Catálogo de publicaciones - libros
Applications of Evolutinary Computing: EvoWorkshops 2007: EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog. Proceedings
Mario Giacobini (eds.)
En conferencia: Workshops on Applications of Evolutionary Computation (EvoWorkshops) . Valencia, Spain . April 11, 2007 - April 13, 2007
Resumen/Descripción – provisto por la editorial
No disponible.
Palabras clave – provistas por la editorial
Artificial Intelligence (incl. Robotics); Computation by Abstract Devices; Programming Techniques; Computer Hardware; Computer Communication Networks; Math Applications in Computer Science
Disponibilidad
Institución detectada | Año de publicación | Navegá | Descargá | Solicitá |
---|---|---|---|---|
No detectada | 2007 | SpringerLink |
Información
Tipo de recurso:
libros
ISBN impreso
978-3-540-71804-8
ISBN electrónico
978-3-540-71805-5
Editor responsable
Springer Nature
País de edición
Reino Unido
Fecha de publicación
2007
Información sobre derechos de publicación
© Springer-Verlag Berlin Heidelberg 2007
Tabla de contenidos
Evaluation of Different Metaheuristics Solving the RND Problem
Miguel A. Vega-Rodríguez; Juan A. Gómez-Pulido; Enrique Alba; David Vega-Pérez; Silvio Priem-Mendes; Guillermo Molina
RND (Radio Network Design) is a Telecommunication problem consisting in covering a certain geographical area by using the smallest number of radio antennas achieving the biggest cover rate. This is an important problem, for example, in mobile/cellular technology. RND can be solved by bio-inspired algorithms. In this work we use different metaheuristics to tackle this problem. PBIL (Population-Based Incremental Learning), based on genetic algorithms and competitive learning (typical in neural networks), is a population evolution model based on probabilistic models. DE (Differential Evolution) is a very simple population-based stochastic function minimizer used in a wide range of optimization problems, including multi-objective optimization. SA (Simulated Annealing) is a classic trajectory descent optimization technique. CHC is a particular class of evolutionary algorithm which does not use mutation and relies instead on incest prevention and disruptive crossover. Due to the complexity of such a large analysis including so many techniques, we have used not only sequential algorithms, but grid computing with BOINC in order to execute thousands of experiments in only several days using around 100 computers. In this paper we present the most interesting results from our work, indicating the pros and cons of the studied solvers.
- EvoCOMNET Contributions | Pp. 101-110
A Comparative Investigation on Heuristic Optimization of WCDMA Radio Networks
Mehmet E. Aydin; Jun Yang; Jie Zhang
The planning and optimization of WCDMA (wideband code-division multiple access)radio network issues remain vital, and are carried out using static snapshot-based simulation. To improve the accuracy of the static simulation, link-level performance factors, such as the impact of power control, pilot power and soft handover, have to be taken into account. These factors have not been investigated together in the previous works. In this paper, we give a brief introduction to our programming models that take these characteristics into account, and present optimisation strategies based on three major Metaheuristics; genetic algorithms (GA), simulated annealing (SA) and tabu search (TS). Extensive experimental results are provided and the performance of different heuristic algorithms is compared.
- EvoCOMNET Contributions | Pp. 111-120
Design of a User Space Software Suite for Probabilistic Routing in Ad-Hoc Networks
Frederick Ducatelle; Martin Roth; Luca Maria Gambardella
We describe the design of MagAntA, a software suite for the implementation of probabilistic routing in ad hoc networks under Linux. MagAntA is written in C and runs completely in user space. This, together with its modular structure, makes it easy to adapt and extend with new algorithms. MagAntA makes use of the Ana4 framework [3], a set of kernel modules that provide the necessary functionalities to support ad hoc mesh networking and facilitate integration with the Linux routing protocol stack. A new version of Ana4 presented in [25] passes each data packet up to user space for routing purposes. Building on this architecture gives MagAntA the possibility to have complete control over routing in user space, so that the per-packet stochastic forwarding typical for probabilistic routing can easily be implemented. MagAntA can also be used in other types of networks such as traditional wired networks, and can easily be extended to incorporate different types of routing algorithms, other than probabilistic ones.
- EvoCOMNET Contributions | Pp. 121-128
Empirical Validation of a Gossiping Communication Mechanism for Parallel EAs
Juan Luís Jiménez Laredo; Pedro Angel Castillo; Ben Paechter; Antonio Miguel Mora; Eva Alfaro-Cid; Anna I. Esparcia-Alcázar; Juan Julián Merelo
The development of Peer-to-Peer (P2P) systems is still a challenge due to the huge number of factors involved. Validation of these systems must be defined in terms of describing the adequacy of the P2P model to the actual environment. This paper focuses on the validation of the Distributed Resource Machine (DRM) as a computational P2P system when applied to Evolutionary Algorithms (EAs ) using exclusively gossip-based mechanisms for communication. The adequacy will be measured by the range in which performance speedup actually takes place. Validation has been carried out by running an empirical performance study based on benchmarking techniques. It shows that it scales only up to a limited and small number of nodes, which is problem-dependent. Furthermore, due to the reason found for this lack of scalability, it seems unlikely that massive scalability takes place.
