EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Understanding Energy Efficiency of AI Deployments in IoT-Driven Smart Cities

Salvatore Bramante, Filippo Ferrandino, Alessandro Cilardo

IoT · 08.03.2026 · 7 (1) · 27

DOI: 10.3390/iot7010027 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IoT, online erschienen am 08.03.2026. Verfasst von Salvatore Bramante und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union—NextGenerationEU.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The pervasive adoption of AI and AIoT applications at the network edge presents both opportunities and challenges for smart cities. With a focus on the energy efficiency of AI in urban environments, this paper provides a systematic comparative analysis of representative edge hardware platforms, i.e., embedded GPUs, FPGAs, and ultra-low-power microcontroller-/sensor-class devices, assessing their suitability for AI workloads in IoT-driven smart city infrastructures. The evaluation, based on direct characterization of diverse neural networks and relevant datasets, quantifies computational performance and energy behavior through inference latency, throughput, and energy/per inference measurements. Across the evaluated network–board pairs, the measured inference power spans several orders of magnitude, ranging from 0.1–10 mW for ultra-low-power Intelligent Sensor Processing Units (ISPUs) up to 1–10 W for embedded GPUs, highlighting the wide design space between the least and most power-demanding configurations. Results indicate that embedded GPUs provide a favorable performance-to-power ratio for computationally intensive workloads, while MCU/ISPU-class solutions, despite throughput limitations, offer compelling advantages in ultra-low-power scenarios when combined with quantization and pruning, making them well-suited for distributed sensing and actuation typical of smart city deployments. Overall, this comparative analysis guides hardware selection for heterogeneous, sustainable AI-enabled urban services.

Förderung

  • European Union—NextGenerationEU

Zitieren

APA

Bramante, S., Ferrandino, F., & Cilardo, A. (2026). Understanding Energy Efficiency of AI Deployments in IoT-Driven Smart Cities. IoT, 7(1), 27. https://doi.org/10.3390/iot7010027

Vancouver

Bramante S, Ferrandino F, Cilardo A. Understanding Energy Efficiency of AI Deployments in IoT-Driven Smart Cities. IoT. 2026;7(1):27. doi:10.3390/iot7010027

BibTeX
@article{Bramante2026,
  author = {Bramante, Salvatore and Ferrandino, Filippo and Cilardo, Alessandro},
  title = {Understanding Energy Efficiency of AI Deployments in IoT-Driven Smart Cities},
  journal = {IoT},
  year = {2026},
  volume = {7},
  number = {1},
  pages = {27},
  doi = {10.3390/iot7010027}
}
Kostenlos starten →