caa a22 4500 44584292X CHVBK 20180317145350.0 cr unu---uuuuu 170323e20111201xx s 000 0 eng 10.1007/s11047-011-9252-2 doi (NATIONALLICENCE)springer-10.1007/s11047-011-9252-2 Evolutionary high-dimensional QoS optimization for safety-critical utility communication networks [Elektronische Daten] [Paskorn Champrasert, Junichi Suzuki, Tetsuo Otani] This paper proposes and evaluates an evolutionary multiobjective optimization algorithm, called EVOLT, which heuristically optimizes quality of service (QoS) parameters in communication networks. EVOLT uses a population of individuals, each of which represents a set of QoS parameters, and evolves the individuals via genetic operators such as crossover, mutation and selection for satisfying given QoS requirements. For evaluating EVOLT in real-world settings that have high-dimensional parameter and optimization objective spaces, this paper focuses on QoS optimization in safety-critical communication networks for electric power utilities. Simulation results show that EVOLT outperforms a well-known existing evolutionary algorithm for multiobjective optimization and efficiently obtains quality QoS parameters with acceptable computational costs. Moreover, EVOLT visualizes obtained QoS parameters in a self-organizing map in order to aid network administrators to intuitively understand the QoS parameters and the tradeoffs among optimization objectives. Springer Science+Business Media B.V., 2011 Quality of service nationallicence Evolutionary multiobjective optimization nationallicence Self-organizing map nationallicence Power utility communication networks nationallicence Champrasert Paskorn Department of Computer Science, University of Massachusetts, Boston, Boston, MA, USA aut Suzuki Junichi Department of Computer Science, University of Massachusetts, Boston, Boston, MA, USA aut Otani Tetsuo Central Research Institute of Electric Power Industry, Tokyo, Japan aut Natural Computing Springer Netherlands 10/4(2011-12-01), 1431-1458 1567-7818 10:4<1431 2011 10 11047 https://doi.org/10.1007/s11047-011-9252-2 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11047-011-9252-2 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Champrasert Paskorn Department of Computer Science, University of Massachusetts, Boston, Boston, MA, USA aut NATIONALLICENCE 700 1- Suzuki Junichi Department of Computer Science, University of Massachusetts, Boston, Boston, MA, USA aut NATIONALLICENCE 700 1- Otani Tetsuo Central Research Institute of Electric Power Industry, Tokyo, Japan aut NATIONALLICENCE 773 0- Natural Computing Springer Netherlands 10/4(2011-12-01), 1431-1458 1567-7818 10:4<1431 2011 10 11047 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer