State of charge (SOC) is a crucial index used in the assessment of electric vehicle (EV) battery storage systems. Thus, SOC estimation of lithium-ion batteries has been widely investigated because of their fast charging, long-life cycle, and high energy density characteristics. However, precise SOC assessment of lithium-ion batteries remains challenging because of their varying characteristics under different working environments. Machine learning techniques have been widely used to design an advanced SOC estimation method without the information of battery chemical reactions, battery models, internal properties, and additional filters. Here, the capacity of optimized machine learning techniques are presented toward enhanced SOC estimation in terms of learning capability, accuracy, generalization performance, and convergence speed. We validate the proposed method through lithium-ion battery experiments, EV drive cycles, temperature, noise, and aging effects. We show that the proposed method outperforms several state-of-the-art approaches in terms of accuracy, adaptability, and robustness under diverse operating conditions.
Micro-energy harvesting (MEH) is a technology of renewable power generation which is a key technology for hosting the future low-powered electronic devices for wireless sensor networks (WSNs) and, the Internet of Things (IoT). Recent technological advancements have given rise to several resources and technologies that are boosting particular facets of society. Many researchers are now interested in studying MEH systems for ultra-low power IoT sensors and WSNs. A comprehensive study of IoT will help to manage a single MEH as a power source for multiple WSNs. The popular database from Scopus was used in this study to perform a review analysis of the MEH system for ultra-low power IoT sensors. All relevant and important literature studies published in this field were statistically analysed using a review analysis method by VOSviewer software, and research gaps, challenges and recommendations of this field were investigated. The findings of the study indicate that there has been an increasing number of literature studies published on the subject of MEH systems for IoT platforms throughout time, particularly from 2013 to 2023. The results demonstrate that 67% of manuscripts highlight problem-solving, modelling and technical overview, simulation, experimental setup and prototype. In observation, 27% of papers are based on bibliometric analysis, systematic review, survey, review and based on case study, and 2% of conference manuscripts are based on modelling, simulation, and review analysis. The top-cited articles are published in 5 different countries and 9 publishers including IEEE 51%, Elsevier 16%, MDPI 10% and others. In addition, several MEH system-related problems and challenges are noted to identify current limitations and research gaps, including technical, modelling, economic, power quality, and environmental concerns. Also, the study offers guidelines and recommendations for the improvement of future MEH technology to increase its energy efficiency, topologies, design, operational performance, and capabilities. This study's detailed information, perceptive analysis, and critical argument are expected to improve MEH research's viable future.