Integrating soft computing techniques for optimizing green vehicular communications and networking in circular digital supply chain

Purpose This study aims to address environmental and societal challenges in reverse logistics within circular digital supply chains (CDSCs), focusing on reducing carbon emissions and improving community well-being. This study emphasizes how the advanced technologies can drive sustainability in CDSC reverse logistics by exploring social innovation through green vehicular communications and networking (GVCN), combined with artificial intelligence (AI) and Internet of Things (IoT). Design/methodology/approach A novel model is developed, leveraging soft computing techniques and multicriteria decision-making approaches (Simple Weighted Additive Ratio Analysis and Weighted Aggregated Sum Product Assessment) to optimize GVCN performance through AI and IOT in CDSC. This model integrates Industry 4.0 technologies to promote real-time decision-making, reduce emissions and mitigate negative environmental impacts. Findings The research highlights the societal impact of integrating predictive analytics and route optimization in reducing fuel consumption and emissions, contributing to cleaner transportation systems. This supports environmental goals and enhances public health and community well-being by reducing pollution and improving urban living conditions. Originality/value This study underscores the role of improved GVCN strategies as a driver of social innovation, demonstrating how advanced communication technologies can lead to tangible social benefits, including reduced environmental impact and improved quality of life, alongside operational efficiency.