Lithium based battery gives huge exposure in Battery Electric Vehicle in recent decade. The main dis-appointment in the field of Pure Electric Vehicle is range estimation. Many researcher work on range maximization of Li-ion Battery (LIB), the range of LIB is affected due to following reason: Initial SOC (State of charge), chemistry used in cell, temperature, road condition, driving performances and behavior. Main objective of this paper to use of adaptive algorithm for estimate accurate SOC and terminal voltage (E_t) of battery pack. Here we use online available experiment battery data for Evaluation: Turnigy Graphene for three drive cycle HWFET, LA92 and US06 for 25 ℃. This experimental data used to find estimated SOC, terminal voltage and error estimation for above drive cycle and temperature range. Compare the result using Extended Kalman filter, Support Vector Machine (SVM), RNN-LSTM and Hybrid approach to estimate SOC error and terminal voltage error. The result shows that for error is minimized using data driven model, SOC estimation error is decrease 33.69%, 55.06% and 62.71% Second, Voltage error also decrease with respect to EKF model-based estimation method is 1.88%, 3.12% and 20.04% for the drive cycle of HWFET, LA92 and US06 respectively.

Global warming has accelerated the global transition toward sustainable transport, positioning electric vehicles (EVs) as a key solution; however, their widespread adoption is hindered by range anxiety caused by unreliable battery State of Charge (SOC) estimation. Existing methods are affected by variables such as road conditions, temperature, and battery voltage, while physical estimation of battery parameters proves neither cost-effective nor time-efficient. To address these issues, this study presents a Simulink-based simulation of an equivalent circuit model for SOC estimation, validated for accuracy under varying conditions. A comparative analysis between the Extended Kalman Filter (EKF) and Ampere-hour integration methods is conducted, revealing that EKF delivers superior accuracy, especially under dynamic operating conditions. The findings demonstrate that integrating EKF with a Simulink-modeled system offers a precise, robust, and scalable approach to SOC estimation, effectively overcoming a major barrier to EV adoption.

Buildings are responsible for nearly 35% of global energy consumption, with heating and cooling accounting for a significant share. As urbanization and population growth accelerate, energy demand in cities continues to rise, leading to increased CO2 emissions, higher electricity costs, and greater stress on power grids. To address these challenges, real-time control systems and building automation have shown strong potential in improving energy efficiency in the built environment. In particular, optimized Heating, Ventilation, and Air Conditioning (HVAC) control systems can significantly reduce energy consumption, lower operational costs, and mitigate environmental impacts. This study investigates the application of machine learning models—including Linear Regression, Random Forest, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)—to predict HVAC performance. The models are evaluated using Mean Squared Error (MSE) and R2 score, with the goal of identifying the most effective approach for enabling data-driven energy optimization in buildings.