Download PDFOpen PDF in browser

A Genetic Algorithm based Control Strategy for the Energy Management Problem in PHEVs

19 pagesPublished: December 18, 2015

Abstract

Genetic algorithms have been applied to various optimization problems in the past. Our library GeneiAL implements a framework for genetic algorithms specially targeted to the area of hybrid electric vehicles. In a parallel hybrid electric vehicle (PHEV), an internal combustion engine and an electrical motor are coupled on the same axis in parallel. In the area of PHEVs, genetic algorithms have been extensively used for the optimization of parameter tuning of control strategies. We use GeneiAL to control the torque distribution between the engines directly. The objective function of this control strategy minimizes the weighted sum of functions that evaluate the fuel consumption, the battery state of charge, and drivability aspects over a prediction horizon of fixed finite length.
We analyze the influence of these weights and different configurations for the genetic algorithm on the computation time, the convergence, and the quality of the optimization result. For promising configurations, we compare the results of our control strategy with common control strategies.

Keyphrases: energy management problem, genetic algorithms, hybrid electric vehicle

In: Georg Gottlob, Geoff Sutcliffe and Andrei Voronkov (editors). GCAI 2015. Global Conference on Artificial Intelligence, vol 36, pages 196-214.

BibTeX entry
@inproceedings{GCAI2015:Genetic_Algorithm_based_Control,
  author    = {Johanna Nellen and Benedikt Wolters and Lukas Netz and Sascha Geulen and Erika Abraham},
  title     = {A Genetic Algorithm based Control Strategy for the Energy Management Problem in PHEVs},
  booktitle = {GCAI 2015. Global Conference on Artificial Intelligence},
  editor    = {Georg Gottlob and Geoff Sutcliffe and Andrei Voronkov},
  series    = {EPiC Series in Computing},
  volume    = {36},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/6CD4},
  doi       = {10.29007/md3x},
  pages     = {196-214},
  year      = {2015}}
Download PDFOpen PDF in browser