Abstract This paper introduces a novel meta-heuristic for addressing a variant of the classical Capacitated Vehicle Routing Problem (CVRP) known as the Generalized Vehicle Routing Problem (GVRP). In the GVRP, nodes are organized into clusters, with the constraint that only one node from each cluster must be visited. The proposed meta-heuristic is a Hybrid Genetic Search (HGS) that leverages recent advancements in CVRP methodologies, adapting successful strategies and techniques from CVRP to the GVRP context. To evaluate the performance of the HGS meta-heuristic, we perform an extensive computational analysis on numerous benchmark instances ranging from small to large sizes. To thoroughly analyze the algorithm’s average behavior, convergence profiles over time are reported for the considered instances. Results show that the proposed algorithm achieves 174 new best solutions out of the 498 instances considered. In only six instances out of 498, the algorithm is unable to reach or improve upon the best-known solution in the literature. These results suggest that the proposed meta-heuristic has significant potential in addressing real-world generalized vehicle routing challenges. Code available at: https://github.com/vlatorre847/HGSGVRP .

This paper presents a new deterministic method and a polynomial-time algorithm for solving general huge-sized sensor network localization problems. The problem is first formulated as a nonconvex minimization, which was considered as an NP-hard based on conventional theories. However, by the canonical duality theory, this challenging problem can be equivalently converted into a convex dual problem. By introducing a new optimality measure, a powerful canonical primal-dual interior (CPDI) point algorithm is developed which can solve efficiently huge-sized problems with hundreds of thousands of sensors. The new method is compared with the popular methods in the literature. Results show that the CPDI algorithm is not only faster than the benchmarks but also much more accurate on networks affected by noise on the distances.

Yield optimization is a challenging topic in electronic circuit design. Methods for yield optimization based on Monte Carlo (MC) analysis of a circuit whose behavior is reproduced by simulations usually require too many time expensive simulations to be effective for iterative optimization. In this paper, we propose a method which tackles the yield optimization problem by combining a support vector machine (SVM) surrogate model (SM) of the circuit to perform the MC analysis and evaluate the yield, and an efficient optimization method to maximize the yield evaluated using the SVM SM. We report the numerical results obtained for the design of two real consumer circuits provided by STMicroelectronics, and we compare these results with the ones obtained using the industrial benchmark currently adopted at STMicroelectronics for yield optimization. These preliminary results show that the method is promising to be very efficient and capable of reaching design solutions with high values of the yield.