arXiv subjects

Lorenzo Maggi

Publications and source records attributed to Lorenzo Maggi.

At least 19 recordsLinked to original sources

arXiv2026

The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms

Agentic AI is rapidly transforming the way research is conducted, from prototyping ideas to reproducing results found in the literature. In this paper, we explore the ability of agentic AI to autonomously design wireless communication algorithms. To that end, we implement a dedicated framework that leverages large language models (LLMs) to iteratively generate, evaluate, and refine candidate algorithms. We evaluate the framework on three tasks spanning the physical (PHY) and medium access control (MAC) layers: statistics-agnostic channel estimation, channel estimation with known covariance, and link adaptation. Our results show that, in a matter of hours, the framework produces algorithms that are competitive with and, in some cases, outperforming conventional baselines. Moreover, unlike neural network-based approaches, the generated algorithms are fully explainable and extensible. This work represents a first step toward the autonomous discovery of novel wireless communication algorithms, and we look forward to the progress our community makes in this direction.

cs.AI↗

arXiv2026

SINR Estimation under Limited Feedback via Online Convex Optimization

We introduce a novel online convex optimization (OCO) framework to estimate the user's signal-to-interference-plus-noise ratio (SINR) from ACK/NACK feedback, channel quality indicator (CQI) reports, and previously selected modulation and coding scheme (MCS) values. Specifically, the proposed approach minimizes a regularized binary cross-entropy loss using mirror descent enhanced with Nesterov momentum for accelerated SINR tracking. Its parameters are tuned online via an expert-advice algorithm, endowing the estimator with continual learning capabilities. Numerical experiments in ray-traced scenarios show that the proposed method outperforms state-of-the-art schemes in estimation accuracy and adapts robustly to time-varying SINR regimes.

cs.IT↗

arXiv2025

SALAD: Self-Adaptive Link Adaptation

Adapting the modulation and coding scheme (MCS) to the wireless link quality is critical for maximizing spectral efficiency while ensuring reliability. We propose SALAD (self-adaptive link adaptation), an algorithm that exclusively leverages ACK/NACK feedback to reliably track the evolution of the signal-to-interference-plus-noise ratio (SINR), achieving high spectral efficiency while keeping the long-term block error rate (BLER) near a desired target. SALAD infers the SINR by minimizing the cross-entropy loss between received ACK/NACKs and predicted BLER values. Based on this inference, SALAD selects the MCS via hypothesis testing: if the SINR is likely underestimated, a higher MCS is selected to accelerate link adaptation under improving channel conditions. To prevent BLER drift from its long-term target, SALAD incorporates a feedback control loop that adjusts the instantaneous BLER target. Over-the-air experiments on a 5G testbed demonstrate that SALAD consistently outperforms the industry-standard outer-loop link adaptation (OLLA). With a single set of parameters, SALAD achieves up to 15% higher throughput and spectral efficiency than multiple OLLA variants across different traffic regimes, while meeting the BLER target.

cs.IT↗

arXiv2025

Sionna Research Kit: A GPU-Accelerated Research Platform for AI-RAN

We introduce the NVIDIA Sionna Research Kit, a GPU-accelerated research platform for developing and testing AI/ML algorithms in 5G NR cellular networks. Powered by the NVIDIA Jetson AGX Orin, the platform leverages accelerated computing to deliver high throughput and real-time signal processing, while offering the flexibility of a software-defined stack. Built on OpenAirInterface (OAI), it unlocks a broad range of research opportunities. These include developing 5G NR and ORAN compliant algorithms, collecting real-world data for AI/ML training, and rapidly deploying innovative solutions in a very affordable testbed. Additionally, AI/ML hardware acceleration promotes the exploration of use cases in edge computing and AI radio access networks (AI-RAN). To demonstrate the capabilities, we deploy a real-time neural receiver - trained with NVIDIA Sionna and using the NVIDIA TensorRT library for inference - in a 5G NR cellular network using commercial user equipment. The code examples will be made publicly available, enabling researchers to adopt and extend the platform for their own projects.

