Smart Waste Management for the Free Nutritious Meal Program: A Systematic Literature Review Based on IoT and Deep Learning

Abstract

The implementation of the Free Nutritious Meal (MBG) program in Indonesia presents significant logistical challenges, particularly regarding the generation of kitchen waste in diverse geographical settings such as coastal and inland areas. An intelligent approach is needed to manage this waste sustainably. This study conducts a systematic literature review integrating concepts from the Internet of Things (IoT), Deep Learning, Multi-Criteria Decision Making (MCDM), and community-based collective action to formulate a conceptual model. The proposed Eco-Dashboard integrates real-time IoT sensors to act as an Early Warning System (EWS) for waste capacity. By employing Deep Learning algorithms, the system gains predictive capabilities to forecast waste accumulation, while enhanced MCDM techniques provide adaptive decision-making logic for waste collection routes and resource recovery. Furthermore, the model incorporates socio-technical frameworks to ensure high community engagement. The adaptive and predictive Eco-Dashboard model offers a comprehensive, localized solution for kitchen waste management. Furthermore, this framework directly supports the United Nations Sustainable Development Goals (SDGs), specifically contributing to SDG 11.6 by mitigating urban and environmental impacts and SDG 12.5 by promoting substantial waste reduction and resource recovery. By bridging technological infrastructure with community-driven food-sharing initiatives, this model ensures that MBG program waste is managed efficiently, preventing environmental hazards in both coastal and inland ecosystems.