ECO: Enabling Energy-Neutral IoT Devices Through Runtime Allocation of Harvested Energy

Energy harvesting offers an attractive and promising mechanism to power low-energy devices. However, it alone is insufficient enable energy-neutral operation, which can eliminate tedious battery charging replacement requirements. Achieving operation challenging since the uncertainties in harvested energy undermine quality of service To address this challenge, we present a runtime energy-allocation framework that optimizes utility target device under constraints using rollout algorithm, sequential approach solve dynamic optimization problems. The proposed uses efficient iterative algorithm compute initial allocations at beginning day. are then corrected every interval compensate for deviations from expected pattern. We evaluate solar motion modalities American Time Use Survey data 4772 different users. Compared prior techniques, achieves up 35% higher even energy-limited scenarios. Moreover, measurements on wearable prototype show has $1000\times $ smaller overhead than approaches with negligible loss utility.