Clustering Algorithms on Low-Power and High-Performance Devices for Edge Computing Environments

Lapegna, Marco; Balzano, Walter; Meyer, Norbert; Romano, Diego

doi:10.3390/s21165395

Cited by 30 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These papers had more features available for consideration through the k-means algorithm, which led to an increase in the efficiency of using that algorithm in solving a specific problem. Other related research includes parallel clustering on low-power devices in edge computing environments [ 30 ] or methods for delivering sensor data and storing them in an IoT environment [ 31 , 32 ].…”

Section: Related Workmentioning

confidence: 99%

Parallel Processing of Sensor Data in a Distributed Rules Engine Environment through Clustering and Data Flow Reconfiguration

Alexandrescu

2023

Sensors

View full text Add to dashboard Cite

An emerging reality is the development of smart buildings and cities, which improve residents’ comfort. These environments employ multiple sensor networks, whose data must be acquired and processed in real time by multiple rule engines, which trigger events that enable specific actuators. The problem is how to handle those data in a scalable manner by using multiple processing instances to maximize the system throughput. This paper considers the types of sensors that are used in these scenarios and proposes a model for abstracting the information flow as a weighted dependency graph. Two parallel computing methods are then proposed for obtaining an efficient data flow: a variation of the parallel k-means clustering algorithm and a custom genetic algorithm. Simulation results show that the two proposed flow reconfiguration algorithms reduce the rule processing times and provide an efficient solution for increasing the scalability of the considered environment. Another aspect being discussed is using an open-source cloud solution to manage the system and how to use the two algorithms to increase efficiency. These methods allow for a seamless increase in the number of sensors in the environment by making smart use of the available resources.

show abstract

Section: Related Workmentioning

confidence: 99%

Parallel Processing of Sensor Data in a Distributed Rules Engine Environment through Clustering and Data Flow Reconfiguration

Alexandrescu

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In the future, benchmarking and extending the solution towards other types of GPUs will be of interest, specifically mobile and embedded type of compute devices in multi-node systems. It has been demonstrated that such devices offer less power demanding computing 40,41 and exploration of performance-power trade-offs using power capping might result in non-trivial configurations under more strict power limitations as compared to powerful GPUs in the traditional servers and HPC systems. Additionally, extending the implementation to use available CPU cores for computations will be performed, according to the concept presented in Appendix E.…”

Section: Data Availability Statementmentioning

confidence: 99%

A multithreaded CUDA and OpenMP based power‐aware programming framework for multi‐node GPU systems

Czarnul

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryIn the article, we have proposed a framework that allows programming a parallel application for a multi‐node system, with one or more graphical processing units (GPUs) per node, using an OpenMP+extended CUDA API. OpenMP is used for launching threads responsible for management of particular GPUs and extended CUDA calls allow to transfer data and launch kernels on local and remote GPUs. The framework hides inter‐node MPI communication from the programmer. For optimization, the implementation takes advantage of the MPI_THREAD_MULTIPLE mode allowing: multiple threads handling distinct GPUs as well as overlapping communication and computations transparently using multiple CUDA streams. The solution allows data parallelization across available GPUs in order to minimize execution time and supports a power‐aware mode in which GPUs are automatically selected for computations using a greedy approach in order not to exceed an imposed power limit. We have implemented and benchmarked three parallel applications including: finding the largest divisors; verification of the Collatz conjecture; finding patterns in vectors. These were tested on three various systems: a GPU cluster with 16 nodes, each with NVIDIA GTX 1060 GPU; a powerful 2‐node system—one node with 8 NVIDIA Quadro RTX 6000 GPUs, the second with 4 NVIDIA Quadro RTX 5000 GPUs; a heterogeneous environment with one node with 2 NVIDIA RTX 2080 and 2 nodes with NVIDIA GTX 1060 GPUs. We demonstrated effectiveness of the framework through execution times versus power caps within ranges of 100–1400 W, 250–3000 W, and 125–600 W for these systems respectively as well as gains from using two versus one CUDA streams per GPU. Finally, we have shown that for the testbed applications the solution allows to obtain high speed‐ups between 89.3% and 97.4% of the theoretically assessed ideal ones, for 16 nodes and 2 CUDA streams, demonstrating very good parallel efficiency.

show abstract

“…Power consumption during ML forecasts on edge is a critical issue due the limited power availability for IoT nodes. Therefore, power consumption optimization on the edge using ML is investigated in [27][28][29]. Also, in [30] ML is applied on time-series data from IoT sensors in order to predict failure in a slitting machine.…”

Section: Platforms Used On the Edgementioning

confidence: 99%

VAMPIRE: vectorized automated ML pre-processing and post-processing framework for edge applications

Daher

Ferrari²,

Muselli

et al. 2022

Computing

View full text Add to dashboard Cite

Machine learning techniques aim to mimic the human ability to automatically learn how to perform tasks through training examples. They have proven capable of tasks such as prediction, learning and adaptation based on experience and can be used in virtually any scientific application, ranging from biomedical, robotic, to business decision applications, and others. However, the lack of domain knowledge for a particular application can make feature extraction ineffective or even unattainable. Furthermore, even in the presence of pre-processed datasets, the iterative process of optimizing Machine Learning parameters, which do not translate from one domain to another, maybe difficult for inexperienced practitioners. To address these issues, we present in this paper a Vectorized Automated ML Pre-processIng and post-pRocEssing framework, approximately named (VAMPIRE), which implements feature extraction algorithms capable of converting large time-series recordings into datasets. Also, it introduces a new concept, the Activation Engine, which is attached to the output of a Multi Layer Perceptron and extracts the optimal threshold to apply binary classification. Moreover, a tree-based algorithm is used to achieve multi-class classification using the Activation Engine. Furthermore, the internet of things gives rise to new applications such as remote sensing and communications, so consequently applying Machine Learning to improve operation accuracy, latency, and reliability is beneficial in such systems. Therefore, all classifications in this paper were performed on the edge in order to reach high accuracy with limited resources. Moreover, forecasts were applied on three unrelated biomedical datasets, and on two other pre-processed urban and activity detection datasets. Features were extracted when required, and training and testing were performed on the Raspberry Pi remotely, where high accuracy and inference speed were achieved in every experiment. Additionally, the board remained competitive in terms of power consumption when compared with a laptop which was optimized using a Graphical Processing Unit.

show abstract

Clustering Algorithms on Low-Power and High-Performance Devices for Edge Computing Environments

Cited by 30 publications

References 35 publications

Parallel Processing of Sensor Data in a Distributed Rules Engine Environment through Clustering and Data Flow Reconfiguration

Parallel Processing of Sensor Data in a Distributed Rules Engine Environment through Clustering and Data Flow Reconfiguration

A multithreaded CUDA and OpenMP based power‐aware programming framework for multi‐node GPU systems

VAMPIRE: vectorized automated ML pre-processing and post-processing framework for edge applications

Contact Info

Product

Resources

About