions that can be performed on the power grid) as a dictionary. When a specific action such as change or set is needed to be performed then we can apply this change to the action_space dictionary by accessing it with the relevant key as discussed below.
# create an environment, and use its action space
env = grid2op.make("educ_case14_storage", test=True, action_class=PlayableAction)
action_space = env.action_space
As opposed to the previous plateform, pypownet, there are no restrictions on actions in Grid2Op. Generally speaking, an Action can modify production, loads, topology, etc. By default though, an Action that an Agent can perform is a TopologyAction, which is a specific type of action. A TopologyAction can :
We will focus on this class in this notebook.
Then best way to get an action is to give a dictionnary
to the "action space" of the player. For example, to get the "do nothing" action, you can just pass the empty dictionnary.
do_nothing = action_space({})
As explained actions can be done in multiple ways. And signifcant more detail can be found in the documentation https://grid2op.readthedocs.io/en/latest/action.html#usage-examples .
Since grid2op version 1.5.0 we recommend to use the "property" way that tries to unify the way to perform every type of actions.
Basically, this always behaves like:
action = env.action_space()
action.property_name = property_description
For example, you can perform a "set_bus" action corresponding to "moving the load with id 1 and set it on bus 2":
load_id = 1
new_bus = 2
action0 = env.action_space()
action1.load_set_bus = [(load_id, new_bus)]
Another example, you can perform the action "change status" which "changes the status of powerlines id 5 and 7":
line_ids = [5, 7]
action1 = env.action_space()
action1.line_change_status = [5, 7]
In order to check that the action implemented is the one you want to implement, you can always "print" the action:
print(action0)
print(action1)
If you want to change (or set) the status of most of the powerlines, you can create a vector having the same size as the number of powerlines in the grid, and pass it to the dictionary with the relevant keys ("set_line_status", "change_line_status") and the proper values (a vector of booleans to set line status, or a vector of integers to change line status). An example is given below. Note that this example only modifies the status of a few powerlines, but this way of defining actions is more adapted when you need to modify the status of many powerlines.
The following code will:
line_id_to_change = [0,1,2]
change_status = action_space()
change_status.line_change_status = line_id_to_change
print("The action `change_status` is ")
print(change_status)
print()
line_id_to_set = [3, 4, 5, 6]
new_status = [1, 1, -1, -1]
set_status = action_space()
set_status.line_set_status = [[l_id, status] for l_id, status in zip(line_id_to_set, new_status)]
print("The action `set_status` is ")
print(set_status)
print()
both_action = change_status + set_status
print("When i combine them its")
print(both_action)
You have the option to do that "all at once" if you use the description of an action as a dictionary:
both_action = action_space({"set_line_status": [[l_id, status] for l_id, status in \
zip(line_id_to_set, new_status)],
"change_line_status": line_id_to_change
})
print("both_action is:")
print(both_action)
One of the interesting aspects of Grid2Op
is the ability to modify the topology of the powergrid. In other words, it allows to reconfigure the way the objects (generators, loads, side of powerlines) are interconnected at their substations. Comparable to the status change, topological change can be interpreted in two disctinct manners, as described above. Topologycal changes include some of the most interesting interactions with the environment. In this section we study how to modify the topology of the powergrid.
In principle, there are two equivalent ways to modify the topology, however, we do not recommend to use both, as it will introduce redundancies (the same thing can be done in two manner, which might badly intearct with each other):
Both are more or less equivalent. Basically, if you imagine in grid2op you have to "press switches", then:
The basic ideas to modify the topology is:
change_buses = action_space({"change_bus": [3, 4]})
# equivalently:
# change_buses = action_space()
# change_buses.change_bus = [3, 4]
print(change_buses)
set_buses = action_space({"set_bus": [(3, 2), (4, 1)]})
# equivalently:
# set_buses = action_space()
# set_buses.set_bus = [(3, 2), (4, 2)]
print(set_buses)
NB: in the above code, it's not explicit that the "element with id 3" is "line 0, extremity side" and the "element with id 4 is "line 2, origin side".
