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

Marwan Krunz

Marwan Krunz contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Networking and Internet Architectureeess.SPMachine LearningArtificial IntelligenceDistributed, Parallel, and Cluster ComputingInformation Theorymath.ITComputer Science and Game Theoryeess.SYMultiagent SystemsSystems and Control

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
11topics
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

SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking

Future networking systems are envisioned to become part of an agentic AI-native ecosystem in which a vast number of heterogeneous and specialized AI agents cooperate seamlessly to fulfill complex user requirements in real time. However, traditional networking paradigms are characterized by a rigid decoupling of communication and computation, which often leads to significant inefficiencies in large-scale agentic AI networking (AgentNet) systems. Emergent communication offers a novel solution by enabling autonomous agents that support task-specific signaling protocols for information exchange and collaborative coordination. In this paper, we consider a multi-agent emergent communication framework, tailored for semantic-aware AgentNet systems in which the user's semantic intent can be automatically detected, inferred, and linked to a set of sub-tasks to be assigned to a set of agents. We investigate how communication and signaling protocols can emerge among collaborative agents with computationally bounded intelligence under stringent bandwidth constraints. Our proposed framework, called SANEmerg, is designed to facilitate the emergence of communication for collaborative task fulfillment while adhering to the physical limits of AgentNet. SANEmerg incorporates a bandwidth-adaptable importance-filter that dynamically prioritizes the transmission of higher-contribution message dimensions, ensuring robust performance in bandwidth-limited environments. Furthermore, SANEmerg integrates a complexity-regularizer grounded in the Minimum Description Length (MDL) principle to facilitate the emergence of computationally bounded signaling. Evaluated via an AgentNet prototype and extensive experimentation, SANEmerg demonstrates significant performance improvements over state-of-the-art solutions, achieving superior task accuracy while significantly reducing bandwidth and computational overhead.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers

Convolutional Neural Networks (CNNs) are one of the most studied family of deep learning models for signal classification, including modulation, technology, detection, and identification. In this work, we focus on technology classification based on raw I/Q samples collected from multiple synchronized receivers. As an example use case, we study protocol identification of Wi-Fi, LTE-LAA, and 5G NR-U technologies that coexist over the 5 GHz Unlicensed National Information Infrastructure (U-NII) bands. Designing and training accurate CNN classifiers involve significant time and effort that goes into fine-tuning a model's architectural settings and determining the appropriate hyperparameter configurations, such as learning rate and batch size. We tackle the former by defining architectural settings themselves as hyperparameters. We attempt to automatically optimize these architectural parameters, along with other preprocessing (e.g., number of I/Q samples within each classifier input) and learning hyperparameters, by forming a Hyperparameter Optimization (HyperOpt) problem, which we solve in a near-optimal fashion using the Hyperband algorithm. The resulting near-optimal CNN (OCNN) classifier is then used to study classification accuracy for OTA as well as simulations datasets, considering various SNR values. We show that the number of receivers to construct multi-channel inputs for CNNs should be defined as a preprocessing hyperparameter to be optimized via Hyperband. OTA results reveal that our OCNN classifiers improve classification accuracy by 24.58% compared to manually tuned CNNs. We also study the effect of min-max normalization of I/Q samples within each classifier's input on generalization accuracy over simulated datasets with SNRs other than training set's SNR and show an average of 108.05% improvement when I/Q samples are normalized.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Game of GANs: Game-Theoretical Models for Generative Adversarial Networks

Generative Adversarial Networks (GANs) have recently attracted considerable attention in the AI community due to its ability to generate high-quality data of significant statistical resemblance to real data. Fundamentally, GAN is a game between two neural networks trained in an adversarial manner to reach a zero-sum Nash equilibrium profile. Despite the improvement accomplished in GANs in the last few years, several issues remain to be solved. This paper reviews the literature on the game theoretic aspects of GANs and addresses how game theory models can address specific challenges of generative model and improve the GAN's performance. We first present some preliminaries, including the basic GAN model and some game theory background. We then present taxonomy to classify state-of-the-art solutions into three main categories: modified game models, modified architectures, and modified learning methods. The classification is based on modifications made to the basic GAN model by proposed game-theoretic approaches in the literature. We then explore the objectives of each category and discuss recent works in each category. Finally, we discuss the remaining challenges in this field and present future research directions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Generative Learning Approach for Spatio-temporal Modeling in Connected Vehicular Network

