The worldwide transition to electric vehicles (EVs) is gaining momentum, propelled by the imperative to reduce carbon emissions and foster sustainable transportation. In Malaysia, the government is facilitating this transformation through targeted initiatives aimed at promoting the use of electric vehicles (EVs) and developing the required infrastructure. This paper investigates the crucial role of artificial intelligence (AI) in developing intelligent electric vehicle (EV) charging infrastructure, specifically focusing on the context of Malaysia. The paper examines the current electric vehicle (EV) charging infrastructure in Malaysia, highlights advancements led by artificial intelligence (AI), and references both local and international case studies. Fluctuations in the Total Industry Volume (TIV) and Total Industry Production (TIP) reflect changes in market demand and production capabilities, with notable peaks in March 2023 and March 2024. The research reveals that AI technologies, such as machine learning and predictive analytics, can enhance charging efficiency, improve user experience, and support grid stability. A mathematical model for an AI-based smart charging system was developed, and the implemented system achieved 30% energy savings and a 20.38% reduction in costs compared to traditional methods. These findings underscore the system’s energy and cost efficiency. In addition, we outline the potential advantages and challenges associated with incorporating artificial intelligence (AI) into Malaysia’s electric vehicle (EV) charging infrastructure. Furthermore, we offer recommendations for researchers, industry stakeholders, and regulators. Malaysia can enhance the uptake of electric vehicles and make a positive impact on the environment by leveraging artificial intelligence (AI) to enhance its electric vehicle charging system (EVCS).

This paper presents an advanced AI-based optimization framework for Electric Vehicle (EV) smart charging systems, focusing on efficient energy distribution to meet dynamic user demand. The study leverages machine learning models such as Random Forest, Support Vector Regression (SVR), Gradient Boosting Regressor, XGBoost, LightGBM, and Long Short-Term Memory (LSTM) to forecast user demand and optimize energy allocation. Among the models, XGBoost demonstrated superior predictive performance, achieving the lowest Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), making it the most effective for real-time user demand prediction in smart charging scenarios. The framework introduces proportional and priority-based allocation strategies to distribute available energy effectively, with a focus on minimizing energy shortfalls and balancing supply with user demand. Results from the XGBoost model reduced prediction error by 15% compared to other models, significantly improving the station’s ability to meet user demand efficiently. The proposed AI framework enhances charging station operations, supports grid stability, and promotes sustainability in the context of increasing EV adoption.

The Information and Communication Technology sector consumes approximately 3% of the world’s electrical energy due to the exploding demand for internet service. The most energy-intensive part of cellular communications is the base station, which there are about four million of them deployed globally. As Fifth Generation (5G) wireless networks are introduced, the number of base stations will be growing in parallel with the data traffic which in turn will increase the energy consumption of the base station to cater for the growing capacity. The high-power consumption and dynamic traffic demand overburden the base station and consequently reduce energy efficiency. In this paper, an energy-efficient hybrid power supply system for a 5G macro base station is proposed. It is analysed that with the solar energy working in conjunction with the conventional supply from the grid, the reduction of poor power quality is observed as the fluctuation of the demand is greatly decreased. The proposed model showed a reduction in the average grid power by 14.9%. Furthermore, the power supply showed peak power shaving of 5kW; thus, reducing the reliance on the grid as well as increased the energy-efficient of this hybrid power supply system.

Wireless power transfer (WPT) technology has revolutionized the charging processes of electric vehicle (EV), presenting a viable alternative to traditional wired charging methods. This paper provides a fundamental exploration of WPT, emphasizing its application in EV charging. The paper examines various WPT technologies, design considerations, and the associated international standards. A critical analysis of the current WPT technological challenges, such as misalignment, is discussed, highlighting effective strategies like multi-coil configurations and dynamic control systems that adapt to variations in alignment, enhancing efficiency and robustness. These methods significantly mitigate the common misalignment issues in deploying WPT systems, ensuring higher operational effectiveness and reliability. This analysis shows that WPT systems achieve power Transfer efficiencies of over 90% at distances up to $$\:20\:\text{c}\text{m}$$ , with misalignment tolerances improving by $$\:30\text{\%}$$ through these advanced designs. The deployment of these systems in urban settings shows a potential reduction in charging infrastructure costs by up to $$\:25\text{\%}$$ , underscoring the economic viability of WPT. Future directions explored include enhancing system compatibility across different EV models and expanding the applicability of WPT in heavy-duty vehicles. This review aims to provide insights for engineers, researchers, and policymakers aiming to optimize WPT technologies for sustainable transportation electrification.

An efficient resource allocation mechanism in the physical layer of wireless networks ensures that resources such as bandwidth and power are used with high efficiency in spite of low delay and high edge user data rate. Microcells in the network are typically set with bias settings to artificially increase the Signal-to-Interference-Plus-Noise Ratio, thus encouraging users to offload to the microcell. However, the artificial bias settings are tedious and often suboptimal. This work presents a low complexity algorithm for maximization of network capacity with load balancing in a heterogeneous network without the need for bias setting. The small cells were deployed in a grid topology at a selected distance from macrocell to enhance network capacity through coverage overlap. User association and minimum user throughput were incorporated as constraints to enable closer simulation to real word Quality of Service requirements. The results showed that the proposed algorithm was able to maintain less than 10% user drop rate. The proposed algorithm can increase user confidence as well as maintain load balancing, maintain the scalability, and reduce power consumption of the wireless network.

Narrowband Internet of Things (NB-IoT), also known as LTE Cat NB1, is a Low Power Wide Area (LPWA) radio technology that works virtually anywhere. Heterogeneous Narrowband Internet of Things (NB-IoT), also known as LTE Cat NB1, is a Low Power Wide Area (LPWA) radio technology that works virtually anywhere. Heterogeneous