This information can be retrieved either using the action_space.load_pos_topo_vect
, action_space.gen_pos_topo_vect
, action_space.line_or_pos_topo_vect
, action_space.line_ex_pos_topo_vect
or action_space.storage_pos_topo_vect
vectors.
For example you can see that action_space.line_ex_pos_topo_vect[0] = 3
so this means that... the "line extremity 0 (extremity side of powerline 0) is encoded as the element 3" and action_space.line_or_pos_topo_vect[2] = 4
meaning that "the line origin 2 (origin side of powerline 2) is encoded as the element 4".
Alternatively, this information can also be retrieved using the action_space.grid_objects_types
matrix and looking at the rows 3
and 4
(because we are interested in element 3 and 4 in this example) and this gives:
action_space.grid_objects_types[[3,4],:]
This matrix can be understood as the following:
0
and env.n_sub-1
)-1
if the object is not a load, otherwise the load id if this is a loadIf you want to modify the "load 5" you can of course do:
set_buses = action_space({"set_bus": [(action_space.load_pos_topo_vect[5], 2)]})
But it's not really convenient (and very verbose...). To do exactly the same, you can:
set_load_5_bus = action_space({"set_bus": {"loads_id": [(5, 2)]}})
# equivalently:
# set_load_5_bus = action_space()
# set_load_5_bus.load_set_bus = [(5, 2)]
print(set_load_5_bus)
NB likewise, you can do that for the "change" way to modify the grid with:
change_buses = action_space({"change_bus": [action_space.load_to_pos_topo_vect[5]]})
Sometimes it can also be interesting to look explicitly at the substation level, and to explicitly say we want to modify this substation and not anything else. This is also an option with grid2op.
To that end, you need to:
sub_id = 1
topo_sub1 = np.zeros(action_space.sub_info[sub_id], dtype=int)
topo_sub1[action_space.line_or_to_sub_pos[2]] = 2 # "line 2 (origin side)"
topo_sub1[action_space.line_ex_to_sub_pos[0]] = 2 # "line 0 (extremity side)"
modify_sub_1 = action_space({"set_bus": {"substations_id": [(sub_id, topo_sub1)]}})
# equivalently:
# modify_sub_1 = action_space()
# modify_sub_1.sub_set_bus = [(sub_id, topo_sub1)]
print(modify_sub_1)
NB likewise, you can do that for the "change" way to modify the grid with:
change_buses_sub_1 = action_space({"set_bus": {"substations_id":
[action_space.line_or_to_sub_pos[2],
action_space.line_ex_to_sub_pos[0]]
}
}
)
Redispatching is explained in depth in its own notebook, see 06_Redispatching_Curtailment. We provide here a brief introduction to perform these types of continuous action.
In summary, redispatching aims at asking generators to change their production setpoint.
For further details, the documentation explains in detail how the generators behave here https://grid2op.readthedocs.io/en/latest/modeled_elements.html#generators)
It can be done with:
gen_id = 0 # on which generator to apply this action
amount = 3.14159262359 # how do you want to modify the generator
redisp_act = action_space({"redispatch": [(gen_id, amount)]})
print(redisp_act)
Alternatively, you can use the "property" method to do it, which would be, in this case:
redisp_act2 = action_space()
redisp_act2.redispatch = [(gen_id, amount)]
print(redisp_act)
As the "redispatching, the detailed behaviour of the curtailment is explained in depth in its own notebook, see 06_Redispatching_Curtailment. We only provide here a brief introduction on how to perform these types of continuous action.
In summary, curtailment aims at limiting the production of renewable generator. For example, if there is too much wind in a certain area, you can ask windmill to decrease their production in order to keep the grid safe.
