University of Oulu

Traffic classification and prediction, and fast uplink grant allocation for machine type communications via support vector machines and long short-term memory

Saved in:
Author: Eldeeb, Eslam1
Organizations: 1University of Oulu, Faculty of Information Technology and Electrical Engineering, Communications Engineering
Format: ebook
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 1.4 MB)
Pages: 43
Persistent link:
Language: English
Published: Oulu : E. Eldeeb, 2020
Publish Date: 2020-12-17
Thesis type: Master's thesis (tech)
Tutor: Alves, Hirley
Reviewer: Alves, Hirley
Morais de Lima, Carlos


The current random access (RA) allocation techniques suffer from congestion and high signaling overhead while serving machine type communication (MTC) applications. Therefore, 3GPP has introduced the need to use fast uplink grant (FUG) allocation. This thesis proposes a novel FUG allocation based on support vector machine (SVM) and long short-term memory (LSTM). First, MTC devices are prioritized using SVM classifier. Second, LSTM architecture is used to predict activation time of each device. Both results are used to achieve an efficient resource scheduler in terms of the average latency and total throughput. Furthermore, a set of correction techniques is introduced to overcome the classification and prediction errors. The Coupled Markov Modulated Poisson Process (CMMPP) traffic model is applied to compare the proposed FUG allocation to other existing allocation techniques. In addition, an extended traffic model based CMMPP is used to evaluate the proposed algorithm in a more dense network. Our simulation results show the proposed model outperforms the existing RA allocation schemes by achieving the highest throughput and the lowest access delay when serving the target massive and critical MTC applications.

see all

Copyright information: © Eslam Eldeeb, 2020. This publication is copyrighted. You may download, display and print it for your own personal use. Commercial use is prohibited.