Asier Perallos

An easy to deploy street light control system based on wireless communication and LED technology.

This paper presents an intelligent streetlight management system based on LED lamps, designed to facilitate its deployment in existing facilities. The proposed approach, which is based on wireless communication technologies, will minimize the cost of investment of traditional wired systems, which always need civil engineering for burying of cable underground and consequently are more expensive than if the connection of the different nodes is made over the air. The deployed solution will be aware of their surroundings environmental conditions, a fact that will be approached for the system intelligence in order to learn, and later, apply dynamic rules. The knowledge of real time illumination needs, in terms of instant use of the street in which it is installed, will also feed our system, with the objective of providing tangible solutions to reduce energy consumption according to the contextual needs, an exact calculation of energy consumption and reliable mechanisms for preventive maintenance of facilities.

A Hybrid Method for Short-Term Traffic Congestion Forecasting Using Genetic Algorithms and Cross Entropy

This paper presents a method of optimizing the elements of a hierarchy of fuzzy-rule-based systems (FRBSs). It is a hybridization of a genetic algorithm (GA) and the cross-entropy (CE) method, which is here called GACE. It is used to predict congestion in a 9-km-long stretch of the I5 freeway in California, with time horizons of 5, 15, and 30 min. A comparative study of different levels of hybridization in GACE is made. These range from a pure GA to a pure CE, passing through different weights for each of the combined techniques. The results prove that GACE is more accurate than GA or CE alone for predicting short-term traffic congestion.

A discrete firefly algorithm to solve a rich vehicle routing problem modelling a newspaper distribution system with recycling policy

A real-world newspaper distribution problem with recycling policy is tackled in this work. To meet all the complex restrictions contained in such a problem, it has been modeled as a rich vehicle routing problem, which can be more specifically considered as an asymmetric and clustered vehicle routing problem with simultaneous pickup and deliveries, variable costs and forbidden paths (AC-VRP-SPDVCFP). This is the first study of such a problem in the literature. For this reason, a benchmark composed by 15 instances has been also proposed. In the design of this benchmark, real geographical positions have been used, located in the province of Bizkaia, Spain. For the proper treatment of this AC-VRP-SPDVCFP, a discrete firefly algorithm (DFA) has been developed. This application is the first application of the firefly algorithm to any rich vehicle routing problem. To prove that the proposed DFA is a promising technique, its performance has been compared with two other well-known techniques: an evolutionary algorithm and an evolutionary simulated annealing. Our results have shown that the DFA has outperformed these two classic meta-heuristics.

Non-Uniformly Distributed-Turns Coil Antenna for Enhanced H-Field in HF-RFID

A design study of coil antennas aimed to be used as Interrogators in high-frequency (HF) radio frequency identification (RFID) is presented. The magnetic field (H-field) of the coil is enhanced by defining optimally the number of turns of the antenna, and optimizing and exploiting the internal area of an initial coil. The distributed turns coil antennas are designed for highest possible H-field without compromising the Q-factor of the antenna with respect to an initial design. To achieve best solution, a non-uniformly distributed turns design is proposed and whose radiating elements are formulated accordingly. The analytical and simulated results show reasonable agreement to validate the designs. The enhanced H-field of the antenna shows an unconstrained Q-factor, indicates a potential rise to the interrogating coverage and as a result a higher efficient antenna.

A multi-crossover and adaptive island based population algorithm for solving routing problems

We propose a multi-crossover and adaptive island based population algorithm (MAIPA). This technique divides the entire population into subpopulations, or demes, each with a different crossover function, which can be switched according to the efficiency. In addition, MAIPA reverses the philosophy of conventional genetic algorithms. It gives priority to the autonomous improvement of the individuals (at the mutation phase), and introduces dynamism in the crossover probability. Each subpopulation begins with a very low value of crossover probability, and then varies with the change of the current generation number and the search performance on recent generations. This mechanism helps prevent premature convergence. In this research, the effectiveness of this technique is tested using three well-known routing problems, i.e., the traveling salesman problem (TSP), capacitated vehicle routing problem (CVRP), and vehicle routing problem with backhauls (VRPB). MAIPA proves to be better than a traditional island based genetic algorithm for all these three problems.

