Digital Twin (DT) technology has recently emerged as a powerful tool with the potential to revolutionize wireless systems as it enables accurate simulations, better decision-making, and tangible operational improvements. Prior studies on DT within the context of next generation wireless technologies has primarily focused on identifying potential use cases, application scenarios, and standardization challenges. However, the existing research lacks translating theoretical ideas into real-world applications. Our research, in this paper, contributes to the practical realization of DT technology in the context of 6G wireless networks, demonstrating its potential impact on network planning, performance, and user experience. In particular, we explore the construction, validation, and applications of DTs utilizing an indoor over-the-air (OTA) testbed powered by an in-house developed Next Generation Radio Access Network (NGRAN) that is fully compliant with 3rd Generation Partnership Project (3GPP) and Open RAN standards. First, we describe the steps that were followed to construct and validate a high-fidelity DT of our OTA testbed modeling both Radio Frequency (RF) environment and system components. Then, we demonstrate two pre-deployment use cases by explaining our extensive coverage estimation and network capacity planning OTA tests. Lastly, we also explore how DT enables practical machine learning solutions for post-deployment use cases and share our comprehensive OTA performance results, highlighting that our proposed mobility technique outperforms the classical approaches in terms of throughput and number of undesired handovers.

Radio signals are well suited for user localization because they are ubiquitous, can operate in the dark and maintain privacy. Many prior works learn mappings between channel state information (CSI) and position fully-supervised. However, that approach relies on position labels which are very expensive to acquire. In this work, this requirement is relaxed by using pseudo-labels during deployment, which are calculated from an inertial measurement unit (IMU). We propose practical algorithms for IMU double integration and training of the localization system. We show decimeter-level accuracy on simulated and challenging real data of 5G measurements. Our IMU-supervised method performs similarly to fully-supervised, but requires much less effort to deploy.

Intelligent integrated sensing and communication is one of key aspects of future wireless networks in which sensing can be leveraged to enhance communications and vice-versa. In this paper, we propose a novel sensing solution that can be used to represent an RF-environment. The proposed solution accounts for practical challenges such as limited time resolution due to limited bandwidth with no angle measurements while providing robustness to wireless propagation phenomena such as diffraction. Our proposed method leverages offline data collection during RF-mapping, and finds the location of virtual anchors (VAs), i.e., mirror images of a physical anchor w.r.t reflectors, through an iterative process called successive tap removal (STR). Afterwards, machine learning (ML) models are trained to predict dominant multipath components of the received wireless channel at a given location. Found VAs and their associated ML models stand for intermediate entities that represent an RF-environment. As an application, we use the developed models in the context of multipath assisted positioning to improve positioning accuracy in challenging indoor environments with heavy non-line-of-sight (NLoS) conditions. Finally, we extend our ideas to systems with multi-antenna transmitters and show that VA detection accuracy can be improved, bringing higher accuracy to the downstream positioning applications.

We present a neural network architecture for jointly learning user locations and environment mapping up to isometry, in an unsupervised way, from channel state information (CSI) values with no location information. The model is based on an encoder-decoder architecture. The encoder network maps CSI values to the user location. The decoder network models the physics of propagation by parametrizing the environment using virtual anchors. It aims at reconstructing, from the encoder output and virtual anchor location, the set of time of flights (ToFs) that are extracted from CSI using super-resolution methods. The neural network task is set prediction and is accordingly trained end-to-end. The proposed model learns an interpretable latent, i.e., user location, by just enforcing a physics-based decoder. It is shown that the proposed model achieves sub-meter accuracy on synthetic ray tracing based datasets with single anchor SISO setup while recovering the environment map up to 4cm median error in a 2D environment and 15cm in a 3D environment.

System level simulations of large 5G networks are essential to evaluate and design algorithms related to network issues such as scheduling, mobility management, interference management, and cell planning. In this paper, we look back to the idea of spatial indexing and its advantages, applications, and future potentials in accelerating large 5G network simulations. We introduce a multi-level inheritance based architecture which is used to index all elements of a heterogeneous network (HetNet) on a single geometry tree. Then, we define spatial queries to accelerate searches in distance, azimuth, and elevation. We demonstrate that spatial indexing can accelerate location-based searches by 3 orders of magnitude. Further, the proposed design is implemented as an open source platform freely available to all.

