arXiv subjects

Hatim Chergui

Publications and source records attributed to Hatim Chergui.

34 records · Page 2Linked to original sources

arXiv2024

Federated Machine Reasoning for Resource Provisioning in 6G O-RAN

O-RAN specifications reshape RANs with function disaggregation and open interfaces, driven by RAN Intelligent Controllers. This enables data-driven management through AI/ML but poses trust challenges due to human operators' limited understanding of AI/ML decision-making. Balancing resource provisioning and avoiding overprovisioning and underprovisioning is critical, especially among the multiple virtualized base station(vBS) instances. Thus, we propose a novel Federated Machine Reasoning (FLMR) framework, a neurosymbolic method for federated reasoning, learning, and querying. FLMR optimizes CPU demand prediction based on contextual information and vBS configuration using local monitoring data from virtual base stations (vBS) on a shared O-Cloud platform.This optimization is critical, as insufficient computing resources can result in synchronization loss and significantly reduce network throughput. In the telecom domain, particularly in the virtual Radio Access Network (vRAN) sector, predicting and managing the CPU load of vBSs poses a significant challenge for network operators. Our proposed FLMR framework ensures transparency and human understanding in AI/ML decisions and addresses the evolving demands of the 6G O-RAN landscape, where reliability and performance are paramount. Furthermore, we performed a comparative analysis using \textit{DeepCog} as the baseline method. The outcomes highlight how our proposed approach outperforms the baseline and strikes a better balance between resource overprovisioning and underprovisioning. Our method notably lowers both provisioning relative to the baseline by a factor of 6.

cs.IT↗

arXiv2023

Joint Explainability and Sensitivity-Aware Federated Deep Learning for Transparent 6G RAN Slicing

In recent years, wireless networks are evolving complex, which upsurges the use of zero-touch artificial intelligence (AI)-driven network automation within the telecommunication industry. In particular, network slicing, the most promising technology beyond 5G, would embrace AI models to manage the complex communication network. Besides, it is also essential to build the trustworthiness of the AI black boxes in actual deployment when AI makes complex resource management and anomaly detection. Inspired by closed-loop automation and Explainable Artificial intelligence (XAI), we design an Explainable Federated deep learning (FDL) model to predict per-slice RAN dropped traffic probability while jointly considering the sensitivity and explainability-aware metrics as constraints in such non-IID setup. In precise, we quantitatively validate the faithfulness of the explanations via the so-called attribution-based \emph{log-odds metric} that is included as a constraint in the run-time FL optimization task. Simulation results confirm its superiority over an unconstrained integrated-gradient (IG) \emph{post-hoc} FDL baseline.

cs.NI↗

arXiv2023

TEFL: Turbo Explainable Federated Learning for 6G Trustworthy Zero-Touch Network Slicing

Sixth-generation (6G) networks anticipate intelligently supporting a massive number of coexisting and heterogeneous slices associated with various vertical use cases. Such a context urges the adoption of artificial intelligence (AI)-driven zero-touch management and orchestration (MANO) of the end-to-end (E2E) slices under stringent service level agreements (SLAs). Specifically, the trustworthiness of the AI black-boxes in real deployment can be achieved by explainable AI (XAI) tools to build transparency between the interacting actors in the slicing ecosystem, such as tenants, infrastructure providers and operators. Inspired by the turbo principle, this paper presents a novel iterative explainable federated learning (FL) approach where a constrained resource allocation model and an \emph{explainer} exchange -- in a closed loop (CL) fashion -- soft attributions of the features as well as inference predictions to achieve a transparent and SLA-aware zero-touch service management (ZSM) of 6G network slices at RAN-Edge setup under non-independent identically distributed (non-IID) datasets. In particular, we quantitatively validate the faithfulness of the explanations via the so-called attribution-based \emph{confidence metric} that is included as a constraint in the run-time FL optimization task. In this respect, Integrated-Gradient (IG) as well as Input $\times$ Gradient and SHAP are used to generate the attributions for the turbo explainable FL (TEFL), wherefore simulation results under different methods confirm its superiority over an unconstrained Integrated-Gradient \emph{post-hoc} FL baseline.

