Multiple-group narrow band Internet of Things optimization based on deep learning
Narrow Band Internet of Things (NB-IoT) is a technology based on cellular which presents different configuration depending on different requirement and supports massive IoT devices to get access in groups. A specific configuration will set the number of resource assigned to different groups, using f...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/141135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Narrow Band Internet of Things (NB-IoT) is a technology based on cellular which presents different configuration depending on different requirement and supports massive IoT devices to get access in groups. A specific configuration will set the number of resource assigned to different groups, using for transmitting data and random access. If the amount of devices in the network is not massive, the sufficient resource will maintain good performance. However, the number of devices in the NB-IoT usually leads to a RACH overload, the performance is hence degraded. This project aims to optimize the configuration which increases the average number of successful devices which can get access and transmit data simultaneously. A deep learning algorithm is proposed, which is based on deep neural network and multi agents. The result shows that the proposed approach has better performance than the traditional conventional approach, reflecting on the value of repetition and RAO. |
|---|