⚡ Forecasting Renewable Energy Production & Electricity Demand

This project applies machine learning techniques to forecast solar (PV) production, wind production, and electricity demand using real-world renewable energy and weather data.

The dataset spans 3 years (2019–2021) and includes key environmental variables such as solar irradiance (DHI, DNI, GHI), wind speed, humidity, temperature, and more.
The goal is to build reliable forecasting models that support renewable energy planning and grid stability.

---

🌍 Project Objectives

• Clean, preprocess, and analyze a multi-year energy dataset
• Perform exploratory data analysis (EDA) and uncover patterns
• Build predictive machine learning models
• Forecast:
  • ☀️ PV (solar) production
  • 🌬️ Wind production
  • ⚡ Electricity demand
• Evaluate model performance
• Provide insights to support renewable energy integration

---

📁 Project Structure

---

🔧 Technologies & Libraries

• Python
• Pandas, NumPy
• Matplotlib, Seaborn
• Scikit-learn
• Joblib
• Jupyter Notebook

---

📊 Key Analysis Performed

• Time-indexed dataset transformation
• Handling missing values and duplicates
• Correlation heatmaps for feature relationships
• Trend analysis across seasons, months, and hours
• ML model training (Random Forest, etc.)
• Model evaluation using standard metrics

---

🚀 Model Outputs

The notebook generates:

• Forecasts for PV production
• Forecasts for wind production
• Forecasts for electricity demand
• Visualizations showing predicted vs actual values

---

📌 How to Use the Notebook

1. Clone this repository:

   git clone https://github.com/Etim-Antai/Forecasting-Renewable-Energy-Production.git