arXiv subjects

Jean-François Frigon

Publications and source records attributed to Jean-François Frigon.

At least 19 recordsLinked to original sources

arXiv2026

Quantized Transformers for Massive MIMO Precoding with Automatic Resolution Tuning

Deep learning precoders, particularly those based on Transformer architectures, offer superior spectral efficiency for Massive MIMO systems but may incur high computational cost. While existing mixed-precision quantization studies on convolutional neural networks establish important energy baselines, traditional discrete search methods fail to scale to the large parameter spaces of modern Transformers. To bridge this gap, we apply a differentiable precision learning technique to massive MIMO precoding. This approach autonomously and jointly optimizes weights, activations, quantization step sizes, and layer-wise bit-widths in a single training loop, directly optimizing for energy efficiency. We further expand this approach by incorporating Neural Architecture Search across various Transformer model sizes and evaluating the impact of random versus floating-point trained initializations on resolution tuning. Ultimately, we demonstrate that the proposed training method enables the deployment of highly compact Transformer precoders, improving energy efficiency by up to 288$\times$ compared to the classical Weighted Minimum Mean Square Error algorithm at equal sum-rate performance in a dense downtown environment.

eess.SP↗

arXiv2026

Is Forecasting Accuracy Enough? A Comparative Study of Traffic Forecasters for Beam-Hopping LEO Satellite Networks

We evaluate diverse models for user traffic demand forecasting in Low Earth Orbit (LEO) satellite networks with Beam Hopping (BH), questioning whether predictive accuracy is the right objective for this task. To capture the complex nature of the user traffic demand, we employ a second-order self-similar traffic model, supplemented by a publicly available Wi-Fi dataset to validate the self-similar model against the empirical traffic patterns. We compare forecasters ranging from classical statistical approaches, such as the optimal forecaster for self-similar data and the optimal linear predictor on the discrete sampling grid, to Fractional Auto-Regressive Integrated Moving Average (FARIMA) models, as well as emerging deep learning architectures. The latter category encompasses foundation and domain-specific transformer models, alongside a lightweight neural network consisting solely of linear layers. We assess these models at two levels: in isolation, through the Mean Absolute Scaled Error (MASE), and in context, through a BH simulator in which the forecast drives the illumination plan. On purely self-similar traffic the three self-similarity aware forecasters perform on par with one another and dominate the learned models, whereas on the raw Wi-Fi trace this ordering nearly reverses. Seasonality violates their stationary increment assumption; removing the periodic component restores their comparative accuracy. Crucially, these accuracy differences barely propagate to the system level. Loss ratio and buffer backlog are affected more by system utilization and the planning period than by the choice of forecaster, with the performance gap between forecasters vanishing entirely below 0.90 utilization. This suggests design efforts are better spent optimizing utilization margins and planning periods rather than chasing marginal gains in raw accuracy.

eess.SP↗

arXiv2026

The Impact of Demand Forecasting on Delay and Jitter in DVB-Based Beam-Hopping LEO Networks

In LEO satellite networks utilizing beam hopping (BH), resource allocation plans must be committed well in advance. This inherent operational delay necessitates predicting future user demand during the planning phase. Such predictive agility is particularly crucial for military applications, where unpredictable tactical environments demand low-latency, resilient communication links. However, existing forecasting models are typically evaluated based on standalone accuracy, ignoring their cross-layer impact on overall network performance. To address this gap, we evaluate two distinct demand forecasting solutions within a comprehensive, full-stack LEO satellite simulation compliant with DVB-S2X standards. Beyond prediction accuracy, we examine how incorporating user demand forecasts into BH plan generation impacts key network metrics, particularly delay and jitter. We evaluate these forecasting solutions alongside a static allocation baseline. Our results demonstrate that forecast-based dynamic planning reduces delay by 10-40% across the beams under certain load conditions compared to static allocation methods. Crucially, marginal improvements in predictive accuracy do not translate into proportional network metric gains. While the evaluated forecasting solutions differ by 14-16% in Normalized Mean Square Error (NMSE), this discrepancy yields less than a 1% reduction in delay and produces nearly identical jitter characteristics. These findings suggest that when designing user demand forecasting solutions for practical LEO deployments, prioritizing system scalability may be more valuable than chasing minor accuracy enhancements.

