Can Evolutionary Algorithms Beat Dynamic Programming for Hybrid Car Control?

被引：0

作者：

Rodemann, Tobias ^{[1
]}

Nishikawa, Ken ^{[2
]}

机构：

[1] Honda Res Inst Europe, Carl Legien Str 30, D-63073 Offenbach, Germany

[2] Tokyo Inst Technol, Grad Sch Informat Sci & Engn, Meguro Ku, O Okayama 2-12-1, Tokyo 1528552, Japan

来源：

APPLICATIONS OF EVOLUTIONARY COMPUTATION, EVOAPPLICATIONS 2016, PT I | 2016年 / 9597卷

关键词：

Hybrid cars; Dynamic programming; Evolutionary algorithms; CONTROL STRATEGY;

D O I：

10.1007/978-3-319-31204-0_50

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Finding the best possible sequence of control actions for a hybrid car in order to minimize fuel consumption is a well-studied problem. A standard method is Dynamic Programming (DP) that is generally considered to provide solutions close to the global optimum in relatively short time. To our knowledge Evolutionary Algorithms (EAs) have so far not been used for this setting, due to the success of DP. In this work we compare DP and EA for a well-studied example and find that for the basic scenario EA is indeed clearly outperformed by DP in terms of calculation time and quality of solutions. But, we also find that when going beyond the standard scenario towards more realistic (and complex) scenarios, EAs can actually deliver a performance en par or in some cases even exceeding DP, making them useful in a number of relevant application scenarios.

引用

页码：789 / 802

页数：14

共 18 条

[1]

[Anonymous], P 17 IFAC WORLD C MA

[2] Reducing the Number of Simulations in Operation Strategy Optimization for Hybrid Electric Vehicles [J].

Bacher, Christopher ;

Krenek, Thorsten ;

Raidl, Guenther R. .

APPLICATIONS OF EVOLUTIONARY COMPUTATION, 2014, 8602 :553-564

[3]

Bellman R., 1958, Information and control, V1, P228, DOI [DOI 10.1016/S0019-9958(58)80003-0, 10.1016/S0019-9958(58)80003-0]

[4]

Cassebaum O., 2011, 2011 IEEE Vehicle Power and Propulsion Conference, P1

[5]

Desai Chirag, 2009, 2009 IEEE Vehicle Power and Propulsion Conference (VPPC), P871, DOI 10.1109/VPPC.2009.5289754

[6]

Desai C., 2009, IEEE Electrical Power Energy Conference (EPEC), P1, DOI [10.1109/EPEC.2009.5420888, DOI 10.1109/EPEC.2009.5420888]

[7] Management of distributed power in hybrid vehicles based on DP or Fuzzy Logic [J].

Guemri, Mouloud ;

Neffati, Ahmed ;

Caux, Stephane ;

Ngueveu, Sandra Ulrich .

OPTIMIZATION AND ENGINEERING, 2014, 15 (04) :993-1012

[8]

Hansen N, 2004, LECT NOTES COMPUT SC, V3242, P282

[9] Dynamic Programming Based Metaheuristic for Energy Planning Problems [J].

Jacquin, Sophie ;

Jourdan, Laetitia ;

Talbi, El-Ghazali .

APPLICATIONS OF EVOLUTIONARY COMPUTATION, 2014, 8602 :165-176

[10]

Krenek Thorsten, 2012, Applications of Evolutionary Computation. Proceedings of EvoApplications 2012: EvoCOMNET, EvoCOMPLEX, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoNUM, EvoPAR, EvoRISK, EvoSTIM, and EvoSTOC, P376, DOI 10.1007/978-3-642-29178-4_38

← 1 2 →