This study aims to optimize vehicular user association to base stations in a mobile network. We propose an efficient heuristic solution that considers the base station average handover frequency, the channel quality indicator, and bandwidth capacity. We evaluate this solution using real-world base station locations from São Paulo, Brazil, and the SUMO mobility simulator. We compare our approach against a state of the art solution which uses route prediction, maintaining or surpassing the provided quality of service with the same number of handover operations. Additionally, the proposed solution reduces the execution time by more than 80% compared to an exact method, while achieving optimal solutions.

The clustering problem, or grouping, has two variants. If the number of clusters is predefined, this problem is known as the Clustering Problem (CP) or k-Clustering Problem, but when the number of clusters is not defined, the problem is known as the Automatic Clustering Problem (ACP). This paper proposes a new multi-population Biased Random-Key Genetic Algorithm (BRKGA) for the ACP, considering the silhouette index as similarity measure. In algorithm, several BRKGA populations evolve independently, such that each population is responsible for searching the best clustering for a given cluster number, i.e., each population solves one k-Clustering Problem for a particular k. Extensive experiments in 53 benchmark instances commonly used in the literature show that the algorithm obtained very competitive results compared to the state-of-the-art algorithms.

In this work, we conduct a comparative study of GPU accelerated metaheuristics for data clustering. Three population-based metaheuristics were implemented in GPU: Particle Swarm Optimization (PSO), Differential Evolution (DE), Scatter Search (SS). These metaheuristics were compared with the state-of-the-art methods for data clustering considering both runtime efficiency and solution quality. GPU-PSO and GPU-DE algorithms demonstrated competitive performance in the data sets proposed by the literature, as well as real-world problems. Moreover, experimental results show that our GPU proposal obtained an average speedup of 175x over the CPU-only implementation.