A Commodity SBC-Edge Cluster for Smart Cities

Abstract

The commodity Single Board Computers (SBCs) are increasingly becoming powerful and can execute standard operating systems and mainstream workloads. In the context of cloud-based smart city applications, SBCs can be utilized as Edge computing devices reducing the network communication. In this paper, we investigate the design and implementation of a SBC based edge cluster (SBC-EC) framework for a smart parking application. Since SBCs are resource constrained devices, we devise a container-based framework for a lighter foot-print. Kubernetes was used as an orchestration tool to orchestrate various containers in the framework. To validate our approach, we implemented a proof-of-concept of the SBC based Edge cluster for a smart parking application, as a possible IoT use-case. Our implementation shows that, the use of SBC devices at the edge of a cloud based smart parking application is a cost effective and low energy, green computing solution. The proposed framework can be extended to similar cloud-based applications in the context of a smart city.

Optimizing Heterogeneous Task Allocation for Edge Compute Micro Clusters Using PSO Metaheuristic

“…Qureshi et al [16] presented a SBC-based cluster for smart parking management system in context of smart city. Specifically, they constructed a small edge cluster using different SBC devices to monitor parking plots and analyse daily data.…”

A Multi-Layer LoRaWAN Infrastructure for Smart Waste Management

“…Apart from waste management, edge computing could generally find a much broader employment within smart cities where multiple facilities (e.g., public lighting, parking structures, energy consumption in buildings, waste management, carpooling, tourism and taxi cabs) may be created, run, maintained and enhanced. This was the scope that motivated [ 37 , 38 ]: the former dealt with the problem by leveraging on Single Board Computers (SBCs), while the latter performed the aforesaid tasks by setting up a comprehensive infrastructure which was developed and tested in the city of Messina, Italy.…”

Lifespan and energy-oriented load balancing algorithms across sets of nodes in Green Edge Computing

“…Single Board Computers (SBCs) that are generally small in size and have non-negligible computational power, are often suitable to be put in strategic positions, for example, in a Smart City [1] thus concretizing the Edge Computing paradigm. Moving the computation to the Edge enables the possibility of drastically reducing processing latency since it avoids the necessity of sending the data to process in the cloud.…”

“…As anticipated, Edge nodes are characterized by two essential traits: (i) they require low operation power, usually ranging from about 10W (Raspberry Pi 4 1 ) to 60W (nVidia Jetson AGX Orin 64GB 2 ) and (ii) they have non-neglibible computing power which can also be used to run deep learning inference [4], [5]. We indeed imagine, as a use case, that each node is coupled with a camera and then it has to perform some deep learning task on the captured images or videos.…”