Integrating the multitude of emerging internet of things (IoT) applications with diverse requirements in beyond fifth generation (B5G) networks necessitates the coexistence of enhanced mobile broadband (eMBB) and ultra-reliable lowlatency communication (URLLC) services. However, bandwidth limited and congested sub-6GHz bands are incapable of fulfilling this coexistence. In this paper, we consider a reconfigurable intelligent surface (RIS)-aided wideband terahertz (THz) communication system to this end. In specific, we formulate a resource management problem, aiming at jointly optimizing the reflection coefficient of the RIS elements and the transmit power of the base station, as well as the wideband THz resource block allocation. To solve this problem, we adopt a supervised learning approach relying on optimization, deep learning and ensemble learning methods. Simulation results show that for an RIS of size 11×11, up to 49% spectral efficiency gain is achieved for the eMBB service compared to the counterparts, while ensuring the reliability and latency requirements of the URLLC service. Further, the ensemble learning model can perform real-time resource management at the expense of up to 1% performance loss, compared to the optimization approach.
Passive beamforming in reconfigurable intelligent surfaces (RISs) enables a feasible and efficient way of communication when the RIS reflection coefficients are precisely adjusted. In this paper, we present a framework to track the RIS reflection coefficients with the aid of deep learning from a time-series prediction perspective in a terahertz (THz) communication system. The proposed framework achieves a two-step enhancement over the similar learning-driven counterparts. Specifically, in the first step, we train a liquid state machine (LSM) to track the historical RIS reflection coefficients at prior time steps (known as a time-series sequence) and predict their upcoming time steps. We also fine-tune the trained LSM through Xavier initialization technique to decrease the prediction variance, thus resulting in a higher prediction accuracy. In the second step, we use ensemble learning technique which leverages on the prediction power of multiple LSMs to minimize the prediction variance and improve the precision of the first step. It is numerically demonstrated that, in the first step, employing the Xavier initialization technique to fine-tune the LSM results in at most 26% lower LSM prediction variance and as much as 46% achievable spectral efficiency (SE) improvement over the existing counterparts, when an RIS of size 11×11 is deployed. In the second step, under the same computational complexity of training a single LSM, the ensemble learning with multiple LSMs degrades the prediction variance of a single LSM up to 66% and improves the system achievable SE at most 54%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.