A Multi-Criteria Decision Support System for a Routing Problem in Waste Collection

Abstract

This work presents a decision support system for route planning of vehicles performing waste collection for recycling. We propose a prototype system that includes three modules: route optimization, waste generation prediction, and multiple-criteria decision analysis (MCDA). In this work we focus on the application of MCDA in route optimization. The structure and functioning of the DSS is also presented. We modelled the waste collection procedure as a routing problem, more specifically as a team orienteering problem with capacity constraints and time windows. To solve the route optimization problem we developed a cellular genetic algorithm. For the MCDA module, we employed three methods: SMART, ValueFn and Analytic Hierarchy Process (AHP). The decision support system was tested with real-world data from a waste management company that collects recyclables, and the capabilities of the system are discussed.

A Study on AI‐based Waste Management Strategies for the COVID‐19 Pandemic

“…Another study found that hybrid GA effectively optimized transport costs and the number of waste collection and disposal vehicles 16. Likewise, another study 17 utilized cellular GA to maximize the amount of waste collected and the waste collection points visited. The other goals were minimizing the travel distance and the number of vehicles used in the process.…”

Internet of things and machine learning‐based approaches in the urban solid waste management: Trends, challenges, and future directions

“…By the combination of multilayer perceptron neural network (MLP‐NN) and k‐nearest neighbour (KNN), a bin level prediction for waste is proposed by (Hannan et al, 2012), in which grey colour aura matrix is used to extract the image of the bin, and the proposed method achieved 90% accuracy. Furthermore, to detect the bins' filling level, which are significant for recycling and ultrasonic sensors, some machine algorithms are utilized by (Ferreira et al, 2015). The proposed technique got a tremendous result of 99.1%.…”

“…Out of all these studies on different classification techniques, (Toğaçar et al, 2020) developed a four‐step method for classifying solid and recyclable waste, which is the combination of Auto‐encoder the Convolutional Neural Network, Ridge Regression, and SVM and ultimately achieved the utmost performance with 99.95% accuracy. For transportation and collection of waste, the GA is used in MSW, such as location collection (Bautista & Pereira, 2006), route planning (Ferreira et al, 2015), collection route (Amal & Chabchoub, 2018; Düzgün et al, 2016). These suggested approaches have shown excellent results during real‐life testing and accomplished the objectives of identifying collection areas correctly, shortening the collection distance and reducing transport times and consumption of oil.…”

Multicriteria decision analysis for optimizing site selection of electronic and electricity equipment waste dismantling and sorting facility (Case study: In Indonesia, using AHP)

“…Some studies of decision making model using AHP were undertaken to solve environmental issues, particularly in solid waste management, such as to choose on waste reduction alternatives [14], to calculate social impacts of sustainable recovery network of end-of-life products design [15], to assess the sustainability of a waste management scenario with energy recovery [16], to assign weightage of each performance indicator for solid waste management [17], and to solve the route optimization problem [18].…”