Research Article

Multi-Tenant Resource Management in Serverless Distributed Data Systems: Efficient Workload Isolation, Burst Capacity Planning, and Auto-Scaling

Authors

  • Sudhir Saxena Anna University, College of Engineering, Guindy, Chennai, India

Abstract

Contemporary enterprise environments increasingly embrace serverless computing paradigms for distributed data processing, creating unprecedented challenges in multi-tenant resource management frameworks. The article presents a comprehensive framework addressing workload isolation, burst capacity planning, and adaptive auto-scaling mechanisms within serverless distributed data systems. Traditional resource allocation strategies prove inadequate for dynamic serverless environments where multiple tenants simultaneously compete for computational resources while maintaining strict isolation guarantees. The proposed framework integrates predictive auto-scaling algorithms with tenant-aware workload scheduling and advanced resource isolation policies to address fundamental limitations in current serverless platforms. Machine learning-based prediction models enable accurate demand forecasting across diverse workload patterns, from batch ETL processing to real-time stream analytics. The frame employs a multi-dimensional profiling approach, landing resource consumption patterns and temporal gesture characteristics across different tenant configurations. Perpetration strategies ensure platform-independent operation across AWS Lambda, Google Cloud Functions, and Azure Functions while maintaining compatibility with deployment patterns. Experimental confirmation demonstrates substantial advancements in job completion times, outturn, and cost effectiveness compared to platform-native bus-scaling mechanisms. The adaptive isolation mechanisms successfully balance security requirements with resource efficiency objectives, maintaining tenant boundaries even under extreme load conditions. Performance validation across diverse geographic regions confirms framework effectiveness with minimal latency variations and consistent throughput characteristics, establishing global scalability essential for distributed enterprise applications requiring stringent isolation assurances. Keywords: Multi-tenant architecture, serverless computing, resource management, auto-scaling mechanisms, workload isolation, burst capacity planning.

Article information

Journal

Journal of Computer Science and Technology Studies

Volume (Issue)

7 (8)

Pages

533-539

Published

2025-08-04

How to Cite

Sudhir Saxena. (2025). Multi-Tenant Resource Management in Serverless Distributed Data Systems: Efficient Workload Isolation, Burst Capacity Planning, and Auto-Scaling. Journal of Computer Science and Technology Studies, 7(8), 533-539. https://doi.org/10.32996/jcsts.2025.7.8.61

Downloads

Views

3

Downloads

4

Keywords:

Multi-Tenant Resource Management; Serverless Distributed Data Systems; Workload Isolation, Burst Capacity Planning; Auto-Scaling