Super macro base station (SMBS) positioning for performance optimization using deep learning for 5G HAPS system | |
| Author | Barai, Joyeeta Rani |
| Call Number | AIT Thesis no.TC-21-03 |
| Subject(s) | Deep Learning Mobile communication systems 5G mobile communication systems |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Telecommunications |
| Publisher | Asian Institute of Technology |
| Abstract | HAPS can be utilized as aerial SMBSs to serve the existing terrestrial infrastructure to keep a continuous wireless network connection in various disaster scenarios depending on the environmental uncertainties. The process becomes complicated if the mobility and locations of users are unknown, uncertain and random. Increasing the number of HAPS to provide connectivity for the users with different movements might work but that makes the network too much expensive and almost impractical. Hence, optimization of the available HAPS’s positions can solve the problem cost effectively. However, if the user locations are not predicted for the positioning of the available HAPS in advance, positioning of HAPS can not be done efficiently. Hence, Deep Machine Learning can be used to solve this problem. Moreover, if the positioning can be done a month ahead, it can be proved to be more efficient. In this thesis work report, the the process of positioning the HAPS-SMBSs is divided into two stages. Stage 1 is the prediction or forecasting of ground user locations and stage 2 is the HAPS-SMBS positioning to optimize the performance depending on the values of stage 1. Two types of modified Deep Neural Networks- GRU-RNN and LSTM-RNN are used to find the best predicted results for stage 1 and optimization was done for the HAPS positioning in stage 2 with minimum delay and loss. The results show that if the user locations are predicted accurately, by solving the optimization problem it is possible to provide faster and reliable continuous 5G connection with better performance to the users in cases of both normal and disaster scenarios. |
| Year | 2021 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Telecommunications (TC) |
| Chairperson(s) | Attaphongse Taparugssanagorn |
| Examination Committee(s) | Teerapat Sanguankotchakorn;Poompat Saengudomlert |
| Scholarship Donor(s) | His Majesty the King’s Scholarships (Thailand) |
| Degree | Thesis (M. Sc.) - Asian Institute of Technology, 2021 |