In this paper, we propose a generalized millimeter-Wave (mmWave) reconfigurable antenna multiple-input multiple-output (RA-MIMO) architecture that takes advantage of lens antennas. The considered antennas can generate multiple independent beams simultaneously using a single RF chain. This property, together with RA-MIMO, is used to combat small-scale fading and shadowing in mmWave bands. To this end, first, we derive a channel matrix for RA-MIMO. Then, we use rate-one space-time block codes (STBCs), together with phase-shifters at the receive reconfigurable antennas, to suppress the effect of small-scale fading. We consider two kinds of phase shifters: i) ideal which is error-free and ii) digital which adds quantization error. The goal of phase-shifters is to convert a complex-valued channel matrix into real-valued. Hence, it is possible to use rate-one STBCs for any dimension of RA-MIMO. We investigate diversity gain and derive an upper bound for symbol error rate in cases of ideal and digital phase-shifters. We show that RA-MIMO achieves the full-diversity gain with ideal phase-shifters and the full-diversity gain for digital phase-shifters when the number of quantization bits is higher than one. We investigate RA-MIMO in the presence of shadowing. Our analysis demonstrates that, by increasing the dimension of RA-MIMO, the outage probability decreases which means the effect of shadowing decreases. Numerical results verify our theoretical derivations.

Self-organizing networks (SONs) can help to manage the severe interference in dense heterogeneous networks (HetNets). Given their need to automatically configure power and other settings, machine learning is a promising tool for data-driven decision making in SONs. In this paper, a HetNet is modeled as a dense two-tier network with conventional macrocells overlaid with denser small cells (e.g. femto or pico cells). First, a distributed framework based on the multi-agent Markov decision process is proposed that models the power optimization problem in the network. Second, we present a systematic approach for designing a reward function based on the optimization problem. Third, we introduce Q-learning-based distributed power allocation algorithm (Q-DPA) as a self-organizing mechanism that enables the ongoing transmit power adaptation as new small cells are added to the network. Furthermore, the sample complexity of the Q-DPA algorithm to achieve ϵ-optimality with high probability is provided. We demonstrate, at the density of several thousands femtocells per km2, the required quality of service of a macrocell user can be maintained via the proper selection of independent or cooperative learning and appropriate Markov state models.

There is an increase in usage of smaller cells or femtocells to improve performance and coverage of next-generation heterogeneous wireless networks (HetNets). However, the interference caused by femtocells to neighboring cells is a limiting performance factor in dense HetNets. This interference is being managed via distributed resource allocation methods. However, as the density of the network increases so does the complexity of such resource allocation methods. Yet, unplanned deployment of femtocells requires an adaptable and self-organizing algorithm to make HetNets viable. As such, we propose to use a machine learning approach based on Q-learning to solve the resource allocation problem in such complex networks. By defining each base station as an agent, a cellular network is modeled as a multi-agent network. Subsequently, cooperative Q-learning can be applied as an efficient approach to manage the resources of a multi-agent network. Furthermore, the proposed approach considers the quality of service (QoS) for each user and fairness in the network. In comparison with prior work, the proposed approach can bring more than a four-fold increase in the number of supported femtocells while using cooperative Q-learning to reduce resource allocation overhead.

Dense deployment of small base stations (SBSs) is one of the main methods to meet the 5G data rate requirements. However, high density of independent SBSs will increase the interference within the network. To circumvent this interference, there is a need to develop self-organizing methods to manage the resources of the network. In this paper, we present a distributed power allocation algorithm based on multi-agent Q-learning in an interference-limited network. The proposed method leverages coordination through simple message passing between SBSs to achieve an optimal joint power allocation. Simulation results show the optimality of the proposed method for a two-user case.