Capacitated Multi Depot Green Vehicle Routing for Transporting End-of-Life electrical waste : A practical study on environmental and social sustainability within the field of CMDGVRP with heterogeneous fleets

A comprehensive study is presented of the Capacitated Multi DepotGreen Vehicle Routing Problem (CMDGVRP) applied to a heterogeneous fleet of electronic waste collecting vehicles with two objectives: to reduce the total fuel consumption of the vehicles (environmental sustainability) and to limit the continuous drive-time of the drivers (social sustainability). Research has been limited from this aspect, and in this study, the focus is on the practical application of pickup and delivery of electronic waste. The study also presents results for the online dynamic routing variant of this problem, where traffic congestion appears mid-route. A detailed analysis and parameter optimization has been done for Simulated Annealing, Genetic algorithm(GA), along with more advanced variants like Non-dominated Sorting GA (NSGA II), NSGA III, UNSGA III, and Indicator-Based Selection Evolutionary Algorithm (IBEA). Additionally, the Gini index is used to create a multi-objective model, which is novel in the context of CMDGVRP to the best of our knowledge. The use of the Gini index in the field of CMDGVRP shows excellent potential in balancing environmental, economic, and social sustainability. An extension of the CMDGVRP is introduced where vehicles can visit dropoff locations mid-route and then continue with a new route. This implementation is novel to our knowledge and is named Drop-and-continue. It is shown to increase the performance on large datasets. Results are presented from realistic simulation studies on a public dataset, with varying route lengths and vehicle fleet sizes, along with a real-world dataset from a waste collection company in Sweden. The results show that the optimal choice of algorithm depends on the dataset size and if there is a maximum budget of evaluations or computation time. Realistic problems are solved in a matter of a few seconds, given that they are initiated well. Simulated Annealing and Genetic algorithm prove to be very competitive in the case of large problems and limited computation time budget