- EvoCOMNET Contributions | Pp. 129-136
A Transport-Layer Based Simultaneous Access Scheme in Integrated WLAN/UMTS Mobile Networks
Hyung-Taig Lim; Seung-Joon Seok; Chul-Hee Kang
The integration of UMTS cellular network and wireless LANs enables users to achieve both the broad coverage of UMTS cellular network and the higher data rate of WLANs. In this paper, we present a transport-layer based simultaneous access scheme which enhances throughput by efficient use of these networks. Two representative transport protocols in the Internet, UDP and TCP, show significantly different behaviors against end-to-end delay and packet losses, and UMTS cellular network and WLANs have different packet losses and end-to-end delay characteristics. After prediction of UDP and TCP throughput in each network, each transport protocol is allocated to the network where total throughput can be maximized. We evaluate the proposed mechanism using NS-2 and show the improvement of the total throughput.
- EvoCOMNET Contributions | Pp. 137-144
Simplified Transformer Winding Modelling and Parameter Identification Using Particle Swarm Optimiser with Passive Congregation
Almas Shintemirov; W. H. Tang; Z. Lu; Q. H. Wu
The paper presents a simplified mathematical model of disc-type transformer winding for frequency response analysis (FRA) based on traveling wave and multiconductor transmission line theories. The simplified model is applied to the FRA simulation of a transformer winding. In order to identify the distributed parameters of the model, an intelligent learning technique, rooted from particle swarm optimiser with passive congregation (PSOPC) is utilised. Simulations and discussions are presented to explore the proposed optimization approach.
- EvoCOMNET Contributions | Pp. 145-152
A Decentralized Hierarchical Aggregation Scheme Using Fermat Points in Wireless Sensor Networks
Jeongho Son; Jinsuk Pak; Hyunsook Kim; Kijun Han
The energy cost for transmission is more expensive than receiving or sensing cost. In this paper, we propose a decentralized aggregation scheme using the Fermat points to save energy for transmitting redundant low-rate data on many-to-one flows in wireless sensor networks. It can reduce the number of transmissions needed to deliver from each source to the sink. Simulation results show that our scheme is better than the GIT (Greedy Incremental Tree) scheme in terms of the number of transmissions and network lifetime.
- EvoCOMNET Contributions | Pp. 153-160
A Gateway Access-Point Selection Problem and Traffic Balancing in Wireless Mesh Networks
Ahmet Cagatay Talay
A wireless mesh network (WMN) composed of multiple access-points (APs) that communicate mutually using radio transmissions, and all the traffics to/from the Internet are aggregated and go through the limited number of gateway APs. The meshed topology provides good reliability, market coverage, and scalability, as well as low upfront investment. However, due to the nature of routing algorithm the traffic load for a access point may be extremely heavy during particular periods while the other access points are in very light load. Consequently, the overall performance of the network are poor even the total traffic load is far below the system capacity. The performance can be improved dramatically by Traffic Balancing. Strategically placing and connecting the gateways to the wired backbone is critical to the management and efficient operation of a WMN. In this paper, we address the problem of gateway access-points placement, consisting in placing a minimum number of gateways such that quality-of-service (QoS) requirements are satisfied. We propose a genetic algorithm that consistently preserves QoS requirements. We evaluate the performance of our algorithm using both analysis and simulation, and show that it outperforms other alternative schemes by comparing the number of gateways placed in different scenarios.
- EvoCOMNET Contributions | Pp. 161-168
A Genetic Programming Approach for Bankruptcy Prediction Using a Highly Unbalanced Database
Eva Alfaro-Cid; Ken Sharman; Anna I. Esparcia-Alcázar
In this paper we present the application of a genetic programming algorithm to the problem of bankruptcy prediction. To carry out the research we have used a database of Spanish companies. The database has two important drawbacks: the number of bankrupt companies is very small when compared with the number of healthy ones () and a considerable number of companies have missing data. For comparison purposes we have solved the same problem using a support vector machine. Genetic programming has achieved very satisfactory results, improving those obtained with the support vector machine.
- EvoFIN Contributions | Pp. 169-178
Multi-objective Optimization Technique Based on Co-evolutionary Interactions in Multi-agent System
Rafał Dreżewski; Leszek Siwik
Co-evolutionary techniques for evolutionary algorithms help overcoming limited adaptive capabilities of evolutionary algorithms, and maintaining population diversity. In this paper the idea and formal model of agent-based realization of predator-prey co-evolutionary algorithm is presented. The effect of using such approach is not only the location of Pareto frontier but also maintaining of useful population diversity. The presented system is compared to classical multi-objective evolutionary algorithms with the use of Kursawe test problem and the problem of effective portfolio building.
- EvoFIN Contributions | Pp. 179-188