Fingerprint-based localization in massive MIMO systems using machine learning and deep learning methods
|Authors:||Moosavi, Seyedeh Samira|
|Advisor:||Fortier, Paul; Chouinard, Jean-Yves|
|Abstract:||As wireless communication networks are growing into 5G, an enormous amount of data will be produced and shared on the new platform, which can be employed in promoting new services. Location information of mobile terminals (MTs) is remarkably useful among them, which can be used in different use cases of inquiry and information services, community services, personal tracking, as well as location-aware communications. Nowadays, although the Global Positioning System (GPS) offers the possibility to localize MTs, it has poor performance in urban areas where a direct line-of-sight (LoS) to the satellites is blocked by many tall buildings. Besides, GPS has a high power consumption. Consequently, the ranging based localization techniques, which are based on radio signal information received from MTs such as time-of-arrival (ToA), angle-of-arrival (AoA), and received signal strength (RSS), are not able to provide satisfactory localization accuracy. Therefore, it is a notably challenging problem to provide precise and reliable location information of MTs in complex environments with rich scattering and multipath propagation. Fingerprinting (FP)-based machine learning methods are widely used for localization in complex areas due to their high reliability, cost-efficiency, and accuracy and they are flexible to be used in many systems. In 5G networks, besides accommodating more users at higher data rates with better reliability while consuming less power, high accuracy localization is also required in 5G networks. To meet such a challenge, massive multiple-input multiple-output (MIMO) systems have been introduced in 5G as a powerful and potential technology to not only improve spectral and energy efficiency using relatively simple processing but also provide an accurate locations of MTs using a very large number of antennas combined with high carrier frequencies. There are two types of massive MIMO (M-MIMO), distributed and collocated. Here, we aim to use the FP-based method in M-MIMO systems to provide an accurate and reliable localization system in a 5G wireless network. We mainly focus on the two extremes of the M-MIMO paradigm. A large collocated antenna array (i.e., collocated M-MIMO ) and a large geographically distributed antenna array (i.e., distributed M-MIMO). Then, we extract signal and channel features from the received signal in M-MIMO systems as fingerprints and propose FP-based models using clustering and regression to estimate MT's location. Through this procedure, we are able to improve localization performance significantly and reduce the computational complexity of the FP-based method.|
|Document Type:||Thèse de doctorat|
|Open Access Date:||5 July 2021|
|Collection:||Thèses et mémoires|
All documents in CorpusUL are protected by Copyright Act of Canada.