For further details, the documentation explains in detail how the generators behave here https://grid2op.readthedocs.io/en/latest/modeled_elements.html#generators)
NB By default, curtailment are given in ratio of pmax. You can also do it in MW if you prefer by adding the _mw (see example below)
It can be done with:
gen_id = 1 # on which generator to apply this action
ratio_curtailment = 0.15 # this is a ratio, between 0.0 and 1.0
# if not in range [0, 1.0] an "ambiguous action" will be raised when calling "env.step"
curtail_act = action_space({"curtail": [(gen_id, ratio_curtailment)]})
print(curtail_act)
Alternatively, you can use the "property" method to do it, which would be, in this case:
curtail_act2 = action_space()
curtail_act2.curtail = [(gen_id, ratio_curtailment)]
print(curtail_act2)
Or you can also do it in MW:
amount_mw = 15 # this should be between 0. and gen_pmax[gen_id], otherwise
curtail_act2_mw = action_space()
curtail_act2_mw.curtail_mw = [(gen_id, amount_mw)]
print(curtail_act2_mw)
Storage units also consist of continuous actions.
Their main property is that they can produce and absorb power (behaving as a load or as a generator). They are also limited in the amount of energy they can store:
We chose, in grid2op to have storage units in the "load convention", this means that:
See the notebook 10_StorageUnits about this element.
For further details, the documentation explains in detail how the storage units behave here https://grid2op.readthedocs.io/en/latest/modeled_elements.html#storage-units-optional
storage_id = [0, 1]
values = [-1.7, 2.3]
action_descr = [(stor_id, val) for stor_id, val in zip(storage_id, values)]
# alternatively: action_descr = np.array([-1.7, 2.3], dtype=float)
# with the dictionnary
action_storage0 = action_space({"set_storage": action_descr})
# or with the property
action_storage1 = action_space()
action_storage1.set_storage = action_descr
print("The storage action applied is")
print(action_storage1)
As of grid2op version 1.2.0 the behavior of the platform with respect to line status modification has been clarified and rationalized (we hope).
The powerline status (connected / disconnected) can now be affected in two different ways:
setting
/ changing
its status directly (using the "set_line_status" or "change_line_status" keyword).In that case, the behavior is:
The way to compute the impact of the action has also been adjusted to reflect these changes.
In the table below we try to summarize all the possible actions and their impact on the powerline. This table is made considering that "LINE_ID
" is an id of a powerline and "SUB_OR
" is the id of the origin of the substation. If a status is 0 it means the powerlines is disconnected, if the status is 1 it means it is connected.
action | original status | final status | substations affected | line status affected |
---|---|---|---|---|
{"set_line_status": [(LINE_ID, -1)]} | 1 | 0 | None | LINE_ID |
{"set_line_status": [(LINE_ID, +1)]} | 1 | 1 | None | LINE_ID |
{"set_line_status": [(LINE_ID, -1)]} | 0 | 0 | None | LINE_ID |
{"set_line_status": [(LINE_ID, +1)]} | 0 | 1 | None | LINE_ID |
{"change_line_status": [LINE_ID]} | 1 | 0 | None | LINE_ID |
{"change_line_status": [LINE_ID]} | 0 | 1 | None | LINE_ID |
{"set_bus": {"lines_or_id": [(LINE_ID, -1)]}} | 1 | 0 | None | LINE_ID |
{"set_bus": {"lines_or_id": [(LINE_ID, -1)]}} | 0 | 0 | SUB_OR | None |
{"set_bus": {"lines_or_id": [(LINE_ID, 2)]}} | 1 | 1 | SUB_OR | None |
{"set_bus": {"lines_or_id": [(LINE_ID, 2)]}} | 0 | 1 | None | LINE_ID |
{"change_bus": {"lines_or_id": [LINE_ID]}} | 1 | 1 | SUB_OR | None |
{"change_bus": {"lines_or_id": [LINE_ID]}} | 0 | 0 | SUB_OR | None |
of course we could have set {"set_bus": {"lines_ex_id": [(LINED_ID, 2)]}}
(ie the extermity bus of the powerline) and it would have the same impact on its status. Assign the powerline extremity to bus 1 (instead of bus 2) by sending the dictionnaries {"set_bus": {"lines_or_id": [(LINED_ID, 1)]}}
or {"set_bus": {"lines_ex_id": [(LINED_ID, 1)]}}
would also lead to the same results.
