arXiv subjects

Petar Popovski

Publications and source records attributed to Petar Popovski.

At least 73 records · Page 4Linked to original sources

arXiv2025

Online Reliable Anomaly Detection via Neuromorphic Sensing and Communications

This paper proposes a low-power online anomaly detection framework based on neuromorphic wireless sensor networks, encompassing possible use cases such as brain-machine interfaces and remote environmental monitoring. In the considered system, a central reader node actively queries a subset of neuromorphic sensor nodes (neuro-SNs) at each time frame. The neuromorphic sensors are event-driven, producing spikes in correspondence to relevant changes in the monitored system. The queried neuro-SNs respond to the reader with impulse radio (IR) transmissions that directly encode the sensed local events. The reader processes these event-driven signals to determine whether the monitored environment is in a normal or anomalous state, while rigorously controlling the false discovery rate (FDR) of detections below a predefined threshold. The proposed approach employs an online hypothesis testing method with e-values to maintain FDR control without requiring knowledge of the anomaly rate, and it dynamically optimizes the sensor querying strategy by casting it as a best-arm identification problem in a multi-armed bandit framework. Extensive performance evaluation demonstrates that the proposed method can reliably detect anomalies under stringent FDR requirements, while efficiently scheduling sensor communications and achieving low detection latency.

cs.LG↗

arXiv2025

Leveraging Generative AI for large-scale prediction-based networking

The traditional role of the network layer is to create an end-to-end route, through which the intermediate nodes replicate and forward the packets towards the destination. This role can be radically redefined by exploiting the power of Generative AI (GenAI) to pivot towards a prediction-based network layer, which addresses the problems of throughput limits and uncontrollable latency. In the context of real-time delivery of image content, the use of GenAI-aided network nodes has been shown to improve the flow arriving at the destination by more than 100%. However, to successfully exploit GenAI nodes and achieve such transition, we must provide solutions for the problems which arise as we scale the networks to include large amounts of users and multiple data modalities other than images. We present three directions that play a significant role in enabling the use of GenAI as a network layer tool at a large scale. In terms of design, we emphasize the need for initialization protocols to select the prompt size efficiently. Next, we consider the use case of GenAI as a tool to ensure timely delivery of data, as well as an alternative to traditional TCP congestion control algorithms.

cs.NI↗

arXiv2025

Multilayer Non-Terrestrial Networks with Spectrum Access aided by Beyond-Diagonal RIS

In this work, we study a multi-user NTN in which a satellite serves as the primary network and a high-altitude platform station (HAPS) operates as the secondary network, acting as a cognitive radio. To reduce the cost, complexity, and power consumption of conventional antenna arrays, we equip the HAPS with a transmissive BD-RIS antenna front end. We then formulate a joint optimization problem for the BD-RIS phase response and the HAPS transmit power allocation under strict per-user interference temperature constraints. To tackle the resulting highly nonconvex problem, we propose an alternating-optimization framework: the power-allocation subproblem admits a closed-form, water-filling-type solution derived from the Karush-Kuhn-Tucker (KKT) conditions, while the BD-RIS configuration is refined via Riemannian manifold optimization. Simulation results show significant gains in data rate and interference suppression over diagonal RIS-assisted benchmarks, establishing BD-RIS as a promising enabler for future multilayer NTNs.

eess.SP↗

arXiv2025

Learning to Speak on Behalf of a Group: Medium Access Control for Sending a Shared Message

The rapid development of Internet of Things (IoT) technologies has not only enabled new applications, but also presented new challenges for reliable communication with limited resources. In this work, we define a novel problem that can arise in these scenarios, in which a set of sensors need to communicate a joint observation. This observation is shared by a random subset of the nodes, which need to propagate it to the rest of the network, but coordination is complex: as signaling constraints require the use of random access schemes over shared channels, sensors need to implicitly coordinate, so that at least one transmission gets through without collisions. Unlike the majority of existing medium access schemes, the goal is to make sure that the shared message gets through, regardless of the sender. We analyze this coordination problem theoretically and provide low-complexity solutions. While a clustering-based approach is near-optimal if the sensors have prior knowledge, we provide a distributed multi-armed bandit (MAB) solution for the more general case and validate it by simulation.

