HERMES: Heterogeneous Application-Enabled Routing Middleware for Edge-IoT Systems
Jéssica Consciência, António Grilo
TL;DR
HERMES tackles the inefficiency of traditional routing in heterogeneous Edge-IoT by introducing an application-aware, multi-hop routing framework with a middleware layer that allows applications to steer routing decisions. It combines a proactive routing core, a HAL for device heterogeneity, and three middleware strategies (Inject, Publish/Subscribe, Topology) to adapt routing and even network structure to application needs. Validated on a physical testbed, the framework demonstrates distributed and centralized NN use cases, showing topology-aware configurations can significantly reduce inference latency and improve throughput, while ensuring fault tolerance in dynamic edge environments. The work offers practical insights into how edge networks can balance computation placement, data flows, and topology design to enable complex, low-latency, and privacy-preserving edge intelligence.
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.