A Platform for Edge Computing Based on Raspberry Pi Clusters

Miori, Lorenzo; Sanin, Julian; Helmer, Sven

doi:10.1007/978-3-319-60795-5_16

Cited by 12 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, we will build larger evaluation scenarios and use emulation techniques [34] to evaluate our solutions. Recently, a number of frameworks have been presented in literature [35] for container orchestration on a cluster of low-cost devices such as Raspberry Pi. These platforms provide an excellent tool to evaluate our solutions in more realistic conditions.…”

Section: Discussionmentioning

confidence: 99%

Docker Layer Placement for On-Demand Provisioning of Services on Edge Clouds

Smet

Dhoedt

Simoens

2018

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Driven by the increasing popularity of the microservice architecture, we see an increase in services with unknown demand pattern located in the edge network. Predeployed instances of such services would be idle most of the time, which is economically infeasible. Also, the finite storage capacity limits the amount of deployed instances we can offer. Instead, we present an on-demand deployment scheme using the Docker platform. In Docker, service images consist of layers, each layer adding specific functionality. This allows different services to reuse layers, avoiding cluttering the storages with redundant replicas. We propose a layer placement method which allows users to connect to a server, retrieve all necessary layers-possibly from multiple locations-and deploy an instance of the requested service within the desired response time. We search for the best layer placement which maximizes the satisfied demand given the storage and delay constraints. We developed an iterative optimization heuristic which is less exhaustive by dividing the global problem in smaller subproblems. Our simulation results show that our heuristic is able to solve the problem with less system resources. Last, we present interesting use-cases to use this approach in real-life scenarios.

show abstract

Section: Discussionmentioning

confidence: 99%

Docker Layer Placement for On-Demand Provisioning of Services on Edge Clouds

Smet

Dhoedt

Simoens

2018

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…The applicability of Raspberry Pi modules for edge computing applications has been considered in the literature for smart manufacturing [74], smart agriculture [75], and smart surveillance [76]. Nevertheless, when processing requirements increase, shortcomings in terms of performance have been reported [77]. Thus, the use of more computationally efficient algorithms (with lesser computational requirements) is of major importance.…”

Section: Methodsmentioning

confidence: 99%

Swarm Optimization for Energy-Based Acoustic Source Localization: A Comprehensive Study

Fé

Correia

Tomic

et al. 2022

Sensors

View full text Add to dashboard Cite

In the last decades, several swarm-based optimization algorithms have emerged in the scientific literature, followed by a massive increase in terms of their fields of application. Most of the studies and comparisons are restricted to high-level languages (such as MATLAB®) and testing methods on classical benchmark mathematical functions. Specifically, the employment of swarm-based methods for solving energy-based acoustic localization problems is still in its inception and has not yet been extensively studied. As such, the present work marks the first comprehensive study of swarm-based optimization algorithms applied to the energy-based acoustic localization problem. To this end, a total of 10 different algorithms were subjected to an extensive set of simulations with the following aims: (1) to compare the algorithms’ convergence performance and recognize novel, promising methods for solving the problem of interest; (2) to validate the importance (in convergence speed) of an intelligent swarm initialization for any swarm-based algorithm; (3) to analyze the methods’ time efficiency when implemented in low-level languages and when executed on embedded processors. The obtained results disclose the high potential of some of the considered swarm-based optimization algorithms for the problem under study, showing that these methods can accurately locate acoustic sources with low latency and bandwidth requirements, making them highly attractive for edge computing paradigms.

show abstract

“…In the experiments, we will use a Raspberry Pi 4 Model B with Quad core ARM Cortex-A72 64-bit 1.5GHz as the edge node. Raspberry Pi is one of the most popular devices 29,30 in edge computing due to its low cost and good performance. Regarding the GPU server used to offload computations from the edge node, it features an Intel(R) Xeon(R) CPU E5-2637 v2 3.50GHz with an NVIDIA V100 GPU.…”

Section: Methodsmentioning

confidence: 99%

Exploring the use of data compression for accelerating machine learning in the edge with remote virtual graphics processing units

Peñaranda

Reaño

Silla

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Internet of Things (IoT) devices are usually low performance nodes connected by low bandwidth networks. To improve performance in such scenarios, some computations could be done at the edge of the network. However, edge devices may not have enough computing power to accelerate applications such as the popular machine learning ones. Using remote virtual graphics processing units (GPUs) can address this concern by accelerating applications leveraging a GPU installed in a remote device. However, this requires exchanging data with the remote GPU across the slow network. To address the problem with the slow network, the data to be exchanged with the remote GPU could be compressed. In this article, we explore the suitability of using data compression in the context of remote GPU virtualization frameworks in edge scenarios executing machine learning applications. We use popular machine learning applications to carry out such exploration. After characterizing the GPU data transfers of these applications, we analyze the usage of existing compression libraries for compressing those data transfers to/from the remote GPU. Our exploration shows that transferring compressed data becomes more beneficial as networks get slower, reducing transfer time by up to 10 times. Our analysis also reveals that efficient integration of compression into remote GPU virtualization frameworks is strongly required.

show abstract

A Platform for Edge Computing Based on Raspberry Pi Clusters

Cited by 12 publications

References 10 publications

Docker Layer Placement for On-Demand Provisioning of Services on Edge Clouds

Docker Layer Placement for On-Demand Provisioning of Services on Edge Clouds

Swarm Optimization for Energy-Based Acoustic Source Localization: A Comprehensive Study

Exploring the use of data compression for accelerating machine learning in the edge with remote virtual graphics processing units

Contact Info

Product

Resources

About