Abstract:
In this paper, the authors propose adaptive
neuro fuzzy inference system (ANFIS) algorithm, based
on extreme learning machine (ELM) concepts for
designing a controller for electric vehicle to grid (V2G)
integration. First, learning speed and accuracy of the
proposed algorithm is checked and second the transient
response of the ELM-ANFIS (e-ANFIS) based controller
is analyzed. The proposed new learning technique
overcomes the slow learning speed of the conventional
ANFIS algorithm without sacrificing the generalization
capability. Thus, even with an involvement of a large
number of plug-in hybrid electric vehicles (PHEV), a
control technique for their charge and discharge pattern
can be easily designed. To study the computational
performance and transient response of the e-ANFIS
based controller, it is compared with conventional
ANFIS based controller. To implement the vehicle to
grid integration concept, IEEE 33 bus radial
distribution system is modelled in MATLAB
environment.