cs.NI↗

arXiv2024

Smooth Actual EIRP Control for EMF Compliance with Minimum Traffic Guarantees

To mitigate Electromagnetic Fields (EMF) human exposure from base stations, international standards bodies define EMF emission requirements that can be translated into limits on the "actual" Equivalent Isotropic Radiated Power (EIRP), i.e., averaged over a sliding time window. We aim to enable base stations to adhere to these constraints while mitigating any impact on user performance. Specifically, our objectives are to: i) ensure EMF exposure compliance using actual EIRP control when implementing the "actual maximum approach" described in IEC 62232:2022, ii) guarantee a minimum EIRP level, and iii) prevent resource shortages at all times. We first investigate exact and conservative algorithms, with linear and constant complexity, respectively, to compute the maximum allowed EIRP consumption under constraints i) and ii), referred to as EIRP "budget". Subsequently, we design a control method based on Drift-Plus-Penalty theory that preemptively curbs EIRP consumption only when needed to avoid future resource shortages.

cs.IT↗

arXiv2024

To RL or not to RL? An Algorithmic Cheat-Sheet for AI-Based Radio Resource Management

Several Radio Resource Management (RRM) use cases can be framed as sequential decision planning problems, where an agent (the base station, typically) makes decisions that influence the network utility and state. While Reinforcement Learning (RL) in its general form can address this scenario, it is known to be sample inefficient. Following the principle of Occam's razor, we argue that the choice of the solution technique for RRM should be guided by questions such as, "Is it a short or long-term planning problem?", "Is the underlying model known or does it need to be learned?", "Can we solve the problem analytically?" or "Is an expert-designed policy available?". A wide range of techniques exists to address these questions, including static and stochastic optimization, bandits, model predictive control (MPC) and, indeed, RL. We review some of these techniques that have already been successfully applied to RRM, and we believe that others, such as MPC, may present exciting research opportunities for the future.

cs.NI↗

arXiv2024

PDCCH Scheduling via Maximum Independent Set

In 5G, the Physical Downlink Control CHannel (PDCCH) carries crucial information enabling the User Equipment (UE) to connect in UL and DL. UEs are unaware of the frequency location at which PDCCH is encoded, hence they need to perform blind decoding over a limited set of possible candidates. We address the problem faced by the gNodeB of selecting PDCCH candidates for each UE to optimize data transmission. We formulate it as a Maximum Weighted Independent Set (MWIS) problem, that is known to be an NP-hard problem and cannot even be approximated. A solution method called Weight-to-Degree Ratio (WDR) Greedy emerges as a strong contender for practical implementations due to its favorable performance-to-complexity trade-off and theoretical performance guarantees.

cs.IT↗

arXiv2024

EMF Exposure Mitigation via MAC Scheduling

International standards bodies define Electromagnetic field (EMF) emission requirements that can be translated into control of the base station actual Effective Isotropic Radiated Power (EIRP), i.e., averaged over a sliding time window. In this work we show how to comply with such requirements by designing a water-filling power allocation method operating at the MAC scheduler level. Our method ensures throughput fairness across users while constraining the EIRP to a value that is produced by an outer-loop procedure which is not the focus of our paper. The low computational complexity of our technique is appealing given the tight computational requirements of the MAC scheduler. Our proposal is evaluated against the prior art approaches through massive-MIMO system level simulations that include realistic modeling of physical and MAC level cellular procedures. We conclude that our proposal effectively mitigates EMF exposure with considerably less impact on network performance, making it a standout candidate for 5G and future 6G MAC scheduler implementations.

cs.NI↗

arXiv2023

Reducing the Environmental Impact of Wireless Communication via Probabilistic Machine Learning

Machine learning methods are increasingly adopted in communications problems, particularly those arising in next generation wireless settings. Though seen as a key climate mitigation and societal adaptation enabler, communications related energy consumption is high and is expected to grow in future networks in spite of anticipated efficiency gains in 6G due to exponential communications traffic growth. To make meaningful climate mitigation impact in the communications sector, a mindset shift away from maximizing throughput at all cost and towards prioritizing energy efficiency is needed. Moreover, this must be adopted in both existing (without incurring further embodied carbon costs through equipment replacement) and future network infrastructure, given the long development time of mobile generations. To that end, we present summaries of two such problems, from both current and next generation network specifications, where probabilistic inference methods were used to great effect: using Bayesian parameter tuning we are able to safely reduce the energy consumption of existing hardware on a live communications network by $11\%$ whilst maintaining operator specified performance envelopes; through spatiotemporal Gaussian process surrogate modeling we reduce the overhead in a next generation hybrid beamforming system by over $60\%$, greatly improving the networks' ability to target highly mobile users such as autonomous vehicles. The Bayesian paradigm is itself helpful in terms of energy usage, since training a Bayesian optimization model can require much less computation than, say, training a deep neural network.

