Digital Twin and Metaverse Integration for Predictive Traffic Management in Malaysian Smart Cities: A Fuzzy Multi-Criteria Decision-Making Approach

Abstract

The rapid urbanization of Malaysian cities like Kuala Lumpur has intensified the demand for intelligent, sustainable traffic management systems. This study proposes an integrated framework that combines digital twin technology, metaverse-based visualization, Internet of Things (IoT)-driven real-time data, and Fuzzy Multi-Criteria Decision-Making (MCDM) methods to address the inherent uncertainty and complexity of predictive traffic routing. Key evaluation criteria—cost, speed, fuel efficiency, CO₂ emissions, user comfort, and infrastructure adaptability—were identified through expert consultations. A Fuzzy Analytical Hierarchy Process (AHP) model was developed to rank alternative traffic management solutions. In the case study of Kuala Lumpur's Central Business District (CBD), simulations using a digital twin environment and live IoT feeds indicated that adaptive traffic signaling emerged as the most preferred strategy with a fuzzy weighted score of 0.362, followed by congestion pricing (0.289) and dedicated bus lanes (0.221). Sensitivity analysis revealed that a 10% change in the weight of CO₂ emissions shifted the optimal strategy towards congestion pricing, highlighting the model’s adaptability to varying stakeholder priorities. Incorporating a metaverse-based Virtual Reality (VR) interface enabled decision-makers and citizens to experience the impact of different traffic policies visually, fostering greater transparency and engagement. Integrating fuzzy methodologies effectively addressed the uncertainties associated with expert judgments and real-time data variability. The proposed model offers a dynamic, robust, and user-centered decision-support tool for sustainable urban traffic management in Malaysia. The framework also presents significant potential for application in broader smart city planning initiatives across Southeast Asia.