In the modern era, a colossal volume of data is generated daily from diverse sources such as IoT networks, smartphones, and social networks. This project seeks to harness this data avalanche to derive actionable insights for businesses, services, and applications.
This initiative revolves around the establishment of a QoS-Based Performance Measurement system for efficient service management using cloud and big data technologies. Utilizing Azure in our primary infrastructure, Cluster 1, we provide a robust foundation for managing this influx of big data characterized by its high volume, diversity, and rapid velocity.
- Cluster Assessment (P1): Apply the K-Nearest Neighbors (KNN) algorithm to determine the presence and characteristics of data clusters.
- Clustering (P2): Partition data into distinct clusters for better management and subsequent processing.
- Cluster Validity (P3): Use a combination of KNN and other metrics to validate the relevance of the clusters and seek opportunities for optimization.
- Azure Integration: Cluster 1 harnesses Azure's capabilities to efficiently handle the challenges of big data.
- KNN Analysis: Embraces the unsupervised learning approach to tackle the limitations of traditional supervised machine learning methods.
- Performance Metrics Visualization: Translate data clusters into tangible metrics, offering stakeholders a comprehensive view of key parameters.
Team members : Akshat, Palak, Parijat, Parth