This study proposes two hardware-agnostic dynamic scheduling strategies, a model-free Reinforcement Learning agent and an on-the-fly Approximated Prediction method, to manage volatile energy in batteryless IoT systems without prior task profiles. Evaluated against adaptive and static baselines using a custom simulation framework, the research highlights distinct operational trade-offs for different system constraints.
- The Approximated Prediction approach delivers lightweight, near-oracle task throughput.
- The Reinforcement Learning agent provides tunable balancing between survival and execution.
- The AsTAR baseline excels at execution pacing across long energy gaps.
- Devices with larger energy buffers can efficiently rely on simpler static policies rather than advanced strategies.
These findings indicate that while advanced dynamic scheduling is critical for resilience in severely constrained systems with small capacitors, less computationally expensive static policies remain efficient for devices with larger energy buffers.