Team ClusterBusters 👩‍💻

Amrita Vishwa Vidyapeetham, Coimbatore
B.Tech Computer Science (Cyber Security)

Project Structure

├── dataset               # Contains the .csv data generated using our script
├── docs                  # Documentation.md
├── presentation          # Presentation Phase I
├── models                # Two models in .pkl format
├── src                   # Source code directory
│── test                  # Python and bash shell script to test the model
|── archive               # Past work (code, datasets, models)
|
└── README.md             # This file

🧠 DT - Model Testing Instructions

This repository contains the codebase and scripts for testing our model submission for the hackathon.

🚀 Quick Start: How to Test the Model

Follow these steps to clone the repository, install dependencies, and run the model on the provided test data.

🔧 Step 1: Clone the Repository

Clone this repository using Git and move into the project directory:

git clone https://github.com/CS-Amritha/DT.git
cd DT

📦 Step 2: Install Python Dependencies

Install all required Python packages using pip. Make sure Python 3.8+ is installed.

pip install -r requirements.txt

▶️ Step 3: Run the Prediction Script

Navigate to the test folder and run the run_predictions.sh script using the provided test CSV file.

cd test
bash run_predictions.sh ../data/test_data.csv

📌 Notes

• After prediction, an output CSV file with predicted results will be generated in the same data/ directory.
• The model’s accuracy will be printed directly in the terminal after the script runs.

Problem Statement ❓ - Phase I

Kubernetes clusters can encounter failures such as pod crashes, resource bottlenecks, and network issues. The challenge in Phase 1 is to build an AI/ML model capable of predicting these issues before they occur by analysing historical and real-time cluster metrics.

Key Challenges ⚠️

• Node or pod failures
• Resource exhaustion (CPU, memory, disk)
• Network or connectivity issues
• Service disruptions based on logs and events

---

Phase I Progress Bar

📌 Data Collection

🟩🟩🟩🟩🟩🟩🟩⬜⬜⬜ 70%

📌 ML Model

🟩🟩🟩🟩🟩🟩🟩⬜⬜⬜ 70%

📌 Live Data Tracking

🟩🟩🟩🟩⬜⬜⬜⬜⬜⬜ 40%

Problem Statement ❓ - Phase II

Once issues are predicted, the next step is to automate or recommend actions for remediation. The challenge in Phase 2 is to create an agent or system capable of responding to these predicted issues by suggesting or implementing actions to mitigate potential failures in the Kubernetes cluster.

Key Challenges ⚠️

• Scaling pods when resource exhaustion is predicted
• Restarting or relocating pods when failures are forecasted
• Optimizing CPU or memory allocation when bottlenecks are detected

Tech Stack & Tools 🛠️

Meet The Team 👥

@ADITHYA-NS

@Avi-Nair

@CS_Amritha

@Anaswara-Suresh

@R-Sruthi