cs.IT↗

arXiv2023

SliceOps: Explainable MLOps for Streamlined Automation-Native 6G Networks

Sixth-generation (6G) network slicing is the backbone of future communications systems. It inaugurates the era of extreme ultra-reliable and low-latency communication (xURLLC) and pervades the digitalization of the various vertical immersive use cases. Since 6G inherently underpins artificial intelligence (AI), we propose a systematic and standalone slice termed SliceOps that is natively embedded in the 6G architecture, which gathers and manages the whole AI lifecycle through monitoring, re-training, and deploying the machine learning (ML) models as a service for the 6G slices. By leveraging machine learning operations (MLOps) in conjunction with eXplainable AI (XAI), SliceOps strives to cope with the opaqueness of black-box AI using explanation-guided reinforcement learning (XRL) to fulfill transparency, trustworthiness, and interpretability in the network slicing ecosystem. This article starts by elaborating on the architectural and algorithmic aspects of SliceOps. Then, the deployed cloud-native SliceOps working is exemplified via a latency-aware resource allocation problem. The deep RL (DRL)-based SliceOps agents within slices provide AI services aiming to allocate optimal radio resources and impede service quality degradation. Simulation results demonstrate the effectiveness of SliceOps-driven slicing. The article discusses afterward the SliceOps challenges and limitations. Finally, the key open research directions corresponding to the proposed approach are identified.

cs.NI↗

arXiv2023

Explanation-Guided Deep Reinforcement Learning for Trustworthy 6G RAN Slicing

The complexity of emerging sixth-generation (6G) wireless networks has sparked an upsurge in adopting artificial intelligence (AI) to underpin the challenges in network management and resource allocation under strict service level agreements (SLAs). It inaugurates the era of massive network slicing as a distributive technology where tenancy would be extended to the final consumer through pervading the digitalization of vertical immersive use-cases. Despite the promising performance of deep reinforcement learning (DRL) in network slicing, lack of transparency, interpretability, and opaque model concerns impedes users from trusting the DRL agent decisions or predictions. This problem becomes even more pronounced when there is a need to provision highly reliable and secure services. Leveraging eXplainable AI (XAI) in conjunction with an explanation-guided approach, we propose an eXplainable reinforcement learning (XRL) scheme to surmount the opaqueness of black-box DRL. The core concept behind the proposed method is the intrinsic interpretability of the reward hypothesis aiming to encourage DRL agents to learn the best actions for specific network slice states while coping with conflict-prone and complex relations of state-action pairs. To validate the proposed framework, we target a resource allocation optimization problem where multi-agent XRL strives to allocate optimal available radio resources to meet the SLA requirements of slices. Finally, we present numerical results to showcase the superiority of the adopted XRL approach over the DRL baseline. As far as we know, this is the first work that studies the feasibility of an explanation-guided DRL approach in the context of 6G networks.

cs.NI↗

arXiv2022

On the Specialization of FDRL Agents for Scalable and Distributed 6G RAN Slicing Orchestration

Network slicing enables multiple virtual networks to be instantiated and customized to meet heterogeneous use case requirements over 5G and beyond network deployments. However, most of the solutions available today face scalability issues when considering many slices, due to centralized controllers requiring a holistic view of the resource availability and consumption over different networking domains. In order to tackle this challenge, we design a hierarchical architecture to manage network slices resources in a federated manner. Driven by the rapid evolution of deep reinforcement learning (DRL) schemes and the Open RAN (O-RAN) paradigm, we propose a set of traffic-aware local decision agents (DAs) dynamically placed in the radio access network (RAN). These federated decision entities tailor their resource allocation policy according to the long-term dynamics of the underlying traffic, defining specialized clusters that enable faster training and communication overhead reduction. Indeed, aided by a traffic-aware agent selection algorithm, our proposed Federated DRL approach provides higher resource efficiency than benchmark solutions by quickly reacting to end-user mobility patterns and reducing costly interactions with centralized controllers.

