VLDB 2026 Research / reviewers in the wild / expert
Memedhe Ibrahimi
dblp:287/8664
· DBLP profile ↗
16ranked-venue papers
2as first author
16since 2021 · last 2026
0000-0002-9823-8206ORCID · verified
Domains — the database's venue-derived domains; a paper can count in several
Computer networks · 12 · 1 first-author · 12 since 2021Software engineering, systems software and programming languages · 1 · 1 since 2021
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2026 | Hollow-Core Fibers for Latency-Constrained and Low-Cost Edge Data Center NetworksabstractRecent advancements in Hollow Core Fibers (HCF) production are paving the way toward new ground-breaking opportunities of HCF for 6G-and-beyond applications. While Standard Single-Mode Fibers (SSMF) have been the go-to solution in optical communications for the past 50 years, HCF is expected to be a turning point in how next-generation optical networks are planned and designed. Compared to SSMF, in which the optical signal is transmitted in a silica core, in HCF, the optical signal is transmitted in a hollow, i.e., air, core, significantly reducing latency (by 30%), while also decreasing attenuation (as low as 0.11 dB/km) and non-linearities. In this study, we investigate the optimal placement of HCF in latency-constrained optical networks to minimize the number of edge Data Centers (edgeDCs), while also ensuring physical-layer validation. Given the optimized placement of HCF and edgeDCs, we minimize the overall network cost in terms of transponders (TXPs) and Wavelength Selective Switches (WSSes) by optimizing the type, number, and transmission mode of TXPs, and the type and number of WSSes. We develop a Mixed Integer Nonlinear Programming (MINLP) model and a Genetic Algorithm (GA) to solve these problems. We validate the GA against the MINLP model in four synthetically generated topologies and perform extensive numerical evaluations in a realistic 25-node metro aggregation topology and a 22-node national topology. We show that by upgrading 25% of the links to HCF, we can significantly reduce the number of edgeDCs by up to 40%, while also reducing network equipment cost by up to 38%, compared to an SSMF-only network. Giovanni Sticca, Memedhe Ibrahimi, Francesco Musumeci 0001, Nicola Di Cicco, Massimo Tornatore |
IEEE Trans. Netw. Serv. Manag. | 2 |
| 2025 | Demo: Design and Implementation of Hierarchical Cross-Domain Orchestration Using TeraFlowSDNabstractThis demonstration showcases the autonomous creation of optical lightpaths across two geographically optical network testbeds, using TeraFlowSDN (TFS) as a high-level intent-based orchestrator for optical service provisioning. Unlike existing approaches that create lightpaths independently within a single domain, our system highlights a hierarchical control model in which a centralized TFS instance coordinates two heterogeneous domain controllers: a vendor-specific controller at Politecnico di Milano (Italy) and a local TFS instance at Sant’Anna School of Advanced Studies (Italy). Southbound adapters enable the translation of high-level service intents into device-specific configurations, making it possible to integrate different controllers and vendors without modifying the underlying infrastructure. The live demo demonstrates automated provisioning of optical lightpaths triggered via a user-friendly graphical interface. The process includes endpoint discovery, transceiver selection, and lightpath establishment, all performed autonomously across multiple domains to support a video streaming service. This work demonstrates the novelty of hierarchical cross-domain orchestration, showing how TFS can unify multivendor environments under a single platform with minimal configuration overhead. This lays the groundwork for future developments in automated service provisioning, closed-loop control, and scalable cross-domain networking. Anouar El Hachimi, Aryanaz Attarpour, Gabriele Nanni, Memedhe Ibrahimi, Sebastian Troia, Andrea Sgambelluri, Emilio Paolini, Massimo Tornatore, Francesco Musumeci 0001 |
CNSM | 4 |
| 2025 | Flow-Rule Generation for SDN Using LLMs with Retry-Based Deployment ValidationabstractThis work proposes a pipeline for Software Defined Networking (SDN) that enables natural-language-based flow rule configuration using large language models (LLMs). The system addresses two key challenges: 1) the ambiguity and incompleteness of natural language inputs, and 2) the difficulty of reliably translating them into deployable SDN configurations. To this end, the pipeline integrates: i) an intent recognition module that refines user prompts via iterative clarification, and ii) a retrybased correction mechanism that handles failed configurations by regenerating and resubmitting corrected versions. These components are combined with intermediate YAML generation, documentation-based enrichment, and final translation into OpenFlow-compliant JSON for Ryu controllers. The pipeline is evaluated on flow rule deployment tasks of varying complexity, achieving an accuracy up to 96.7%, while maintaining costefficiency with an estimated API cost of only 0.08 per 100 configurations and remaining model model-agnostic. Anouar El Hachimi, Nicola Di Cicco, Memedhe Ibrahimi, Francesco Musumeci 0001, Massimo Tornatore |
