Smart City Gnosys

Smart city article details

Title	Choosing Appropriate Ai-Enabled Edge Devices, Not The Costly Ones
ID_Doc	13948
Authors	Zhang Z.; Li F.; Lin C.; Wen S.; Liu X.; Liu J.
Year	2021
Published	Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS, 2021-December
DOI	http://dx.doi.org/10.1109/ICPADS53394.2021.00031
Abstract	Advances in Edge AI make it possible to achieve inference deep learning for emerging applications, e.g., smart transportation and smart city on the edge in real-time. Nowadays, different industry companies have developed several edge AI devices with various architectures. However, it is hard for application users to justify how to choose the appropriate edge-AI, due to the lack of benchmark testing results and testbeds specifically used to evaluate the system performance for those edge-AI systems. In this paper, we attempt to design a benchmark test platform for the edge-AI devices and evaluate six mainstream edge devices that are equipped with different computing powers and AI chip architectures. Throughput, power consumption ratio, and cost-effectiveness are chosen as the performance metrics for the evaluation process. Three classic deep learning workloads: object detection, image classification, and natural language processing are adopted with different batch sizes. The results show that under different batch sizes, compared with traditional edge devices, edge devices equipped with AI chips have out-performance in throughput, power consumption ratio, and cost-effectiveness by 134×, 57×, and 32×, respectively. From system perspective, our work not only demonstrates the effective AI capabilities of those edge AI devices, but also provide suggestions for AI optimization at edge in details. © 2021 IEEE.
Author Keywords	Deep Learning; Edge AI; System Performance

Similar Articles

Id	Similarity	Authors	Title	Published
41334	0.87	Xiao D.; Wang X.; Yang Z.; Huang C.	Partial Distributed Deep Learning Inference Model For Image Based Edge Device Cluster	Proceedings of 2024 8th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2024 (2025)
21762	0.865	Chandrasekaran S.; Athinarayanan S.; Masthan M.; Kakkar A.; Bhatnagar P.; Samad A.	Edge Computing Revolution: Unleashing Artificial Intelligence Potential In The World Of Edge Intelligence	Edge of Intelligence: Exploring the Frontiers of AI at the Edge (2025)
19453	0.864	Nair R.R.; Babu T.; Ebin P.M.	Developing Edge Ai For Embedded Systems	Embedded Artificial Intelligence: Real-Life Applications and Case Studies (2025)
5251	0.861	Hoffpauir K.; Simmons J.; Schmidt N.; Pittala R.; Briggs I.; Makani S.; Jararweh Y.	A Survey On Edge Intelligence And Lightweight Machine Learning Support For Future Applications And Services	Journal of Data and Information Quality, 15, 2 (2023)
41774	0.858	Bulut A.; Ozdemir F.; Bostanci Y.S.; Soyturk M.	Performance Evaluation Of Recent Object Detection Models For Traffic Safety Applications On Edge	ACM International Conference Proceeding Series (2023)
21792	0.856	Chandrasekaran S.; Athinarayanan S.; Masthan M.; Kakkar A.; Bhatnagar P.; Samad A.	Edge Intelligence Paradigm Shift On Optimizing The Edge Intelligence Using Artificial Intelligence State-Of-The-Art Models	Advancing Intelligent Networks Through Distributed Optimization (2024)
42119	0.854	Constantinou G.; Shahabi C.; Kim S.H.	Placement Of Dnn Models On Mobile Edge Devices For Effective Video Analysis	Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 (2021)
13852	0.852	Prashanthi S.K.; Kesanapalli S.A.; Simmhan Y.	Characterizing The Performance Of Accelerated Jetson Edge Devices For Training Deep Learning Models	Proceedings of the ACM on Measurement and Analysis of Computing Systems, 6, 3 (2022)
21736	0.851	Anchitaalagammai J.V.; Kavitha S.; Buurvidha R.; Santhiya T.S.; Roopa M.D.; Sankari S.S.	Edge Artificial Intelligence For Real-Time Decision Making Using Nvidia Jetson Orin, Google Coral Edge Tpu And 6G For Privacy And Scalability	Proceedings of International Conference on Visual Analytics and Data Visualization, ICVADV 2025 (2025)
14842	0.851	Grzesik P.; Mrozek D.	Combining Machine Learning And Edge Computing: Opportunities, Challenges, Platforms, Frameworks, And Use Cases	Electronics (Switzerland), 13, 3 (2024)