cs.NI↗

arXiv2022

Actor-Critic-Based Learning for Zero-touch Joint Resource and Energy Control in Network Slicing

To harness the full potential of beyond 5G (B5G) communication systems, zero-touch network slicing (NS) is viewed as a promising fully-automated management and orchestration (MANO) system. This paper proposes a novel knowledge plane (KP)-based MANO framework that accommodates and exploits recent NS technologies and is termed KB5G. Specifically, we deliberate on algorithmic innovation and artificial intelligence (AI) in KB5G. We invoke a continuous model-free deep reinforcement learning (DRL) method to minimize energy consumption and virtual network function (VNF) instantiation cost. We present a novel Actor-Critic-based NS approach to stabilize learning called, twin-delayed double-Q soft Actor-Critic (TDSAC) method. The TDSAC enables central unit (CU) to learn continuously to accumulate the knowledge learned in the past to minimize future NS costs. Finally, we present numerical results to showcase the gain of the adopted approach and verify the performance in terms of energy consumption, CPU utilization, and time efficiency.

cs.NI↗

arXiv2022

A Collaborative Statistical Actor-Critic Learning Approach for 6G Network Slicing Control

Artificial intelligence (AI)-driven zero-touch massive network slicing is envisioned to be a disruptive technology in beyond 5G (B5G)/6G, where tenancy would be extended to the final consumer in the form of advanced digital use-cases. In this paper, we propose a novel model-free deep reinforcement learning (DRL) framework, called collaborative statistical Actor-Critic (CS-AC) that enables a scalable and farsighted slice performance management in a 6G-like RAN scenario that is built upon mobile edge computing (MEC) and massive multiple-input multiple-output (mMIMO). In this intent, the proposed CS-AC targets the optimization of the latency cost under a long-term statistical service-level agreement (SLA). In particular, we consider the Q-th delay percentile SLA metric and enforce some slice-specific preset constraints on it. Moreover, to implement distributed learners, we propose a developed variant of soft Actor-Critic (SAC) with less hyperparameter sensitivity. Finally, we present numerical results to showcase the gain of the adopted approach on our built OpenAI-based network slicing environment and verify the performance in terms of latency, SLA Q-th percentile, and time efficiency. To the best of our knowledge, this is the first work that studies the feasibility of an AI-driven approach for massive network slicing under statistical SLA.

cs.NI↗

arXiv2021

Continuous Multi-objective Zero-touch Network Slicing via Twin Delayed DDPG and OpenAI Gym

Artificial intelligence (AI)-driven zero-touch network slicing (NS) is a new paradigm enabling the automation of resource management and orchestration (MANO) in multi-tenant beyond 5G (B5G) networks. In this paper, we tackle the problem of cloud-RAN (C-RAN) joint slice admission control and resource allocation by first formulating it as a Markov decision process (MDP). We then invoke an advanced continuous deep reinforcement learning (DRL) method called twin delayed deep deterministic policy gradient (TD3) to solve it. In this intent, we introduce a multi-objective approach to make the central unit (CU) learn how to re-configure computing resources autonomously while minimizing latency, energy consumption and virtual network function (VNF) instantiation cost for each slice. Moreover, we build a complete 5G C-RAN network slicing environment using OpenAI Gym toolkit where, thanks to its standardized interface, it can be easily tested with different DRL schemes. Finally, we present extensive experimental results to showcase the gain of TD3 as well as the adopted multi-objective strategy in terms of achieved slice admission success rate, latency, energy saving and CPU utilization.

