BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Marco Ruffini

Marco Ruffini contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Networking and Internet ArchitectureMachine Learning

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
2topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

9 published item(s)

preprint2026arXiv

Beyond Redundancy: Toward Agile Resilience in Optical Networks to Overcome Unpredictable Disasters

Resilience in optical networks has traditionally relied on redundancy and pre-planned recovery strategies, both of which assume a certain level of disaster predictability. However, recent environmental changes such as climate shifts, the evolution of communication services, and rising geopolitical risks have increased the unpredictability of disasters, reducing the effectiveness of conventional resilience approaches. To address this unpredictability, this paper introduces the concept of agile resilience, which emphasizes dynamic adaptability across multiple operators and layers. We identify key requirements and challenges, and present enabling technologies for the realization of agile resilience. Using a field-deployed transmission system, we demonstrate rapid system characterization, optical path provisioning, and database migration within six hours. These results validate the effectiveness of the proposed enabling technologies and confirm the feasibility of agile resilience.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

PRIM: Meta-Learned Bayesian Root Cause Analysis

Root cause analysis (RCA) in complex systems is challenging due to error propagation across multiple variables, the need for structural causal knowledge, and the computational cost of inference at test time. We introduce PRIM (Prior-fitted Root cause Identification with Meta-learning), a causal meta-learning approach that frames RCA as a Bayesian inference task over a synthetic prior of causal models. By marginalising out structural uncertainty, PRIM implicitly identifies changes in the data-generating mechanism between baseline and anomalous periods. In doing so, PRIM infers distributional differences without explicit statistical testing, and implicitly learns causal structure without model fitting at test time. Following the simulation-based meta-learning paradigm of prior-fitted networks, PRIM uses a Model-Averaged Causal Estimation (MACE) transformer neural process that jointly attends over observational and anomalous samples and the causal structure of nodes, enabling zero-shot inference in 17,ms for systems with up to 100 variables. Across synthetic benchmarks and two realistic benchmark datasets, PetShop and CausRCA, PRIM is competitive with methods that are aware of the system's causal graphical structure a priori while outperforming graph-unaware methods on several tasks. Lightweight fine-tuning to specific domains and data dynamics improves performance further.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models

Heterogeneous LoRA-rank methods address system heterogeneity in federated fine-tuning of foundation models by assigning client-specific ranks based on computational capabilities. However, these methods achieve only marginal computational savings, as dense feed-forward computations dominate. Sparse Mixture-of-Experts (SMoE) provides a promising alternative through conditional computation, yet we identify that its naive application to heterogeneous federated settings introduces two critical discordances: (i) expert utilization imbalance and (ii) non-differentiability of Top-K routing. Our convergence analysis demonstrates that these discordances lead to degraded convergence, particularly for resource-constrained clients. To address these challenges, we propose Universally Balanced Sparse Mixture-of-Experts (UB-SMoE), which introduces Dynamic Modulated Routing (DMR) to rebalance expert utilization, and Universal Pseudo-Gradient (PG) to reconstruct learning signals for non-activated experts. These mechanisms form a self-reinforcing cycle that maintains expert viability across heterogeneous clients. Experiments on benchmarks show that UB-SMoE achieves up to $45.0\%$ computational reduction on low-resource clients while improving their performance by $8.7 \times$ compared to existing heterogeneous LoRA-rank methods.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

ML Approach for Power Consumption Prediction in Virtualized Base Stations

The flexibility introduced with the Open Radio Access Network (O-RAN) architecture allows us to think beyond static configurations in all parts of the network. This paper addresses the issue related to predicting the power consumption of different radio schedulers, and the potential offered by O-RAN to collect data, train models, and deploy policies to control the power consumption. We propose a black-box (Neural Network) model to learn the power consumption function. We compare our approach with a known hand-crafted solution based on domain knowledge. Our solution reaches similar performance without any previous knowledge of the application and provides more flexibility in scenarios where the system behavior is not well understood or the domain knowledge is not available.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Min-Max Fair Resource Allocation Framework for Optical x-haul and DU/CU in Multi-tenant O-RANs

The recently proposed open-radio access network (O-RAN) architecture embraces cloudification and network function virtualization techniques to perform the base-band function processing by dis-aggregated radio units (RUs), distributed units (DUs), and centralized units (CUs). This enables the cloud-RAN vision in full, where mobile network operators (MNOs) could install their own RUs, but then lease on-demand computational resources for the processing of DU and CU functions from commonly available open-cloud (O-Cloud) servers via open x-haul interfaces due to variation of load over the day. This creates a multi-tenant scenario where multiple MNOs share networking as well as computational resources. In this paper, we propose a framework that dynamically allocates x-haul and DU/CU resources in a multi-tenant O-RAN ecosystem with min-max fairness guarantees. This framework ensures that a maximum number of RUs get sufficient resources while minimizing the OPEX for their MNOs. Moreover, in order to provide an access network architecture capable of sustaining low-latency and high capacity between RUs and edge-computing devices, we consider time-wavelength division multiplexed (TWDM) passive optical network (PON)-based x-haul interfaces where the PON virtualization technique is used to provide a direct optical connection between end-points. This creates a virtual mesh interconnection among all the nodes such that the RUs can be connected to the Edge-Clouds at macro-cell RU locations as well as to the O-Cloud servers at the central office locations. Furthermore, we analyze the system performance with our proposed framework and show that MNOs can operate with a better cost-efficiency than baseline greedy resource allocation with uniform cost-sharing.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Optical Front/Mid-haul with Open Access-Edge Server Deployment Framework for Sliced O-RAN

The fifth-generation of mobile radio technologies is expected to be agile, flexible, and scalable while provisioning ultra-reliable and low-latency communication (uRLLC), enhanced mobile broadband (eMBB), and massive machine type communication (mMTC) applications. An efficient way of implementing these is by adopting cloudification, network function virtualization, and network slicing techniques with open-radio access network (O-RAN) architecture where the base-band processing functions are disaggregated into virtualized radio unit (RU), distributed unit (DU), and centralized unit (CU) over front/mid-haul interfaces. However, cost-efficient solutions are required for designing front/mid-haul interfaces and time-wavelength division multiplexed (TWDM) passive optical network (PON) appears as a potential candidate. Therefore, in this paper, we propose a framework for the optimal placement of RUs based on long-term network statistics and connecting them to open access-edge servers for hosting the corresponding DUs and CUs over front/mid-haul interfaces while satisfying the diverse QoS requirements of uRLLC, eMBB, and mMTC slices. In turn, we formulate a two-stage integer programming problem and time-efficient heuristics for users to RU association and flexible deployment of the corresponding DUs and CUs. We evaluate the O-RAN deployment cost and latency requirements with our TWDM-PON-based framework against urban, rural, and industrial areas and show its efficiency over the optical transport network (OTN)-based framework.

0 citations0 reviewsNo code linkedOpen access