In grid2op there is a convention that if an object is disconnected, then it is assigned to bus "-1". For a powerline this entails that a status changed affects the bus of
As we explained in the previous paragraph, some action on one end of a powerline can reconnect a powerline or disconnect it. This means they modify the bus of both the extremity of the powerline.
Here is a table summarizing how the buses are impacted. We denoted by "PREVIOUS_OR
" the last bus at which the origin end of the powerline was connected and "PREVIOUS_EX
" the last bus at which the extremity end of the powerline was connected. Note that for clarity when something is not modified by the action we decided to write on the table "not modified" (this entails that after this action, if the powerline is connected then "new origin bus" is "PREVIOUS_OR
" and "new extremity bus" is "PREVIOUS_EX
"). We remind the reader that "-1" encode for a disconnected object.
action | original status | final status | new origin bus | new extremity bus |
---|---|---|---|---|
{"set_line_status": [(LINE_ID, -1)]} | 1 | 0 | -1 | -1 |
{"set_line_status": [(LINE_ID, +1)]} | 1 | 1 | Not modified | Not modified |
{"set_line_status": [(LINE_ID, -1)]} | 0 | 0 | Not modified | Not modified |
{"set_line_status": [(LINE_ID, +1)]} | 0 | 1 | PREVIOUS_OR | PREVIOUS_EX |
{"change_line_status": [LINE_ID]} | 1 | 0 | -1 | -1 |
{"change_line_status": [LINE_ID]} | 0 | 1 | PREVIOUS_OR | PREVIOUS_EX |
{"set_bus": {"lines_or_id": [(LINE_ID, -1)]}} | 1 | 0 | -1 | -1 |
{"set_bus": {"lines_or_id": [(LINE_ID, -1)]}} | 0 | 0 | Not modified | Not modified |
{"set_bus": {"lines_or_id": [(LINE_ID, 2)]}} | 1 | 1 | 2 | Not modified |
{"set_bus": {"lines_or_id": [(LINE_ID, 2)]}} | 0 | 1 | 2 | PREVIOUS_EX |
{"change_bus": {"lines_or_id": [(LINE_ID, 2)]}} | 1 | 1 | * | Not modified |
{"change_bus": {"lines_or_id": [(LINE_ID, 2)]}} | 0 | 0 | Not modified | Not modified |
* means that this bus is affected: if it was on bus 1 it moves on bus 2 and vice versa.
As we can see here, but this is true in general in grid2op, each action you do is labeled to have at least an impact on some object. Some actions are considered to have impact on powerline status, some have impact on substations.
This is always the case regardless of the actual impact of this action on the powergrid. For example, if we look at the second and third row of the tables above we notice that:
This is particularly important for what we call "cooldown" (see the notebook 0_Introduction section Introduction of "operational constraints" in grid2op
for more information). You action can trigger a cooldown (preventing future action on the same element) while not impacting the grid at all.
Sampling random actions uniformly is not an easy task. Especially because "unform random actions" (taken on all the action space) will most likely be either ambiguous or illegal.
Grid2op comes with a tool to sample random actions. A possibility for such puporse is simply:
print(action_space.sample())
print(action_space.sample())
NB This method will sample action at random that meets the following properties:
redispatching
OR set_bus
OR change_bus
OR set_status
OR change_status
OR storage
(these are "exclusive or"). It will not act on multiple of these at the same time. The choice of the "type" of the action is uniform at random among the supported types.set_status
or a change_status
it will only affect 1 powerline at a timeset_bus
or a change_bus
it will only affect 1 substationredispatching
: will sample a single generator at random, and apply unformly at random redispatching on this single generatorredispatching
: will sample a single storage unit at random, and only act on this particular one.You can combine these "unary actions" with the +=
operator if you want, for example if you want to combine three such action:
action = action_space()
action += action_space.sample()
action += action_space.sample()
action += action_space.sample()
NB This method is not uniform on all the actions. It's uniform among the type of actions.
