A two-phase possibilistic linear programming methodology for multi-objective supplier evaluation and order allocation problems

Evaluation and selection of resilient suppliers in fuzzy environment

Purpose

– Supply chains (SCs) have become increasingly vulnerable to catastrophic events/disruptions that may be natural or man-made. Hurricanes, tsunamis and floods are natural disasters, whereas man-made disasters may be strikes, terrorist attacks, etc. Failure at any point in the SC network has the potential to cause the entire network to fail. SCs must therefore be properly designed to survive well in the disruption scenario. The capability of successful survival (of the firm’s SC) against those adverse events/happenings is termed as resilience; and, the SC designed under resilience consideration is called a resilient SC. Effective supplier selection is considered as a key strategic consideration in SC management. It is felt that apart from considering traditional suppliers selection criterions, suppliers’ resiliency strategy must be incorporated while selecting a potential supplier which can provide best support to the firm even in the disaster/disruption scenario. The purpose of this paper is to focus aspects of evaluation and selection of resilience supplier by considering general as well as resiliency strategy, simultaneously.

Design/methodology/approach

– In this work, subjectivity associated with ill-defined (vague) evaluation information has been tackled through logical exploration of fuzzy numbers set theory. Application of VIKOR embedded with fuzzy mathematics has been utilized here. Sensitivity analysis has been performed to reflect the effect of decision-makers’ (DM) risk bearing attitude in selecting the best potential supplier in a resilient SC. A case empirical example has also been presented.

Findings

– The work attempts to focus on a decision-making procedural hierarchy towards effective supplier selection in a resilient SC. The work exhibits application potential of VIKOR method integrated with fuzzy set theory to select potential supplier based on general strategy as well as resiliency strategy. The final supplier selection score (obtained by considering general strategy) and that of obtained by analyzing resiliency strategy have been combined to get a final compromise solution. The decision-support framework thus reported here also considers DMs’ risk bearing attitude.

Practical implications

– The study bears significant impact to the industry managers who are trying to adapt resiliency strategy in their SC followed by potential supplier selection in the context of resilient SC.

Originality/value

– Exploration of VIKOR embedded with fuzzy set theory towards suppliers’ evaluation and selection by considering general and resiliency criteria both. The decision-support module(s) adapted in this paper considers DMs’ risk bearing attitude to arrive the best compromise solution.

An analysis of the optimal multiobjective inventory clustering decision with small quantity and great variety inventory by applying a DPSO

When an enterprise has thousands of varieties in its inventory, the use of a single management method could not be a feasible approach. A better way to manage this problem would be to categorise inventory items into several clusters according to inventory decisions and to use different management methods for managing different clusters. The present study applies DPSO (dynamic particle swarm optimisation) to a problem of clustering of inventory items. Without the requirement of prior inventory knowledge, inventory items are automatically clustered into near optimal clustering number. The obtained clustering results should satisfy the inventory objective equation, which consists of different objectives such as total cost, backorder rate, demand relevance, and inventory turnover rate. This study integrates the above four objectives into a multiobjective equation, and inputs the actual inventory items of the enterprise into DPSO. In comparison with other clustering methods, the proposed method can consider different objectives and obtain an overall better solution to obtain better convergence results and inventory decisions.

Benchmarking suppliers’ performance when some factors play the role of both inputs and outputs

Purpose

– The purpose of this paper is to develop a slack-based measure (SBM) model in the presence of dual-role factor. Then it is applied in supplier selection problem.

Design/methodology/approach

– The developed model in this paper is based on data envelopment analysis (DEA) technique.

Findings

– The proposed evaluation platform is capable of identifying ill-performing suppliers which seek to future improvement. The findings provide valuable insights for practitioners, as well as academicians, policy makers and also integrate selection criteria under the supply chain.

Originality/value

– This is the first time that a non-radial DEA model considers dual-role factors. The proposed model does not deal with dual-role factor as a non-discretionary factor. The proposed model considers dual-role factors on both the input and output sides in a similar manner. The proposed model can fully measure the inefficiency of suppliers. The proposed model can give a complete ranking of suppliers.

