Machine Learning Based Modulation and Coding Scheme Selection
(2019) EITM02 20191Department of Electrical and Information Technology
- Abstract
- In wireless communication, resources like bandwidth and energy are scarce and extremely valuable, any system should serve as many users as possible while preserving high Quality of Service (QoS) for the best user experience. Accordingly, the Base Station (BS) has the responsibility to optimally schedule its resources to the users based on the available information. Consequently, the whole process of scheduling is truly demanding and requires high complex calculations from the overall system. Hence, the request of more sophisticated and effective methods is substantial in order to minimize the challenges of scheduling.
This master’s thesis focuses on the Modulation and Coding Scheme (MCS) selection in a Time Division Duplex (TDD) based... (More) - In wireless communication, resources like bandwidth and energy are scarce and extremely valuable, any system should serve as many users as possible while preserving high Quality of Service (QoS) for the best user experience. Accordingly, the Base Station (BS) has the responsibility to optimally schedule its resources to the users based on the available information. Consequently, the whole process of scheduling is truly demanding and requires high complex calculations from the overall system. Hence, the request of more sophisticated and effective methods is substantial in order to minimize the challenges of scheduling.
This master’s thesis focuses on the Modulation and Coding Scheme (MCS) selection in a Time Division Duplex (TDD) based mobile network. The main objective is the simplification and optimization of the downlink process at the base station by predicting the MCS index for a single User Equipment (UE), using Machine Learning (ML). The developed machine learning algorithms is in accordance with the LTE-Advanced Pro (release 12,13,14) lookup tables and is based on similar parameters. For a given frame,this thesis targets predicting the MCS index of future subframes. Thus, the resource allocation process for independent users is becoming quicker and easier for the BS. The results are based on laboratory measurements at Ericsson, where the collection of data logs for several stationary UEs, occurred on a network testing environment and their different cell characteristics investigated thoroughly.
Concluding, the accuracy level which the ML classification algorithm achieved was approximately 50 percent. Therefore, the prediction accuracy can be described as sufficient for the BS to decrease the computation complexity and energy consumption during the downlink process. The data logs that the project took into account cannot be generalized for real-time scenarios as it is explained in detail finally. (Less) - Popular Abstract
- Machine Learning (ML), as part of Artificial Intelligence (AI), is the most promising candidate to improve to a whole new perspective our modern world. Hundreds million of dollars are being invested worldwide on this technology, either by private companies or even by entire nations, to make all the existing systems smarter, more efficient and low-cost. An expected economic growth of approximately $40 billion by 2025, from $1.29 billion in 2016, is anticipated by the global ML market [1].
The best way to define ML is given by Arthur Samuel in 1959 and is the ability that computers learn without being explicitly programmed [2]. Nowadays, the majority of Internet users are handling and operating, in one way or another, several ML... (More) - Machine Learning (ML), as part of Artificial Intelligence (AI), is the most promising candidate to improve to a whole new perspective our modern world. Hundreds million of dollars are being invested worldwide on this technology, either by private companies or even by entire nations, to make all the existing systems smarter, more efficient and low-cost. An expected economic growth of approximately $40 billion by 2025, from $1.29 billion in 2016, is anticipated by the global ML market [1].
The best way to define ML is given by Arthur Samuel in 1959 and is the ability that computers learn without being explicitly programmed [2]. Nowadays, the majority of Internet users are handling and operating, in one way or another, several ML algorithms, and possibly most of them without being experts in the subject. Google, Netflix and YouTube are some examples of well-known technology giants that are deploying ML methods on their platforms, and we are using them in our everyday life. Whenever someone is typing for a new TV show or a song in a search engine, an ML algorithm is performing a historical exploration in the vast databases in order to, either suggest or find the matching word of the user’s wish. Moreover, ML methods are expanded and deployed by various industries, as the vehicular, medical, retail, marketing etc. Therefore, ML is going to upgrade the lives of people in a easier, and more beneficial way than it used to be.
In this thesis, the focus is on integrating this technology in telecommunication, specifically at the Base Station (BS), to decrease the scheduling process and increase the quality of service for the users. Based on the users’ behavior, the BS will be able to allocate its resource in an efficient way. Hence, under ML usage, complexity and energy consumption are decreased, while still providing the users with their required resources. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8992560
- author
- Chamat, Michel LU and Kodra, Bersi Dimitrios LU
- supervisor
- organization
- course
- EITM02 20191
- year
- 2019
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Machine Learning, ML, Modulation and Coding Scheme, MCS, Scheduler, Scheduling
- report number
- LU/LTH-EIT 2019-716
- language
- English
- id
- 8992560
- date added to LUP
- 2019-08-20 11:12:43
- date last changed
- 2019-08-20 11:12:43
@misc{8992560,
abstract = {{In wireless communication, resources like bandwidth and energy are scarce and extremely valuable, any system should serve as many users as possible while preserving high Quality of Service (QoS) for the best user experience. Accordingly, the Base Station (BS) has the responsibility to optimally schedule its resources to the users based on the available information. Consequently, the whole process of scheduling is truly demanding and requires high complex calculations from the overall system. Hence, the request of more sophisticated and effective methods is substantial in order to minimize the challenges of scheduling.
This master’s thesis focuses on the Modulation and Coding Scheme (MCS) selection in a Time Division Duplex (TDD) based mobile network. The main objective is the simplification and optimization of the downlink process at the base station by predicting the MCS index for a single User Equipment (UE), using Machine Learning (ML). The developed machine learning algorithms is in accordance with the LTE-Advanced Pro (release 12,13,14) lookup tables and is based on similar parameters. For a given frame,this thesis targets predicting the MCS index of future subframes. Thus, the resource allocation process for independent users is becoming quicker and easier for the BS. The results are based on laboratory measurements at Ericsson, where the collection of data logs for several stationary UEs, occurred on a network testing environment and their different cell characteristics investigated thoroughly.
Concluding, the accuracy level which the ML classification algorithm achieved was approximately 50 percent. Therefore, the prediction accuracy can be described as sufficient for the BS to decrease the computation complexity and energy consumption during the downlink process. The data logs that the project took into account cannot be generalized for real-time scenarios as it is explained in detail finally.}},
author = {{Chamat, Michel and Kodra, Bersi Dimitrios}},
language = {{eng}},
note = {{Student Paper}},
title = {{Machine Learning Based Modulation and Coding Scheme Selection}},
year = {{2019}},
}