If you want more control on these action types you can use the following code snippet, that sample 2 actions only of types "set_status"
random_set_line_action = action_space()
random_set_line_action.update(action_space._sample_set_line_status())
random_set_line_action.update(action_space._sample_set_line_status())
print(random_set_line_action)
The other methods are:
action_space._sample_set_line_status()
: to sample action of type "set_line_status" (still acting only on one powerline)action_space._sample_change_line_status()
: to sample action of type "change_status" (still acting only on one powerline)action_space._sample_set_bus()
: to sample action of type "set_bus" (still acting on one substation)action_space._sample_change_bus()
: to sample action of type "set_bus" (still acting on one substation)action_space._sample_redispatch()
: to sample action of type "redispatching" (still acting on one single generator)action_space._sample_storage_power()
: to sample action of type "storage unit" (still acting on one single storage unit)One of the main "properties" of a powergrid is that, at every time the total demand (including the losses) should match exactly the total generation.
This entails that the "redispatching", "curtailment" and "storage units" type of actions have "side effects".
For example, if you curtail xxx
MW of power from renewable energy sources, they will be compensated by a corresponding increase of xxx
MW from the controlable generators. Hence, if you perform a "curtail" action you will also affect the "redispatching. The same goes for the actions on storage units.
Generators are in turn limited in their capacity. For example (for each controlable generator), its production $p_t$ is limited between $p_min$ and $p_max$ as well as the variation of this production $-ramp_{min} <= p_t - p_{t-1} <= ramp_{max}$. One the main consequences if that you are limited by the total amount of MW you can curtail and or absorb / produce by the storage units.
In particular, at each time, the equations:
If there is no solution to these equations there is a "game over" (done=True) and the info["exception"]
will say something like:
InvalidRedispatching('\nThis is an attempt to explain why the dispatch did not succeed and caused a game over.\nTo compensate the decrease of loads and / or increase of renewable energy (due to naturl causes but also through curtailment) and / or variation in the storage units, the generators should decrease their total production of -634.39MW (in total).\nBut, if you take into account the generator constraints (pmin and max_ramp_down) you can have at most -151.20MW.\nIndeed at time t, generators are in state:\n\t[369.6 25.5 228.71 228.71 369.6 231.2 28.9 135.88 128.08 369.6\n 40.41 231.2 0. 231.2 231.2 37.47 231.2 150. 81.88 25.16]\ntheir ramp max is:\n\t[ 3.5 8.5 11.2 11.2 3.5 11.2 8.5 5.3 5.3 3.5 9.9 11.2 5.7 11.2\n 11.2 8.5 11.2 5.3 5.3 5.7]\n and pmax is:\n\t[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]\nWrapping up, each generator can decrease at minimum of:\n\t[ 3.5 8.5 11.2 11.2 3.5 11.2 8.5 5.3 5.3 3.5 9.9 11.2 5.7 11.2\n 11.2 8.5 11.2 -0. 5.3 5.7]\nNB: if you did not do any dispatch during this episode, it would have been possible to meet these constraints. This situation is caused by not having enough degree of freedom to "compensate" the variation of the load due to (most likely) an "over usage" of redispatching feature (some generators stuck at pmin as a consequence of your redispatching. They can\'t increase their productions to meet the decrease in demand or increase of renewables)'), Grid2OpException AmbiguousAction InvalidRedispatching InvalidRedispatching('Game over due to infeasible redispatching state. The routine used to compute the "next state" has diverged. This means that there is no way to compute a physically valid generator state (one that meets all pmin / pmax - ramp min / ramp max with the information provided. As one of the physical constraints would be violated, this means that a generator would be damaged in real life. This is a game over.')