cs.NI↗

arXiv2021

Zero-touch Continuous Network Slicing Control via Scalable Actor-Critic Learning

Artificial intelligence (AI)-driven zero-touch network slicing is envisaged as a promising cutting-edge technology to harness the full potential of heterogeneous 5G and beyond 5G (B5G) communication systems and enable the automation of demand-aware resource management and orchestration (MANO). In this paper, we tackle the issue of B5G radio access network (RAN) joint slice admission control and resource allocation according to proposed slice-enabling cell-free massive multiple-input multiple-output (mMIMO) setup by invoking a continuous deep reinforcement learning (DRL) method. We present a novel Actor-Critic-based network slicing approach called, prioritized twin delayed distributional deep deterministic policy gradient (D-TD3)}. The paper defines and corroborates via extensive experimental results a zero-touch network slicing scheme with a multi-objective approach where the central server learns continuously to accumulate the knowledge learned in the past to solve future problems and re-configure computing resources autonomously while minimizing latency, energy consumption, and virtual network function (VNF) instantiation cost for each slice. Moreover, we pursue a state-action return distribution learning approach with the proposed replay policy and reward-penalty mechanisms. Finally, we present numerical results to showcase the gain of the adopted multi-objective strategy and verify the performance in terms of achieved slice admission rate, latency, energy, CPU utilization, and time efficiency.

cs.NI↗

arXiv2019

On Physical Layer Security over Fox's $H$-Function Wiretap Fading Channels

Most of the well-known fading distributions, if not all of them, could be encompassed by Fox's $H$-function fading. Consequently, we investigate the exact and asymptotic behavior of physical layer security (PLS) over Fox's $H$-function fading wiretap channels. In particular, closed-form expressions are derived for secrecy outage probability (SOP), probability of non-zero secrecy capacity (PNZ), and average secrecy capacity (ASC). These expressions are given in terms of either univariate or bivariate Fox's $H$-function. In order to show the comprehensive effectiveness of our derivations, three metrics are respectively listed over the following frequently used fading channels, including Rayleigh, Weibull, Nakagami-$m$, $α-μ$, Fisher-Snedecor (F-S) $\mathcal{F}$, and extended generalized-$\mathcal{K}$ (EGK). Our tractable results are more straightforward and general, besides that, they are feasible and applicable, especially the SOP, which was mostly limited to the lower bound in literature due to the difficulty of achieving closed-from expressions. In order to validate the accuracy of our analytical results, Monte-Carlo simulations are subsequently performed for the special case $α-μ$ fading channels. One can observe perfect agreements between the exact analytical and simulation results, and highly accurate approximations between the exact and asymptotic analytical results.

cs.IT↗

arXiv2019

Self-Tuning Spectral Clustering for Adaptive Tracking Areas Design in 5G Ultra-Dense Networks

In this paper, we address the issue of automatic tracking areas (TAs) planning in fifth generation (5G) ultra-dense networks (UDNs). By invoking handover (HO) attempts and measurement reports (MRs) statistics of a 4G live network, we first introduce a new kernel function mapping HO attempts, MRs and inter-site distances (ISDs) into the so-called similarity weight. The corresponding matrix is then fed to a self-tuning spectral clustering (STSC) algorithm to automatically define the TAs number and borders. After evaluating its performance in terms of the $Q$-metric as well as the silhouette score for various kernel parameters, we show that the clustering scheme yields a significant reduction of tracking area updates and average paging requests per TA; optimizing thereby network resources.

cs.IT↗

arXiv2018

Classification Algorithms for Semi-Blind Uplink/Downlink Decoupling in sub-6 GHz/mmWave 5G Networks

