Electricity Demand Historical Data

Project Video available on YouTube - https://youtu.be/iop8TUxmgO0

Electricity Demand Forecasting Dataset (XGBoost Model Ready)

This dataset contains historical information of 5 years to help predict electricity demand using machine learning, especially with models like XGBoost. It includes features such as temperature, humidity, wind speed, and past electricity usage across different time intervals.

The dataset is designed to help you learn and build models that can forecast how much electricity people might use in the future. This is useful for energy companies, smart grids, and power management systems.

The Features/Columns available in the dataset are :

• Timestamp: The date of the observation
• Demand: Actual electricity demand at that time (target variable)
• Temperature: Temperature in degrees Celsius
• Humidity: Humidity percentage
• Hour: Hour of the day (0–23)
• DayOfWeek: Day of the week (0 = Monday, 6 = Sunday)
• Month: Month number (1 = January, 12 = December)
• Year: Year of the observation

Potential Use Cases :

-Build regression models to forecast electricity demand

-Use lag and rolling features in time series models

-Compare performance of ML algorithms like XGBoost, Random Forest, and LSTM

-Learn how environmental and time-based factors affect electricity usage