cs.NI↗

arXiv2025

Prediction-Powered Communication with Distortion Guarantees

The development of 6G wireless systems is taking place alongside the development of increasingly intelligent wireless devices and network nodes. The changing technological landscape is motivating a rethinking of classical Shannon information theory that emphasizes semantic and task-oriented paradigms. In this paper, we study a prediction-powered communication setting, in which devices, equipped with artificial intelligence (AI)-based predictors, communicate under zero-delay constraints with strict distortion guarantees. Two classes of distortion measures are considered: (i) outage-based metrics, suitable for tasks tolerating occasional packet losses, such as real-time control or monitoring; and (ii) bounded distortion metrics, relevant to semantic-rich tasks like text or video transmission. We propose two zero-delay compression algorithms leveraging online conformal prediction to provide per-sequence guarantees on the distortion of reconstructed sequences over error-free and packet-erasure channels with feedback. For erasure channels, we introduce a doubly-adaptive conformal update to compensate for channel-induced errors and derive sufficient conditions on erasure statistics to ensure distortion constraints. Experiments on semantic text compression validate the approach, showing significant bit rate reductions while strictly meeting distortion guarantees compared to state-of-the-art prediction-powered compression methods.

cs.IT↗

arXiv2025

On the Deployment of Multiple Radio Stripes for Large-Scale Near-Field RF Wireless Power Transfer

This paper investigates the deployment of radio stripe systems for indoor radio-frequency (RF) wireless power transfer (WPT) in line-of-sight near-field scenarios. The focus is on environments where energy demand is concentrated in specific areas, referred to as 'hotspots', spatial zones with higher user density or consistent energy requirements. We formulate a joint clustering and radio stripe deployment problem that aims to maximize the minimum received power across all hotspots. To address the complexity, we decouple the problem into two stages: i) clustering for assigning radio stripes to hotspots based on their spatial positions and near-field propagation characteristics, and ii) antenna element placement optimization. In particular, we propose four radio stripe deployment algorithms. Two are based on general successive convex approximation (SCA) and signomial programming (SGP) methods. The other two are shape-constrained solutions where antenna elements are arranged along either straight lines or regular polygons, enabling simpler deployment. Numerical results show that the proposed clustering method converges effectively, with Chebyshev initialization significantly outperforming random initialization. The optimized deployments consistently outperform baseline benchmarks across a wide range of frequencies and radio stripe lengths, while the polygon-shaped deployment achieves better performance compared to other approaches. Meanwhile, the line-shaped deployment demonstrates an advantage under high boresight gain settings, benefiting from increased spatial diversity and broader angular coverage.

eess.SP↗

arXiv2025

Data Sourcing Random Access using Semantic Queries for Massive IoT Scenarios

Efficiently retrieving relevant data from massive Internet of Things (IoT) networks is essential for downstream tasks such as machine learning. This paper addresses this challenge by proposing a novel data sourcing protocol that combines semantic queries and random access. The key idea is that the destination node broadcasts a semantic query describing the desired information, and the sensors that have data matching the query then respond by transmitting their observations over a shared random access channel, for example to perform joint inference at the destination. However, this approach introduces a tradeoff between maximizing the retrieval of relevant data and minimizing data loss due to collisions on the shared channel. We analyze this tradeoff under a tractable Gaussian mixture model and optimize the semantic matching threshold to maximize the number of relevant retrieved observations. The protocol and the analysis are then extended to handle a more realistic neural network-based model for complex sensing. Under both models, experimental results in classification scenarios demonstrate that the proposed protocol is superior to traditional random access, and achieves a near-optimal balance between inference accuracy and the probability of missed detection, highlighting its effectiveness for semantic query-based data sourcing in massive IoT networks.

cs.IT↗

arXiv2025

6G Resilience -- White Paper

6G must be designed to withstand, adapt to, and evolve amid prolonged, complex disruptions. Mobile networks' shift from efficiency-first to sustainability-aware has motivated this white paper to assert that resilience is a primary design goal, alongside sustainability and efficiency, encompassing technology, architecture, and economics. We promote resilience by analysing dependencies between mobile networks and other critical systems, such as energy, transport, and emergency services, and illustrate how cascading failures spread through infrastructures. We formalise resilience using the 3R framework: reliability, robustness, resilience. Subsequently, we translate this into measurable capabilities: graceful degradation, situational awareness, rapid reconfiguration, and learning-driven improvement and recovery. Architecturally, we promote edge-native and locality-aware designs, open interfaces, and programmability to enable islanded operations, fallback modes, and multi-layer diversity (radio, compute, energy, timing). Key enablers include AI-native control loops with verifiable behaviour, zero-trust security rooted in hardware and supply-chain integrity, and networking techniques that prioritise critical traffic, time-sensitive flows, and inter-domain coordination. Resilience also has a techno-economic aspect: open platforms and high-quality complementors generate ecosystem externalities that enhance resilience while opening new markets. We identify nine business-model groups and several patterns aligned with the 3R objectives, and we outline governance and standardisation. This white paper serves as an initial step and catalyst for 6G resilience. It aims to inspire researchers, professionals, government officials, and the public, providing them with the essential components to understand and shape the development of 6G resilience.

