Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning for Digital Twins

Digital twin (DT) platforms are increasingly regarded as a promising technology for controlling, optimizing, and monitoring complex engineering systems such as next-generation wireless networks. An important challenge in adopting DT solutions is their reliance on data collected offline, lacking direct access to the physical environment. This limitation is particularly severe in multi-agent systems, for which conventional multi-agent reinforcement (MARL) requires online interactions with the environment. A direct application of online MARL schemes to an offline setting would generally fail due to the epistemic uncertainty entailed by the limited availability of data. In this work, we propose an offline MARL scheme for DT-based wireless networks that integrates distributional RL and conservative Q-learning to address the environment's inherent aleatoric uncertainty and the epistemic uncertainty arising from limited data. To further exploit the offline data, we adapt the proposed scheme to the centralized training decentralized execution framework, allowing joint training of the agents' policies. The proposed MARL scheme, referred to as multi-agent conservative quantile regression (MA-CQR) addresses general risk-sensitive design criteria and is applied to the trajectory planning problem in drone networks, showcasing its advantages.

On the Spectral Efficiency of Indoor Wireless Networks with a Rotary Uniform Linear Array

Contemporary wireless communication systems rely on Multi-User Multiple-Input Multiple-Output (MU-MIMO) techniques. In such systems, each Access Point (AP) is equipped with multiple antenna elements and serves multiple devices simultaneously. Notably, traditional systems utilize fixed antennas, i.e., antennas without any movement capabilities, while the idea of movable antennas has recently gained traction among the research community. By moving in a confined region, movable antennas are able to exploit the wireless channel variation in the continuous domain. This additional degree of freedom may enhance the quality of the wireless links, and consequently the communication performance. However, movable antennas for MU-MIMO proposed in the literature are complex, bulky, expensive and present a high power consumption. In this paper, we propose an alternative to such systems that has lower complexity and lower cost. More specifically, we propose the incorporation of rotation capabilities to APs equipped with Uniform Linear Arrays (ULAs) of antennas. We consider the uplink of an indoor scenario where the AP serves multiple devices simultaneously. The optimal rotation of the ULA is computed based on estimates of the positions of the active devices and aiming at maximizing the per-user mean achievable Spectral Efficiency (SE). Adopting a spatially correlated Rician channel model, our numerical results show that the rotation capabilities of the AP can bring substantial improvements in the SE in scenarios where the line-of-sight component of the channel vectors is strong. Moreover, our proposed system is robust against imperfect positioning estimates.

Traffic Learning and Proactive UAV Trajectory Planning for Data Uplink in Markovian IoT Models

The age of information (AoI) is used to measure the freshness of the data. In IoT networks, the traditional resource management schemes rely on a message exchange between the devices and the base station (BS) before communication which causes high AoI, high energy consumption, and low reliability. Unmanned aerial vehicles (UAVs) as flying BSs have many advantages in minimizing the AoI, energy-saving, and throughput improvement. In this paper, we present a novel learning-based framework that estimates the traffic arrival of IoT devices based on Markovian events. The learning proceeds to optimize the trajectory of multiple UAVs and their scheduling policy. First, the BS predicts the future traffic of the devices. We compare two traffic predictors: the forward algorithm (FA) and the long short-term memory (LSTM). Afterward, we propose a deep reinforcement learning (DRL) approach to optimize the optimal policy of each UAV. Finally, we manipulate the optimum reward function for the proposed DRL approach. Simulation results show that the proposed algorithm outperforms the random-walk (RW) baseline model regarding the AoI, scheduling accuracy, and transmission power.

Energy-Efficient Analog Beamforming for RF-WET with Charging Time Constraint

Internet of Things (IoT) sustainability may hinge on radio frequency wireless energy transfer (RF-WET). However, energy-efficient charging strategies are still needed, motivating our work. Specifically, this letter proposes a time division scheme to efficiently charge low-power devices in an IoT network. For this, a multi-antenna power beacon (PB) drives the devices' energy harvesting circuit to the highest power conversion efficiency point via energy beamforming, thus achieving minimum energy consumption. Herein, we adopt the analog multi-antenna architecture due to its low complexity, cost, and energy consumption. The proposal includes a simple yet accurate model for the transfer characteristic of the energy harvesting circuit, enabling the optimization framework. The results evince the effectiveness of our RF-WET strategy over a benchmark scheme where the PB charges all the IoT devices simultaneously. Furthermore, the performance increases with the number of PB antennas.

Energy Efficiency Optimization for Subterranean LoRaWAN Using A Reinforcement Learning Approach: A Direct-to-Satellite Scenario

The integration of subterranean LoRaWAN and non-terrestrial networks (NTN) delivers substantial economic and societal benefits in remote agriculture and disaster rescue operations. The LoRa modulation leverages quasi-orthogonal spreading factors (SFs) to optimize data rates, airtime, coverage and energy consumption. However, it is still challenging to effectively assign SFs to end devices for minimizing co-SF interference in massive subterranean LoRaWAN NTN. To address this, we investigate a reinforcement learning (RL)-based SFs allocation scheme to optimize the system's energy efficiency (EE). To efficiently capture the device-to-environment interactions in dense networks, we proposed an SFs allocation technique using the multi-agent dueling double deep Q-network (MAD3QN) and the multi-agent advantage actor-critic (MAA2C) algorithms based on an analytical reward mechanism. Our proposed RL-based SFs allocation approach evinces better performance compared to four benchmarks in the extreme underground direct-to-satellite scenario. Remarkably, MAD3QN shows promising potentials in surpassing MAA2C in terms of convergence rate and EE.

