Researchers have developed novel hardware-agnostic scheduling strategies for batteryless Internet of Things (IoT) devices. These methods, a Reinforcement Learning (RL) agent and an Approximated Prediction (AP) approach, manage unpredictable workloads without prior energy information. Evaluations using real-world solar data and LoRa transmission profiles show distinct trade-offs: AP offers high throughput, RL provides tunable balancing, and AsTAR excels at pacing. The study suggests these advanced strategies are crucial for systems with small energy buffers, while larger buffers can utilize simpler static policies. AI
IMPACT These methods could enable more reliable and complex applications on energy-constrained IoT devices.
RANK_REASON The cluster contains an academic paper detailing novel methods for managing task execution in batteryless IoT devices.
- alphaXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- IArxiv
- Influence Flower
- Internet of Things
- LoRa
- reinforcement learning
- ScienceCast
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
