Federated learning enables intelligent-Source-Code-2021.zip

The Intelligent Reflecting Surface (IRS) is a ground-breaking technology that can boost the efficiencyof wireless data transmission systems. Specifically, the wireless signal transmitting environment isreconfigured by adjusting a large number of small reflecting units simultaneously. Therefore, intelligentreflecting surface (IRS) has been suggested as a possible solution for improving several aspects of futurewireless communication. However, individual nodes are empowered in IRS, but decisions and learning ofdata are still made by the centralized node in the IRS mechanism. Whereas, in previous works, theproblem of energy-efficient and delayed awareness learning IRS-assisted communications has beenlargely overlooked. The federated learning aware Intelligent Reconfigurable Surface Task Schedulingschemes (FL-IRSTS) algorithm is proposed in this paper to achieve high-speed communication withenergy and delay efficient offloading and scheduling. The training of models is divided into differentnodes. Therefore, the trained model will decide the IRSTS configuration that best meets the goals interms of communication rate. Multiple local models trained with the local healthcare fog-cloud networkfor each workload using federated learning (FL) to generate a global model. Then, each trained modelshared its initial configuration with the global model for the next training round. Each application’shealthcare data is handled and processed locally during the training process. Simulation results showthat the proposed algorithm’s achievable rate output can effectively approach centralized machinelearning (ML) while meeting the study’s energy and delay objectives.