https://github.com/amancore/radiant-future-ai
AI-powered solution for personalized solar panel recommendations, using machine learning and real-time weather data to optimize energy efficiency, reduce carbon footprints, and maximize savings.
https://github.com/amancore/radiant-future-ai
api-integration carbon-footprint-reduction machine-learning open-weather-api predictive-analytics random-forest-regression renewable-energy smart-pricing solar-energy
Last synced: 2 months ago
JSON representation
AI-powered solution for personalized solar panel recommendations, using machine learning and real-time weather data to optimize energy efficiency, reduce carbon footprints, and maximize savings.
- Host: GitHub
- URL: https://github.com/amancore/radiant-future-ai
- Owner: amancore
- Created: 2025-01-09T12:14:58.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-01-09T12:41:53.000Z (10 months ago)
- Last Synced: 2025-03-26T03:43:28.761Z (7 months ago)
- Topics: api-integration, carbon-footprint-reduction, machine-learning, open-weather-api, predictive-analytics, random-forest-regression, renewable-energy, smart-pricing, solar-energy
- Language: Jupyter Notebook
- Homepage:
- Size: 11.1 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Radiant Future AI 🌞
**Radiant Future AI** is an innovative, AI-powered solution designed to deliver personalized recommendations for solar panel installations. At its core lies a state-of-the-art machine learning model that predicts solar panel requirements with exceptional accuracy. This feature ensures precise, reliable, and actionable insights, making solar energy adoption easier and more effective.
---
## 🌟 Core Features
### 1. Solar Panel Requirements Prediction
- **Advanced Machine Learning Model**:
Utilizes **Random Forest Regression (RFR)**, chosen for its superior performance after rigorous comparisons with models like **Stochastic Gradient Descent (SGD)** and **Multi-Layer Perceptron (MLP)**. The RFR model ensures high accuracy and robustness in predictions.
- **Dataset**:
Trained on a curated dataset featuring historical solar energy production, geographical information, and weather patterns. Data preprocessing included normalization, handling missing values, and feature selection to enhance model performance.
- **Model Tuning**:
Hyperparameter tuning via grid search optimized parameters like the number of trees and depth to boost efficiency.
- **Evaluation Metrics**:
The model was evaluated using metrics such as **R² score**, **Mean Absolute Error (MAE)**, and **Root Mean Squared Error (RMSE)** to meet and exceed industry benchmarks.
### 2. Energy Consumption Prediction
A system that forecasts energy consumption based on historical data and user inputs, enabling efficient energy planning.
### 3. Weather-Driven Insights
Real-time weather data integration provides actionable insights into solar energy generation, helping users optimize energy usage and panel positioning.
### 4. ROI Analysis
A comprehensive tool offering visualized insights, such as daily energy generation, monthly energy consumption, and installation costs, showcasing the financial benefits of investing in solar energy.
### 5. Installation Pricing
An intelligent pricing calculator that provides accurate cost estimates for solar panel installations based on multiple parameters.
### 6. Carbon Footprint Reduction Estimation
Estimates the reduction in carbon footprint achieved through solar energy adoption, promoting sustainable energy practices.
---
## 💻 Technologies Used
- **Machine Learning Models**:
- Random Forest Regression (RFR)
- Stochastic Gradient Descent (SGD)
- Multi-Layer Perceptron (MLP)
- **Evaluation Metrics**:
- R² score
- Mean Absolute Error (MAE)
- Root Mean Squared Error (RMSE)
- **Frontend**: HTML, CSS, JavaScript
- **Backend**: Node.js, Firebase Authentication, MongoDB
- **APIs Used**:
- **Open Weather API**: For real-time weather data
- **Geocode API**: For geographical data
- **Peak Sunny Hours by NASA API**: To predict solar energy potential
---
## 🏗️ Project Architecture
### Frontend
Developed with **HTML**, **CSS**, and **JavaScript**, ensuring a responsive and interactive user experience.
### Backend
Built with **Node.js**, the backend handles secure and efficient user data interactions. **Firebase Authentication** manages user access, while **MongoDB** serves as the database for storing user data and project details.
### APIs
Real-time data fetching enhances prediction accuracy and user experience by integrating weather, location, and solar energy data.
---
## 🚀 How to Run
1. **Clone the repository**:
Open your terminal and run:
```bash
git clone https://github.com/soumya-1712/radiant-future-ai.git
2. **Navigate to the project directory**:
```bash
cd radiant-future-ai
3. **Install dependencies**:
```bash
npm install
4. **Run the application**:
```bash
npm start
5. **Run the application**:
```bash
http://localhost:3000
## 🤝 Contributors
- [Aman Raj](https://github.com/Amanraj4482)
- [Soumya Dhakad](https://github.com/soumya-1712)
- [Hardik Kanzariya](https://github.com/MrHardik-k)
- [Priyanshu Pandey](https://github.com/Harshpf)