Back to Top

■ Charging control of electric vehicles using contextual bandits considering the electrical distribution grid

C. Römer, J. Hiry, C. Kittl, T. Liebig, and C. Rehtanz, ”Charging control of electric vehicles using contextual bandits considering the electrical distribution grid,” in Proceedings of the 2nd International Workshop on Knowledge Discovery from Mobility and Transportation Systems, KNOWme, co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (PKDD), 2018.

Abstract.
With the proliferation of electric vehicles, the electrical dis-
tribution  grids  are  more  prone  to  overloads.  In  this  paper,  we  study
an intelligent pricing and power control mechanism based on contextual
bandits to provide incentives for distributing charging load and prevent-
ing network failure. The presented work combines the microscopic mobil-
ity simulator SUMO with electric network simulator SIMONA and thus
produces reliable electrical distribution load values. Our experiments are
carefully  conducted  under  realistic  conditions  and  reveal  that  condi-
tional  bandit  learning  outperforms  context-free  reinforcement  learning
algorithms  and  our  approach  is  suitable  for  the  given  problem.  As  re-
inforcement learning algorithms can be adapted rapidly to include new
information we assume these to be suitable as part of a holistic traffic
control scenario.