A survey of deep reinforcement learning application in 5G and beyond network slicing and virtualization

Location information is expected to be the key to meeting the needs of communication and context-aware services in 6G systems. User localization is achieved based on delay and/or angle estimation using uplink or downlink pilot signals. However, hardware impairments (HWIs) distort the signals at both the transmitter and receiver sides and thus affect the localization performance. While this impact can be ignored at lower frequencies where HWIs are less severe, modeling and analysis efforts are needed for 6G to evaluate the localization degradation due to HWIs. In this work, we model various types of impairments and conduct a misspecified Cramér-Rao bound analysis to evaluate the HWI-induced performance loss. Simulation results with different types of HWIs show that each HWI leads to a different level of degradation in angle and delay estimation performance.

https://zenodo.org/record/7078748/files/2022%20ICC%20workshop.pdf

MCRB-based Performance Analysis of 6G Localization under Hardware Impairments

Enhanced mobile broadband (eMBB) and ultra-reliable and low-latency communications (URLLC) are the two core services of the emerging fifth-generation (5G) systems. URLLC services require lower latency and high reliability, whereas eMBB services expect maximum data rates. Since 5G new radio (NR) aims to support heterogeneous services, the 3rd generation partnership project (3GPP) supports a highly flexible frame structure by introducing mixed numerology and mini-slot approaches. In these systems, the time slot is further divided into mini-slots. The coexistence of these two heterogeneous services leads to a challenging resource allocation problem. In this paper, we study the joint resource allocation problem of eMBB and URLLC schedulers to maximize the minimum expected achieved rate (MEAR) of eMBB users while satisfying URLLC users’ quality of service (QoS) constraints. The resource allocation of eMBB traffic occurs at time slot boundaries. In contrast, URLLC traffic is overlapped at the mini-slot timescale by adopting the non-orthogonal multiple access (NOMA) superposition technique. The suitable pairs of eMBB, URLLC users are evaluated using the one-one matching theory by inculcating fairness among eMBB users while satisfying the QoS parameters of URLCC users. The significance of the proposed approach over the baseline approaches is evaluated through numerical simulations in terms of the MEAR, mixed numerologies, and fairness scores among eMBB users. 

Coordinated Resource Allocations for eMBB and URLLC in 5G Communication Networks

Recent modifications to the air interface of 5G and beyond networks have improved the support for mixed enhanced mobile broadband (eMBB) and ultra-reliable and low-latency (URLLC) traffic. In particular, the concept of mini-slots has been introduced, and URLLC traffic is served at the mini-slot boundaries using superposition or puncturing of eMBB resources. This approach enables low latency for URLLC traffic, but it can incur a rate loss for eMBB traffic. To alleviate the latter, we propose a novel hybrid puncturing and superposition policy that jointly maximizes the minimum average throughput of eMBB traffic and the number of admitted URLLC users. Using sequential convex programming, a joint access technology selection, resource block, and power allocation problem is solved, where eMBB and URLLC user pairing and the decoding order in case of superposition are optimized based on channel state information. Our numerical results confirm that our proposed policy achieves a better trade-off between eMBB throughput and the number of admissible URLLC users when compared with existing solutions.

Hybrid Puncturing and Superposition Scheme for Joint Scheduling of URLLC and eMBB Traffic

Ultra-Reliable Low-Latency Communications (URLLC) are one of the service types supported by 5G. These are characterized by a high reliability of delivering packets within a short deadline. To fulfill these stringent requirements, a special care must be taken to determine the required data rate of a user, given its traffic intensity and channel conditions. Furthermore, with the network resources being limited and the competition between the users in the cell, an important question that arises is that of admission control, so that the admitted users do not experience performance deterioration. In this paper, we provide the analysis that leads to an admission control policy. We do this for two types of users in terms of their traffic intensities and channel conditions: 1) homogeneous users, and 2) heterogeneous users. We validate our results on a trace. Results show that the number of admitted users depends on the traffic intensity and the worst channel conditions. An increase in traffic intensity by 3 times can decrease the number of admitted users by almost 35%.

https://dl.acm.org/doi/pdf/10.1145/3479239.3485686

Admission Control for URLLC Users in 5G Networks

In this paper, we consider the problem of admission control in 5G networks where enhanced mobile broadband (eMBB) users and ultra-reliable low-latency communication (URLLC) users are coexisting URLLC users require low latency and high reliability while eMBB users require high data rates Thus, it is essential to control the admission of eMBB users while giving priority to all URLLC users in a network where both types of users are coexisting Our aim is to maximize the number of admitted eMBB users to the system with a guaranteed data rate while allocating resources to all URLLC users We formulated this as an $\ell_{0}$ minimization problem Since it is an NP-hard problem we have used approximation methods and sequential convex programming to obtain a suboptimal solution Numerically we have shown that the proposed algorithm achieves near-optimal performance Our algorithm is able to maximize the number of admitted eMBB users with an optimal allocation of resources while giving priority to all URLLC users

/pdf/admission-control-in-5g-networks-for-the-coexistence-of-embb-37spb7hdfq.pdf

Admission Control in 5G Networks for the Coexistence of eMBB-URLLC Users

Reconfigurable intelligent surface (RIS) is an emerging technology for improving performance in fifth-generation (5G) and beyond networks. Practically channel estimation of RIS-assisted systems is challenging due to the passive nature of the RIS. The purpose of this paper is to introduce a deep learning-based, low complexity channel estimator for the RIS-assisted multi-user single-input-multiple-output (SIMO) orthogonal frequency division multiplexing (OFDM) system with hardware impairments. We propose an untrained deep neural network (DNN) based on the deep image prior (DIP) network to denoise the effective channel of the system obtained from the conventional pilot-based least-square (LS) estimation and acquire a more accurate estimation. We have shown that our proposed method has high performance in terms of accuracy and low complexity compared to conventional methods. Further, we have shown that the proposed estimator is robust to interference caused by the hardware impairments at the transceiver and RIS.

Untrained DNN for Channel Estimation of RIS-Assisted Multi-User OFDM System with Hardware Impairments

In this paper, we consider the problem of admission control in 5G networks where enhanced mobile broadband (eMBB) users and ultra-reliable low-latency communication (URLLC) users are coexisting. URLLC users require low latency and high reliability while eMBB users require high data rates. Thus, it is essential to control the admission of eMBB users while giving priority to all URLLC users in a network where both types of users are coexisting. Our aim is to maximize the number of admitted eMBB users to the system with a guaranteed data rate while allocating resources to all URLLC users. We formulated this as an l_0 minimization problem. Since it is an NP-hard problem we have used approximation methods and sequential convex programming to obtain a suboptimal solution. Numerically we have shown that the proposed algorithm achieves near-optimal performance. Our algorithm is able to maximize the number of admitted eMBB users with an optimal allocation of resources while giving priority to all URLLC users.

Nipuni Uthpala Ginige

Papers

Admission Control in 5G Networks for the Coexistence of eMBB-URLLC Users

Untrained DNN for Channel Estimation of RIS-Assisted Multi-User OFDM System with Hardware Impairments

Admission Control in 5G Networks for the Coexistence of eMBB-URLLC Users

Untrained DNN for Channel Estimation of RIS-Assisted Multi-User OFDM System with Hardware Impairments