Panagiotis Trakadas

Alexandros S. Kalafatelis, Nikolaos Nomikos, Vasileios Nikolakakis et al.

Smart shipping operations increasingly depend on collaborative AI, yet the underlying data are generated across vessels with uneven connectivity, limited backhaul, and clear commercial sensitivity. In such settings, server-coordinated FL remains a weak systems assumption, depending on a reachable aggregation point and repeated wide-area synchronization, both of which are difficult to guarantee in maritime networks. A serverless gossip approach therefore represents a more natural approach, but existing methods still treat communication mainly as an optimization bottleneck, rather than as a resource that must be managed jointly with carbon cost, reliability, and long-term participation balance. In this context, this paper presents CARGO, a carbon-aware gossip orchestration framework for smart-shipping. CARGO separates learning into a control and a data plane. The data plane performs local optimization with compressed gossip exchange, while the control plane decides, at each round, which vessels should participate, which communication edges should be activated, how aggressively updates should be compressed, and when recovery actions should be triggered. We evaluate CARGO under a predictive-maintenance scenario using operational bulk-carrier engine data and a trace-driven maritime communication protocol that captures client dropout, partial participation, packet loss, and multiple connectivity regimes, derived from mobility-aware vessel interactions. Across the tested stress settings, CARGO consistently remains in the high-accuracy regime while reducing carbon footprint and communication overheads, compared to accuracy-competitive decentralized baselines. Overall, the conducted performance evaluation demonstrates that CARGO is a feasible and practical solution for reliable and resource-conscious maritime AI deployment.

Anastasios Giannopoulos, Sotirios Spantideas, Panagiotis Trakadas

The evolution of Open Radio Access Networks (O-RAN) enables programmable and intelligent control of radio resources through disaggregated architectures and open interfaces. However, existing solutions typically rely on isolated control loops and fail to jointly address end-to-end optimization objectives across multiple timescales. Thus, it remains a key challenge to functionally split optimization algorithms across timescale-specific O-RAN layers while complying with control loop latency specifications. This article proposes CollabORAN, a collaborative rApp-xApp-dApp hierarchical framework for dynamic and equitable spectrum sharing in O-RAN systems. CollabORAN leverages a nested control structure in which the rApp performs traffic-aware policy generation, the xApp executes interference-aware spectrum allocation via hypergraph-based PRB coloring, and the DU-level dApp enforces temporal fairness through fast scheduling. The proposed end-to-end closed-loop design enables coordinated optimization across minutes, seconds, and millisecond time scales. Simulation results demonstrate that CollabORAN significantly improves service fairness and reduces user starvation while maintaining efficient spectrum reuse in dense and dynamic network environments.

Spyros Rigas, Thanasis Papaioannou, Panagiotis Trakadas et al.

Kolmogorov-Arnold Networks (KANs) have recently demonstrated promising potential in scientific machine learning, partly due to their capacity for grid adaptation during training. However, existing adaptation strategies rely solely on input data density, failing to account for the geometric complexity of the target function or metrics calculated during network training. In this work, we propose a generalized framework that treats knot allocation as a density estimation task governed by Importance Density Functions (IDFs), allowing training dynamics to determine grid resolution. We introduce a curvature-based adaptation strategy and evaluate it across synthetic function fitting, regression on a subset of the Feynman dataset and different instances of the Helmholtz PDE, demonstrating that it significantly outperforms the standard input-based baseline. Specifically, our method yields average relative error reductions of 25.3% on synthetic functions, 9.4% on the Feynman dataset, and 23.3% on the PDE benchmark. Statistical significance is confirmed via Wilcoxon signed-rank tests, establishing curvature-based adaptation as a robust and computationally efficient alternative for KAN training.

Anastasios Giannopoulos, Sotirios Spantideas, Panagiotis Trakadas

The rapid proliferation of latency-sensitive and battery-constrained Internet-of-Things (IoT) applications has intensified the need for intelligent workload placement mechanisms across the Edge-Cloud computing continuum. In such environments, far-edge nodes must dynamically decide whether to execute workloads locally or offload them to neighboring nodes or the cloud, while accounting for execution delay, energy consumption, and strict timeout constraints. However, workload placement in large-scale distributed infrastructures is a highly dynamic and non-convex optimization problem due to stochastic arrivals, heterogeneous computing capacities, and time-varying network conditions. This paper proposes DECOFFEE, a decentralized reinforcement learning framework for time-critical workload offloading and energy-efficient operation across the computing continuum. The proposed multi-agent learning scheme jointly optimizes system delay, energy consumption, and workload drop rate through adaptive placement decisions. Each edge agent operates as an autonomous learning entity that derives an optimal policy from local system observations and predicted network conditions. The workload placement process is formulated as parallel Markov Decision Processes and solved using a Double Dueling Deep Q-Network (DQN) architecture enhanced with Long Short-Term Memory (LSTM) forecasting to anticipate future load conditions. Extensive simulations demonstrate that DECOFFEE and its variants consistently outperform conventional rule-based and heuristic placement strategies, achieving significant reductions in delay, energy consumption, and workload drop rate under varying traffic and network conditions.

Dmitrij Lagutin, Francesco Bellesini, Tommaso Bragatto et al.

The lack of interoperability among IoT platforms has led to a fragmented environment, where the users and society as a whole suffer from lock-ins, lack of privacy, and reduced functionality. This paper presents SOFIE, a solution for federating the existing IoT platforms in an open and secure manner using Distributed Ledger Technologies (DLTs) and without requiring modifications to the IoT platforms, and describes how SOFIE is used to enable two complex real life pilots: food supply chain tracking from field to fork and electricity distribution grid balancing with guided electrical vehicle (EV) charging. SOFIE's main contribution is to provide interoperability between IoT systems while also enabling new functionality and business models.