CNSM | 3 |
| 2025 | Vertical Federated Learning for Failure-Cause Identification in Disaggregated Microwave NetworksabstractMachine Learning (ML) has proven to be a promising solution to provide novel scalable and efficient fault management solutions in modern 5G-and-beyond communication networks. In the context of microwave networks, ML-based solutions have received significant attention. However, current solutions can only be applied to monolithic scenarios in which a single entity (e.g., an operator) manages the entire network. As current network architectures move towards disaggregated communication platforms in which multiple operators and vendors collaborate to achieve cost-efficient and reliable network management, new ML-based approaches for fault management must tackle the challenges of sharing business-critical information due to potential conflicts of interest. In this study, we explore the application of Federated Learning in disaggregated microwave networks for failure-cause identification using a real microwave hardware failure dataset. In particular, we investigate the application of two Vertical Federated Learning (VFL), namely using Split Neural Networks (SplitNNs) and Federated Learning based on Gradient Boosting Decision Trees (FedTree), on different multi-vendor deployment scenarios, and we compare them to a centralized scenario where data is managed by a single entity. Our experimental results show that VFL-based scenarios can achieve F1-Scores consistently within at most a 1% gap with respect to a centralized scenario, regardless of the deployment strategies or model types, while also ensuring minimal leakage of sensitive-data. Fatih Temiz, Memedhe Ibrahimi, Francesco Musumeci 0001, Claudio Passera, Massimo Tornatore |
ICC | 2 |
| 2025 | Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks
Qiaolun Zhang, Nicola Di Cicco, Memedhe Ibrahimi, Raul C. Almeida, Alberto Gatto 0001, Raouf Boutaba, Massimo Tornatore |
INFOCOM | 3 |
| 2025 | Guiding Network Function Virtualization Orchestration Through the Digital Twin TechnologyabstractNext-generation networks rely on the network softwarization paradigm to enable faster and more cost-effective deployment of telecommunications services. The ETSI MANO framework plays a critical role in orchestrating these networks, yet it faces challenges such as the hidden state problem, arising from the NFVO's lack of holistic visibility into the internal state of NFVI-PoPs, which can lead to the choice of sub-optimal allocation schemes. This work introduces a novel approach to address the hidden state problem by integrating the Digital Twin (DT) paradigm into the MANO architecture. The proposed DT is a model-based solution employing neural networks to predict orchestration costs and estimate prediction errors, enabling the NFVO to make informed orchestration decisions through what-if analyses while preserving scalability and administrative independence. Performance evaluation demonstrates the DT's ability to mimic the behavior of an NFVI-PoP with high precision, i.e., in 84% of the cases, it returns a prediction that is 5% close to the actual value. Furthermore, the DT-aided NFVO achieves orchestration performance equivalent to approaches that assume full knowledge of the actual allocation costs, while overcoming in the 43% of cases traditional benchmark policies. Marco Polverini, Giuseppe G. Sirico, Francesco Giacinto Lavacca, Antonio Cianfrani, Sebastian Troia, Nicola Di Cicco, Memedhe Ibrahimi |
NetSoft | 7 |
| 2025 | From amplifiers to OTN boards: Multi-layer optimization for low-cost optical metro networksabstractOptical metro networks interconnect access networks to core networks and must support traffic ranging from aggregation of low-rate end-user requests to high-rate inter-datacenter transfers. To effectively support traffic volumes consisting of heterogeneous flows at extremely different bit-rate, optical metro networks must jointly support coherent (100/200Gbps) and non-coherent (10Gbps) transmission technologies. When deploying these networks, network operators prioritize seeking solutions that consider both scalability and equipment cost minimization. In metro optical networks, different technologies can enable cost savings: at Optical Transport Network (OTN) layer, traffic grooming can be used to reduce equipment cost, while, at Wavelength Division Multiplexing (WDM) layer, filterless optical switching nodes , based on purely passive components, can be used to avoid expensive Wavelength Selective Switches deployment (WSS), and optimized Optical Amplifiers (OA) placement can decrease significantly required amplifiers cost. Joint deployment of these technologies can facilitate significant cost savings, but requires coordination in form of multi-layer optimization, across OTN and WDM network layers to minimize overall equipment cost (from amplifiers at WDM layer, to OTN boards at OTN layer). In this paper, we propose a novel single-step Genetic Algorithm (GA) to jointly optimize OTN-layer equipment cost (OTN boards) and WDM-layer equipment (mainly OAs) cost. We propose two sequential GA approaches, named two-step and three-step. Numerical results, obtained using real network topologies and traffic matrices provided by our industrial collaborators, show that our proposed GA-based approaches can save costs up to 58% compared to real-world baseline solutions, and that single-step approach outperforms two- and three-step cases up to 10%. Aryanaz Attarpour, Sanaz Ghane, Memedhe Ibrahimi, Francesco Musumeci 0001, Andrea Castoldi, Andrea Bovio, Massimo Tornatore |
