Uma proposta de adaptação dinâmica da iluminação urbana baseada em IoT e DCOP

Abstract

In the smart cities paradigm, the efficient management of urban resources is essential to promote sustainability and quality of life. Street lighting, a crucial component of urban infrastructure, can significantly benefit from integration with IoT technologies and adaptive systems. These systems allow the collection and analysis of data in real time, enabling dynamic and efficient adjustments to urban lighting. The research explores the application of Distributed Constraint Optimization Problems (DCOP) algorithms for the adaptability of public lighting. Using algorithms such as DPOP, MGM and DSA, the study seeks to adjust the brightness of lampposts based on environmental variables detected, such as vehicle traffic and the presence of pedestrians. The methodology involves modeling a real urban scenario where DCOP algorithms are implemented to manage public lighting in an adaptive way. The collected data was analyzed to verify the efficiency of the algorithms in terms of energy consumption and lighting quality. The results indicate a reduction in energy consumption and an improvement in the operational efficiency of the public lighting system. The application of DCOP algorithms in the adaptive management of urban lighting promotes a more rational use of energy resources, improving the safety and comfort of citizens. This study demonstrates that the integration of IoT technologies with distributed optimization algorithms offers practical and replicable solutions for the efficient management of urban resources, contributing to the advancement of smart cities.