Towards the improvement of multi-objective evolutionary algorithms for service restoration

被引：0
|
作者：
Marques, Leandro T. [1 ]
Delbem, Alexandre C. B. [1 ]
London, Joao Bosco A., Jr. [1 ]
机构：
[1] Univ Sao Paulo, Sao Carlos, SP, Brazil
来源：
2017 IEEE POWER & ENERGY SOCIETY INNOVATIVE SMART GRID TECHNOLOGIES CONFERENCE (ISGT) | 2017年
关键词：
Evolutionary computation; Power distribution faults; Power system restoration; Smart grids; DISTRIBUTION-SYSTEM;
D O I：
暂无
中图分类号：
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号：
0807 ; 0820 ;
摘要：
Distribution systems (DS) service restoration is a multi-objective, multi-constraint, combinatorial and non-linear optimization problem that must be quickly solved. Four multiobjective evolutionary algorithms (MOEAs) are proposed, which combine prominent aspects of highlighted MOEAs in the literature, for dealing with SR problem. Their main differentials are the providing of improved Pareto fronts and prioritization of switching operation in remotely controlled switches, which is widely used in smart grids. Proposed MOEAs were compared with a MOEA from literature by several tests in a large-scale DS. The MOEAs' performance was measured by four metrics for evaluation of Pareto fronts and Welch's t-hypothesis test was used for statistical comparison of such performance. Test results indicate all proposed MOEAs performed better than the MOEA from literature.
引用
收藏
页数：5
相关论文
共 50 条
  • [1] Towards the improvement of multi-objective evolutionary algorithms for service restoration
    Marques, Leandro T.
    Delbem, Alexandre C. B.
    London, Joao Bosco A., Jr.
    Camillo, Marcos H. M.
    2017 IEEE POWER & ENERGY SOCIETY GENERAL MEETING, 2017,
  • [2] Towards Running Time Analysis of Interactive Multi-Objective Evolutionary Algorithms
    Lu, Tianhao
    Bian, Chao
    Qian, Chao
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 18, 2024, : 20777 - 20785
  • [3] An effective model of multiple multi-objective evolutionary algorithms with the assistance of regional multi-objective evolutionary algorithms: VIPMOEAs
    Cheshmehgaz, Hossein Rajabalipour
    Desa, Mohamad Ishak
    Wibowo, Antoni
    APPLIED SOFT COMPUTING, 2013, 13 (05) : 2863 - 2895
  • [4] Genetic diversity as an objective in multi-objective evolutionary algorithms
    Toffolo, A
    Benini, E
    EVOLUTIONARY COMPUTATION, 2003, 11 (02) : 151 - 167
  • [5] Optimization of a Demand Responsive Transport Service Using Multi-objective Evolutionary Algorithms
    Viana, Renan J. S.
    Santos, Andre G.
    Martins, Flavio V. C.
    Wanner, Elizabeth F.
    PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION (GECCCO'19 COMPANION), 2019, : 2064 - 2067
  • [6] Towards a Microservices-Based Product Line with Multi-Objective Evolutionary Algorithms
    Mendonca, Willian D. F.
    Assuncao, Wesley K. G.
    Estanislau, Lucas, V
    Vergilio, Silvia R.
    Garcia, Alessandro
    2020 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2020,
  • [7] Multi-objective evolutionary algorithms for structural optimization
    Coello, CAC
    Pulido, GT
    Aguirre, AH
    COMPUTATIONAL FLUID AND SOLID MECHANICS 2003, VOLS 1 AND 2, PROCEEDINGS, 2003, : 2244 - 2248
  • [8] Fuzzy Classification with Multi-objective Evolutionary Algorithms
    Jimenez, Fernando
    Sanchez, Gracia
    Sanchez, Jose F.
    Alcaraz, Jose M.
    HYBRID ARTIFICIAL INTELLIGENCE SYSTEMS, 2008, 5271 : 730 - 738
  • [9] Multi-Objective BOO Optimization with Evolutionary Algorithms
    Shirinzadeh, Saeideh
    Soeken, Mathias
    Drechsler, Rolf
    GECCO'15: PROCEEDINGS OF THE 2015 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2015, : 751 - 758
  • [10] Robustness using Multi-Objective Evolutionary Algorithms
    Gaspar-Cunha, A.
    Covas, J. A.
    APPLICATIONS OF SOFT COMPUTING: RECENT TRENDS, 2006, : 353 - +
12345