Tags: SUMO, Python, TraCI, Adaptive Traffic Signals, Traffic Simulation, Intelligent Transportation Systems (ITS), Smart Cities
What I did technically:
Built a full SUMO simulation environment (network, routes, flows, traffic lights).
Integrated SUMO with Python (TraCI) to implement an adaptive signal algorithm.
Generated detailed outputs (tripinfo.xml, summary.xml) and developed comparison scripts to evaluate performance.
Extracted key indicators such as average travel time, waiting time, vehicle speed, and throughput from both baseline (fixed-time) and adaptive scenarios.
Findings:
The adaptive system reduced average waiting times and time loss for several vehicle classes compared to fixed-time.
Vehicles experienced slightly faster mean speeds under adaptive control, resulting in smoother traffic flows.
Even in a small grid, the experiment demonstrated how real-time control logic can outperform static signal plans.
Impact:
This project showcases my ability to combine transportation engineering concepts (traffic signal design, flow analysis) with computational tools (SUMO, Python, TraCI, XML data analytics). It represents a bridge between civil engineering expertise and intelligent transportation systems (ITS) research. The approach is scalable: the same framework could be applied to larger, real-world urban networks or integrated with reinforcement learning controllers.