It is absolutely NOT recommended to use Actions outside of the action space, for example building an action directly with the class constructor.
However, it is possible, in grid2op to combine different action, or to create an action "step by step".
Let's take an example. Let's say we want an action to:
It is possible to do the following "at once", with:
combined_action = action_space({"redispatch": [(0, 3.1)],
"change_bus": {"loads_id": [0], "lines_or_id": [1]},
"set_storage": [(0, -1.5)]
}
)
print(combined_action)
But it is also possible to build it "little by little" by using the +=
(or +
) python operator. This can be done like this:
This can be useful particularly if different "entities" are responsible to perform different kind of actions.
In the example given above, we could imagine having a "stuff" that takes redispatching
action, another that takes change bus
actions and finally another affecting storages
, and then combine the action easily, giving a code looking like:
action_redispatch = entitiy_handling_redispatching(...)
action_change_bus = entitiy_handling_change_bus(...)
action_storage = entitiy_handling_storage(...)
combined_action = action_redispatch + action_change_bus + action_storage
Using the same principle as above, it is also possible to combine the type of action (say disconnecting a powerline) using the +
operator.
For example, to disconnect powerline i
and powerline j
you can do:
i = 0
j = 1
disco_line_i = action_space({"set_line_status": [(i, -1)]})
disco_line_j = action_space({"set_line_status": [(j, -1)]})
disco_both = disco_line_i + disco_line_j
This might be especially usefull if you have different agent acting on different part of the grid for example. One agent could be responsible to handle the "top part" (whatever it means) of the grid and another the "bottom part" (whatever it means) of it and you can combine the actions of both agents this way.
Combining actions this way might come with different caveat:
i
to bus 1 in an action but you also say to disconnect powerline i
in a second action. Grid2op currently will not "chose for you" what you want to do*.* Depending on the outcome of issue https://github.com/rte-france/Grid2Op/issues/201 we might chose in this case to have the last action added "take the priority" over the previous one. This might "solve" this specific problem but will also introduce a really important role in the order on which actions are summed.
As of grid2op version 1.5.0 we simplified and rationalized the way to interact with the powergrid. We do not recommend to use the older API described here.
However, for backward compatibility (and for people using grid2op version 1.4 or below) we still kept these features in the notebook.
Each powerline / load / generator has an ID and a name.
Keep in mind that the IDs of the powerlines are 0, 1, 2, ..., env.n_line
- 1 (where env.n_line
is the number of lines in the environment). The same goes for the loads and generators.
On the other hand, the names are more human-friendly identifiers for the different objects in the grid.
Therefore, for any vector
containing information about the powerlines, the variable relative to the powerline of id i
can be accessed or modified with vector[i]
since it is the i+1
th powerline in the grid.
This is how we will proceed in the next cell. However, the IDs are easy to use but less meaningful for a human (since it is the names of the powerlines that we see) and sometimes, when inspecting an observation for example, we may want to look at a specific powerline by specifying its name. This will be covered later in the notebook 7_PlottingCapabilities.
Another way to achieve the same things is:
change_status = action_space.get_change_line_status_vect()
change_status[0] = True
change_status[1] = True
change_status[2] = True
set_status = action_space.get_set_line_status_vect()
set_status[3] = 1
set_status[4] = 1
set_status[5] = -1
set_status[6] = -1
this_first_act = action_space({"set_line_status": set_status, "change_line_status": change_status})
NB even if it can handle different types, for performance reasons it's better to follow the type of data mentionned below : The dictionnary values should be:
True
means "change"False
means "don't change"0
means "do nothing"1
means "connect it"-1
means "disconnect it"For convenience, an Action object can be inspected easily by using the print
method. It will summarize on which object it has an impact:
print(this_first_act)
this_first_act.is_ambiguous()
NB This action is ambiguous so it cannot be implemented on the powergrid. Indeed, powerlines 3 and 4 are reconnected, but we don't specify on which bus! Implementing this action on a grid will be equivalent to doing nothing.