cs.NI↗

arXiv2023

Bayesian and Multi-Armed Contextual Meta-Optimization for Efficient Wireless Radio Resource Management

Optimal resource allocation in modern communication networks calls for the optimization of objective functions that are only accessible via costly separate evaluations for each candidate solution. The conventional approach carries out the optimization of resource-allocation parameters for each system configuration, characterized, e.g., by topology and traffic statistics, using global search methods such as Bayesian optimization (BO). These methods tend to require a large number of iterations, and hence a large number of key performance indicator (KPI) evaluations. In this paper, we propose the use of meta-learning to transfer knowledge from data collected from related, but distinct, configurations in order to speed up optimization on new network configurations. Specifically, we combine meta-learning with BO, as well as with multi-armed bandit (MAB) optimization, with the latter having the potential advantage of operating directly on a discrete search space. Furthermore, we introduce novel contextual meta-BO and meta-MAB algorithms, in which transfer of knowledge across configurations occurs at the level of a mapping from graph-based contextual information to resource-allocation parameters. Experiments for the problem of open loop power control (OLPC) parameter optimization for the uplink of multi-cell multi-antenna systems provide insights into the potential benefits of meta-learning and contextual optimization.

eess.SP↗

arXiv2023

Tracking the Best Beam for a Mobile User via Bayesian Optimization

The standard beam management procedure in 5G requires the user equipment (UE) to periodically measure the received signal reference power (RSRP) on each of a set of beams proposed by the basestation (BS). It is prohibitively expensive to measure the RSRP on all beams and so the BS should propose a beamset that is large enough to allow a high-RSRP beam to be identified, but small enough to prevent excessive reporting overhead. Moreover, the beamset should evolve over time according to UE mobility. We address this fundamental performance/overhead trade-off via a Bayesian optimization technique that requires no or little training on historical data and is rooted on a low complexity algorithm for the beamset choice with theoretical guarantees. We show the benefits of our approach on 3GPP compliant simulation scenarios.

cs.IT↗

arXiv2023

Energy savings under performance constraints via carrier shutdown with Bayesian learning

By shutting down frequency carriers, the power consumed by a base station can be considerably reduced. However, this typically comes with traffic performance degradation, as the congestion on the remaining active carriers is increased. We leverage a hysteresis carrier shutdown policy that attempts to keep the average traffic load on each sector within a certain min/max threshold pair. We propose a closed-loop Bayesian method optimizing such thresholds on a sector basis and aiming at minimizing the power consumed by the power amplifiers while maintaining the probability that KPI's are acceptable above a certain value. We tested our approach in a live customer 4G network. The power consumption at the base station was reduced by 11% and the selected KPI's met the predefined targets.

cs.IT↗

arXiv2021

Learning Algorithms for Regenerative Stopping Problems with Applications to Shipping Consolidation in Logistics

We study regenerative stopping problems in which the system starts anew whenever the controller decides to stop and the long-term average cost is to be minimized. Traditional model-based solutions involve estimating the underlying process from data and computing strategies for the estimated model. In this paper, we compare such solutions to deep reinforcement learning and imitation learning which involve learning a neural network policy from simulations. We evaluate the different approaches on a real-world problem of shipping consolidation in logistics and demonstrate that deep learning can be effectively used to solve such problems.

