A Novel Parallel Heuristic Method to Design a Sustainable Medical Waste Management System

Efficient management of waste generated in healthcare systems is crucial to minimize its environmental impact and ensure public health. Sustainable medical waste management (MWM) systems require careful network design, which can be achieved through optimization techniques. This work extends one of the recently suggested mixed-integer linear programming (MILP) models and develops, a two-step MILP (TSMILP) to generate quality lower bounds, and a novel parallel heuristic algorithm to configure a sustainable waste management system including waste generation centers (WGCs), waste collection/treatment centers (WTCs), waste recycling centers (WRCs), waste disposal centers (WDCs) and waste incineration centers (WICs). The aim is to address strategic (establishment of facilities), tactical (employment of transportation system), and operational decisions (transportation planning) optimally in large networks. As reflected in the literature, there is a huge gap in efficiency and application of combinatorial optimization, and parallel computing in sustainable MWM systems, where the suggested MILPs’ solvers are not technically capable of discovering quality solutions in reasonable runtimes on large-sized instances. Thus, we suggest a novel heuristic equipped with parallel computing to share the complexity of the problem, with all the CPU cores to shorten runtime. Comparing the results generated by the parallel heuristic with those of the sequential heuristic, the MILP, and the TSMILP on three sets of benchmark instances using Nemenyi’s post-hoc procedure for Friedman’s test, it is inferred that the parallel heuristic is so effective in coping with the problem, and produces high-quality solutions, especially on the large-sized set. Finally, sensitivity analysis is adopted to analyze the effects of parameters on the objective values