Isaac Lera

Isaac Lera, Carlos Guerrero

Simulation plays a key role in the design and evaluation of distributed systems, yet it is often treated as a static tool with limited interaction capabilities. In this work, we present Yet (not) Another Intelligent Fog Simulator (YAIFS), and evolution of YAFS that redefines simulation as an interactive, service-oriented environment. YAIFS introduce a layered architecture that exposes the simulation through a unified API and service interface, enabling external entities to observe, control, and modify its execution. A central contribution is the integration of the Model Context Protocol (MCP) as a standardized interaction layer between agents and the simulation. Through MCP, heterogeneous agents can access state, invoke actions and coordinate behavior using a common set of tools, decoupling agent experimentation workflows. We illustrate these capabilities through two scenarios: an LLM-based assistant that enable natural language control of simulations, and a multi-agent setting where agents monitor system conditions and adapt placement decisions at runtime. These scenarios demonstrate how MCP structures agent-simulation interaction and enable adaptive behavior under dynamic workloads. The proposed approach transforms simulation into an interactive and programmable environment, opening new directions for AI-driven experimentation in cloud-edge systems. The implementation is publicly available at: http://github.com/acsicuib/YAIFS

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.

Isaac Lera, Carlos Guerrero

We propose a framework designed to tackle a multi-objective optimization challenge related to the placement of applications in fog computing, employing a deep reinforcement learning (DRL) approach. Unlike other optimization techniques, such as integer linear programming or genetic algorithms, DRL models are applied in real time to solve similar problem situations after training. Our model comprises a learning process featuring a graph neural network and two actor-critics, providing a holistic perspective on the priorities concerning interconnected services that constitute an application. The learning model incorporates the relationships between services as a crucial factor in placement decisions: Services with higher dependencies take precedence in location selection. Our experimental investigation involves illustrative cases where we compare our results with baseline strategies and genetic algorithms. We observed a comparable Pareto set with negligible execution times, measured in the order of milliseconds, in contrast to the hours required by alternative approaches.

Francisco Talavera, Isaac Lera, Carlos Guerrero

This paper presents a method that generates a hierarchical user mobility model from the analysis of the data available from Wi-Fi connections. The data obtained from the Wi-Fi infrastructure is defined in terms of the coverage areas of the access points that the users move through. These access points are recursively grouped into different levels of granularity based on their geospatial features. The track of a user is defined as a sequence of Wi-Fi access points, which is enough to simulate user mobility in, for example, fog scenarios. The hierarchical definition of the region under study is proposed to reduce the complexity of the model in high-scale scenarios and to increase the adaptability between scenarios with different geospatial features. The model creation is based on a user profiling method that uses a clustering algorithm and each user type is defined with a transition matrix between coverage areas and a time length vector for the areas. The method is applied to the case of the campus of the University of the Balearic Islands. From the analysis of the mean square error of the results, we determined that the proposed method obtains good results for the transition matrices, but that the time vector definition should be improved. The results also show lower complexity in the case of the hierarchical model, with one area for each building and three levels, in regard to a non-hierarchical model, with only one area and one level for the whole campus.

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.