Urban traffic congestion has a significant detrimental impact on the environment, public health and the economy, with at a high cost to society worldwide. Moreover, it is not possible to continually modify urban road infrastructure in order to mitigate increasing traffic demand. Therefore, it is important to develop traffic control models that can handle high-volume traffic data and synchronize traffic lights in an urban network in real time, without interfering with other initiatives. Within this context, this study proposes a model, based on deep reinforcement learning, for synchronizing the traffic signals of an urban traffic network composed of two intersections. The calibration of this model, including training of its neural network, was performed using real traffic data collected at the approach to each intersection. The results achieved through simulations were very promising, yielding significant improvements in indicators measured in relation to the pre-existing conditions in the network. The model was able to deal with a broad spectrum of traffic flows and, in peak demand periods, reduced delays and queue lengths by more than 28% and 42%, respectively.

Resumo: O setor agrícola Brasileiro encontra-se em expansão, tornando-se um dos principais contribuintes do aumento do crescimento do PIB nacional e participação ativa na economia mundial. No entanto, a produção agrícola e agropecuária encontra na infraestrutura logística física seu principal desafio, já que tem que procurar soluções para os problemas de escoamento da produção. Este problema soma-se à falta de planejamento estratégico das cadeias de suprimento, de produção e distribuição, e essencialmente ao problema de planejamento de redes logísticas. Para contribuir na solução deste problema, este trabalho desenvolveu um modelo de planejamento do sistema logístico de distribuição para o setor hortigranjeiro de produtos orgânicos. O modelo propõe a criação de um banco de dados para diagnosticar a situação de áreas de estudos e simular cenários alternativos de redes logísticas, tendo como principais variáveis de decisão: o agrupamento de unidades produtivas, as características de veículos e localizações de pontos de venda alternativos. The Brazilian agricultural sector is under enlargement, becoming one of the main contributors to the growth of national GDP as well active involvement in the worldwide economy. However, the logistic physical infrastructure is the main endeavor for the agricultural and farming production since it’s necessary to find solutions for the problems related to production delivery. This problem must be considered in addition to the lack of strategic planning of supply chains, of production and distribution, and mainly to the problem of logistics networks planning. In order to assist the solution of this problem, this study developed a model for the planning of logistic distribution system to the produce sector for organic products. This model suggests the creation of a database to diagnose the condition of study areas and simulate alternative logistic network scenarios, having as the main variables decision: the grouping of productive units, vehicle characteristics and the location of alternative selling spots.