Comput. Networks | 3 |
| 2025 | Multi-Failure Localization in High-Degree ROADM-Based Optical Networks Using Rules-Informed Neural NetworksabstractTo accommodate ever-growing traffic, network operators are actively deploying high-degree reconfigurable optical add/drop multiplexers (ROADMs) to build large-capacity optical networks. High-degree ROADM-based optical networks have multiple parallel fibers between ROADM nodes, requiring the adoption of ROADM nodes with a large number of inter-/intra-node components. However, this large number of inter-/intra-node optical components in high-degree ROADM networks increases the likelihood of multiple failures simultaneously, and calls for novel methods for accurate localization of multiple failed components. To the best of our knowledge, this is the first study investigating the problem of multi-failure localization for high-degree ROADM-based optical networks. To solve this problem, we first provide a description of the failures affecting both inter-/intra-node components, and we consider different deployments of optical power monitors (OPMs) to obtain information (i.e., optical power) to be used for automated multi-failure localization. Then, as our main and original contribution, we propose a novel method based on a rules-informed neural network (RINN) for multi-failure localization, which incorporates the benefits of both rules-based reasoning and artificial neural networks (ANN). Through extensive simulations and experimental demonstrations, we show that our proposed RINN algorithm can achieve up to around 20% higher localization accuracy compared to baseline algorithms, incurring only around 4.14 ms of average inference time. Ruikun Wang, Qiaolun Zhang, Jiawei Zhang 0004, Zhiqun Gu, Memedhe Ibrahimi, Hao Yu 0013, Bojun Zhang 0002, Francesco Musumeci 0001, Yuefeng Ji, Massimo Tornatore |
IEEE J. Sel. Areas Commun. | 5 |
| 2024 | Vertical Federated Learning for Failure Localization in Partially Disaggregated Optical NetworksabstractMachine Learning (ML) for failure management in optical networks has recently gained noteworthy attention. Even though real field-collected data is crucial for ML-based failure management, it is challenging to access data in emerging disaggregated optical networks, where multi-vendor equipment co-exist, and the end-to-end network management requires coordination between operators that manage different network segments. Due to data confidentiality issues, network operators tend not to share business-critical data, which sets a barrier to utilizing ML-based approaches. To overcome this issue, we propose a Vertical Federated Learning (VFL) approach based on Split-Neural-Network (SplitNN) for failure localization. We consider different deployment scenarios for ML-based solutions in a collaborative and privacy-preserving manner. Our experiments show that, depending on the VFL client and server model architectures, the proposed approaches provide very similar accuracy compared to a baseline scenario of a single operator managing the whole network (differences are mostly within $1 \%$ of accuracy), while minimizing the exposure of risk-sensitive data. Memedhe Ibrahimi, Fatih Temiz, Francesco Musumeci 0001, Massimo Tornatore |
HPSR | 1 |
| 2024 | Joint QoT-Aware Optimization of OTN and WDM Layers for Low-Cost Optical Metro NetworksabstractOptical metro networks currently support various traffic demands with different bit-rates, ranging from low values, e.g., 1 Gbps and 10 Gbps, to high values, e.g., 100 Gbps and 200 Gbps. These traffic demands can be served through coexistence of non-coherent transmission technology (mostly 10 Gbps) or by coherent high-rate technology (100 Gbps and above), characterized by different transmission requirements (e.g., in terms of Signal-to-Noise Ratio (SNR)). To achieve a low-cost metro architecture, various technical directions can be followed: (i) traffic grooming can be employed to decrease the number of line transmission interfaces (at the cost of increased Optical-Transport-Network (OTN) grooming boards), (ii) filterless nodes can reduce the node cost and power consumption by replacing costly Wavelength Selective Switches (WSS) with passive splitters and combiners, and (iii) amplifiers placement can be optimized, benefiting from short distances in metro areas. In this paper, we observe, for the first time to the best of our knowledge, that traffic grooming