It's not always convenient to manipulate all the status of all the powerlines, or change it. For mor convenience, it's possible to modify only a few of them. The syntax is the following.
the_same_act = action_space({"set_line_status": [(3,1), (4,1), (5,-1), (6,-1)],
"change_line_status": [0,1,2]
})
print(the_same_act)
We can check that the two actions are indeed equal:
the_same_act == this_first_act
One of the interesting aspects of Grid2Op is to be able to modify the topology of the powergrid. In other words it allows to reconfigure the way the objects (generators, loads, end of powerlines) are interconnected at their substations.
Comparable to the status change, topological change can be interpreted in two disctinct manners, as described above. Topologycal changes include some of the most interesting interactions with the environment.
In this section we study how to modify the topology of the powergrid.
The underlying way to represent the topology is through a integer vector, having the same dimension as the number of objects of the grid. For each object in the grid, this vector tells on which bus it's connected. Manipulating this vector can be done, but is absolutely not handy. We present here the way to change the topology through the helped, which can be done more easily.
To set the bus to which a load is connected, it is recommended to do:
set_bus_load_0 = action_space({"set_bus": {"loads_id": [(0,2)]}})
print(set_bus_load_0)
To change the bus, a similar interface can be used:
change_bus_load_0 = action_space({"change_bus": {"loads_id": [0]}})
print(change_bus_load_0)
The API is really similar for generator:
change_bus_gen_0_and_1 = action_space({"change_bus": {"generators_id": [0,1]}})
set_bus_gen_3_and_4 = action_space({"set_bus": {"generators_id": [(3,2), (4,2)]}})
print(set_bus_gen_3_and_4)
The same goes for each ends of the powerlines:
change_bus_lines_or_0 = action_space({"change_bus": {"lines_or_id": [0]}})
set_bus_lines_or_4 = action_space({"set_bus": {"lines_or_id": [(3,2)]}})
change_bus_lines_ex_15 = action_space({"change_bus": {"lines_ex_id": [15]}})
set_bus_lines_ex_18 = action_space({"set_bus": {"lines_ex_id": [(18,2)]}})
print(set_bus_lines_ex_18)
When reconnecting a powerline, if the bus to which this powerline is reconnected is not specified, the action is ambiguous and thus will not be implemented. It is, in that case, recommended to use the reconnect_powerline
method as followed:
reconnecting_line_1 = action_space.reconnect_powerline(line_id=1,bus_or=1,bus_ex=1)
print(reconnecting_line_1)
Finally, if you know how many objects are in a substation, you can also modify all their buses in one call:
reconfigure_substation_id_1 = action_space({"set_bus": {"substations_id": [(1, (1,2,2,1,1,2))]}})
In the above code we knew that the substations of id 1 had 6 elements, and we assign to the elements of id 1,2 and 5 [second, third and sixth] the bus 2 and the others to bus 1.
Using this way does not make explicit which objects are modified. You need to know beforehand that the element of id 0 of this substation is the extremity of powerline 0, the element of id 1 of this substation is the origin of powerline 1 etc. We explain how to do so in the next paragraph.
You can also have a look at the grid_objects_types
object that is a representation, as a numpy array, of which element is connected to each substation. It counts as many rows as there are elements on the powergrid (here 56: 5 generators, 11 loads and 20 lines each having two ends - making 5 + 11 + 2*20 = 56
objects) and exactly 5 columns. The first column of this matrix of this matrix represents the id of the substation at which the object represented by the row is located.
