Updated thesis

src/models/diffusion_model.py

@@ -39,7 +39,6 @@ class SimpleDiffusionModel(DiffusionModel):
         hidden_sizes: list,
         other_inputs_dim: int,
         time_dim: int = 64,
-        dropout_rate: float = 0.2,
     ):
         super(SimpleDiffusionModel, self).__init__(time_dim)
 
@@ -49,7 +48,6 @@ class SimpleDiffusionModel(DiffusionModel):
             nn.Linear(input_size + time_dim + other_inputs_dim, hidden_sizes[0])
         )
         self.layers.append(nn.ReLU())
-        self.layers.append(nn.Dropout(dropout_rate))
 
         for i in range(1, len(hidden_sizes)):
             self.layers.append(
@@ -58,7 +56,6 @@ class SimpleDiffusionModel(DiffusionModel):
                 )
             )
             self.layers.append(nn.ReLU())
-            self.layers.append(nn.Dropout(dropout_rate))
 
         self.layers.append(
             nn.Linear(hidden_sizes[-1] + time_dim + other_inputs_dim, input_size)

src/training_scripts/autoregressive_quantiles.py

@@ -2,7 +2,9 @@ from src.utils.clearml import ClearMLHelper
 
 #### ClearML ####
 clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
-task = clearml_helper.get_task(task_name="AQR: Non Linear + Load + Wind + PV + QE + NP")
+task = clearml_helper.get_task(
+    task_name="AQR: GRU (8 - 512) + Load + Wind + PV + QE + NP"
+)
 task.execute_remotely(queue_name="default", exit_process=True)
 
 from src.policies.PolicyEvaluator import PolicyEvaluator
@@ -44,7 +46,7 @@ data_config.NOMINAL_NET_POSITION = True
 
 data_config = task.connect(data_config, name="data_features")
 
-data_processor = DataProcessor(data_config, path="", lstm=False)
+data_processor = DataProcessor(data_config, path="", lstm=True)
 data_processor.set_batch_size(512)
 data_processor.set_full_day_skip(False)
 
@@ -67,7 +69,7 @@ else:
 
 model_parameters = {
     "learning_rate": 0.0001,
-    "hidden_size": 256,
+    "hidden_size": 512,
     "num_layers": 8,
     "dropout": 0.2,
     "time_feature_embedding": 5,
@@ -81,25 +83,25 @@ time_embedding = TimeEmbedding(
 
 # time_embedding = TrigonometricTimeEmbedding(data_processor.get_time_feature_size())
 
-# lstm_model = GRUModel(
-#     time_embedding.output_dim(inputDim),
-#     len(quantiles),
-#     hidden_size=model_parameters["hidden_size"],
-#     num_layers=model_parameters["num_layers"],
-#     dropout=model_parameters["dropout"],
-# )
-
-non_linear_model = NonLinearRegression(
+lstm_model = GRUModel(
     time_embedding.output_dim(inputDim),
     len(quantiles),
-    hiddenSize=model_parameters["hidden_size"],
-    numLayers=model_parameters["num_layers"],
+    hidden_size=model_parameters["hidden_size"],
+    num_layers=model_parameters["num_layers"],
     dropout=model_parameters["dropout"],
 )
 
+# non_linear_model = NonLinearRegression(
+#     time_embedding.output_dim(inputDim),
+#     len(quantiles),
+#     hiddenSize=model_parameters["hidden_size"],
+#     numLayers=model_parameters["num_layers"],
+#     dropout=model_parameters["dropout"],
+# )
+
 # linear_model = LinearRegression(time_embedding.output_dim(inputDim), len(quantiles))
 
-model = nn.Sequential(time_embedding, non_linear_model)
+model = nn.Sequential(time_embedding, lstm_model)
 
 model.output_size = 1
 optimizer = torch.optim.Adam(model.parameters(), lr=model_parameters["learning_rate"])

src/training_scripts/diffusion_training.py

@@ -2,7 +2,7 @@ from src.utils.clearml import ClearMLHelper
 
 clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
 task = clearml_helper.get_task(
-    task_name="Diffusion Training: hidden_sizes=[2048, 2048, 2048] (300 steps), lr=0.0001, time_dim=8"
+    task_name="Diffusion Training (GRUs): hidden_sizes=[1024, 1024] (300 steps), lr=0.0001, time_dim=8 + NRV + L + W + PV + NP",
 )
 task.execute_remotely(queue_name="default", exit_process=True)
 
@@ -19,20 +19,20 @@ from src.policies.PolicyEvaluator import PolicyEvaluator
 data_config = DataConfig()
 data_config.NRV_HISTORY = True
 
-data_config.LOAD_HISTORY = False
-data_config.LOAD_FORECAST = False
+data_config.LOAD_HISTORY = True
+data_config.LOAD_FORECAST = True
 
-data_config.PV_FORECAST = False
-data_config.PV_HISTORY = False
+data_config.PV_FORECAST = True
+data_config.PV_HISTORY = True
 
-data_config.WIND_FORECAST = False
-data_config.WIND_HISTORY = False
+data_config.WIND_FORECAST = True
+data_config.WIND_HISTORY = True
 
-data_config.NOMINAL_NET_POSITION = False
+data_config.NOMINAL_NET_POSITION = True
 
 data_config = task.connect(data_config, name="data_features")
 
-data_processor = DataProcessor(data_config, path="", lstm=False)
+data_processor = DataProcessor(data_config, path="", lstm=True)
 data_processor.set_batch_size(64)
 data_processor.set_full_day_skip(True)
 
@@ -42,28 +42,28 @@ print("Input dim: ", inputDim)
 model_parameters = {
     "epochs": 15000,
     "learning_rate": 0.0001,
-    "hidden_sizes": [2048, 2048, 2048],
+    "hidden_sizes": [1024, 1024],
     "time_dim": 8,
 }
 
 model_parameters = task.connect(model_parameters, name="model_parameters")
 
 #### Model ####
-model = SimpleDiffusionModel(
-    96,
-    model_parameters["hidden_sizes"],
-    other_inputs_dim=inputDim[1],
-    time_dim=model_parameters["time_dim"],
-)
-
-# model = GRUDiffusionModel(
+# model = SimpleDiffusionModel(
 #     96,
 #     model_parameters["hidden_sizes"],
-#     other_inputs_dim=inputDim[2],
+#     other_inputs_dim=inputDim[1],
 #     time_dim=model_parameters["time_dim"],
-#     gru_hidden_size=128,
 # )
 
+model = GRUDiffusionModel(
+    96,
+    model_parameters["hidden_sizes"],
+    other_inputs_dim=inputDim[2],
+    time_dim=model_parameters["time_dim"],
+    gru_hidden_size=512,
+)
+
 ### Policy Evaluator ###
 battery = Battery(2, 1)
 baseline_policy = BaselinePolicy(battery, data_path="")