Self-adapting real-time data ecosystems with autonomous multi-agent systems
Independent Researcher, USA.
Research Article
World Journal of Advanced Research and Reviews, 2022, 13(03), 593-607
Publication history:
Received on 06 February 2022; revised on 20 March 2022; accepted on 23 March 2022
Abstract:
As data ecosystems grow increasingly complex, traditional centralized control systems struggle to manage dynamic, large-scale workloads effectively. This paper introduces an autonomous multi-agent system (MAS) framework that uses reinforcement learning to enable self-adapting real-time data ecosystems. Each agent optimizes specific pipeline components, such as ingestion, transformation, and storage, while collaborating with other agents via a decentralized coordination protocol. Results from deployment in a smart city analytics platform demonstrate enhanced scalability and resilience, achieving a 40% improvement in system uptime and a 35% reduction in latency under dynamic workloads.
Keywords:
Real-Time Data Processing; Autonomous Multi-Agent Systems; Self-Adaptive Systems; Data Ecosystem Optimization; Distributed Intelligence
Full text article in PDF:
This paper has received CERTIFICATE OF BEST PAPER (Volume 13, Issue 3, Year 2022).
Copyright information:
Copyright © 2022 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0