Algorithm for selecting input variables for solving the problem of forecasting the set of entrants using the ANFIS neuro-fuzzy system

Minaev, O. M.; Vakhazhi, KH-M. M.; Uspanova, A.

doi:10.1063/5.0075434

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptive network is usually trained through a hybrid‐based learning algorithm grouping of least‐squares type (hybrid learning algorithm) and backpropagation type (gradient‐descent (GD) algorithm). Thus, it allows the FIS to learn by the data set and is intended at corresponding the proposed ANFIS output with the trained data set [51]. To get the desired outputs and the error rates (

d/de)

execute the proposed system for all iterations.…”

Section: Coordinated Control Strategymentioning

confidence: 99%

Intelligent energy management scheme‐based coordinated control for reducing peak load in grid‐connected photovoltaic‐powered electric vehicle charging stations

Amir

Din

Haque

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Solar‐based Distributed Generation (DG) powered Electric Vehicles (EVs) charging stations are widely adopted nowadays in the power system networks. In this process, the distribution grid faces various challenges caused by intermittent solar irradiance, peak EVs load, while controlling the state of charge (SoC) of batteries during dis(charging) phenomena. In this paper, an intelligent energy management scheme (IEMS)‐based coordinated control for photovoltaic (PV)‐based EVs charging stations is proposed. The proposed IEMS optimizes the PV generation and grid power utilization for EV charging stations (EVCS) by analysing real‐time meteorological and load demand data. The coordinated control of EMS provides power flow between PV generation, distribution grid, and EVs battery storage in a manner which results in the reduction of peak power demand by a factor of two. Further, the adaptive neuro‐based fuzzy control approach includes forecasting solar‐based electricity generation and EVs loads demand predictions to optimize IEMS according to the Indian power scenario. The proposed IEMS optimally utilizes the buffer batteries system for reducing the peak electricity demand with low system losses and reducing the impact of EVs charging load on distribution grid. The results are analysed using the digital simulation model and validated with real‐time hardware‐in‐loop experimental setup.

show abstract