Reliability and latency challenges in future mixed sub-6 GHz/millimeter wave (mmWave) fifth generation (5G) cell-free massive multiple-input multiple-output (MIMO) networks is to guarantee a fast radio resource management in both uplink (UL) and downlink (DL), while tackling the corresponding propagation imbalance that may arise in blockage situations. In this context, we introduce a semi-blind UL/DL decoupling concept where, after its initial activation, the central processing unit (CPU) gathers measurements of the Rician $K$-factor---reflecting the line-of-sight (LOS) condition of the user equipment (UE)---as well as the DL reference signal receive power (RSRP) for both 2.6 GHz and 28 GHz frequency bands, and then train a non-linear support vector machine (SVM) algorithm. The CPU finally stops the measurements of mmWave definitely, and apply the trained SVM algorithm on the 2.6 GHz data to blindly predict the target frequencies and access points (APs) that can be independently used for the UL and DL. The accuracy score of the proposed classifier reaches $95\%$ for few training samples.

cs.IT↗

arXiv2018

Rician $K$-Factor-Based Analysis of XLOS Service Probability in 5G Outdoor Ultra-Dense Networks

In this report, we introduce the concept of Rician $K$-factor-based radio resource and mobility management for fifth generation (5G) ultra-dense networks (UDN), where the information on the gradual visibility between the new radio node B (gNB) and the user equipment (UE)---dubbed X-line-of-sight (XLOS)---would be required. We therefore start by presenting the XLOS service probability as a new performance indicator; taking into account both the UE serving and neighbor cells. By relying on a lognormal $K$-factor model, a closed-form expression of the XLOS service probability in a 5G outdoor UDN is derived in terms of the multivariate Fox H-function; wherefore we develop a GPU-enabled MATLAB routine and automate the definition of the underlying Mellin-Barnes contour via linear optimization. Residue theory is then applied to infer the relevant asymptotic behavior and show its practical implications. Finally, numerical results are provided for various network configurations, and underpinned by extensive Monte-Carlo simulations.

cs.IT↗

arXiv2018

On Multihop Weibull-Fading Communications: Performance Analysis Framework and Applications

The paper presents a comprehensive closed-form performance analysis framework for multihop communications over Weibull fading channels. The analyzed scheme consists basically of multiple regenerative relays with generalized high-order quadrature amplitude modulation (M-QAM) transmissions. To take into consideration the channel fading in the mmWave range, we adopt the advocated Weibull model for its flexible ability to cover different channel conditions. The end-to-end performance is evaluated in terms of outage probability, bit error probability (BER), symbol error probability (SER), block error rate (BLER), ergodic capacity, and energy efficiency (EE). For all the metrics, we present exact closed-form expressions along with their asymptotic behavior, some in terms of generalized hypergeometric functions. Based on the obtained analytical results, we also present a practical application, we derive two BER- and EE-optimal transmit power allocation strategies, and we discuss the resulting performance gains. The exactness of our analysis is illustrated by numerical examples, and assessed via Monte-Carlo simulations for different system and channel parameters. Finally, as a secondary contribution, noting the increasing popularity of Fox's H and bivariate H functions, we provide new and generalized codes for computing these functions which are of practical utility in different contexts.

cs.IT↗

arXiv2016

Performance Analysis of Project-and-Forward Relaying in Mixed MIMO-Pinhole and Rayleigh Dual-Hop Channel

In this letter, we present an end-to-end performance analysis of dual-hop project-and-forward relaying in a realistic scenario, where the source-relay and the relay-destination links are experiencing MIMO-pinhole and Rayleigh channel conditions, respectively. We derive the probability density function of both the relay post-processing and the end-to-end signal-to-noise ratios, and the obtained expressions are used to derive the outage probability of the analyzed system as well as its end-to-end ergodic capacity in terms of generalized functions. Applying then the residue theory to Mellin-Barnes integrals, we infer the system asymptotic behavior for different channel parameters. As the bivariate Meijer-G function is involved in the analysis, we propose a new and fast MATLAB implementation enabling an automated definition of the complex integration contour. Extensive Monte-Carlo simulations are invoked to corroborate the analytical results.

cs.IT↗