Edge Computing-enabled Predictive Maintenance for Energy Management Systems in Buildings

Irsyad N Haq, Edi Leksono, Justin Pradipta

Abstract


Abstract: Predictive maintenance plays a crucial role in ensuring the reliable operation of energy management systems (EMS) in buildings. This paper investigates the integration of edge computing for enabling predictive maintenance in EMS. By deploying edge devices within the building infrastructure, we propose a framework that enables real-time data collection, local data processing, and predictive analytics. We demonstrate how edge computing can facilitate early fault detection, proactive maintenance scheduling, and reduced system downtime. Through extensive experiments and case studies, we evaluate the effectiveness of our approach in enhancing system reliability and reducing maintenance costs. We discuss the integration challenges, resource optimization, and scalability considerations associated with deploying edge-enabled predictive maintenance solutions in building EMS. Our findings contribute to the advancement of intelligent maintenance strategies for building energy management.

References


Al Faruque, Mohammad Abdullah, and Korosh Vatanparvar. ‘Energy Management-as-a-Service over Fog Computing Platform’. IEEE Internet of Things Journal, vol. 3, no. 2, IEEE, 2015, pp. 161–169.

Guleria, Charu, et al. ‘A Survey on Mobile Edge Computing: Efficient Energy Management System’. 2021 Innovations in Energy Management and Renewable Resources (52042), IEEE, 2021, pp. 1–4.

Maatoug, Abdelfettah, et al. ‘Fog Computing Framework for Location-Based Energy Management in Smart Buildings’. Multiagent and Grid Systems, vol. 15, no. 1, IOS Press, 2019, pp. 39–56.

Vatanparvar, Korosh, and Mohammad Abdullah Al Faruque. ‘Energy Management as a Service over Fog Computing Platform’. Proceedings of the ACM/IEEE Sixth International Conference on Cyber-Physical Systems, 2015, pp. 248–249.


Refbacks

  • There are currently no refbacks.




Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.