Module ml4opf.models.penalty_nn

A basic feed-forward fully-connected neural network, using the PenaltyLoss loss function.

Sub-modules

ml4opf.models.penalty_nn.acopf_penalty_nn
ml4opf.models.penalty_nn.dcopf_penalty_nn
ml4opf.models.penalty_nn.ed_penalty_nn
ml4opf.models.penalty_nn.penalty_nn
ml4opf.models.penalty_nn.socopf_penalty_nn

Classes

class ACPenaltyNeuralNet (config: dict,
problem: OPFProblem)
Browse git

A basic feed-forward neural network.

Args

config : dict
Dictionary containing the model configuration.

optimizer (str): Optimizer. Supported: "adam", "adamw", "sgd".

loss (str): Loss function. Supported: "mse", "l1".

hidden_sizes (list[int]): List of hidden layer sizes.

activation (str): Activation function. Supported: "relu", "tanh", "sigmoid".

boundrepair (str): Bound clipping method. Supported: "none", "relu", "clamp", "sigmoid".

learning_rate (float): Learning rate.

problem : OPFProblem
The OPFProblem object.

Ancestors

Class variables

var model : ACPenaltyNN

Inherited members

class DCPenaltyNeuralNet (config: dict,
problem: OPFProblem)
Browse git

A basic feed-forward neural network.

Args

config : dict
Dictionary containing the model configuration.

optimizer (str): Optimizer. Supported: "adam", "adamw", "sgd".

loss (str): Loss function. Supported: "mse", "l1".

hidden_sizes (list[int]): List of hidden layer sizes.

activation (str): Activation function. Supported: "relu", "tanh", "sigmoid".

boundrepair (str): Bound clipping method. Supported: "none", "relu", "clamp", "sigmoid".

learning_rate (float): Learning rate.

problem : OPFProblem
The OPFProblem object.

Ancestors

Class variables

var model : DCPenaltyNN

Inherited members