Energy Efficient Multicast Routing Protocol Using FL-Based Optimal Route Selection in IoT-Enabled MANETs With RIS and CF-mMIMO

In this paper, we propose a novel energy-efficient multicast routing protocol using federated learning (FL)-based optimal route selection (FLEMR) in internet of things (IoT)-enabled mobile ad hoc networks (MANETs) with reconfigurable intelligent surfaces (RIS) and cell-free massive MIMO (CF-mMIMO). The proposed FLEMR protocol integrates cross-layer design and federated learning (FL) to improve the network and physical layers performance. Specifically, the cross-layer design combines information from the physical layer, such as mobility (speed and direction), position, remaining energy, and spectral efficiency, with information from the network layer (hop count) to maximize a cost function for optimal route selection. RISs are deployed to improve the strength of the received signals, thus enhancing overall connectivity. To further enhance energy efficiency during data transmission, we design an adaptive transmit power allocation technique that dynamically divides the transmission area into regions and zones based on receiver positions. Furthermore, we design the FL framework to solve two problems: infer the optimal weight values of the cost function to select the multicast route and decide the optimal region and zone for adaptive transmit power allocation. The simulation results show that the proposed FLEMR protocol, integrated with the cross-layer federated learning-based clustering (CFLC) protocol under the reference point group mobility (RPGM) model, establishes more robust multicast routes, demonstrating superior performance in terms of connectivity, scalability, and energy efficiency compared to benchmark protocols.