Routing Optimization Based on Distributed Intelligent Network Softwarization for the Internet of Things

2024-04-08

ACM Symposium on Applied Computing

AI Summary

To address routing optimization challenges in resource-constrained, large-scale IoT networks characterized by heterogeneous devices and scalability limitations, this paper proposes a synergistic routing architecture integrating Software-Defined Networking (SDN), Network Function Virtualization (NFV), and Federated Deep Reinforcement Learning (FDRL). We innovatively design a distributed controller framework coupled with an FDRL-based joint decision-making mechanism, enabling efficient edge-side collaborative routing while preserving data privacy. Simulation results demonstrate significant improvements over conventional approaches: 32% reduction in end-to-end latency, 27% decrease in node energy consumption, and 21% increase in network throughput. The proposed architecture markedly enhances energy efficiency, real-time performance, and scalability in resource-limited IoT environments, establishing a novel paradigm for decentralized intelligent routing.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The Internet of Things (IoT) establishes connectivity between billions of heterogeneous devices that provide a variety of essential everyday services. The IoT faces several challenges, including energy efficiency and scalability, that require consideration of enabling technologies such as network softwarization. This technology is an appropriate solution for IoT, leveraging Software Defined Networking (SDN) and Network Function Virtualization (NFV) as two main techniques, especially when combined with Machine Learning (ML). Although many efforts have been made to optimize routing in softwarized IoT, the existing solutions do not take advantage of distributed intelligence. In this paper, we propose to optimize routing in softwarized IoT networks using Federated Deep Reinforcement Learning (FDRL), where distributed network softwarization and intelligence (i.e., FDRL) join forces to improve routing in constrained IoT networks. Our proposal introduces the combination of two novelties (i.e., distributed controller design and intelligent routing) to meet the IoT requirements (mainly performance and energy efficiency). The simulation results confirm the effectiveness of our proposal compared to the conventional counterparts.

Problem

• IoT energy consumption
• network scalability
• distributed network optimization

Innovation

• Federated Deep Reinforcement Learning
• IoT Network Optimization
• Distributed Control