Federated Learning-Distillation Alternation for Resource-Constrained IoT

Federated learning (FL) faces significant challenges in Internet of Things (IoT) networks due to device limitations in energy and communication resources, especially when considering the large size of FL models. From an energy perspective, the challenge is aggravated if devices rely on energy harvesting (EH), as energy availability can vary significantly over time, influencing the average number of participating users in each iteration. Additionally, the transmission of large model updates is more susceptible to interference from uncorrelated background traffic in shared wireless environments. As an alternative, federated distillation (FD) reduces communication overhead and energy consumption by transmitting local model outputs, which are typically much smaller than the entire model used in FL. However, this comes at the cost of reduced model accuracy. Therefore, in this paper, we propose FL-distillation alternation (FLDA). In FLDA, devices alternate between FD and FL phases, balancing model information with lower communication overhead and energy consumption per iteration. We consider a multichannel slotted-ALOHA EH-IoT network subject to background traffic/interference. In such a scenario, FLDA demonstrates higher model accuracy than both FL and FD, and achieves faster convergence than FL. Moreover, FLDA achieves target accuracies saving up to 98% in energy consumption, while also being less sensitive to interference, both relative to FL.

Age of Information in Multi-Relay Networks with Maximum Age Scheduling

We propose and evaluate age of information (AoI)-aware multiple access mechanisms for the Internet of Things (IoT) in multi-relay two-hop networks. The network considered comprises end devices (EDs) communicating with a set of relays in ALOHA fashion, with new information packets to be potentially transmitted every time slot. The relays, in turn, forward the collected packets to an access point (AP), the final destination of the information generated by the EDs. More specifically, in this work we investigate the performance of four age-aware algorithms that prioritize older packets to be transmitted, namely max-age matching (MAM), iterative max-age scheduling (IMAS), age-based delayed request (ABDR), and buffered ABDR (B-ABDR). The former two algorithms are adapted into the multi-relay setup from previous research, and achieve satisfactory average AoI and average peak AoI performance, at the expense of a significant amount of information exchange between the relays and the AP. The latter two algorithms are newly proposed to let relays decide which one(s) will transmit in a given time slot, requiring less signaling than the former algorithms. We provide an analytical formulation for the AoI lower bound performance, compare the performance of all algorithms in this set-up, and show that they approach the lower bound. The latter holds especially true for B-ABDR, which approaches the lower bound the most closely, tilting the scale in its favor, as it also requires far less signaling than MAM and IMAS.

Reinforcenment Learning-Aided NOMA Random Access: An AoI-Based Timeliness Perspective

In this paper, we investigate the age-of-information (AoI) of a power domain non-orthogonal multiple access (NOMA) network, where multiple internet-of-things (IoT) devices transmit to a common gateway in a grant-free random fashion. More specifically, we consider a framed setup composed of multiple time slots, and resort to the $Q$-learning algorithm to properly define, in a distributed manner, the time slot and the power level each IoT device transmits within a frame. In the proposed AoI-QL-NOMA scheme, the $Q$-learning reward is adapted with the aim of minimizing the average AoI of the network, while only requiring a single feedback bit per time slot, in a frame basis. Our results show that AoI-QL-NOMA significantly improves the AoI performance compared to some recently proposed schemes, without significantly reducing the network throughput.

Probabilistic Allocation of Payload Code Rate and Header Copies in LR-FHSS Networks

We evaluate the performance of the LoRaWAN Long-Range Frequency Hopping Spread Spectrum (LR-FHSS) technique using a device-level probabilistic strategy for code rate and header replica allocation. Specifically, we investigate the effects of different header replica and code rate allocations at each end-device, guided by a probability distribution provided by the network server. As a benchmark, we compare the proposed strategy with the standardized LR-FHSS data rates DR8 and DR9. Our numerical results demonstrate that the proposed strategy consistently outperforms the DR8 and DR9 standard data rates across all considered scenarios. Notably, our findings reveal that the optimal distribution rarely includes data rate DR9, while data rate DR8 significantly contributes to the goodput and energy efficiency optimizations.

Non-Orthogonal Multiple-Access Strategies for Direct-to-Satellite IoT Networks

Direct-to-Satellite IoT (DtS-IoT) has the potential to support multiple verticals, including agriculture, industry, smart cities, and environmental disaster prevention. This work introduces two novel DtS-IoT schemes using power domain NonOrthogonal Multiple Access (NOMA) in the uplink with either fixed (FTP) or controlled (CTP) transmit power. We consider that the IoT devices use LoRa technology to transmit data packets to the satellite in orbit, equipped with a Successive Interference Cancellation (SIC)-enabled gateway. We also assume the IoT devices are empowered with a predictor of the satellite orbit. Using real geographic location and trajectory data, we evaluate the performance of the average number of successfully decoded transmissions, goodput (bytes/lap), and energy consumption (bytes/Joule) as a function of the number of network devices. Numerical results show the trade-off between goodput and energy efficiency for both proposed schemes. Comparing FTP and CTP with regular ALOHA for 100 (600) devices, we find goodput improvements of 65% (29%) and 52% (101%), respectively. Notably, CTP effectively leverages transmission opportunities as the network size increases, outperforming the other strategies. Moreover, CTP shows the best performance in energy efficiency compared to FTP and ALOHA.

