We propose in this article a linear quadratic regulation model for urban road networks. The model combines semi-decentralization of the control with the additive conflict flow model. The idea is to consider a centralized optimal control for the traffic, where optimal split times are determined for the traffic lights. We then relax the centralization to some optimally chosen times windows, during which main streams get green lights and are considered as priority streams, while secondary ones get yellow lights and are considered as non-priority streams. We assume that during such time periods, the traffic is managed locally at each intersection, by applying the additive conflict flow model. By this semi-decentralization, we aim to relax the rigid central control (Red/Green) during the free flow time periods. We simulate our traffic control model numerically using the simulator SUMO (Simulation of Urban Mobility), and illustrate the results on some selected traffic scenarios. The results show that our proposed model increases the capacity of the road network by more than 800 vehicles per hour, compared to the semi-decentralized control model. This performance proves clearly the effectiveness of our approach.