The Internet of Things (IoT) is widely adopted in industrial applications and smart infrastructures, enabling large-scale data collection and intelligent services. However, the distributed nature of IoT networks introduces significant energy challenges, as devices often operate under heterogeneous conditions and with highly variable energy availability. Ensuring the sustainability of such systems requires adaptive energy management strategies and localized processing techniques that reduce unnecessary energy usage while preserving reliable performance. Federated Learning (FL) has emerged as a promising paradigm for IoT, allowing the collaborative training of a global model on a server aggregating parameters from different devices, the clients, without exposing private data. Nevertheless, the repetitive communication and computation inherent to FL can exacerbate energy constraints. To minimize energy consumption, communication strategies such as model compression can be used to transmit updates, or client selection (CS), to select clients that can effectively improve the global model with their updates. Our work introduces SAGE , a novel energy efficient CS strategy tailored for distributed IoT scenarios. Unlike conventional methods, the proposed approach jointly considers the residual energy available at each client device, the Jensen–Shannon divergence (JSD) as a statistical measure of data dissimilarity, and the proportion of renewable energy in the client’s power supply. By combining these factors, the method not only improves energy balancing across the network but also promotes the prioritization of renewable energy usage, enhancing both system efficiency and environmental sustainability while maintaining competitive model accuracy. The code is available at https://github.com/MODAL-UNINA/SAGE . • Addresses energy and non-IID challenges in IoT Federated Learning. • SAGE leverages residual energy, data divergence, and green energy. • Improves FL sustainability in IoT without sacrificing accuracy.
Savoia et al. (Mon,) studied this question.