Air quality monitoring and forecasting play a vital role in mitigating environmental health risks, especially in densely populated and rapidly industrializing cities. This paper presents a real-time air quality monitoring system that integrates IoT technology, advanced sensors, fog computing, and a portable energy module. The system provides improved portability, accuracy, and scalability, addressing the limitations of traditional monitoring methods. A prediction module supported by deep learning methods, including Transformer, CNN model, and improved versions of Random Forest, SVM, and LSTM, enables accurate forecasting of air quality indices. This method enhances real-time forecasting, provides proactive recommendations, and supports informed decision-making. The system’s mobile design and reliance on renewable energy ensure resource efficiency and sustainability. The results demonstrate that the proposed solution outperforms existing systems in terms of affordability, flexibility, and reliability, making it an effective tool for urban air quality management and public health awareness.