International Journal of Leading Research Publication

E-ISSN: 2582-8010   •   Impact Factor: 9.56

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 6 Issue 6 June 2025 Submit your research before last 3 days of to publish your research paper in the issue of June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 6 Issue 6
June 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Adaptive Reinforcement Learning for Dynamic Resource Allocation in Cloud Data Pipelines

Author(s) Srikanth Jonnakuti
Country United States
Abstract The explosive growth in data-driven applications has increased the need for real-time analytics of data, requiring extremely efficient and scalable resource provisioning within cloud and edge computing setups. Conventional resource allocation methods do not effectively respond to changing workloads, leading to wastage of resources or decline in performance. This work introduces a reinforcement learning (RL)-driven auto-scaling framework tailored for streaming analytics platforms with an emphasis on optimizing ETL and inference clusters. Using deep and multi-agent RL agents, the system learns about workload patterns and anticipates scaling resources to ensure latency service-level objectives (SLOs) while reducing operational expenses. The framework integrates intelligent policy learning from past and real-time metrics to facilitate context-aware decision-making in heterogeneous multi-cloud and edge environments. Large-scale simulation and real-world validations illustrate that the developed RL framework outperforms static and rule-based methods in latency conformity, energy efficiency, and cost-effectiveness. The architecture facilitates joint optimization of task offloading, network routing, and resource orchestration. The employment of meta-RL also increases the model's resilience in time-sensitive situations. Experiments validate that adaptive RL policies work efficiently in real-time streaming environments where workload volatility is significant. This research advances the ever-growing stream of research on autonomous cloud infrastructure management and provides the foundation for smart orchestration in exa-scale distributed systems.
Field Engineering
Published In Volume 4, Issue 2, February 2023
Published On 2023-02-04
Cite This Adaptive Reinforcement Learning for Dynamic Resource Allocation in Cloud Data Pipelines - Srikanth Jonnakuti - IJLRP Volume 4, Issue 2, February 2023. DOI 10.70528/IJLRP.v4.i2.1556
DOI https://doi.org/10.70528/IJLRP.v4.i2.1556
Short DOI https://doi.org/g9nhqm
View / Download PDF File

Share this



CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJLRP DOI prefix is
10.70528/IJLRP

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 5 Isu 12 Cover Page Vol 5 Isu 11 Cover Page Vol 5 Isu 10

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJLRP
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijlrp.com