eess.SP↗

arXiv2025

Information Age and Correctness for Energy Harvesting Devices with Random Access

We investigate accuracy and freshness of status updates from a large number of energy-harvesting devices that monitor two-state Markov processes and access the medium using the slotted ALOHA protocol without feedback. Using a Markovian framework, we analyze the average value of a generic state-dependent penalty function that grows whenever there is a state estimation error. The age of incorrect information (AoII) is an example of such penalty function. We propose an accurate and easy-to-compute approximation for the average penalty. Numerical results demonstrate the benefits of optimizing the transmission probabilities according to the process state transitions and current battery levels to minimize the average penalty. Minimizing a state-independent penalty function can be highly suboptimal in terms of average penalty when one of the process states is critical, i.e., entails a high penalty if wrongly estimated. Furthermore, minimizing the average penalty does not guarantee a low probability of misdetecting a critical state period.

cs.IT↗

arXiv2025

Time-constrained Federated Learning (FL) in Push-Pull IoT Wireless Access

Training a high-quality Federated Learning (FL) model at the network edge is challenged by limited transmission resources. Although various device scheduling strategies have been proposed, it remains unclear how scheduling decisions affect the FL model performance under temporal constraints. This is pronounced when the wireless medium is shared to enable the participation of heterogeneous Internet of Things (IoT) devices with distinct communication modes: (1) a scheduling (pull) scheme, that selects devices with valuable updates, and (2) random access (push), in which interested devices transmit model parameters. This work investigates the interplay of push-pull interactions in a time-constrained FL setting, where the communication opportunities are finite, with a utility-based analytical model. Using real-world datasets, we provide a performance tradeoff analysis that validates the significance of strategic device scheduling under push-pull wireless access for several practical settings. The simulation results elucidate the impact of the device sampling strategy on learning efficiency under timing constraints.

eess.SP↗

arXiv2025

To Share, or Not to Share: A Study on GEO-LEO Systems for IoT Services with Random Access

The increasing number of satellite deployments, both in the low and geostationary Earth orbit exacerbates the already ongoing scarcity of wireless resources when targeting ubiquitous connectivity. For the aim of supporting a massive number of IoT devices characterized by bursty traffic and modern variants of random access, we pose the following question: Should competing satellite operators share spectrum resources or is an exclusive allocation preferable? This question is addressed by devising a communication model for two operators which serve overlapping coverage areas with independent IoT services. Analytical approximations, validated by Monte Carlo simulations, reveal that spectrum sharing can yield significant throughput gains for both operators under certain conditions tied to the relative serviced user populations and coding rates in use. These gains are sensitive also to the system parameters and may not always render the spectral coexistence mutually advantageous. Our model captures basic trade-offs in uplink spectrum sharing and provides novel actionable insights for the design and regulation of future 6G non-terrestrial networks.

eess.SP↗

arXiv2025

Coexistence of Radar and Communication with Rate-Splitting Wireless Access

Future wireless networks are envisioned to facilitate the seamless coexistence of communication and sensing functionalities, thereby enabling the much-touted integrated sensing and communication (ISAC) paradigm. A key challenge in ISAC is managing inter-functionality interference while maintaining a balanced performance trade-off. In this work, we propose a rate-splitting (RS)-inspired approach to address this challenge in an uplink ISAC scenario, where a base station (BS) serves an uplink communication user while detecting a radar target. We derive inner bounds on the ergodic data information rate for the communication user and the ergodic radar estimation information rate for the sensing target. A closed-form solution is also derived for the optimal power split in RS that maximizes the communication user's performance. Compared to orthogonal multiple access (OMA)- and non-orthogonal multiple access (NOMA)-inspired approaches, the proposed approach achieves a more favorable sensing-communication trade-off by virtue of the decoding order flexibility introduced through splitting the communication message. Notably, this is the first work to employ an RS-inspired strategy as a general framework for non-orthogonal coexistence of sensing and communication, extending its applicability beyond traditional digital-only settings.

eess.SP↗

arXiv2025

Energy Management and Wake-up for IoT Networks Powered by Energy Harvesting

The rapid growth of the Internet of Things (IoT) presents sustainability challenges such as increased maintenance requirements and overall higher energy consumption. This motivates self-sustainable IoT ecosystems based on Energy Harvesting (EH). This paper treats IoT deployments in which IoT devices (IoTDs) rely solely on EH to sense and transmit information about events/alarms to a base station (BS). The objective is to effectively manage the duty cycling of the IoTDs to prolong battery life and maximize the relevant data sent to the BS. The BS can also wake up specific IoTDs if extra information about an event is needed upon initial detection. We propose a K-nearest neighbors (KNN)-based duty cycling management to optimize energy efficiency and detection accuracy by considering spatial correlations among IoTDs' activity and their EH process. We evaluate machine learning approaches, including reinforcement learning (RL) and decision transformers (DT), to maximize information captured from events while managing energy consumption. Significant improvements over the state-ofthe-art approaches are obtained in terms of energy saving by all three proposals, KNN, RL, and DT. Moreover, the RL-based solution approaches the performance of a genie-aided benchmark as the number of IoTDs increases.