eess.SP↗

arXiv2026

A Low-Complexity Plug-and-Play Deep Learning Model for Generalizable Massive MIMO Precoding

Massive multiple-input multiple-output (mMIMO) downlink precoding offers high spectral efficiency but remains challenging to deploy in practice because near-optimal algorithms such as the weighted minimum mean squared error (WMMSE) are computationally expensive, and sensitive to SNR and channel-estimation quality, while existing deep learning (DL)-based solutions often lack robustness and require retraining for each deployment site. This paper proposes a plug-and-play precoder (PaPP), a DL framework with a backbone that can be trained for either fully digital (FDP) or hybrid beamforming (HBF) precoding and reused across sites, transmit-power levels, and with varying amounts of channel estimation error, avoiding the need to train a new model from scratch at each deployment. PaPP combines a high-capacity teacher and a compact student with a self-supervised loss that balances teacher imitation and normalized sum-rate, trained using meta-learning domain-generalization and transmit-power-aware input normalization. Numerical results on ray-tracing data from three unseen sites show that the PaPP FDP and HBF models both outperform conventional and deep learning baselines, after fine-tuning with a small set of local unlabeled samples. Across both architectures, PaPP achieves more than 21$\times$ reduction in modeled computation energy and maintains good performance under channel-estimation errors, making it a practical solution for energy-efficient mMIMO precoding.

cs.LG↗

arXiv2025

Forecasting Self-Similar User Traffic Demand Using Transformers in LEO Satellite Networks

In this paper, we propose the use of a transformer-based model to address the need for forecasting user traffic demand in the next generation Low Earth Orbit (LEO) satellite networks. Considering a LEO satellite constellation, we present the need to forecast the demand for the satellites in-orbit to utilize dynamic beam-hopping in high granularity. We adopt a traffic dataset with second-order self-similar characteristics. Given this traffic dataset, the Fractional Auto-regressive Integrated Moving Average (FARIMA) model is considered a benchmark forecasting solution. However, the constrained on-board processing capabilities of LEO satellites, combined with the need to fit a new model for each input sequence due to the nature of FARIMA, motivate the investigation of alternative solutions. As an alternative, a pretrained probabilistic time series model that utilizes transformers with a Prob-Sparse self-attention mechanism is considered. The considered solution is investigated under different time granularities with varying sequence and prediction lengths. Concluding this paper, we provide extensive simulation results where the transformer-based solution achieved up to six percent better forecasting accuracy on certain traffic conditions using mean squared error as the performance indicator.

eess.SP↗

arXiv2025

A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff

Deep learning (DL) has emerged as a solution for precoding in massive multiple-input multiple-output (mMIMO) systems due to its capacity to learn the characteristics of the propagation environment. However, training such a model requires high-quality, local datasets at the deployment site, which are often difficult to collect. We propose a transformer-based foundation model for mMIMO precoding that seeks to minimize the energy consumption of the transmitter while dynamically adapting to per-user rate requirements. At equal energy consumption, zero-shot deployment of the proposed foundation model significantly outperforms zero forcing, and approaches weighted minimum mean squared error performance with 8x less complexity. To address model adaptation in data-scarce settings, we introduce a data augmentation method that finds training samples similar to the target distribution by computing the cosine similarity between the outputs of the pre-trained feature extractor. Our work enables the implementation of DL-based solutions in practice by addressing challenges of data availability and training complexity. Moreover, the ability to dynamically configure per-user rate requirements can be leveraged by higher level resource allocation and scheduling algorithms for greater control over energy efficiency, spectral efficiency and fairness.