Spatio-temporal modeling of wireless access latency is of great importance for connected-vehicular systems. The quality of the molded results rely heavily on the number and quality of samples which can vary significantly due to the sensor deployment density as well as traffic volume and density. This paper proposes LaMI (Latency Model Inpainting), a novel framework to generate a comprehensive spatio-temporal of wireless access latency of a connected vehicles across a wide geographical area. LaMI adopts the idea from image inpainting and synthesizing and can reconstruct the missing latency samples by a two-step procedure. In particular, it first discovers the spatial correlation between samples collected in various regions using a patching-based approach and then feeds the original and highly correlated samples into a Variational Autoencoder (VAE), a deep generative model, to create latency samples with similar probability distribution with the original samples. Finally, LaMI establishes the empirical PDF of latency performance and maps the PDFs into the confidence levels of different vehicular service requirements. Extensive performance evaluation has been conducted using the real traces collected in a commercial LTE network in a university campus. Simulation results show that our proposed model can significantly improve the accuracy of latency modeling especially compared to existing popular solutions such as interpolation and nearest neighbor-based methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Distributed Optimization for Energy-efficient Fog Computing in the Tactile Internet

Tactile Internet is an emerging concept that focuses on supporting high-fidelity, ultra-responsive, and widely available human-to-machine interactions. To reduce the transmission latency and alleviate Internet congestion, fog computing has been advocated as an important component of the Tactile Internet. In this paper, we focus on energy-efficient design of fog computing networks that support low-latency Tactile Internet applications. We investigate two performance metrics: Service response time of end-users and power usage efficiency of fog nodes. We quantify the fundamental tradeoff between these two metrics and then extend our analysis to fog computing networks involving cooperation between fog nodes. We introduce a novel cooperative fog computing concept, referred to as offload forwarding, in which a set of fog nodes with different computing and energy resources can cooperate with each other. The objective of this cooperation is to balance the workload processed by different fog nodes, further reduce the service response time, and improve the efficiency of power usage. We develop a distributed optimization framework based on dual decomposition to achieve the optimal tradeoff. Our framework does not require fog nodes to disclose their private information nor conduct back-and-forth negotiations with each other. Two distributed optimization algorithms are proposed. One is based on the subgradient method with dual decomposition and the other is based on distributed ADMM-VS. We prove that both algorithms can achieve the optimal workload allocation that minimizes the response time under the given power efficiency constraints of fog nodes.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Distributed Resource Allocation for Network Slicing over Licensed and Unlicensed Bands

Network slicing is considered one of the key enabling technologies for 5G due to its ability to customize and "slice" a common resource to support diverse services and verticals.This paper introduces a novel inter-operator network slicing framework in which multiple mobile network operators (MNOs) can coordinate and jointly slice their accessible spectrum resources in both licensed and unlicensed bands. For licensed band slicing, we propose an inter-operator spectrum aggregation method that allows two or more MNOs to cooperate and share their licensed bands to support a common set of service types. We then consider the sharing of unlicensed bands. Because all MNOs enjoy equal rights to accessing these bands, we introduce the concept of right sharing for MNOs to share and trade their spectrum access rights. We develop a {\em modified back-of-the-envelope (mBoE) method} for MNOs to evaluate their {\em Value-of-Rights (VoR)} when coexisting with other wireless technologies. A {\em network slicing game} based on the overlapping coalition formation game is formulated to investigate cooperation between MNOs. We prove that our proposed game always has at least one stable slicing structure that maximizes the social welfare. To implement our proposed framework without requiring MNOs to reveal private information to other MNOs, we develop a distributed algorithm called D-ADMM-PVS. Performance evaluation of our proposed framework is provided using a discrete-event simulator that is driven by real MNO deployment scenarios based on over 400 base station locations deployed by two primary cellular operators in the city of Dublin.Numerical results show that our proposed framework can almost double the capacity for all supported services for each MNO in an urban setting.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Dynamic Network Slicing for Scalable Fog Computing Systems with Energy Harvesting