cs.LG↗

arXiv2021

Bayesian Optimization for Radio Resource Management: Open Loop Power Control

We provide the reader with an accessible yet rigorous introduction to Bayesian optimisation with Gaussian processes (BOGP) for the purpose of solving a wide variety of radio resource management (RRM) problems. We believe that BOGP is a powerful tool that has been somewhat overlooked in RRM research, although it elegantly addresses pressing requirements for fast convergence, safe exploration, and interpretability. BOGP also provides a natural way to exploit prior knowledge during optimization. After explaining the nuts and bolts of BOGP, we delve into more advanced topics, such as the choice of the acquisition function and the optimization of dynamic performance functions. Finally, we put the theory into practice for the RRM problem of uplink open-loop power control (OLPC) in 5G cellular networks, for which BOGP is able to converge to almost optimal solutions in tens of iterations without significant performance drops during exploration.

cs.IT↗

arXiv2018

Multi-Path Alpha-Fair Resource Allocation at Scale in Distributed Software Defined Networks

The performance of computer networks relies on how bandwidth is shared among different flows. Fair resource allocation is a challenging problem particularly when the flows evolve over time. To address this issue, bandwidth sharing techniques that quickly react to the traffic fluctuations are of interest, especially in large scale settings with hundreds of nodes and thousands of flows. In this context, we propose a distributed algorithm based on the Alternating Direction Method of Multipliers (ADMM) that tackles the multi-path fair resource allocation problem in a distributed SDN control architecture. Our ADMM-based algorithm continuously generates a sequence of resource allocation solutions converging to the fair allocation while always remaining feasible, a property that standard primal-dual decomposition methods often lack. Thanks to the distribution of all computer intensive operations, we demonstrate that we can handle large instances at scale.

cs.NI↗

arXiv2018

Lower Bounds for the Fair Resource Allocation Problem

The $α$-fair resource allocation problem has received remarkable attention and has been studied in numerous application fields. Several algorithms have been proposed in the context of $α$-fair resource sharing to distributively compute its value. However, little work has been done on its structural properties. In this work, we present a lower bound for the optimal solution of the weighted $α$-fair resource allocation problem and compare it with existing propositions in the literature. Our derivations rely on a localization property verified by optimization problems with separable objective that permit one to better exploit their local structures. We give a local version of the well-known midpoint domination axiom used to axiomatically build the Nash Bargaining Solution (or proportionally fair resource allocation problem). Moreover, we show how our lower bound can improve the performances of a distributed algorithm based on the Alternating Directions Method of Multipliers (ADMM). The evaluation of the algorithm shows that our lower bound can considerably reduce its convergence time up to two orders of magnitude compared to when the bound is not used at all or is simply looser.

cs.NI↗

arXiv2017

Real-Time Fair Resource Allocation in Distributed Software Defined Networks

The performance of computer networks relies on how bandwidth is shared among different flows. Fair resource allocation is a challenging problem particularly when the flows evolve over time.To address this issue, bandwidth sharing techniques that quickly react to the traffic fluctuations are of interest, especially in large scale settings with hundreds of nodes and thousands of flows. In this context, we propose a distributed algorithm that tackles the fair resource allocation problem in a distributed SDN control architecture. Our algorithm continuously generates a sequence of resource allocation solutions converging to the fair allocation while always remaining feasible, a property that standard primal-dual decomposition methods often lack. Thanks to the distribution of all computer intensive operations, we demonstrate that we can handle large instances in real-time.

cs.NI↗

arXiv2017

Virtual Function Placement for Service Chaining with Partial Orders and Anti-Affinity Rules

Software Defined Networking and Network Function Virtualization are two paradigms that offer flexible software-based network management. Service providers are instantiating Virtualized Network Functions - e.g., firewalls, DPIs, gateways - to highly facilitate the deployment and reconfiguration of network services with reduced time-to-value. They employ Service Function Chaining technologies to dynamically reconfigure network paths traversing physical and virtual network functions. Providing a cost-efficient virtual function deployment over the network for a set of service chains is a key technical challenge for service providers, and this problem has recently caught much attention from both Industry and Academia. In this paper, we propose a formulation of this problem as an Integer Linear Program that allows one to find the best feasible paths and virtual function placement for a set of services with respect to a total financial cost, while taking into account the (total or partial) order constraints for Service Function Chains of each service and other constraints such as end-to-end latency, anti-affinity rules between network functions on the same physical node and resource limitations in terms of network and processing capacities. Furthermore, we propose a heuristic algorithm based on a linear relaxation of the problem that performs close to optimum for large scale instances.

cs.NI↗