eess.SP↗

arXiv2025

A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites

Massive multiple-input multiple-output (mMIMO) technology has transformed wireless communication by enhancing spectral efficiency and network capacity. This paper proposes a novel deep learning-based mMIMO precoder to tackle the complexity challenges of existing approaches, such as weighted minimum mean square error (WMMSE), while leveraging meta-learning domain generalization and a teacher-student architecture to improve generalization across diverse communication environments. When deployed to a previously unseen site, the proposed model achieves excellent sum-rate performance while maintaining low computational complexity by avoiding matrix inversions and by using a simpler neural network structure. The model is trained and tested on a custom ray-tracing dataset composed of several base station locations. The experimental results indicate that our method effectively balances computational efficiency with high sum-rate performance while showcasing strong generalization performance in unseen environments. Furthermore, with fine-tuning, the proposed model outperforms WMMSE across all tested sites and SNR conditions while reducing complexity by at least 73$\times$.

eess.SP↗

arXiv2025

Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding

The deployment of deep learning (DL) models for precoding in massive multiple-input multiple-output (mMIMO) systems is often constrained by high computational demands and energy consumption. In this paper, we investigate the compute energy efficiency of mMIMO precoders using DL-based approaches, comparing them to conventional methods such as zero forcing and weighted minimum mean square error (WMMSE). Our energy consumption model accounts for both memory access and calculation energy within DL accelerators. We propose a framework that incorporates mixed-precision quantization-aware training and neural architecture search to reduce energy usage without compromising accuracy. Using a ray-tracing dataset covering various base station sites, we analyze how site-specific conditions affect the energy efficiency of compressed models. Our results show that deep neural network compression generates precoders with up to 35 times higher energy efficiency than WMMSE at equal performance, depending on the scenario and the desired rate. These results establish a foundation and a benchmark for the development of energy-efficient DL-based mMIMO precoders.

eess.SP↗

arXiv2025

Adaptive Detection of On-Orbit Jamming for Securing GEO Satellite Links

This paper introduces a scenario where a maneuverable satellite in geostationary orbit (GEO) conducts on-orbit attacks, targeting communication between a GEO satellite and a ground station, with the ability to switch between stationary and time-variant jamming modes. We propose a machine learning-based detection approach, employing the random forest algorithm with principal component analysis (PCA) to enhance detection accuracy in the stationary model. At the same time, an adaptive threshold-based technique is implemented for the time-variant model to detect dynamic jamming events effectively. Our methodology emphasizes the need for the use of orbital dynamics in integrating physical constraints from satellite dynamics to improve model robustness and detection accuracy. Simulation results highlight the effectiveness of PCA in enhancing the performance of the stationary model, while the adaptive thresholding method achieves high accuracy in detecting jamming in the time-variant scenario. This approach provides a robust solution for mitigating the evolving threats to satellite communication in GEO environments.

eess.SP↗

arXiv2024

A Scalable Architecture for Future Regenerative Satellite Payloads

This paper addresses the limitations of current satellite payload architectures, which are predominantly hardware-driven and lack the flexibility to adapt to increasing data demands and uneven traffic. To overcome these challenges, we present a novel architecture for future regenerative and programmable satellite payloads and utilize interconnected modem banks to promote higher scalability and flexibility. We formulate an optimization problem to efficiently manage traffic among these modem banks and balance the load. Additionally, we provide comparative numerical simulation results, considering end-to-end delay and packet loss analysis. The results illustrate that our proposed architecture maintains lower delays and packet loss even with higher traffic demands and smaller buffer sizes.

eess.SP↗

arXiv2024

SAGE-HB: Swift Adaptation and Generalization in Massive MIMO Hybrid Beamforming

Deep learning (DL)-based solutions have emerged as promising candidates for beamforming in massive Multiple-Input Multiple-Output (mMIMO) systems. Nevertheless, it remains challenging to seamlessly adapt these solutions to practical deployment scenarios, typically necessitating extensive data for fine-tuning while grappling with domain adaptation and generalization issues. In response, we propose a novel approach combining Meta-Learning Domain Generalization (MLDG) with novel data augmentation techniques during fine-tuning. This approach not only accelerates adaptation to new channel environments but also significantly reduces the data requirements for fine-tuning, thereby enhancing the practicality and efficiency of DL-based mMIMO systems. The proposed approach is validated by simulating the performance of a backbone model when deployed in a new channel environment, and with different antenna configurations, path loss, and base station height parameters. Our proposed approach demonstrates superior zero-shot performance compared to existing methods and also achieves near-optimal performance with significantly fewer fine-tuning data samples.

