Urban traffic frequently encounters significant congestion due to the rapid growth of vehicles on the road. This poses a vital challenge in developing countries that demand prompt and effective traffic solutions. In addition to increasing accident rates and emitting considerable amounts of Green House Gases (GHG), traffic congestion has a negative impact on the environment because of its lengthy delays that cost a lot of energy and time. Hence, Intelligent Traffic Signal management is needed to reduce delays at signalized intersections and improve traffic flow in a transportation network. To control and optimize Traffic Signal Control (TSC), this work proposes an OANFIS (Optimized Adaptive Neuro Fuzzy Inference System) model at signalized intersections to generate an efficient traffic signal plan to reduce average delay. OANFIS is a combination of an ANFIS (Adaptive Neuro-Fuzzy Inference System) with a Firefly Algorithm; ANFIS is used to generate signal phase length according to changes in traffic, and a Firefly algorithm is used to optimize the traffic signal plan. To evaluate the effectiveness of the OANFIS model, a comparative analysis is carried out with fixed TSC and ANFIS TSC on the SUMO simulation platform using real-time data. The results show OANFIS adaptability to real traffic fluctuations, improving traffic flow and reducing delay and CO2 emission.