2021/06/21 by Abdelrahman S. Elgamal, Elgamal, Abdelrahman S., Osama Zwaid Alsulami +7 · 2 citations
Engineering · #FOS: Computer and information sciences #FOS: Electrical engineering #Networking and Internet Architecture (cs.NI) #Optical Wireless Communication Technologies #Photonic and Optical Devices #Semiconductor Lasers and Optical Devices #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2106.11368
openalex publication_date 2021/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Vertical Cavity Surface Emitting Lasers (VCSELs) have demonstrated\nsuitability for data transmission in indoor optical wireless communication\n(OWC) systems due to the high modulation bandwidth and low manufacturing cost\nof these sources. Specifically, resource allocation is one of the major\nchallenges that can affect the performance of multi-user optical wireless\nsystems. In this paper, an optimisation problem is formulated to optimally\nassign each user to an optical access point (AP) composed of multiple VCSELs\nwithin a VCSEL array at a certain time to maximise the signal to interference\nplus noise ratio (SINR). In this context, a mixed-integer linear programming\n(MILP) model is introduced to solve this optimisation problem. Despite the\noptimality of the MILP model, it is considered impractical due to its high\ncomplexity, high memory and full system information requirements. Therefore,\nreinforcement Learning (RL) is considered, which recently has been widely\ninvestigated as a practical solution for various optimization problems in\ncellular networks due to its ability to interact with environments with no\nprevious experience. In particular, a Q-learning (QL) algorithm is investigated\nto perform resource management in a steerable VCSEL-based OWC systems. The\nresults demonstrate the ability of the QL algorithm to achieve optimal\nsolutions close to the MILP model. Moreover, the adoption of beam steering,\nusing holograms implemented by exploiting liquid crystal devices, results in\nfurther enhancement in the performance of the network considered.\n