ROCK-CNN: a Distributed RockPro64-based Convolutional Neural Network Cluster for IoT. Verification and Performance Analysis
| Autor: | Vladislav Shmatkov, Maksim Lapaev, Dmitriy Mouromtsev, Rezeda Khaydarova, Vladislav Fishchenko |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
iot
Service (systems architecture) single-board computer Artificial neural network Computer science Distributed computing Node (networking) intelligent pseudo real-time architecture deep learning convolutional neural network computer clusters Convolutional neural network lcsh:Telecommunication rockpro64 performance testing Single-board computer lcsh:TK5101-6720 Server Scalability Software architecture |
| Zdroj: | FRUCT Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 26, Iss 1, Pp 174-181 (2020) |
| DOI: | 10.23919/fruct48808.2020.9087457 |
| Popis: | The paper is dedicated to optimization of machine learning and neural networks applications by replacing common servers with Single Board Computer (SBC) clusters to minimize mounting and service expenses, simplify node mounting process and organize parallel computing in IoT applications. Authors focus on former experience of using distributed computing, mainly, light-weight and cost-optimized SBCs to classify use-cases, then, choose an appropriate hardware platform enabling sufficient data processing and easy hot-replacing of nodes. This task requires organizing an efficient software architecture to make use of advantages of SBCs. A comparison for various SBSs is presented. Authors suggest their formerly-designed architecture with changes allowing using it for neural network applications. Authors pay attention to thorough parameter examination based on numerous tests. Parameter timelines are presented in the paper. The paper describes a number of test-cases to validate the efficiency of suggested architecture based on common use-cases. Performance analysis and cluster scalability potential estimation are conducted as well to estimate an efficient number of nodes required for future tasks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|