An Adaptive Multi-Crossover Population Algorithm for Solving Routing Problems

Throughout the history, Genetic Algorithms (GA) have been widely applied to a broad range of combinatorial optimization problems. Its easy applicability to areas such as transport or industry has been one of the reasons for its great success. In this paper, we propose a new Adaptive Multi-Crossover Population Algorithm (AMCPA). This new technique changes the philosophy of the basic genetic algorithms, giving priority to the mutation phase and providing dynamism to the crossover probability. To prevent the premature convergence, in the proposed AMCPA, the crossover probability begins with a low value, and varies depending on two factors: the algorithm performance on recent generations and the current generation number. Apart from this, as another mechanism to avoid premature convergence, our AMCPA has different crossover functions, which are used alternatively. We test the quality of our new technique applying it to three routing problems: the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP) and the Vehicle Routing Problem with Backhauls (VRPB). We compare the results with the ones obtained by a basic GA to conclude that our new proposal outperforms it.

Analysis of the suitability of using blind crossover operators in genetic algorithms for solving routing problems

Genetic algorithms (GA) are one of the most successful techniques in solving combinatorial optimization problems. Its general character has enabled its application to different types of problems: vehicle routing, planning, scheduling, etc. This article shows that there is controversy in the basic structure of the algorithm steps when it is applied at routing problems. Specifically in this paper we show that the crossover (CX) offers no advantage in the optimization process. To solve such problems, the most important steps are mutation and selection of individuals. These two steps are what help to analyze the solution space exhaustively and give GA optimization capability. To prove our hypothesis we will analyze the results obtained by applying different blind crossover operators to solve multiple instances of the TSP (Travelling Salesman Problem).

Design and Implementation of Context Aware Applications With Wireless Sensor Network Support in Urban Train Transportation Environments

Transportation system is experiencing steady growth, with the aim of providing more efficient, reliable, and comfortable services, in the framework of intelligent transportation systems. Moreover, context aware environments are one of the main drivers in the achievement of smart cities and smart regions. In this paper, wireless sensor networks (WSNs) embedded in urban transportation systems will be analyzed in terms of impact on wireless channel behavior and system performance. An in-house developed 3-D ray launching tool, with the inclusion of in-house human body model as well as with the study of interference levels is employed. Wireless channel estimations indicate an initial infrastructure node density in the order of 1node/150m2 to 1node/500m2 as a function of the employed transceivers. A practical solution has been implemented, combining an Android-based application and a system level architecture over the WSN for urban train transportation environmental monitoring, providing interaction between users and the environment, with the aid of a combined WSN/WLAN platform as well as an implemented software architecture, scalable in terms of user density and future needs.

Ubiquitous Connected Train Based on Train-to-Ground and Intra-Wagon Communications Capable of Providing on Trip Customized Digital Services for Passengers

During the last years, the application of different wireless technologies has been explored in order to enable Internet connectivity from vehicles. In addition, the widespread adoption of smartphones by citizens represents a great opportunity to integrate such nomadic devices inside vehicles in order to provide new and personalized on trip services for passengers. In this paper, a proposal of communication architecture to provide the ubiquitous connectivity needed to enhance the smart train concept is presented and preliminarily tested. It combines an intra-wagon communication system based on nomadic devices connected through a Bluetooth Piconet Network with a highly innovative train-to-ground communication system. In order to validate this communication solution, several tests and simulations have been performed and their results are described in this paper.

GACE: A meta-heuristic based in the hybridization of Genetic Algorithms and Cross Entropy methods for continuous optimization

Abstract Metaheuristics have proven to get a good performance solving difficult optimization problems in practice. Despite its success, metaheuristics still suffers from several problems that remains open as the variability of their performance depending on the problem or instance being solved. One of the approaches to deal with these problems is the hybridization of techniques. This paper presents a hybrid metaheuristic that combines a Genetic Algorithm (GA) with a Cross Entropy (CE) method to solve continuous optimization functions. The algorithm divides the population into two sub-populations, in order to apply GA in one sub-population and CE in the other. The proposed method is tested on 24 continuous benchmark functions, with four different dimension configurations. First, a study to find the best parameter configuration is done. The best configuration found is compared with several algorithms in the literature in order to demonstrate the competitiveness of the proposal. The results shows that GACE is the best performing method for instances with high dimensionality. Statistical tests have been applied, to support the conclusions obtained in the experimentation.