State of charge estimation in lithium-ion batteries: A critical review of traditional and AI-driven methods with pathways to real-world implementation

Document Type

Article

Publication Date

Summer 7-2-2026

Abstract

Accurate state-of-charge (SoC) estimation is critical for the safe and efficient operation of lithium-ion batteries in electric vehicles and energy storage systems. However, its practical implementation remains challenging due to the nonlinear battery behavior, aging effects, and varying operating conditions. This paper reviews the existing state-of-charge estimation techniques, including the conventional, model-based, and data-driven approaches, with a focus on their applicability in real scenarios. The novelty of this paper lies in the development of a structured taxonomy that categorizes state-of-charge estimation methods according to their robustness, adaptability, and scalability. In addition, a unified framework is proposed that combines the multi-sensor data with the adaptive artificial intelligence models to improve the estimation performance under dynamic conditions. The paper also discusses the role of emerging technologies, such as edge computing and federated learning, in the context of real-time battery management systems. The paper further identifies the key research gaps and outlines the practical roadmap for bridging the gap between the theoretical advancements and the industrial deployment. The findings provide useful insights into the design of reliable and scalable state-of-charge estimation strategies in the next-generation battery systems.

Share

COinS