Motoharu Matsuura

Egemen Erbayat, Gustavo B. Figueiredo, Shih-Chun Lin et al.

As mobile networks transition toward 5G and 6G RAN architectures, Passive Optical Networks (PONs) offer a critical solution for cost-effective fronthaul transport. However, the lack of standardized evaluation models in current literature makes an objective comparison of diverse optimization strategies difficult. This paper addresses this gap by proposing a unified benchmarking framework that standardizes cost catalogs and deployment scenarios. We formulate the network design problem using Integer Linear Programming (ILP) to establish optimality bounds and evaluate three scalable heuristic strategies: a Genetic Algorithm, K-Means Clustering (KMC+), and a graph-based Randomized Successive Splitter Assignment (RSSA+) algorithm. Simulation results show that a time-limited ILP remains a strong reference point, even when optimality is not reached. Despite being rarely used in prior fronthaul planning studies, it consistently yields solutions superior to those produced by standard heuristic methods. Among scalable approaches, RSSA+ reliably attains near-ILP performance while ensuring feasibility across all evaluated scenarios, which underscores the importance of advanced, constraint-aware algorithmic designs over simpler heuristics.

Faisal Ahmed, Myungjin Lee, Suresh Subramaniam et al.

Federated Learning (FL) has garnered significant interest recently due to its potential as an effective solution for tackling many challenges in diverse application scenarios, for example, data privacy in network edge traffic classification. Despite its recognized advantages, FL encounters obstacles linked to statistical data heterogeneity and labeled data scarcity during the training of single-task models for machine learning-based traffic classification, leading to hindered learning performance. In response to these challenges, adopting a hard-parameter sharing multi-task learning model with auxiliary tasks proves to be a suitable approach. Such a model has the capability to reduce communication and computation costs, navigate statistical complexities inherent in FL contexts, and overcome labeled data scarcity by leveraging knowledge derived from interconnected auxiliary tasks. This paper introduces a new framework for federated auxiliary hard-parameter sharing multi-task learning, namely, FedAuxHMTL. The introduced framework incorporates model parameter exchanges between edge server and base stations, enabling base stations from distributed areas to participate in the FedAuxHMTL process and enhance the learning performance of the main task-network edge traffic classification. Empirical experiments are conducted to validate and demonstrate the FedAuxHMTL's effectiveness in terms of accuracy, total global loss, communication costs, computing time, and energy consumption compared to its counterparts.