and amplifier placement are interdependent problems if we aim to achieve overall network cost minimization. Therefore, we propose and compare two cost-effective cross-layer optimization approaches that jointly consider the optical and OTN layers. Precisely, we propose two Quality-of-Transmission (QoT) aware approaches that optimize deployment cost of OTN grooming boards and interfaces in OTN layer while guaranteeing SNR and power on receiver of lightpaths as QoT metrics by considering placement of optical amplifiers along fibers in optical layer. The results indicate that our proposed approaches can save up to 40% compared to real-world baseline solutions. Aryanaz Attarpour, Memedhe Ibrahimi, Nicola Di Cicco, Francesco Musumeci 0001, Andrea Castoldi, Mario Ragni, Massimo Tornatore |
ICC | 2 |
| 2024 | ASAP Hardware Failure-Cause Identification in Microwave Networks Using Venn-Abers PredictorsabstractWe investigate classifying hardware failures in microwave networks via Machine Learning (ML). Although MLbased approaches excel in this task, they usually provide only hard failure predictions without guarantees on their reliability, i.e., on the probability of correct classification. Generally, accumulating data for longer time horizons increases the model’s predictive accuracy. Therefore, in real-world applications, a trade-off arises between two contrasting objectives: i) ensuring high reliability for each classified observation, and ii) collecting the minimal amount of data to provide a reliable prediction. To address this problem, we formulate hardware failure-cause identification as an As-Soon-As-Possible (ASAP) selective classification problem where data streams are sequentially provided to an ML classifier, which outputs a prediction as soon as the probability of correct classification exceeds a user-specified threshold. To this end, we leverage Inductive and Cross Venn-Abers Predictors to transform heuristic probability estimates from any ML model into rigorous predictive probabilities. Numerical results on a real-world dataset show that our ASAP framework reduces the time-to-predict by 8x compared to the state-of-the-art, while ensuring a selective classification accuracy greater than 95%. The dataset utilized in this study is publicly available, aiming to facilitate future investigations in failure management for microwave networks. Nicola Di Cicco, Memedhe Ibrahimi, Omran Ayoub, Federica Bruschetta, Michele Milano, Claudio Passera, Francesco Musumeci 0001 |
IEEE Trans. Netw. Serv. Manag. | 2 |
| 2024 | Machine Learning for Failure Management in Microwave Networks: A Data-Centric ApproachabstractWe consider the problem of classifying hardware failures in microwave networks given a collection of alarms using Machine Learning (ML). While ML models have been shown to work extremely well on similar tasks, an ML model is, at most, as good as its training data. In microwave networks, building a good-quality dataset is significantly harder than training a good classifier: annotating data is a costly and time-consuming procedure. We, therefore, shift the perspective from a Model-Centric approach, i.e., how to train the best ML model from a given dataset, to a Data-Centric approach, i.e., how to make the best use of the data at our disposal. To this end, we explore two orthogonal Data-Centric approaches for hardware failure identification in microwave networks. At training time, we leverage synthetic data generation with Conditional Variational Autoencoders to cope with extreme data imbalance and ensure fair performance in all failure classes. At inference time, we leverage Batch Uncertainty-based Active Learning to guide the data annotation procedure of multiple concurrent domain-expert labelers and achieve the best possible classification performance with the smallest possible training dataset. Illustrative experimental results on a real-world dataset show that our Data-Centric approaches allow for training top-performing models with ~4.5x less annotated data, while improving the classifier’s F1-Score by ~2.5% in a condition of extreme data scarcity. Finally, for the first time to the best of our knowledge, we make our dataset (curated by microwave industry experts) publicly available, aiming to foster research in data-driven failure management. Nicola Di Cicco, Memedhe Ibrahimi, Francesco Musumeci 0001, Federica Bruschetta, Michele Milano, Claudio Passera, Massimo Tornatore |
IEEE Trans. Netw. Serv. Manag. | 2 |
