Herein, we present an advanced approach for the estimation of battery model parameters using the Cuckoo Search optimization algorithm (CSA) for lithium-ion batteries (LIB) in electric vehicle applications. In any battery-powered system, accurate determination of internal battery parameters and, as a consequence, state of charge (SOC) prediction is essential. The precision of parameter identification, which is mostly governed by battery model parameters, will significantly impact the battery’s safety, characteristics, and performance. Hence, we need effective, simple, and efficient parameter estimation algorithms to estimate the parameters accurately. The parameters of the NMC cell are predicted using a 2RC (second-order RC) equivalent circuit model. The experimental data was utilized to determine the parameters and the correlation between OCV and SOC. The suggested approach and validation results demonstrate that the CSA for detecting parameters in LIBs is efficient and resilient. The proposed algorithm tends to limit the root mean square error of 0.44 percent between experimental and simulation results. Simulated results show that the novel approach outperforms the standard algorithm nonlinear least square method and other metaheuristic methods such as GA and PSO.