Module ml4opf.models.basic_nn

A basic feed-forward fully-connected neural network.

Sub-modules

ml4opf.models.basic_nn.acopf_basic_nn

ml4opf.models.basic_nn.basic_nn

ml4opf.models.basic_nn.dcopf_basic_nn

ml4opf.models.basic_nn.ed_basic_nn

ml4opf.models.basic_nn.lightning_basic_nn

ml4opf.models.basic_nn.socopf_basic_nn

Classes

class ACBasicNeuralNet (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

• BasicNeuralNet
• ACModel
• OPFModel
• abc.ABC

Subclasses

• ACLDFNeuralNet
• ACPCANeuralNet
• ACPenaltyNeuralNet

Class variables

var model : ACBasicNN

Inherited members

• BasicNeuralNet:
  • evaluate_model
  • load_from_checkpoint
  • model_cls
  • predict
  • save_checkpoint

class DCBasicNeuralNet (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

• BasicNeuralNet
• DCModel
• OPFModel
• abc.ABC

Subclasses

• DCLDFNeuralNet
• DCPCANeuralNet
• DCPenaltyNeuralNet

Class variables

var model : DCBasicNN

Inherited members

• BasicNeuralNet:
  • evaluate_model
  • load_from_checkpoint
  • model_cls
  • predict
  • save_checkpoint

class EDBasicNeuralNet (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

• BasicNeuralNet
• EDModel
• OPFModel
• abc.ABC

Subclasses

• EDE2ELRNeuralNet
• EDLDFNeuralNet
• EDPCANeuralNet
• EDPenaltyNeuralNet

Class variables

var model : EDBasicNN

Inherited members

• BasicNeuralNet:
  • evaluate_model
  • load_from_checkpoint
  • model_cls
  • predict
  • save_checkpoint

class SOCBasicNeuralNet (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

• BasicNeuralNet
• SOCModel
• OPFModel
• abc.ABC

Subclasses

• SOCLDFNeuralNet
• SOCPCANeuralNet
• SOCPenaltyNeuralNet

Class variables

var model : SOCBasicNN

Inherited members

• BasicNeuralNet:
  • evaluate_model
  • load_from_checkpoint
  • model_cls
  • predict
  • save_checkpoint