Towards software-defined tactical networks: Experiments and challenges for control overhead

PHL Rettore, M Djurica, RRF Lopes… - MILCOM 2022-2022 …, 2022‏ - ieeexplore.ieee.org
Software-defined Tactical Networks (SDTNs) have the potential to host intelligent
mechanisms to manage ever-changing communication scenarios in networks with …

Adversarial attacks against reinforcement learning based tactical networks: A case study

JF Loevenich, J Bode, T Hürten… - MILCOM 2022-2022 …, 2022‏ - ieeexplore.ieee.org
Dynamic changes caused by conditions such as challenging terrain or hostile encounters
force tactical networks to be highly adaptable. To tackle this problem, new proposals …

Mobility prediction at the tactical edge: A handover for centralized/decentralized networks

M Von Rechenberg, JF Loevenich… - 2023 International …, 2023‏ - ieeexplore.ieee.org
This paper presents a mobility prediction model as part of a handover mechanism
combining centralized and decentralized network control to improve performance and …

Cooperative agent system for quantifying link robustness in tactical networks

JF Loevenich, P Zißner, PHL Rettore… - MILCOM 2023-2023 …, 2023‏ - ieeexplore.ieee.org
This paper presents a cooperative agent system employing Reinforcement Learning (RL) to
quantify path robustness in tactical networks. We implement an environment builder agent …

Coordinating the sdn and tdma planes in software-defined tactical manets with adaptive coding and modulation

Y Papageorgiou, JF Loevenich… - 2023 International …, 2023‏ - ieeexplore.ieee.org
In this paper, we investigate a tactical mobile ad hoc network (MANET) enhanced with
software defined networking (SDN) functionality. Radio transmissions of network links are …

Controller Placement and TDMA Link Scheduling in Software Defined Wireless Multihop Networks

Y Papageorgiou, M Karaliopoulos… - ICC 2023-IEEE …, 2023‏ - ieeexplore.ieee.org
In this paper, we iterate on Software Defined wireless Multihop Networks (SDWMNs) and
TDMA-scheduled links, where data and SDN control traffic compete for the same resources …

DRL meets GNN to improve QoS in Tactical MANETs

JF Loevenich, RRF Lopes - NOMS 2024-2024 IEEE Network …, 2024‏ - ieeexplore.ieee.org
This paper proposes a hybrid AI model combining Graph Neural Network (GNN) and Deep
Reinforcement Learning (DRL) to improve QoS in modern communication systems deployed …

GNN-based Deep Reinforcement Learning with Adversarial Training for Robust Optimization of Modern Tactical Communication Systems

J Loevenich, RRF Lopes - Authorea Preprints, 2023‏ - techrxiv.org
This paper investigates the feasibility of a Graph Neural Network (GNN)-based Deep
Reinforcement Learning (DRL) for tackling complex optimization problems in modern …

[PDF][PDF] Bachelor's Thesis

J Bode - 2023‏ - rettore.com.br
Reinforcement Learning (RL) is a promising approach for routing in highly dynamic
environments such as Tactical Networks (TNs). However, the use of RL in TNs exposes a …

[PDF][PDF] SOFTANET: Slices, QoS and Resilience in Federated Mission Networks with SDN

M de Graaf, PHL Rettore, D Belabed, A van der Linden…‏ - sto.nato.int
The EDA project SOFTANET has investigated how to apply Software-defined Networking
(SDN) and Network Function Virtualisation (NFV) to achieve flexible and robust military …