Minimizing the Carbon Footprint in LoRa-Based IoT Networks: A Machine Learning Perspective on Gateway Positioning

The Internet of Things (IoT) is gaining significant attention for its ability to digitally transform various sectors by enabling seamless connectivity and data exchange. However, deploying these networks is challenging due to the need to tailor configurations to diverse application requirements. To date, there has been limited focus on examining and enhancing the carbon footprint (CF) associated with these network deployments. In this study, we present an optimization framework leveraging machine learning techniques to minimize the carbon footprint (CF) associated with IoT multi-hop network deployments by varying the placement of the required gateways. Additionally, we establish a direct comparison between our proposed machine learning method and the integer linear program (ILP) approach. Our findings reveal that placing gateways using neural networks can achieve a 14% reduction in the reduction in the CF for simple networks compared to those not using optimization for gateway placement. The integer linear program (ILP) method could reduce the CF by 16.6% for identical networks, although it incurs a computational cost more than 250 times higher, which has its own environmental impact. Furthermore, we highlight the superior scalability of machine learning techniques, particularly advantageous for larger networks, as discussed in our concluding remarks.