Generalizability across passive DVFS-capable SoCs

Determine whether the empirically calibrated, state-aware DVFS thermal control methodology generalizes to other DVFS-capable passively cooled systems-on-chip beyond the Raspberry Pi 5 Model B.

Background

The study evaluates the proposed scheduler only on a Raspberry Pi 5 Model B under a specific passive-cooling configuration. Because thermal dynamics, DVFS states, sensor behavior, and leakage characteristics can vary substantially across SoC architectures and cooling assemblies, transferability to other passive edge platforms is unresolved.

References

Generalizability to other DVFS-capable passive SoCs remains future work.

— Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled Hardware  (2609.04705 - Marasini et al., 4 Sep 2026) in Section 7, Limitations