An Online Model to Minimize Energy Consumption of IoT Sensors in Smart Cities

The Internet of Things (IoT), which allows systems of billions or trillions of things, such as sensors, to communicate with each other over the Internet, is encountering several technical and application challenges. One of these challenges is that IoT sensors send redundant and self-similar data to the edge gateways consuming a large amount of energy and making it extremely difficult to obtain an appropriate network lifetime, which has become a bottleneck in scaling such applications. To address these issues, we propose a new solution based on powering sensors using artificial intelligence to make smart decisions about transmitting collected readings. We take advantage of autocorrelation (AC) to detect self-similarity and propose updating mechanism that employs deep reinforcement learning (RL). Our proposed model is a real-time model that can determine the redundant data and self-similarity and then make the smart decision about transmitting data. We evaluate our proposed solution using measurements obtained from Queanbeyan smart city, Australia, and available-public dataset and show that our proposed model can reduce the amount of transmitted data and minimize the power consumption of sensors.

Automated summary

The Internet of Things (IoT) is facing challenges related to data redundancy and energy consumption. To address this, we propose an AI-powered solution that utilizes autocorrelation and deep reinforcement learning to make smart decisions about transmitting data, thereby reducing data redundancy and minimizing sensor power consumption.