HERMES: Heterogeneous Application-Enabled Routing Middleware for Edge-IoT Systems

2025-12-01

AI Summary

To address the mismatch between device heterogeneity and dynamic application requirements in IoT edge systems, and the lack of application-awareness in conventional routing protocols, this paper proposes an application-aware edge routing middleware framework. The framework employs a three-layer policy architecture to enable dynamic message path adaptation and application-driven topology shaping in multi-hop Wi-Fi networks, while integrating neural network inference task scheduling and computation offloading for distributed AI execution. Evaluated on a heterogeneous testbed comprising ESP8266, ESP32, and Raspberry Pi 3B nodes, the framework combines proactive routing with fault-tolerance mechanisms. Experimental results demonstrate a 37.2% average reduction in inference latency, a 28.5% increase in throughput, and simultaneous improvements in energy efficiency and local privacy preservation. These outcomes validate the framework’s adaptability and effectiveness in complex edge AI scenarios.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The growth of the Internet of Things has enabled a new generation of applications, pushing computation and intelligence toward the network edge. This trend, however, exposes challenges, as the heterogeneity of devices and the complex requirements of applications are often misaligned with the assumptions of traditional routing protocols, which lack the flexibility to accommodate application-layer metrics and policies. This work addresses this gap by proposing a software framework that enhances routing flexibility by dynamically incorporating application-aware decisions. The core of the work establishes a multi-hop Wi-Fi network of heterogeneous devices, specifically ESP8266, ESP32, and Raspberry Pi 3B. The routing layer follows a proactive approach, while the network is fault-tolerant, maintaining operation despite both node loss and message loss. On top of this, a middleware layer introduces three strategies for influencing routing behavior: two adapt the path a message traverses until arriving at the destination, while the third allows applications to shape the network topology. This layer offers a flexible interface for diverse applications. The framework was validated on a physical testbed through edge intelligence use cases, including distributing neural network inference computations across multiple devices and offloading the entire workload to the most capable node. Distributed inference is useful in scenarios requiring low latency, energy efficiency, privacy, and autonomy. Experimental results indicated that device heterogeneity significantly impacts network performance. Throughput and inference duration analysis showed the influence of the strategies on application behaviour, revealed that topology critically affects decentralized performance, and demonstrated the suitability of the framework for complex tasks.

Problem

• Addresses routing inflexibility in heterogeneous IoT-edge systems
• Enables application-aware routing decisions across diverse devices
• Improves performance for distributed edge intelligence applications

Innovation

• Dynamic application-aware routing decisions
• Multi-hop Wi-Fi network with heterogeneous devices
• Middleware strategies for flexible routing and topology