AI Framework for Energy-Efficient Smart City Environmental Monitoring
A new AI-driven framework aims to reduce energy consumption in smart city environmental monitoring. The framework, detailed in arXiv preprint 2605.22824, uses TinyML-enabled edge devices and context-aware adaptive decision-making to dynamically activate sensors based on spatiotemporal conditions, environmental statistics, and energy constraints. A utility function considers real-time conditions, sensor location, and remaining battery lifespan to optimize sensor activation. This approach addresses concerns about excessive energy use and redundant data collection in large-scale sensor deployments, potentially extending sensor lifespan and improving sustainability.
Key facts
- Framework uses TinyML-enabled edge devices
- Sensors activated dynamically based on spatiotemporal conditions
- Utility function considers real-time conditions, sensor location, battery lifespan
- Aims to reduce energy consumption and redundant data collection
- Preprint available on arXiv with ID 2605.22824
- Focuses on smart city environmental monitoring
Entities
Institutions
- arXiv