Then the next 4 columns each account for an object type: either it's a load (column 1) or a generator (column 2) or the extremity of a powerline (column 3) or the extremity of a powerline (column 4). Let's take some example instead of getting lost in the details:
If at row 0 of grid_objects_types
i see [ 0, -1, -1, 0, -1]
this means that: the object of id 0 (remember we were looking for the row 0) is connected to substation 0 (first element of this vector). This is not a load nor a generator (there are -1
in columns 1 and 2 encoding for load and generators respectively. This is not an extremity of a powerline (there is a -1
in the 4th column encoding for the powerline extremity). We see a "0" on column 3, encoding for "powerline origin" this means that this is the origin of the powerline of id 0.
On the row 1 of grid_objects_types
we see [ 0, -1, -1, 1, -1]
. With the same reasoning we know that it corresponds to the origin of powerline 1 that is connected to substation 0.
On the row 2 we see [ 0, -1, 4, -1, -1]
. This means that the third object of the substation 0 is the generator of id 4.
And a last example is the following. The row 12 of grid_objects_types
is [ 2, 1, -1, -1, -1]
(see below) this means that the 12th element of the grid is: connected to substation 2, is a load, this load has id 1.
action_space.grid_objects_types[12]
This representation in terms of grid_objects_types
is rather explicit for a human but is also particularly suited to look for information informatically thanks to numpy indexing. For example if you want to know where the loads are located you can do:
is_load = action_space.grid_objects_types[:,action_space.LOA_COL] != -1
print("The substation with at least one load are: {}".format(
action_space.grid_objects_types[is_load,action_space.SUB_COL]))
is_sub1 = action_space.grid_objects_types[:, action_space.SUB_COL] == 1
is_gen = action_space.grid_objects_types[:, action_space.GEN_COL] != -1
print("The generator ids connected to substations 1 are: {}".format(
action_space.grid_objects_types[is_sub1 & is_gen, action_space.GEN_COL]))
print("The object connected to substation 1 are: {}".format(
action_space.grid_objects_types[is_sub1,:]))
# etc.
However, the method "get_obj_connect_to
" is clearer to read for human. This gives the following information:
action_space.get_obj_connect_to(substation_id=1)
In this case it means on the substation 1 are connected:
And this substation counts 6 elements.
Note that this does not allow easily to know which object is assign to which bus with the action reconfigure_substation_id_1
For convenience, it might be better sometimes to change the bus of an object from its name instead of its ID in case the ID is not known. Grid2Op allows to do that, but only for changing or setting a bus. These methods take longer than the methods shown above. If they are used at all, it's recommended NOT to use them for training an Agent. Their main goal aims at debugging and / or understanding the behaviour of an Agent.
These methods are:
action_space.change_bus
($\leftarrow$ this is a link)action_space.set_bus
($\leftarrow$ this is a link)Please refer to the official documentation for a complete description of their behaviour. To sum up, we can use them this way:
my_act = action_space.set_bus("gen_1_0", # mandatory name of the element
new_bus=2, # mandatory the new bus to connect it too
type_element="gen", # optional the type of the element, one of "line", "gen" or "load"
previous_action=None # optional: if you want to combine multiple action, you can do it with this
)
print(my_act)
action_space.set_bus("1_3_3", # mandatory name of the element
extremity="or", # mandatory, which extrmity to change
new_bus=2, # mandatory the new bus to connect it too
type_element="line", # optional the type of the element, one of "line", "gen" or "load"
previous_action=my_act # optional: if you want to combine multiple action, you can do it with this
)
print(my_act)
action_redispatch = action_space()
action_redispatch.redispatch = [3.1, 0, 0, 0, 0, 0] # or action_redispatch.redispatch = [(0, 3.1)]
action_change_bus = action_space()
action_change_bus.load_change_bus = [0]
action_change_bus.line_or_change_bus = [1]
action_storage = action_space()
action_storage.storage_power = [-1.5, 0.] # or action_storage.storage_power = [(0, -1.5)]
combined_action2 = action_redispatch + action_change_bus + action_storage
print(combined_action2)