Sensing and Storing Less: A MARL-based Solution for Energy Saving in Edge Internet of Things

TL;DR

The paper tackles the rising energy cost of expansive IoT data in edge networks by introducing Senses, an online, MARL-based solution that reduces data generation and balances device lifetimes through sensor-level deduplication, controller-level data partitioning, and cross-layer load distribution. It employs MAPPO with strong/weak agent roles, centralized training, and GAE-based policy optimization to dynamically adjust sensor coverage and data routing in heterogeneous edge environments. Empirical results from simulations and a Raspberry Pi/STM32 testbed show notable energy savings (e.g., $11.37\%$ on control devices) and longer network lifetimes ($\approx 20\%$ more operational duration), alongside reduced data duplication and robust handling of fixed sensors. The work demonstrates the practical potential of cross-layer, online MARL approaches to green edge IoT and provides a plug-in framework that can augment existing energy optimization techniques.

Abstract

As the number of Internet of Things (IoT) devices continuously grows and application scenarios constantly enrich, the volume of sensor data experiences an explosive increase. However, substantial data demands considerable energy during computation and transmission. Redundant deployment or mobile assistance is essential to cover the target area reliably with fault-prone sensors. Consequently, the ``butterfly effect" may appear during the IoT operation, since unreasonable data overlap could result in many duplicate data. To this end, we propose Senses, a novel online energy saving solution for edge IoT networks, with the insight of sensing and storing less at the network edge by adopting Muti-Agent Reinforcement Learning (MARL). Senses achieves data de-duplication by dynamically adjusting sensor coverage at the sensor level. For exceptional cases where sensor coverage cannot be altered, Senses conducts data partitioning and eliminates redundant data at the controller level. Furthermore, at the global level, considering the heterogeneity of IoT devices, Senses balances the operational duration among the devices to prolong the overall operational duration of edge IoT networks. We evaluate the performance of Senses through testbed experiments and simulations. The results show that Senses saves 11.37% of energy consumption on control devices and prolongs 20% overall operational duration of the IoT device network.

Figures (14)

• Figure 1: An example of edge-assistant IoT networks.
• Figure 2: Edge IoT network workflow.
• Figure 3: The framework of MARL-based solution at the edge.
• Figure 4: The control strategy on fixed-coverage sensors (Left) and adjustable sensors (Right).
• Figure 5: The testbed platform with $4$ Raspberry Pi devices and $6$ STM32F407ZG microcontrollers.