The objective of this project is to develop a model that accurately predicts the energy consumption of household appliances based on various input features. By leveraging data on temperature, humidity, time of day, and appliance power readings, the model aims to provide insights into energy usage patterns and facilitate energy efficiency improvements in residential settings.
The project utilizes a comprehensive dataset containing information on household appliance energy consumption and relevant environmental factors. Here are the key variables included in the dataset:
- T1: Temperature in the kitchen area (°C)
- RH_1: Humidity in the kitchen area (%)
- T2: Temperature in the living room area (°C)
- RH_2: Humidity in the living room area (%)
- T3: Temperature in the laundry room area (°C)
- RH_3: Humidity in the laundry room area (%)
- T4: Temperature in the office room (°C)
- RH_4: Humidity in the office room (%)
- T5: Temperature in the bathroom (°C)
- RH_5: Humidity in the bathroom (%)
- T6: Temperature outside the building (north side) (°C)
- RH_6: Humidity outside the building (north side) (%)
- T7: Temperature in the ironing room (°C)
- RH_7: Humidity in the ironing room (%)
- T8: Temperature in teenager room 2 (°C)
- RH_8: Humidity in teenager room 2 (%)
- T9: Temperature in the parents' room (°C)
- RH_9: Humidity in the parents' room (%)
- T_out: Temperature outside (from Chièvres weather station) (°C)
- Press_mm_hg: Pressure (from Chièvres weather station) (mm Hg)
- RH_out: Humidity outside (from Chièvres weather station) (%)
- Windspeed: Wind speed (from Chièvres weather station) (m/s)
- Visibility: Visibility (from Chièvres weather station) (km)
- Tdewpoint: Dew point (from Chièvres weather station) (°C)
- rv1: Random variable 1 (nondimensional)
- rv2: Random variable 2 (nondimensional)
The project involves the development and evaluation of predictive models using advanced machine learning techniques. By training on the provided dataset, the models will be able to forecast household energy consumption accurately.
Stay tuned for updates on the model development process and insights gained from the analysis!