On the Spectral Efficiency of Movable and Rotary Access Points under Rician Fading

Multi-User Multiple-Input Multiple-Output (MU-MIMO) is a pivotal technology in present-day wireless communication systems. In such systems, a base station or Access Point (AP) is equipped with multiple antenna elements and serves multiple active devices simultaneously. Nevertheless, most of the works evaluating the performance of MU-MIMO systems consider APs with static antenna arrays, that is, without any movement capability. Recently, the idea of APs and antenna arrays that are able to move have gained traction among the research community. Many works evaluate the communications performance of antenna systems able to move on the horizontal plane. However, such APs require a very bulky, complex and expensive movement system. In this work, we propose a simpler and cheaper alternative: the utilization of rotary APs, i.e. APs that can rotate. We also analyze the performance of a system in which the AP is able to both move and rotate. The movements and/or rotations of the APs are computed in order to maximize the mean per-user achievable spectral efficiency, based on estimates of the locations of the active devices and using particle swarm optimization. We adopt a spatially correlated Rician fading channel model, and evaluate the resulting optimized performance of the different setups in terms of mean per-user achievable spectral efficiencies. Our numerical results show that both the optimal rotations and movements of the APs can provide substantial performance gains when the line-of-sight components of the channel vectors are strong. Moreover, the simpler rotary APs can outperform the movable APs when their movement area is constrained.

Distributed MIMO Networks with Rotary ULAs for Indoor Scenarios under Rician Fading

The Fifth-Generation (5G) wireless communications networks introduced native support for Machine-Type Communications (MTC) use cases. Nevertheless, current 5G networks cannot fully meet the very stringent requirements regarding latency, reliability, and number of connected devices of most MTC use cases. Industry and academia have been working on the evolution from 5G to Sixth Generation (6G) networks. One of the main novelties is adopting Distributed Multiple-Input Multiple-Output (D-MIMO) networks. However, most works studying D-MIMO consider antenna arrays with no movement capabilities, even though some recent works have shown that this could bring substantial performance improvements. In this work, we propose the utilization of Access Points (APs) equipped with Rotary Uniform Linear Arrays (RULAs) for this purpose. Considering a spatially correlated Rician fading model, the optimal angular position of the RULAs is jointly computed by the central processing unit using particle swarm optimization as a function of the position of the active devices. Considering the impact of imperfect positioning estimates, our numerical results show that the RULAs's optimal rotation brings substantial performance gains in terms of mean per-user spectral efficiency. The improvement grows with the strength of the line-of-sight components of the channel vectors. Given the total number of antenna elements, we study the trade-off between the number of APs and the number of antenna elements per AP, revealing an optimal number of APs for the cases of APs equipped with static ULAs and RULAs.

Assessment of the Sparsity-Diversity Trade-offs in Active Users Detection for mMTC

Wireless communication systems must increasingly support a multitude of machine-type communications (MTC) devices, thus calling for advanced strategies for active user detection (AUD). Recent literature has delved into AUD techniques based on compressed sensing, highlighting the critical role of signal sparsity. This study investigates the relationship between frequency diversity and signal sparsity in the AUD problem. Single-antenna users transmit multiple copies of non-orthogonal pilots across multiple frequency channels and the base station independently performs AUD in each channel using the orthogonal matching pursuit algorithm. We note that, although frequency diversity may improve the likelihood of successful reception of the signals, it may also damage the channel sparsity level, leading to important trade-offs. We show that a sparser signal significantly benefits AUD, surpassing the advantages brought by frequency diversity in scenarios with limited temporal resources and/or high numbers of receive antennas. Conversely, with longer pilots and fewer receive antennas, investing in frequency diversity becomes more impactful, resulting in a tenfold AUD performance improvement.

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.

Energy-Aware Federated Learning with Distributed User Sampling and Multichannel ALOHA

Distributed learning on edge devices has attracted increased attention with the advent of federated learning (FL). Notably, edge devices often have limited battery and heterogeneous energy availability, while multiple rounds are required in FL for convergence, intensifying the need for energy efficiency. Energy depletion may hinder the training process and the efficient utilization of the trained model. To solve these problems, this letter considers the integration of energy harvesting (EH) devices into a FL network with multi-channel ALOHA, while proposing a method to ensure both low energy outage probability and successful execution of future tasks. Numerical results demonstrate the effectiveness of this method, particularly in critical setups where the average energy income fails to cover the iteration cost. The method outperforms a norm based solution in terms of convergence time and battery level.