Adaptive Beamforming and Energy-Efficient Resource Allocation for Sustainable 6G THz Networks
- p1090-1104
The rollout of sixth-generation (6G) wireless networks is likely to transform communication systems in terms of speed, latency, and connectivity. This paper investigates adaptive beamforming schemes for communications in the Terahertz (THz) range. Additionally, it investigates the possibility of resource management that minimizes energy consumption. The problem of communication in the THz range is mitigated by the AMAB approach which varies beam angles and uses Reconfigurable Intelligent Surface (RIS) technology to improve signal delivery. This overcomes the drawback of THz frequencies' large attenuation and short range, which are a hindrance to effective high-rate data transmission needed in 6G applications. The Energy Adaptive Resource Allocation with Predictive Optimization (EARAPO) algorithm applies Machine Learning approaches to resource allocation and management of network demand by forecasting traffic trends. Such a predictive strategy supports enhanced resource utilization through the elasticity of network technology which leads to a reduction of energy cost with zero impact on the quality of service (QoS). The Adaptive Meta-Surface Assisted Beamforming (AMAB) algorithm with RIS consistently improves SINR across various numbers of multiuser equipment (UE), even in network-intensive scenarios. The power consumption efficiency of EARAPO was also superior while adaptation to power-hungry variants of both algorithms resulted in power consumption being moderated until later in the escalation of network requirements. These algorithms are quite effective in enhancing the quality of signals, making better use of resources and reducing energy usage in the upcoming wireless networks. All these studies open up a perspective for the future of sustainable and high-performance wireless technologies.