Source code for grid2op.Reward.linesCapacityReward

# Copyright (c) 2019-2020, RTE (
# See AUTHORS.txt
# This Source Code Form is subject to the terms of the Mozilla Public License, version 2.0.
# If a copy of the Mozilla Public License, version 2.0 was not distributed with this file,
# you can obtain one at
# SPDX-License-Identifier: MPL-2.0
# This file is part of Grid2Op, Grid2Op a testbed platform to model sequential decision making in power systems.

import numpy as np
from grid2op.Reward.baseReward import BaseReward
from grid2op.dtypes import dt_float

[docs]class LinesCapacityReward(BaseReward): """ Reward based on lines capacity usage Returns max reward if no current is flowing in the lines Returns min reward if all lines are used at max capacity Compared to `:class:L2RPNReward`: This reward is linear (instead of quadratic) and only considers connected lines capacities Examples --------- You can use this reward in any environment with: .. code-block:: python import grid2op from grid2op.Reward import LinesCapacityReward # then you create your environment with it: NAME_OF_THE_ENVIRONMENT = "l2rpn_case14_sandbox" env = grid2op.make(NAME_OF_THE_ENVIRONMENT,reward_class=LinesCapacityReward) # and do a step with a "do nothing" action obs = env.reset() obs, reward, done, info = env.step(env.action_space()) # the reward is computed with the LinesCapacityReward class """
[docs] def __init__(self, logger=None): BaseReward.__init__(self, logger=logger) self.reward_min = dt_float(0.0) self.reward_max = dt_float(1.0)
[docs] def __call__(self, action, env, has_error, is_done, is_illegal, is_ambiguous): if has_error or is_illegal or is_ambiguous: return self.reward_min obs = env.get_obs(_do_copy=False) n_connected = dt_float(obs.line_status.sum()) usage = obs.rho[obs.line_status == True].sum() usage = np.clip(usage, 0.0, float(n_connected)) reward = np.interp( n_connected - usage, [dt_float(0.0), float(n_connected)], [self.reward_min, self.reward_max], ) return reward