From Latent Space to Training Data: Explainable Specialization in Minimal MLPs

We here study whether training biases can make hidden neurons specialize in minimal one-hidden-layer MLPs, and whether such specialization improves prototype-based reconstruction of the training dataset from the learned weights. We consider Gaussianactivation MLPs of width equal to dataset size and compare three structural losses that respectively encourage coverage of the training samples, separation between neuron-induced prototypes, and low overlap of hidden responses, against the standard fitting baseline. Experiments on uniformly sampled one-dimensional datasets show a stable pattern from N = 3 to N = 100 across 480 controlled runs. Coverage regularization gives the lowest mean reconstruction error at every tested size and raises the prototype-usage specialization ratio relative to the standard baseline, while separation has mixed effects and overlap penalties are systematically harmful. We show that the harm is not an optimization failure: overlap-active approaches fit the data as well as overlap-free ones but route the optimizer to a degenerate equilibrium in which prototype centers are pushed outside the convex hull of the training inputs. Coverage cannot reward this expulsion and acts as an attractor: separation admits it only at large temperature and overlap admits it at the nominal hyperparameter choice. A direct τ-sweep on the separation-only mask and a prototype-position visualization at N = 100 confirm the mechanism. The findings yield a simple design principle for prototype-recoverability-aware training: every repulsive structural loss must be compensated by a compatible attractor, or it will collapse the latent geometry it was meant to refine.

Green Optimization: Energy-aware Design of Metaheuristics by Using Machine Learning Surrogates to Cope with Real Problems

Addressing real-world optimization challenges requires not only advanced metaheuristics but also continuous refinement of their internal mechanisms. This paper explores the integration of machine learning in the form of neural surrogate models into metaheuristics through a recent lens: energy consumption. While surrogates are widely used to reduce the computational cost of expensive objective functions, their combined impact on energy efficiency, algorithmic performance, and solution accuracy remains largely unquantified. We provide a critical investigation into this intersection, aiming to advance the design of energy-aware, surrogate-assisted search algorithms. Our experiments reveal substantial benefits: employing a state-of-the-art pre-trained surrogate can reduce energy consumption by up to 98\%, execution time by approximately 98%, and memory usage by around 99\%. Moreover, increasing the training dataset size further enhances these gains by lowering the per-use computational cost, while static pre-training versus continuous (iterative) retraining have relatively different advantages depending on whether we aim at time/energy or accuracy and general cost across problems, respectively. Surrogates also have a negative impact on costs and accuracy at times, and then they cannot be blindly adopted. These findings support a more holistic approach to surrogate-assisted optimization, integrating energy with time and predictive accuracy into performance assessments.

A Methodology for Effective Surrogate Learning in Complex Optimization

Solving complex problems requires continuous effort in developing theory and practice to cope with larger, more difficult scenarios. Working with surrogates is normal for creating a proxy that realistically models the problem into the computer. Thus, the question of how to best define and characterize such a surrogate model is of the utmost importance. In this paper, we introduce the PTME methodology to study deep learning surrogates by analyzing their Precision, Time, Memory, and Energy consumption. We argue that only a combination of numerical and physical performance can lead to a surrogate that is both a trusted scientific substitute for the real problem and an efficient experimental artifact for scalable studies. Here, we propose different surrogates for a real problem in optimally organizing the network of traffic lights in European cities and perform a PTME study on the surrogates' sampling methods, dataset sizes, and resource consumption. We further use the built surrogates in new optimization metaheuristics for decision-making in real cities. We offer better techniques and conclude that the PTME methodology can be used as a guideline for other applications and solvers.

Energy-Aware Metaheuristics

This paper presents a principled framework for designing energy-aware metaheuristics that operate under fixed energy budgets. We introduce a unified operator-level model that quantifies both numerical gain and energy usage, and define a robust Expected Improvement per Joule (EI/J) score that guides adaptive selection among operator variants during the search. The resulting energy-aware solvers dynamically choose between operators to self-control exploration and exploitation, aiming to maximize fitness gain under limited energy. We instantiate this framework with three representative metaheuristics - steady-state GA, PSO, and ILS - each equipped with both lightweight and heavy operator variants. Experiments on three heterogeneous combinatorial problems (Knapsack, NK-landscapes, and Error-Correcting Codes) show that the energy-aware variants consistently reach comparable fitness while requiring substantially less energy than their non-energy-aware baselines. EI/J values stabilize early and yield clear operator-selection patterns, with each solver reliably self-identifying the most improvement-per-Joule - efficient operator across problems.