eess.SY↗

arXiv2025

Ultra-Low-Latency Edge Inference for Distributed Sensing

There is a broad consensus that artificial intelligence (AI) will be a defining component of the sixth-generation (6G) networks. As a specific instance, AI-empowered sensing will gather and process environmental perception data at the network edge, giving rise to integrated sensing and edge AI (ISEA). Many applications, such as autonomous driving and industrial manufacturing, are latency-sensitive and require end-to-end (E2E) performance guarantees under stringent deadlines. However, the 5G-style ultra-reliable and low-latency communication (URLLC) techniques designed with communication reliability and agnostic to the data may fall short in achieving the optimal E2E performance of perceptive wireless systems. In this work, we introduce an ultra-low-latency (ultra-LoLa) inference framework for perceptive networks that facilitates the analysis of the E2E sensing accuracy in distributed sensing by jointly considering communication reliability and inference accuracy. By characterizing the tradeoff between packet length and the number of sensing observations, we derive an efficient optimization procedure that closely approximates the optimal tradeoff. We validate the accuracy of the proposed method through experimental results, and show that the proposed ultra-Lola inference framework outperforms conventional reliability-oriented protocols with respect to sensing performance under a latency constraint.

math.NA↗

arXiv2025

Low-Power and Accurate IoT Monitoring Under Radio Resource Constraint

This paper investigates how to achieve both low-power operations of sensor nodes and accurate state estimation using Kalman filter for internet of things (IoT) monitoring employing wireless sensor networks under radio resource constraint. We consider two policies used by the base station to collect observations from the sensor nodes: (i) an oblivious policy, based on statistics of the observations, and (ii) a decentralized policy, based on autonomous decision of each sensor based on its instantaneous observation. This work introduces a wake-up receiver and wake-up signaling to both policies to improve the energy efficiency of the sensor nodes. The decentralized policy designed with random access prioritizes transmissions of instantaneous observations that are highly likely to contribute to the improvement of state estimation. Our numerical results show that the decentralized policy improves the accuracy of the estimation in comparison to the oblivious policy under the constraint on the radio resource and consumed energy when the correlation between the processes observed by the sensor nodes is low. We also clarify the degree of correlation in which the superiority of two policies changes.

cs.NI↗

arXiv2025

Preserving Simultaneity and Chronology for Sensing in Perceptive Wireless Networks

We address the challenge of preserving the simultaneity and chronology of sensing events in multisensor systems with wireless links. The network uses temporal windows of integration (TWIs), borrowed from human multisensory perception, to preserve the temporal structure of the sensing data at the application side. We introduce a composite latency model for propagation, sensing, and communication that leads to the derivation of the probability of simultaneity violation. This is used to select the TWI duration aiming to achieve the desired degrees of chronological preservation, while maintaining the throughput of events. The letter provides important insights and analytical tools about the TWI impact on the event registration.

cs.IT↗

arXiv2025

Prediction of Wireless Channel Statistics with Ray Tracing and Uncalibrated Digital Twin

We introduce a framework for predicting wireless channel statistics based on digital twin (DT) and ray tracing. The DT is derived from satellite images and is uncalibrated, as it does not assume precise information on the electromagnetic properties of the materials in the environment. The uncalibrated DT is utilized to derive a geometric prior that informs a Gaussian process (GP) and thereby predict channel statistics using only a few measurements. The framework also quantifies uncertainty, offering statistical guarantees for rate selection in ultra-reliable low-latency communication (URLLC). Experimental validation demonstrates the efficacy of the proposed framework using measurement data.

cs.IT↗

arXiv2025

Reinforcement Learning-Based Policy Optimisation For Heterogeneous Radio Access

Flexible and efficient wireless resource sharing across heterogeneous services is a key objective for future wireless networks. In this context, we investigate the performance of a system where latency-constrained internet-of-things (IoT) devices coexist with a broadband user. The base station adopts a grant-free access framework to manage resource allocation, either through orthogonal radio access network (RAN) slicing or by allowing shared access between services. For the IoT users, we propose a reinforcement learning (RL) approach based on double Q-Learning (QL) to optimise their repetition-based transmission strategy, allowing them to adapt to varying levels of interference and meet a predefined latency target. We evaluate the system's performance in terms of the cumulative distribution function of IoT users' latency, as well as the broadband user's throughput and energy efficiency (EE). Our results show that the proposed RL-based access policies significantly enhance the latency performance of IoT users in both RAN Slicing and RAN Sharing scenarios, while preserving desirable broadband throughput and EE. Furthermore, the proposed policies enable RAN Sharing to be energy-efficient at low IoT traffic levels, and RAN Slicing to be favourable under high IoT traffic.

eess.SP↗