This paper studies fog computing systems, in which cloud data centers can be supplemented by a large number of fog nodes deployed in a wide geographical area. Each node relies on harvested energy from the surrounding environment to provide computational services to local users. We propose the concept of dynamic network slicing in which a regional orchestrator coordinates workload distribution among local fog nodes, providing partitions/slices of energy and computational resources to support a specific type of service with certain quality-of-service (QoS) guarantees. The resources allocated to each slice can be dynamically adjusted according to service demands and energy availability. A stochastic overlapping coalition-formation game is developed to investigate distributed cooperation and joint network slicing between fog nodes under randomly fluctuating energy harvesting and workload arrival processes. We observe that the overall processing capacity of the fog computing network can be improved by allowing fog nodes to maintain a belief function about the unknown state and the private information of other nodes. An algorithm based on a belief-state partially observable Markov decision process (B-POMDP) is proposed to achieve the optimal resource slicing structure among all fog nodes. We describe how to implement our proposed dynamic network slicing within the 3GPP network sharing architecture, and evaluate the performance of our proposed framework using the real BS location data of a real cellular system with over 200 BSs deployed in the city of Dublin. Our numerical results show that our framework can significantly improve the workload processing capability of fog computing networks. In particular, even when each fog node can coordinate only with its closest neighbor, the total amount of workload processed by fog nodes can be almost doubled under certain scenarios.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multi-operator Network Sharing for Massive IoT

Recent study predicts that by 2020 up to 50 billion IoT devices will be connected to the Internet, straining the capacity of wireless network that has already been overloaded with data-hungry mobile applications, such as high-definition video streaming and virtual reality(VR)/augmented reality(AR). How to accommodate the demand for both massive scale of IoT devices and high-speed cellular services in the physically limited spectrum without significantly increasing the operational and infrastructure costs is one of the main challenges for operators. In this article, we introduce a new multi-operator network sharing framework that supports the coexistence of IoT and high-speed cellular services. Our framework is based on the radio access network (RAN) sharing architecture recently introduced by 3GPP as a promising solution for operators to improve their resource utilization and reduce the system roll-out cost. We evaluate the performance of our proposed framework using the real base station location data in the city of Dublin collected from two major operators in Ireland. Numerical results show that our proposed framework can almost double the total number of IoT devices that can be supported and coexist with other cellular services compared with the case without network sharing.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Ubiquitous AI in 6G with Federated Learning

With 5G cellular systems being actively deployed worldwide, the research community has started to explore novel technological advances for the subsequent generation, i.e., 6G. It is commonly believed that 6G will be built on a new vision of ubiquitous AI, an hyper-flexible architecture that brings human-like intelligence into every aspect of networking systems. Despite its great promise, there are several novel challenges expected to arise in ubiquitous AI-based 6G. Although numerous attempts have been made to apply AI to wireless networks, these attempts have not yet seen any large-scale implementation in practical systems. One of the key challenges is the difficulty to implement distributed AI across a massive number of heterogeneous devices. Federated learning (FL) is an emerging distributed AI solution that enables data-driven AI solutions in heterogeneous and potentially massive-scale networks. Although it still in an early stage of development, FL-inspired architecture has been recognized as one of the most promising solutions to fulfill ubiquitous AI in 6G. In this article, we identify the requirements that will drive convergence between 6G and AI. We propose an FL-based network architecture and discuss its potential for addressing some of the novel challenges expected in 6G. Future trends and key research problems for FL-enabled 6G are also discussed.

0 citations0 reviewsNo code linkedOpen access