Municipal solid waste management planning considering greenhouse gas emission trading under fuzzy environment

Waste management activities can release greenhouse gases (GHGs) to the atmosphere, intensifying global climate change. Mitigation of the associated GHG emissions is vital and should be considered within integrated municipal solid waste (MSW) management planning. In this study, a fuzzy possibilistic integer programming (FPIM) model has been developed for waste management facility expansion and waste flow allocation planning with consideration of GHG emission trading in an MSW management system. It can address the interrelationships between MSW management planning and GHG emission control. The scenario of total system GHG emission control is analyzed for reflecting the feature that GHG emission credits may be tradable. An interactive solution algorithm is used to solve the FPIM model based on the uncertainty-averse preferences of decision makers in terms of p-necessity level, which represents the certainty degree of the imprecise objective. The FPIM model has been applied to a hypothetical MSW planning problem, where optimal decision schemes for facility expansion and waste flow allocation have been achieved with consideration of GHG emission control. The results indicate that GHG emission credit trading can decrease total system cost through re-allocation of GHG emission credits within the entire MSW management system. This will be helpful for decision makers to effectively determine the allowable GHG emission permits in practices.

Planning of municipal solid waste management under dual uncertainties

Municipal solid waste management is a complex and multidisciplinary problem, involving a number of impact factors associated with various uncertainties. In this study, a hybrid interval-parameter possibilistic programming (IPP) approach was developed and applied for planning municipal solid waste management under dual uncertainties. The IPP improves upon the existing management approaches by allowing possibility distributions of the lower and upper bounds of some interval parameters in the objective function and interval information in the modelling coefficients to be effectively incorporated within its optimization. By introducing the concept of possibilistic interval numbers, the dual uncertainties can be communicated into the optimization process and the resulting solutions, such that the generated decision schemes can effectively reflect the highly complex system features under uncertainty. The results of the case study indicate that useful information can be obtained for providing feasible decision schemes for waste flow allocation. Different decision schemes can be generated by adjusting waste flow allocation patterns within the solution intervals. Lower decision variable values should be used to obtain lower system cost of waste treatment and disposal under advantageous conditions, and higher decision variable values should be used under demanding conditions (worst case conditions). A strong desire to acquire the lower system cost will lead to the decreased probability of meeting the treatment and disposal requirements (i.e. the increased risk of unforeseen conditions); willingness to accept the upper limit of the system cost will guarantee that waste treatment and disposal requirements are met.

Robust stochastic fuzzy possibilistic programming for environmental decision making under uncertainty

Nonpoint source (NPS) water pollution is one of serious environmental issues, especially within an agricultural system. This study aims to propose a robust chance-constrained fuzzy possibilistic programming (RCFPP) model for water quality management within an agricultural system, where solutions for farming area, manure/fertilizer application amount, and livestock husbandry size under different scenarios are obtained and interpreted. Through improving upon the existing fuzzy possibilistic programming, fuzzy robust programming and chance-constrained programming approaches, the RCFPP can effectively reflect the complex system features under uncertainty, where implications of water quality/quantity restrictions for achieving regional economic development objectives are studied. By delimiting the uncertain decision space through dimensional enlargement of the original fuzzy constraints, the RCFPP enhances the robustness of the optimization processes and resulting solutions. The results of the case study indicate that useful information can be obtained through the proposed RCFPP model for providing feasible decision schemes for different agricultural activities under different scenarios (combinations of different p-necessity and p(i) levels). A p-necessity level represents the certainty or necessity degree of the imprecise objective function, while a p(i) level means the probabilities at which the constraints will be violated. A desire to acquire high agricultural income would decrease the certainty degree of the event that maximization of the objective be satisfied, and potentially violate water management standards; willingness to accept low agricultural income will run into the risk of potential system failure. The decision variables under combined p-necessity and p(i) levels were useful for the decision makers to justify and/or adjust the decision schemes for the agricultural activities through incorporation of their implicit knowledge. The results also suggest that this developed approach is applicable to many practical problems where fuzzy and probabilistic distribution information simultaneously exist.