Traffic Microssimulation: Modelling with SUMO, TRaCi + AI

Master micro-simulation with SUMO to model networks, model demand, program traffic signals, calibrate results, and analyze transportation systems through XML files and real-world case study.

Install sumo from the official site, enable extras for geo referencing and shapefile support, set up sumo home and python path, and use the GitHub repository for help and updates.

Open sumo ui and netaji, switch to network and edge mode, create your first edge, extend the network, inspect edge properties, and save as .net.xml.

Establish a route with a vehicle and set a flow with an hourly volume, save demand and configuration files, and run a SUMO simulation to observe buses on the route.

Learn how XML files structure data for sumo, using XML schema definitions to shape routes, vehicle types, and flows, and read the schema definitions to edit network and route files.

Generate a vehicle distribution using vtype distribution in sumo and assign it to a flow, including cars, motorcycles, trucks, and buses with specified probabilities.

Create a standard network with net generate in Sumo, using the GUI or command line, adjusting grid number and folders, and consulting the documentation via the help parameter.

Create a network from a satellite image by exporting a georeferenced background in ArcGIS, then import the image into sumo UI with WGS 84 coordinates.

Learn to automatically create a network from OpenStreetMap using the OSM web wizard, generate car-based demand, customize areas, inspect generated XML files and configuration to run a complete SUMO simulation.

Generate a random demand in sumo using the random trips function with a net file, adjusting seeds, distributions, and validation to reflect real-world traffic.

Learn how to convert a traffic network to dot XML and to KML using Python tools, export a net file to Google Earth, and visualize neighborhood polygons for edge analysis.

Generate and save a configuration file that records parameters and values used when calling a function, enabling repeatable sumo traffic simulations with a predefined grid, fringe factor, and vehicle count.

Learn to program traffic lights in SUMO using semaphoric logic, defining phases and color codes, and synchronizing multiple groups with offsets.

Model public transport with a simple network by defining routes, demand, vehicle types, bus stops and exclusive lanes, then run a simulation to observe bus flows.

Add induction loop additionals to the SUMO network, configure id, position, five-minute aggregation, and output file in the network files, then save as additionals for data collection during simulation.

Learn how to collect and analyze Sumo simulation results, select outputs like trip info and statistics, and export xml data for analysis in Excel or Python.

Learn to generate graphs directly in sumo with matplotlib, plotting FCD and summary outputs from configuration files. Compare networks using mean travel time and time loss.

Run SUMO directly from the command line to speed up simulations, control seeds for reproducibility, and automate multiple runs with run seeds to analyze deviations.

Model a study case in Joinville with SUMO; build the network using OSM web wizard, set connections and lanes, and derive demand from Good Vision Live counts.

Calibrate the traffic microsimulation to ensure it represents real-world conditions. Compare simulated mean travel times with real-world measures, adjust parameters, and validate within a 10% tolerance.

Learn calibration and validation in traffic microsimulation, using RMSE to compare observed and simulated measures, with a 10% error threshold guiding a loop of refinements.