Carlos Juiz

Francisco Talavera, Isaac Lera, Carlos Juiz et al.

The organization of fog devices into fog colonies has reduced the complexity management of fog domains. One of the main influencing factors on this complexity is the large number of devices, i.e. the high scale level of the infrastructure. Fog colonies are subsets of fog devices that are managed independently from the other colonies. Thus, the number of devices involved in the management of a colony is much smaller. Previous studies have evaluated the influence of the fog colony layout on system performance metrics. We propose to use a hierarchical clustering as the base definition of the fog colony layout of the fog infrastructure. The dendrogram obtained from this hierarchical clustering includes all the colony candidates. A genetic algorithm is in charge of selecting the subset of colony candidates that optimizes the two performance metrics under study: the network communication time between users and applications, and the execution time of the algorithms that manage internally the placement of the applications in each colony. We implemented the NSGA-II, a common multi-objective approach for GAs, to evaluate our proposal. The results show that a meta-heuristic such as a GA improves the performance metrics by defining the fog colony layout through the use of the dendrogram. Nine different experiment scenarios, varying the number of applications and fog devices, were studied. In the worst of the cases, 137 generations were enough to the results of the GA dominated the solutions obtained with two control algorithms. The number of genetic solutions and their homogeneous distribution in the Pareto front were also satisfactory.

David Cortes, Carlos Juiz, Belen Bermejo

Training large-scale deep learning models has become a key challenge for the scientific community and industry. While the massive use of GPUs can significantly speed up training times, this approach has a negative impact on efficiency. In this article, we present a detailed analysis of the times reported by MLPerf Training v4.1 on four workloads: BERT, Llama2 LoRA, RetinaNet, and Stable Diffusion, showing that there are configurations that optimise the relationship between performance, GPU usage, and efficiency. The results point to a break-even point that allows training times to be reduced while maximising efficiency.

Carlos Guerrero, Isaac Lera, Carlos Juiz

The increasing complexity of fog computing environments calls for efficient resource optimization techniques. In this paper, we propose and evaluate three distributed designs of a genetic algorithm (GA) for resource optimization in fog computing, within an increasing degree of distribution. The designs leverage the execution of the GA in the fog devices themselves by dealing with the specific features of this domain: constrained resources and widely geographical distribution of the devices. For their evaluation, we implemented a benchmark case using the NSGA-II for the specific problem of optimizing the fog service placement, according to the guidelines of our three distributed designs. These three experimental scenarios were compared with a control case, a traditional centralized version of this GA algorithm, considering solution quality and network overhead. The results show that the design with the lowest distribution degree, which keeps centralized storage of the objective space, achieves comparable solution quality to the traditional approach but incurs a higher network load. The second design, which completely distributes the population between the workers, reduces network overhead but exhibits lower solution diversity while keeping enough good results in terms of optimization objective minimization. Finally, the proposal with a distributed population and that only interchanges solution between the workers' neighbors achieves the lowest network load but with compromised solution quality.