Print Email Facebook Twitter Sustainability of Edge AI at Scale Title Sustainability of Edge AI at Scale: An empirical study on the sustainability of Edge AI in terms of energy consumption Author van der Noort, Rover (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Cruz, Luis (mentor) Martínez-Fernández, Silverio (mentor) van Deursen, A. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science Date 2024-05-08 Abstract Edge AI is an architectural deployment tactic that brings AI models closer to the user and data, relieving internet bandwidth usage and providing low latency and privacy. It remains unclear how this tactic performs at scale, since the distribution overhead could impact the total energy consumption. We identify four architectural scalability factors that could impact the energy consumption of AI: environment, optimisation, throughput, and overhead. The latter consists of downloading, verification, and updating the model over time. This work performs an empirical study on the sustainability of Edge AI compared to Cloud AI at scale in terms of energy consumption. For the environment variable, energy consumption measurement experiments are run on a cloud device and multiple edge devices, various quantized models for optimisation, and various throughput levels per hour. We simulate the distribution overhead and combine the results with the measurements to find the holistic energy efficiency of each architectural strategy. We find that all four variables impact energy consumption, but the main contributors are environment, throughput, and overhead. We observe that Edge AI is most energy-efficient in low-distribution, low-demand scenarios, whereas in high-distribution, high-demand scenarios Cloud AI is better optimised and outperforms Edge AI in energy efficiency. This means that developers depending on their use case and the project’s scalability need to consider these quality attributes for the most sustainable architectural solution. Subject Sustainable software engineeringGreen AIQuantizationScalabilityEdge-cloud architectureEnergy-aware software To reference this document use: http://resolver.tudelft.nl/uuid:78ac2503-426c-406b-a88f-8c0ed1abe0c0 Embargo date 2024-05-08 Bibliographical note https://zenodo.org/records/11065939 Reproducability package https://github.com/rvandernoort/local-vs-cloud Repository of code used for this study Part of collection Student theses Document type master thesis Rights © 2024 Rover van der Noort Files PDF Sustainability_of_Edge_AI ... Thesis.pdf 3.78 MB Close viewer /islandora/object/uuid:78ac2503-426c-406b-a88f-8c0ed1abe0c0/datastream/OBJ/view