In this paper, we use the NCTUns network simulator to study intelligent traffic signal control algorithms. NCTUns is both a microscopic traffic simulator and a network simulator. We imported the real-life map of a district of the Taipei city into NCTUns to let simulated vehicles move on the roads of the imported map. Then, we used a new and unique feature of NCTUns - each simulated vehicle moves towards its assigned landmark on the map as its destination, to create more realistic traffic patterns in the studied district. With these realistic settings, we studied an intelligent traffic signal control algorithm that has been proposed in the literature. We found that this algorithm has unfairness problems and thus we proposed two mechanisms to improve it. Our simulation results show that, when compared with the original algorithm, the improved algorithm can further reduce the average time needed for a vehicle to reach its destination. In addition, the improved algorithm can mitigate the unfairness problem.