| 2024 | DeepLS: Local Search for Network Optimization Based on Lightweight Deep Reinforcement LearningabstractDeep Reinforcement Learning (DRL) is being investigated as a competitive alternative to traditional techniques for solving network optimization problems. A promising research direction lies in enhancing traditional optimization algorithms by offloading low-level decisions to a DRL agent. In this study, we consider how to effectively employ DRL to improve the performance of Local Search algorithms, i.e., algorithms that, starting from a candidate solution, explore the solution space by iteratively applying local changes (i.e., moves), yielding the best solution found in the process. We propose a Local Search algorithm based on lightweight Deep Reinforcement Learning (DeepLS) that, given a neighborhood, queries a DRL agent for choosing a move, with the goal of achieving the best objective value in the long term. Our DRL agent, based on permutation-equivariant neural networks, is composed by less than a hundred parameters, requiring only up to ten minutes of training and can evaluate problem instances of arbitrary size, generalizing to networks and traffic distributions unseen during training. We evaluate DeepLS on two illustrative NP-Hard network routing problems, namely OSPF Weight Setting and Routing and Wavelength Assignment, training on a single small network only and evaluating on instances 2x-10x larger than training. Experimental results show that DeepLS outperforms existing DRL-based approaches from literature and attains competitive results with state-of-the-art metaheuristics, with computing times up to 8x smaller than the strongest algorithmic baselines. Nicola Di Cicco, Memedhe Ibrahimi, Sebastian Troia, Massimo Tornatore |
IEEE Trans. Netw. Serv. Manag. | 2 |
| 2023 | Uncertainty-Aware QoT Forecasting in Optical Networks with Bayesian Recurrent Neural NetworksabstractWe consider the problem of forecasting the Quality-of-Transmission (QoT) of deployed lightpaths in a Wavelength Division Multiplexing (WDM) optical network. QoT forecasting plays a determinant role in network management and planning, as it allows network operators to proactively plan maintenance or detect anomalies in a lightpath. To this end, we leverage Bayesian Recurrent Neural Networks for learning uncertainty-aware probabilistic QoT forecasts, i.e., for modelling a probability distribution of the QoT over a time horizon. We evaluate our proposed approach on the open-source Microsoft Wide Area Network (WAN) optical backbone dataset. Our illustrative numerical results show that our approach not only outperforms state-of-the-art models from literature, but also predicts intervals providing near-optimal empirical coverage. As such, we demonstrate that uncertainty-aware probabilistic modelling enables the application of QoT forecasting in risk-sensitive application scenarios. Nicola Di Cicco, Jacopo Talpini, Memedhe Ibrahimi, Marco Savi, Massimo Tornatore |
ICC | 3 |
| 2022 | Minimizing Cost of Hierarchical OTN Traffic Grooming Boards in Mesh NetworksabstractThe continuous traffic growth experienced in telecom networks pushes network operators to constantly investigate new solutions to deploy scalable and cost-effective network architectures, especially in the metro segment. These solutions should also ensure backward compatibility with existing network architectures. A cost-effective technical solution for today's metro networks consists in optimizing the deployment cost of hierarchical traffic-grooming boards while considering a mix of coherent (typically 100 Gbps) and non-coherent (typically 10 Gbps) transmission technologies. In this study, we consider metro regional networks composed of interconnected filterless rings, and we investigate how to minimize the joint cost of stacked Optical Transport Network (OTN) traffic-grooming boards, coherent and non-coherent transponders and interfaces, and Dispersion Compensation Modules (DCM). We propose a novel optimization approach based on Genetic Algorithms to effectively solve the associated grooming problem and compare its performance to baseline strategies, showing that we can reach up to 79% cost savings in terms of the total cost of deployed equipment. Aryanaz Attarpour, Memedhe Ibrahimi, Francesco Musumeci 0001, Andrea Castoldi, Mario Ragni, Massimo Tornatore |
GLOBECOM | 2 |
| 2021 | Strategies for Dedicated Path Protection in Filterless Optical NetworksabstractEnabling Dedicated Path Protection (DPP) in Filter-less Optical Networks (FONs) poses specific design challenges, as FONs require dividing the network topology in non-overlapping fiber trees, and lightpaths cannot cross from one tree to another unless additional devices are installed. In this study, we consider the possibility to deploy three type of devices, namely I nter-Tree Transceivers (ITTs), Wavelength Blockers (WBs) and Colored Passive Filters (CPFs) to achieve DPP in FON, and we compare the three resulting DPP strategies, called P-ITT, P- WB and P- WBC. More specifically, we formulate three Integer Linear Programming (ILP) models for DPP in FON with the objective to minimize additional device cost and minimize total wavelength consumption. Numerical results over two realistic topologies show that P-WBC achieves cost savings up to 33% in comparison to P-WB and up to 97% in comparison to P-ITT. However, even if it is the costliest approach, P-ITT ensures up to 7 % savings in wavelength consumption and up to 23 % savings in resource overbuild compared to P- WB and P- WBC, making it a possible candidate in spectrum-scarce deployments. Memedhe Ibrahimi, Omran Ayoub, Fabio Albanese, Francesco Musumeci 0001, Massimo Tornatore |
GLOBECOM | 1 |