Update app_backend.py

app_backend.py

@@ -1,46 +1,3 @@
-# import pandas as pd
-# import numpy as np
-# import plotly.express as px
-# from datetime import datetime, timedelta
-# import requests
-
-# # Function to fetch real-time weather data
-# def fetch_weather(api_key, location):
-#     url = f"http://api.openweathermap.org/data/2.5/weather?q={location}&appid={api_key}&units=metric"
-#     response = requests.get(url).json()
-#     if response["cod"] == 200:
-#         return {
-#             "temperature": response["main"]["temp"],
-#             "wind_speed": response["wind"]["speed"],
-#             "weather": response["weather"][0]["description"]
-#         }
-#     return None
-
-# # Generate synthetic grid data
-# def generate_synthetic_data():
-#     time_index = pd.date_range(start=datetime.now(), periods=24, freq="H")
-#     return pd.DataFrame({
-#         "timestamp": time_index,
-#         "total_consumption_kwh": np.random.randint(200, 500, len(time_index)),
-#         "grid_generation_kwh": np.random.randint(150, 400, len(time_index)),
-#         "storage_usage_kwh": np.random.randint(50, 150, len(time_index)),
-#         "solar_output_kw": np.random.randint(50, 150, len(time_index)),
-#         "wind_output_kw": np.random.randint(30, 120, len(time_index)),
-#         "grid_health": np.random.choice(["Good", "Moderate", "Critical"], len(time_index))
-#     })
-
-# # Load optimization recommendation
-# def optimize_load(demand, solar, wind):
-#     renewable_supply = solar + wind
-#     if renewable_supply >= demand:
-#         return "Grid Stable"
-#     return "Use Backup or Adjust Load"
-
-# # Export functions for use in Streamlit
-# if __name__ == "__main__":
-#     print("Backend ready!")
-
-
 import pandas as pd
 import numpy as np
 import plotly.express as px
@@ -59,19 +16,20 @@ def fetch_weather(api_key, location):
         }
     return None
 
-# Generate synthetic grid data in MW (for generation) and kWh (for load)
+# Generate synthetic grid data
 def generate_synthetic_data():
     time_index = pd.date_range(start=datetime.now(), periods=24, freq="H")
     return pd.DataFrame({
         "timestamp": time_index,
-        "load_demand_mw": np.random.uniform(0.2, 0.5, len(time_index)),  # Load demand in MW
-        "solar_output_mw": np.random.uniform(0.05, 0.15, len(time_index)),  # Solar output in MW
-        "wind_output_mw": np.random.uniform(0.03, 0.12, len(time_index)),  # Wind output in MW
-        "battery_storage_kwh": np.random.randint(100, 500, len(time_index)),  # Battery storage in kWh
+        "total_consumption_kwh": np.random.randint(200, 500, len(time_index)),
+        "grid_generation_kwh": np.random.randint(150, 400, len(time_index)),
+        "storage_usage_kwh": np.random.randint(50, 150, len(time_index)),
+        "solar_output_kw": np.random.randint(50, 150, len(time_index)),
+        "wind_output_kw": np.random.randint(30, 120, len(time_index)),
         "grid_health": np.random.choice(["Good", "Moderate", "Critical"], len(time_index))
     })
 
-# Load optimization recommendation in MW
+# Load optimization recommendation
 def optimize_load(demand, solar, wind):
     renewable_supply = solar + wind
     if renewable_supply >= demand:
@@ -80,4 +38,6 @@ def optimize_load(demand, solar, wind):
 
 # Export functions for use in Streamlit
 if __name__ == "__main__":
-    print("Backend ready!")
+    print("Backend ready!")
+
+