eess.SP↗

arXiv2023

Evolution of High Throughput Satellite Systems: Vision, Requirements, and Key Technologies

High throughput satellites (HTS), with their digital payload technology, are expected to play a key role as enablers of the upcoming 6G networks. HTS are mainly designed to provide higher data rates and capacities. Fueled by technological advancements including beamforming, advanced modulation techniques, reconfigurable phased array technologies, and electronically steerable antennas, HTS have emerged as a fundamental component for future network generation. This paper offers a comprehensive state-of-the-art of HTS systems, with a focus on standardization, patents, channel multiple access techniques, routing, load balancing, and the role of software-defined networking (SDN). In addition, we provide a vision for next-satellite systems that we named as extremely-HTS (EHTS) toward autonomous satellites supported by the main requirements and key technologies expected for these systems. The EHTS system will be designed such that it maximizes spectrum reuse and data rates, and flexibly steers the capacity to satisfy user demand. We introduce a novel architecture for future regenerative payloads while summarizing the challenges imposed by this architecture.

eess.SP↗

arXiv2023

Learning Energy-Efficient Hardware Configurations for Massive MIMO Beamforming

Hybrid beamforming (HBF) and antenna selection are promising techniques for improving the energy efficiency~(EE) of massive multiple-input multiple-output~(mMIMO) systems. However, the transmitter architecture may contain several parameters that need to be optimized, such as the power allocated to the antennas and the connections between the antennas and the radio frequency chains. Therefore, finding the optimal transmitter architecture requires solving a non-convex mixed integer problem in a large search space. In this paper, we consider the problem of maximizing the EE of fully digital precoder~(FDP) and hybrid beamforming~(HBF) transmitters. First, we propose an energy model for different beamforming structures. Then, based on the proposed energy model, we develop an unsupervised deep learning method to maximize the EE by designing the transmitter configuration for FDP and HBF. The proposed deep neural networks can provide different trade-offs between spectral efficiency and energy consumption while adapting to different numbers of active users. Finally, to ensure that the proposed method can be implemented in practice, we investigate the ability of the model to be trained exclusively using imperfect channel state information~(CSI), both for the input to the deep learning model and for the calculation of the loss function. Simulation results show that the proposed solutions can outperform conventional methods in terms of EE while being trained with imperfect CSI. Furthermore, we show that the proposed solutions are less complex and more robust to noise than conventional methods.

eess.SP↗

arXiv2022

Flexible Unsupervised Learning for Massive MIMO Subarray Hybrid Beamforming

Hybrid beamforming is a promising technology to improve the energy efficiency of massive MIMO systems. In particular, subarray hybrid beamforming can further decrease power consumption by reducing the number of phase-shifters. However, designing the hybrid beamforming vectors is a complex task due to the discrete nature of the subarray connections and the phase-shift amounts. Finding the optimal connections between RF chains and antennas requires solving a non-convex problem in a large search space. In addition, conventional solutions assume that perfect CSI is available, which is not the case in practical systems. Therefore, we propose a novel unsupervised learning approach to design the hybrid beamforming for any subarray structure while supporting quantized phase-shifters and noisy CSI. One major feature of the proposed architecture is that no beamforming codebook is required, and the neural network is trained to take into account the phase-shifter quantization. Simulation results show that the proposed deep learning solutions can achieve higher sum-rates than existing methods.

