Machine Learning Methods for RSS-Based User Positioning in Distributed Massive MIMO

Prasad, K. N. R. Surya Vara; Hossain, Ekram; Bhargava, V.K.

doi:10.1109/twc.2018.2876832

Cited by 73 publications

(74 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Distributed massive MIMO is also considered an energy-efficient way to allocate resources. Compared to conventional massive MIMO, its throughput, energy efficiency, and channel modelling in a complex environment are noticeable [108]. Also, the beamforming in massive MIMO results in improved energy efficiency on the targeted coverage area [109].…”

Section: B Access Network 1) Massive Mimomentioning

confidence: 99%

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

et al. 2020

View full text Add to dashboard Cite

As the world pushes toward the use of greener technology and minimizes energy waste, energy efficiency in the wireless network has become more critical than ever. The next-generation networks, such as 5G, are being designed to improve energy efficiency and thus constitute a critical aspect of research and network design. The 5G network is expected to deliver a wide range of services that includes enhanced mobile broadband, massive machine-type communication and ultra-reliability, and low latency. To realize such a diverse set of requirement, 5G network has evolved as a multi-layer network that uses various technological advances to offer an extensive range of wireless services. Several technologies, such as software-defined networking, network function virtualization, edge computing, cloud computing, and small cells, are being integrated into the 5G networks to fulfill the need for diverse requirements. Such a complex network design is going to result in increased power consumption; therefore, energy efficiency becomes of utmost importance. To assist in the task of achieving energy efficiency in the network machine learning technique could play a significant role and hence gained significant interest from the research community. In this paper, we review the state-of-art application of machine learning techniques in the 5G network to enable energy efficiency at the access, edge, and core network. Based on the review, we present a taxonomy of machine learning applications in 5G networks for improving energy efficiency. We discuss several issues that can be solved using machine learning regarding energy efficiency in 5G networks. Finally, we discuss various challenges that need to be addressed to realize the full potential of machine learning to improve energy efficiency in the 5G networks. The survey presents a broad range of ideas related to machine learning in 5G that addresses the issue of energy efficiency in virtualization, resource optimization, power allocation, and incorporating enabling technologies of 5G can enhance energy efficiency.

show abstract

Section: B Access Network 1) Massive Mimomentioning

confidence: 99%

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

et al. 2020

View full text Add to dashboard Cite

show abstract

“…There is much work that uses the RSS [ 20 , 21 , 22 , 23 , 24 ], the ToA [ 25 , 26 , 27 ], or their combinations [ 28 ]. Some use machine learning (ML) based schemes such as neural networks with a single hidden layer [ 21 , 26 , 28 ], variants of neural networks (i.e., deep belief networks [ 22 , 29 ], deep neural networks [ 30 , 31 ], fuzzy neural networks [ 32 ], artificial synaptic networks [ 25 ]), Gaussian regression [ 33 ], support vector machines (SVM) [ 27 ], random decision forest [ 34 ], or combinations of them [ 20 ].…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning Approach to Position Estimation from Channel Impulse Responses

Niitsoo

Edelhäußer

Eberlein

et al. 2019

Sensors

View full text Add to dashboard Cite

Radio-based locating systems allow for a robust and continuous tracking in industrial environments and are a key enabler for the digitalization of processes in many areas such as production, manufacturing, and warehouse management. Time difference of arrival (TDoA) systems estimate the time-of-flight (ToF) of radio burst signals with a set of synchronized antennas from which they trilaterate accurate position estimates of mobile tags. However, in industrial environments where multipath propagation is predominant it is difficult to extract the correct ToF of the signal. This article shows how deep learning (DL) can be used to estimate the position of mobile objects directly from the raw channel impulse responses (CIR) extracted at the receivers. Our experiments show that our DL-based position estimation not only works well under harsh multipath propagation but also outperforms state-of-the-art approaches in line-of-sight situations.

show abstract

“…√ β u of different users are independent of each other. If d u is the distance between user u and the AP, b 0 is the path-loss at reference distance d 0 , α is the path-loss exponent, and z mk is the channel gain due to shadowing noise, we model the large-scale fading coefficient β u as [38]…”

Section: Protocol Model Analysismentioning

confidence: 99%

Multi-User MAC Protocol for WLANs in MmWave Massive MIMO Systems With Mobile Edge Computing

Zhao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Merging mobile edge computing (MEC) service with the wireless local area networks (WLANs) provides enormous benefits such as intensive computation capabilities. Access to high-speed WLANs has become an urgent challenge due to the fast rate of application development and user adoption. Providing increased wireless resources is one solution, but millimeter (mmWave) multiuser massive Multiple-Input Multiple-Output (MIMO) technology has also attracted attention due to a series of features such as high throughput, strong anti-interference ability, and small fading. Hence, exploring the potential of mmWave MIMO systems for WLAN could play a significant role in improving network performance, especially throughput. In this paper, we introduce mmWave and massive MIMO into traditional WLAN with MEC, which enables a large portion of spatial resources to be allocated among users, and mitigates inter-user interference. Moreover, we propose a novel media access control (MAC) protocol, named as LSMWN-MAC, to adapt to a series of unique characteristics of mmWave and massive MIMO, which adopts space division multiple access (SDMA) as one of the resource methods, taking full advantage of spatial resources. In addition, we modify the protocol and propose the MLSMWN-MAC protocol to allocate resources dynamically, a solution that is particularly suitable for scenes with 30-50 users. Simulation results show that compared to 802.11ad, the proposed two protocols can increase the saturated throughput by 4.7Gb/s and 5.4Gb/s respectively, which are close to the throughput upper limit of the mmWave MIMO system. Meanwhile, we observe that when the number of users exceeds the threshold, the performance of the LSMWN-MAC protocol using a static allocation method is superior to the MLSMWN-MAC protocol using a dynamic method. In other cases, the dynamic protocol has better performances. INDEX TERMS MEC, MAC protocol, massive MIMO, millimeter wave, resource pre-allocation.

show abstract

Machine Learning Methods for RSS-Based User Positioning in Distributed Massive MIMO

Cited by 73 publications

References 31 publications

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

A Deep Learning Approach to Position Estimation from Channel Impulse Responses

Multi-User MAC Protocol for WLANs in MmWave Massive MIMO Systems With Mobile Edge Computing

Contact Info

Product

Resources

About