The forthcoming sixth generation (6G) of mobile communication networks is envisioned to be AI-native, supporting intelligent services and pervasive computing at unprecedented scale. Among the key paradigms enabling this vision, Federated Learning (FL) has gained prominence as a distributed machine learning framework that allows multiple devices to collaboratively train models without sharing raw data, thereby preserving privacy and reducing the need for centralized storage. This capability is particularly attractive for vision-based applications, where image and video data are both sensitive and bandwidth-intensive. However, the integration of FL with 6G networks presents unique challenges, including communication bottlenecks, device heterogeneity, and trade-offs between model accuracy, latency, and energy consumption. In this paper, we developed a simulation-based framework to investigate the performance of FL in representative vision tasks under 6G-like environments. We formalize the system model, incorporating both the federated averaging (FedAvg) training process and a simplified communication cost model that captures bandwidth constraints, packet loss, and variable latency across edge devices. Using standard image datasets (e.g., MNIST, CIFAR-10) as benchmarks, we analyze how factors such as the number of participating clients, degree of data heterogeneity, and communication frequency influence convergence speed and model accuracy. Additionally, we evaluate the effectiveness of lightweight communication-efficient strategies, including local update tuning and gradient compression, in mitigating network overhead. The experimental results reveal several key insights: (i) communication limitations can significantly degrade FL convergence in vision tasks if not properly addressed; (ii) judicious tuning of local training epochs and client participation levels enables notable improvements in both efficiency and accuracy; and (iii) communication-efficient FL strategies provide a promising pathway to balance performance with the stringent latency and reliability requirements expected in 6G. These findings highlight the synergistic role of AI and next-generation networks in enabling privacy-preserving, real-time vision applications, and they provide concrete design guidelines for researchers and practitioners working at the intersection of FL and 6G.

The Vehicle Routing Problem with Time Windows (VRPTW) presents a significant challenge in combinatorial optimization, especially under real-world uncertainties such as variable travel times, service durations, and dynamic customer demands. These uncertainties make traditional deterministic models inadequate, often leading to suboptimal or infeasible solutions. To address these challenges, this work proposes an adaptive hybrid metaheuristic that integrates Genetic Algorithms (GA) with Local Search (LS), while incorporating stochastic uncertainty modeling through probabilistic travel times. The proposed algorithm dynamically adjusts parameters—such as mutation rate and local search probability—based on real-time search performance. This adaptivity enhances the algorithm’s ability to balance exploration and exploitation during the optimization process. Travel time uncertainties are modeled using Gaussian noise, and solution robustness is evaluated through scenario-based simulations. We test our method on a set of benchmark problems from Solomon’s instance suite, comparing its performance under deterministic and stochastic conditions. Results show that the proposed hybrid approach achieves up to a 9% reduction in expected total travel time and a 40% reduction in time window violations compared to baseline methods, including classical GA and non-adaptive hybrids. Additionally, the algorithm demonstrates strong robustness, with lower solution variance across uncertainty scenarios, and converges faster than competing approaches. These findings highlight the method’s suitability for practical logistics applications such as last-mile delivery and real-time transportation planning, where uncertainty and service-level constraints are critical. The flexibility and effectiveness of the proposed framework make it a promising candidate for deployment in dynamic, uncertainty-aware supply chain environments.