2026-05-28T12:22:26Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/225112026-02-03T11:23:28Zcom_10630_2254col_10630_37953

An open source framework based on Kafka-ML for Distributed DNN inference over the Cloud-to-Things continuum Torres, Daniel R. Martín-Fernández, Cristian Díaz, Manuel Rubio-Muñoz, Bartolomé Computación Inteligencia artificial The current dependency of Artificial Intelligence (AI) systems on Cloud computing implies higher transmission latency and bandwidth consumption. Moreover, it challenges the real-time monitoring of physical objects, e.g., the Internet of Things (IoT). Edge systems bring computing closer to end devices and support time-sensitive applications. However, Edge systems struggle with state-of-the-art Deep Neural Networks (DNN) due to computational resource limitations. This paper proposes a technology framework that combines the Edge-Cloud architecture concept with BranchyNet advantages to support fault-tolerant and low-latency AI predictions. The implementation and evaluation of this framework allow assessing the benefits of running Distributed DNN (DDNN) in the Cloud-to-Things continuum. Compared to a Cloud-only deployment, the results obtained show an improvement of 45.34% in the response time. Furthermore, this proposal presents an extension for Kafka-ML that reduces rigidness over the Cloud-to-Things continuum managing and deploying DDNN. 2021-07-01T11:25:34Z 2021-07-01T11:25:34Z 2021 2021-06-16 journal article Journal of Systems Architecture, Volume 118, September 2021, 102214 https://hdl.handle.net/10630/22511 https://doi.org/10.1016/j.sysarc.2021.102214 eng open access Elsevier