The Electric Vehicle Travelling Salesman Problem on Digital Elevation Models for Traffic-Aware Urban Logistics Supplementary Material

These files correspond to the supplementary material of the article <em>The Electric Vehicle Travelling Salesman Problem on Digital Elevation Models for Traffic-Aware Urban Logistics</em>. <strong>Code</strong> - <strong>algorithm.py</strong> corresponds to an implementation of the algorithm developed in the paper to solve the EV-TSP for the city of Madrid. It takes as input a list of nodes from the graph of Madrid city <strong>madrid_elevation_energy.pckl</strong> and the output consists of an ordered list of all the nodes representing the solution to the TSP.<br> - <strong>bellmanFord.py</strong> is a Python implementation of the Bellman-Ford algorithm. <br> - <strong>evaluation.py</strong> is the script that offers the evaluation of the algorithm offered in Tables 1 and 2 in the paper.<br> - <strong>neuralNetworkTraining.py</strong> is the script used to train and save the Neural Network model using the data generated by <strong>simulation.py</strong>.<br> - <strong>nn_model_predictor.py</strong> is a script where the model trained in <strong>neuralNetworkTraining.py</strong> can be used to generate predictions.<br> - <strong>simulation.py</strong> is the script that simulated the routes through the months of October and November 2022 using the data in <strong>snapshots_2022.zip</strong>. It generates the routes in <strong>simulationOctober.csv</strong> and <strong>simulationNovember.csv</strong><br> - <strong>twoOptNearestNeighnors.py</strong> is a Pyhton implementation of the 2-Opt algorithm that uses Nearest Neighbors to generate the initial tour. ## Files - <strong>Madrid{5,10,15}.pkl</strong> are the test instances for the city of Madrid. Correspond to Python list of list. Each list is a set of stops to visit in the city graph of Madrid (<strong>madrid_elevation_energy.pckl</strong>) <br> - <strong>energy_estimation_full.h5</strong> is a Keras model trained using <strong>nn_model_predictor.py</strong> to estimate the energy.<br> - <strong>scaler_full.pkl</strong> is the scaler needed to use the <strong>energy_estimation_full.h5</strong> model.<br> - <strong>simulation{October, November}.pkl</strong> are the routes generated for each month using <strong>simulation.py</strong>.<br> - <strong>snapshots_2022.zip</strong> are the traffic data for the months of October and November 2022