Energy and Quality of Surrogate-Assisted Search Algorithms: a First Analysis

Solving complex real problems often demands advanced algorithms, and then continuous improvements in the internal operations of a search technique are needed. Hybrid algorithms, parallel techniques, theoretical advances, and much more are needed to transform a general search algorithm into an efficient, useful one in practice. In this paper, we study how surrogates are helping metaheuristics from an important and understudied point of view: their energy profile. Even if surrogates are a great idea for substituting a time-demanding complex fitness function, the energy profile, general efficiency, and accuracy of the resulting surrogate-assisted metaheuristic still need considerable research. In this work, we make a first step in analyzing particle swarm optimization in different versions (including pre-trained and retrained neural networks as surrogates) for its energy profile (for both processor and memory), plus a further study on the surrogate accuracy to properly drive the search towards an acceptable solution. Our conclusions shed new light on this topic and could be understood as the first step towards a methodology for assessing surrogate-assisted algorithms not only accounting for time or numerical efficiency but also for energy and surrogate accuracy for a better, more holistic characterization of optimization and learning techniques.

Infrastructure Deployment in Vehicular Communication Networks Using a Parallel Multiobjective Evolutionary Algorithm

This article describes the application of a multiobjective evolutionary algorithm for locating roadside infrastructure for vehicular communication networks over realistic urban areas. A multiobjective formulation of the problem is introduced, considering quality-of-service and cost objectives. The experimental analysis is performed over a real map of M\'alaga, using real traffic information and antennas, and scenarios that model different combinations of traffic patterns and applications (text/audio/video) in the communications. The proposed multiobjective evolutionary algorithm computes accurate trade-off solutions, significantly improving over state-of-the-art algorithms previously applied to the problem.

Fast energy-aware OLSR routing in VANETs by means of a parallel evolutionary algorithm

This work tackles the problem of reducing the power consumption of the OLSR routing protocol in vehicular networks. Nowadays, energy-aware and green communication protocols are important research topics, specially when deploying wireless mobile networks. This article introduces a fast automatic methodology to search for energy-efficient OLSR configurations by using a parallel evolutionary algorithm. The experimental analysis demonstrates that significant improvements over the standard configuration can be attained in terms of power consumption, with no noteworthy loss in the QoS.

A swarm algorithm for collaborative traffic in vehicular networks

Vehicular ad hoc networks (VANETs) allow vehicles to exchange warning messages with each other. These specific kinds of networks help reduce hazardous traffic situations and improve safety, which are two of the main objectives in developing Intelligent Transportation Systems (ITS). For this, the performance of VANETs should guarantee the delivery of messages in a required time. An obstacle to this is that the data traffic generated may cause network congestion. Data congestion control is used to enhance network capabilities, increasing the reliability of the VANET by decreasing packet losses and communication delays. In this study, we propose a swarm intelligence based distributed congestion control strategy to maintain the channel usage level under the threshold of network malfunction, while keeping the quality-of-service of the VANET high. An exhaustive experimentation shows that the proposed strategy improves the throughput of the network, the channel usage, and the stability of the communications in comparison with other competing congestion control strategies.

Parallel multi-objective metaheuristics for smart communications in vehicular networks

This article analyzes the use of two parallel multi-objective soft computing algorithms to automatically search for high-quality settings of the Ad hoc On Demand Vector routing protocol for vehicular networks. These methods are based on an evolutionary algorithm and on a swarm intelligence approach. The experimental analysis demonstrates that the configurations computed by our optimization algorithms outperform other state-of-the-art optimized ones. In turn, the computational efficiency achieved by all the parallel versions is greater than 87 %. Therefore, the line of work presented in this article represents an efficient framework to improve vehicular communications.

Intelligent OLSR Routing Protocol Optimization for VANETs

Recent advances in wireless technologies have given rise to the emergence of vehicular ad hoc networks (VANETs). In such networks, the limited coverage of WiFi and the high mobility of the nodes generate frequent topology changes and network fragmentations. For these reasons, and taking into account that there is no central manager entity, routing packets through the network is a challenging task. Therefore, offering an efficient routing strategy is crucial to the deployment of VANETs. This paper deals with the optimal parameter setting of the optimized link state routing (OLSR), which is a well-known mobile ad hoc network routing protocol, by defining an optimization problem. This way, a series of representative metaheuristic algorithms (particle swarm optimization, differential evolution, genetic algorithm, and simulated annealing) are studied in this paper to find automatically optimal configurations of this routing protocol. In addition, a set of realistic VANET scenarios (based in the city of M\'alaga) have been defined to accurately evaluate the performance of the network under our automatic OLSR. In the experiments, our tuned OLSR configurations result in better quality of service (QoS) than the standard request for comments (RFC 3626), as well as several human experts, making it amenable for utilization in VANET configurations.