cs.IT↗

arXiv2020

RSSI-Based Hybrid Beamforming Design with Deep Learning

Hybrid beamforming is a promising technology for 5G millimetre-wave communications. However, its implementation is challenging in practical multiple-input multiple-output (MIMO) systems because non-convex optimization problems have to be solved, introducing additional latency and energy consumption. In addition, the channel-state information (CSI) must be either estimated from pilot signals or fed back through dedicated channels, introducing a large signaling overhead. In this paper, a hybrid precoder is designed based only on received signal strength indicator (RSSI) feedback from each user. A deep learning method is proposed to perform the associated optimization with reasonable complexity. Results demonstrate that the obtained sum-rates are very close to the ones obtained with full-CSI optimal but complex solutions. Finally, the proposed solution allows to greatly increase the spectral efficiency of the system when compared to existing techniques, as minimal CSI feedback is required.

eess.SP↗

arXiv2014

Priority Queueing Models for Cognitive Radio Networks with Traffic Differentiation

In this paper, we present a new queueing model providing the accurate average system time for packets transmitted over a cognitive radio (CR) link for multiple traffic classes with the preemptive and non-preemptive priority service disciplines. The analysis considers general packet service time, general distributions for the channel availability periods and service interruption periods, and a service-resume transmission. We further introduce and analyze two novel priority service disciplines for opportunistic spectrum access (OSA) networks which take advantage of interruptions to preempt low priority traffic at a low cost. Analytical results, in addition to simulation results to validate their accuracy, are also provided and illustrate the impact of different OSA network parameters on the average system time. We particularly show that, for the same average CR transmission link availability, the packet system time significantly increases in a semi-static network with long operating and interruption periods compared to an OSA network with fast alternating operating and interruption periods. We also present results indicating that, due to the presence of interruptions, priority queueing service disciplines provide a greater differentiated service in OSA networks than in traditional networks. The analytical tools presented in this paper are general and can be used to analyze the traffic metrics of most OSA networks carrying multiple classes of traffic with priority queueing service differentiation.

cs.NI↗

arXiv2014

Delay Analysis of Multichannel Opportunistic Spectrum Access MAC Protocols

We provide in this paper a comprehensive delay and queueing analysis for two baseline medium access control (MAC) protocols for multi-user cognitive radio (CR) networks and investigate the impact of different network parameters, such as packet size, Aloha-type medium access probability and number of channels on the system performance. In addition to an accurate Markov chain, which follows the queue status of all users, several lower complexity queueing theory approximations are provided. Accuracy and performance of the proposed analytical approximations are verified with extensive simulations. It is observed that for CR networks using an Aloha-type access to the control channel, a buffering MAC protocol, where in case of interruption the CR user waits for the primary user to vacate the channel before resuming the transmission, outperforms a switching MAC protocol, where the CR user vacates the channel in case of appearance of primary users and then compete again to gain access to a new channel. The reason is that the delay bottleneck for both protocols is the time required to successfully access the control channel, which occurs more frequently for the switching MAC protocol. We also propose a user clustering approach, where users are divided into clusters with a separate control channel per cluster, and observe that it can significantly improve the performance by reducing the number of competing users per control channel.

cs.NI↗

arXiv2014

Efficient Heuristic for Resource Allocation in Zero-forcing OFDMA-SDMA Systems with Minimum Rate Constraints

4G wireless access systems require high spectral efficiency to support the ever increasing number of users and data rates for real time applications. Multi-antenna OFDM-SDMA systems can provide the required high spectral efficiency and dynamic usage of the channel, but the resource allocation process becomes extremely complex because of the augmented degrees of freedom. In this paper, we propose two heuristics to solve the resource allocation problem that have very low computational complexity and give performances not far from the optimal. The proposed heuristics select a set of users for each subchannel, but contrary to the reported methods that solve the throughput maximization problem, our heuristics consider the set of real-time (RT) users to ensure that their minimum rate requirements are met. We compare the heuristics' performance against an upper bound and other methods proposed in the literature and find that they give a somewhat lower performance, but support a wider range of minimum rates while reducing the computational complexity. The gap between the objective achieved by the heuristics and the upper bound is not large. In our experiments this gap is 10.7% averaging over all performed numerical evaluations for all system configurations. The increase in the range of the supported minimum rates when compared with a method reported in the literature is 14.6% on average.

cs.NI↗