Age Minimization in Massive IoT via UAV Swarm: A Multi-agent Reinforcement Learning Approach

In many massive IoT communication scenarios, the IoT devices require coverage from dynamic units that can move close to the IoT devices and reduce the uplink energy consumption. A robust solution is to deploy a large number of UAVs (UAV swarm) to provide coverage and a better line of sight (LoS) for the IoT network. However, the study of these massive IoT scenarios with a massive number of serving units leads to high dimensional problems with high complexity. In this paper, we apply multi-agent deep reinforcement learning to address the high-dimensional problem that results from deploying a swarm of UAVs to collect fresh information from IoT devices. The target is to minimize the overall age of information in the IoT network. The results reveal that both cooperative and partially cooperative multi-agent deep reinforcement learning approaches are able to outperform the high-complexity centralized deep reinforcement learning approach, which stands helpless in large-scale networks.

Trade-Off Between Beamforming and Macro-Diversity Gains in Distributed mMIMO

Industry and academia have been working towards the evolution from Centralized massive Multiple-Input Multiple-Output (CmMIMO) to Distributed mMIMO (DmMIMO) architectures. Instead of splitting a coverage area into many cells, each served by a single Base Station equipped with several antennas, the whole coverage area is jointly covered by several Access Points (AP) equipped with few or single antennas. Nevertheless, when choosing between deploying more APs with few or single antennas or fewer APs equipped with many antennas, one observes an inherent trade-off between the beamforming and macro-diversity gains that has not been investigated in the literature. Given a total number of antenna elements and total downlink power, under a channel model that takes into account a probability of Line-of-Sight (LoS) as a function of the distance between the User Equipments (UEs) and APs, our numerical results show that there exists a ``sweet spot" on the optimal number of APs and of antenna elements per AP which is a function of the physical dimensions of the coverage area.

Sustainable Radio Frequency Wireless Energy Transfer for Massive Internet of Things

Reliable energy supply remains a crucial challenge in the Internet of Things (IoT). Although relying on batteries is cost-effective for a few devices, it is neither a scalable nor a sustainable charging solution as the network grows massive. Besides, current energy-saving technologies alone cannot cope, for instance, with the vision of zero-energy devices and the deploy-and-forget paradigm which can unlock a myriad of new use cases. In this context, sustainable radio frequency wireless energy transfer emerges as an attractive solution for efficiently charging the next generation of ultra low power IoT devices. Herein, we highlight that sustainable charging is broader than conventional green charging, as it focuses on balancing economy prosperity and social equity in addition to environmental health. Moreover, we overview the key enablers for realizing this vision and associated challenges. We discuss the economic implications of powering energy transmitters with ambient energy sources, and reveal insights on their optimal deployment. We highlight relevant research challenges and candidate solutions.

Meta-Learning Based Few Pilots Demodulation and Interference Cancellation For NOMA Uplink

Non-Orthogonal Multiple Access (NOMA) is at the heart of a paradigm shift towards non-orthogonal communication due to its potential to scale well in massive deployments. Nevertheless, the overhead of channel estimation remains a key challenge in such scenarios. This paper introduces a data-driven, meta-learning-aided NOMA uplink model that minimizes the channel estimation overhead and does not require perfect channel knowledge. Unlike conventional deep learning successive interference cancellation (SICNet), Meta-Learning aided SIC (meta-SICNet) is able to share experience across different devices, facilitating learning for new incoming devices while reducing training overhead. Our results confirm that meta-SICNet outperforms classical SIC and conventional SICNet as it can achieve a lower symbol error rate with fewer pilots.

Joint Activity Detection and Channel Estimation for Clustered Massive Machine Type Communications

Compressed sensing multi-user detection (CS-MUD) algorithms play a key role in optimizing grant-free (GF) non-orthogonal multiple access (NOMA) for massive machine-type communications (mMTC). However, current CS-MUD algorithms cannot be efficiently parallelized, which results in computationally expensive implementations of joint activity detection and channel estimation (JADCE) as the number of deployed machine-type devices (MTDs) increases. To address this, the present work proposes novel JADCE algorithms that can be applied in parallel for different clusters of MTDs by exploiting the structure of the pilot sequences. These are the approximation error method (AEM)-alternating direction method of multipliers (ADMM) and AEM-sparse Bayesian learning (SBL). Results presented in terms of the normalized mean square error and the probability of miss detection evince comparable performance to the conventional algorithms. However, both AEM-ADMM and AEM-SBL algorithms have significantly reduced computational complexity and run-times, thus, increasing network scalability.