Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Teng Moh
Second Advisor
Ramin Moazeni
Third Advisor
Melody Moh
Keywords
Content-based routing, Google Kubernetes Engine(GKE), resource optimization, load balancing, performance optimization, cluster-level load balancing
Abstract
Adaptive Metric-Driven Load Balancer is an innovative two-tier load-balancing system that uses NGINX and Prometheus to optimize resource allocation in specialized cloud clusters. This framework is built to give great performance and flexibility and runs on Google Kubernetes Engine (GKE), but it may also be deployed on local cloud environments for added security. The first tier of our system uses an NGINX-based load balancer to route incoming requests based on content type, sending traffic to hardware-optimized clusters for processing requests through specialized hardware. In our algorithm, the second tier dynamically modifies load distribution throughout each cluster by calculating pod weights based on CPU, memory, and network consumption on a regular basis. This adaptive weight distribution maximizes resource consumption and responsiveness, outperforming existing fixed-weight systems. In comparison to typical multi-component solutions, our system’s lightweight architecture minimizes configuration and management overhead while scaling fluidly to address dynamic traffic patterns. Its modular design paves a path for seamless integration with the existing cloud architectures providing organizations with a straightforward yet powerful solution for handling variable and unpredictable workloads. Our system provides high availability, optimal resource efficiency, and considerable performance increases under changing workloads due to its simplicity, scalability, and greater adaptability.
Recommended Citation
Malkani, Juhi Raju, "Adaptive Metric-Driven Load Balancing for Specialized Clusters using NGINX" (2024). Master's Projects. 1463.
https://scholarworks.sjsu.edu/etd_projects/1463