Efficient energy consumption minimization and comfort index maximization in electric vehicles have grasped the attention of many researchers in recent years. Several models have been proposed and developed for this purpose, but these models have limitations in one way or another; some provide good results in energy consumption minimization but compromise on comfort, and some are capable of maximizing the comfort level but also increasing the energy consumption. Hence, to tackle these problems, we have proposed a model based on optimization, machine learning, smoothing, and control algorithms. The purpose of the proposed model is two folds, first, to minimize energy consumption and second, to maximize user comfort. The suggested model comprises three main modules: the smoothing module, the optimization module, and the control module. In the smoothing module, the alpha-beta filter, the simplest and most effective filter, has been used to remove noise and smooth the data. The optimization module is further divided into two sub-modules: the FA-GA module and the support vector machine module. The purpose of the support vector machine in the optimization module is to make the system fully automatic and dynamic by setting the user parameters in the objective function of the FA-GA module. In the control module, Mamdani fuzzy logic has been used to provide the desired energy to corresponding actuators. The proposed method is compared with some well-known approaches, and the results indicate that the proposed method provides good results compared to counterpart algorithms.