Multi-agent LoRaWAN Network for End-of-Life Management of Electric Vehicle Batteries

• Celia Garrido-Hidalgo ^[1] ; Luis Roda-Sanchez ^[1] ; Teresa Olivares ^[1] ; F. Javier Ramírez ^[1] ; Antonio Fernández-Caballero ^[1]
  1. [1] Universidad de Castilla-La Mancha

     Universidad de Castilla-La Mancha

     Ciudad Real, España

     
• Localización: Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence: 9th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2022, Puerto de la Cruz, Tenerife, Spain, May 31 – June 3, 2022, Proceedings, Part II / José Manuel Ferrández Vicente (dir. congr.), José Ramón Álvarez Sánchez (dir. congr.), Félix de la Paz López (dir. congr.), Hojjat Adeli (aut.), 2022, ISBN 978-3-031-06527-9, págs. 505-514
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • The LoRaWAN standard has become one of the most extended Internet-of-Things technologies in both academia and industry due to its long communication range and high energy efficiency. Given the fast-growth expectations of the reverse logistics sector —partly caused by an imminent number of electric-vehicle batteries to be disposed of in the coming years—, the adoption of wireless machine-type communications promises several benefits towards products’ end-of-life monitoring and diagnosis. While LoRaWAN seems a suitable technology for this purpose, its scalability limitations need to be first resolved. To shed light on this matter, this work presents a multi-agent approach to support an efficient allocation of network resources in time-slotted communications running on top of LoRaWAN’s MAC layer. By considering different slot-length computation strategies, the multi-agent network components interact with joining LoRaWAN devices and assign them to the most convenient transmission schedule which, in turn, depends on both application and hardware-specific constraints. Our results point to network scalability improvements ranging from 43.22% to 86.54% depending on the slot-length computation strategy being applied