Start changes for WindNet

configs/model/multimodal.yaml

@@ -43,6 +43,19 @@ pv_encoder:
   kdim: 40
   pv_id_embed_dim: 20
 
+#--------------------------------------------
+# Sensor encoder settings
+#--------------------------------------------
+
+sensor_encoder:
+  _target_: pvnet.models.multimodal.site_encoders.encoders.SingleAttentionNetwork
+  _partial_: True
+  num_sites: 123
+  out_features: 40
+  num_heads: 4
+  kdim: 40
+  pv_id_embed_dim: 20
+
 #--------------------------------------------
 # Tabular network settings
 #--------------------------------------------

pvnet/models/base_model.py

@@ -68,6 +68,11 @@ def make_clean_data_config(input_path, output_path, placeholder="PLACEHOLDER"):
             d["pv_filename"] = f"{placeholder}.netcdf"
             d["pv_metadata_filename"] = f"{placeholder}.csv"
 
+    if "sensor" in config["input_data"]:
+        # If not empty - i.e. if used
+        if config["input_data"][source][f"{source}_filename"] != "":
+            config["input_data"][source][f"{source}_filename"] = f"{placeholder}.nc"
+
     with open(output_path, "w") as outfile:
         yaml.dump(config, outfile, default_flow_style=False)
 
@@ -237,6 +242,7 @@ def __init__(
         forecast_minutes: int,
         optimizer: AbstractOptimizer,
         output_quantiles: Optional[list[float]] = None,
+        target_key: BatchKey = BatchKey.gsp,
     ):
         """Abtstract base class for PVNet submodels.
 
@@ -246,10 +252,12 @@ def __init__(
             optimizer (AbstractOptimizer): Optimizer
             output_quantiles: A list of float (0.0, 1.0) quantiles to predict values for. If set to
                 None the output is a single value.
+            target_key: BatchKey of the target variable
         """
         super().__init__()
 
         self._optimizer = optimizer
+        self._target_key = target_key
 
         # Model must have lr to allow tuning
         # This setting is only used when lr is tuned with callback
@@ -424,7 +432,7 @@ def _training_accumulate_log(self, batch, batch_idx, losses, y_hat):
     def training_step(self, batch, batch_idx):
         """Run training step"""
         y_hat = self(batch)
-        y = batch[BatchKey.gsp][:, -self.forecast_len_30 :, 0]
+        y = batch[self._target_key][:, -self.forecast_len_30 :, 0]
 
         losses = self._calculate_common_losses(y, y_hat)
         losses = {f"{k}/train": v for k, v in losses.items()}
@@ -440,7 +448,7 @@ def training_step(self, batch, batch_idx):
     def validation_step(self, batch: dict, batch_idx):
         """Run validation step"""
         y_hat = self(batch)
-        y = batch[BatchKey.gsp][:, -self.forecast_len_30 :, 0]
+        y = batch[self._target_key][:, -self.forecast_len_30 :, 0]
 
         losses = self._calculate_common_losses(y, y_hat)
         losses.update(self._calculate_val_losses(y, y_hat))
@@ -484,7 +492,7 @@ def validation_step(self, batch: dict, batch_idx):
     def test_step(self, batch, batch_idx):
         """Run test step"""
         y_hat = self(batch)
-        y = batch[BatchKey.gsp][:, -self.forecast_len_30 :, 0]
+        y = batch[self._target_key][:, -self.forecast_len_30 :, 0]
 
         losses = self._calculate_common_losses(y, y_hat)
         losses.update(self._calculate_val_losses(y, y_hat))

pvnet/models/multimodal/multimodal.py

@@ -42,9 +42,11 @@ def __init__(
         nwp_encoder: Optional[AbstractNWPSatelliteEncoder] = None,
         sat_encoder: Optional[AbstractNWPSatelliteEncoder] = None,
         pv_encoder: Optional[AbstractPVSitesEncoder] = None,
+        sensor_encoder: Optional[AbstractPVSitesEncoder] = None, # TODO Change to SensorEncoder
         add_image_embedding_channel: bool = False,
         include_gsp_yield_history: bool = True,
         include_sun: bool = True,
+        include_gsp: bool = True,
         embedding_dim: Optional[int] = 16,
         forecast_minutes: int = 30,
         history_minutes: int = 60,
@@ -53,6 +55,7 @@ def __init__(
         nwp_forecast_minutes: Optional[int] = None,
         nwp_history_minutes: Optional[int] = None,
         pv_history_minutes: Optional[int] = None,
+        sensor_history_minutes: Optional[int] = None,
         optimizer: AbstractOptimizer = pvnet.optimizers.Adam(),
     ):
         """Neural network which combines information from different sources.
@@ -100,6 +103,8 @@ def __init__(
         self.include_nwp = nwp_encoder is not None
         self.include_pv = pv_encoder is not None
         self.include_sun = include_sun
+        self.include_gsp = include_gsp
+        self.include_sensor = sensor_encoder is not None
         self.embedding_dim = embedding_dim
         self.add_image_embedding_channel = add_image_embedding_channel
 
@@ -159,6 +164,18 @@ def __init__(
             # Update num features
             fusion_input_features += self.pv_encoder.out_features
 
+        if self.include_sensor:
+            if sensor_history_minutes is None:
+                sensor_history_minutes = history_minutes
+
+            self.sensor_encoder = sensor_encoder(
+                sequence_length=sensor_history_minutes // 30 + 1,
+                # Sensors are currently resampled to 30min
+            )
+
+            # Update num features
+            fusion_input_features += self.sensor_encoder.out_features
+
         if self.embedding_dim:
             self.embed = nn.Embedding(num_embeddings=318, embedding_dim=embedding_dim)
 
@@ -227,6 +244,11 @@ def forward(self, x):
             id_embedding = self.embed(id)
             modes["id"] = id_embedding
 
+        # *********************** Sensor Data ************************************
+        # add sensor yield history
+        if self.include_sensor:
+            modes["sensor"] = self.sensor_encoder(x)
+
         if self.include_sun:
             sun = torch.cat(
                 (x[BatchKey.gsp_solar_azimuth], x[BatchKey.gsp_solar_elevation]), dim=1

pvnet/models/multimodal/site_encoders/encoders.py

@@ -125,6 +125,8 @@ def __init__(
         n_kv_res_blocks: int = 2,
         kv_res_block_layers: int = 2,
         use_pv_id_in_value: bool = False,
+        use_gsp_embedding: bool = True,
+        sensor_embed_dim: int = 123,
     ):
         """A simple attention-based model with a single multihead attention layer
 
@@ -142,6 +144,7 @@ def __init__(
                 the key and value encoders.
             use_pv_id_in_value: Whether to use a PV ID embedding in network used to produce the
                 value for the attention layer.
+            use_gsp_embedding: Whether to use embedding of the GSP ID
 
         """
         super().__init__(sequence_length, num_sites, out_features)