Anda di halaman 1dari 8

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/261379725

A review of modelling approaches for supply chain planning under


uncertainty

Conference Paper · July 2012


DOI: 10.1109/ICSSSM.2012.6252220

CITATIONS READS

7 71

2 authors, including:

Morteza Lalmazloumian
University of Windsor
7 PUBLICATIONS   39 CITATIONS   

SEE PROFILE

All content following this page was uploaded by Morteza Lalmazloumian on 16 March 2016.

The user has requested enhancement of the downloaded file.


A Review of Modelling Approaches for Supply Chain
Planning Under Uncertainty

Morteza Lalmazloumian Kuan Yew Wong


Faculty of Mechanical Engineering Faculty of Mechanical Engineering
Universiti Teknologi Malaysia (UTM) Universiti Teknologi Malaysia (UTM)
81310 Johor Bahru, Malaysia 81310 Johor Bahru, Malaysia
Lmorteza2@live.utm.my wongky@fkm.utm.my

Abstract—Since 1959 in which one of the earliest attempts to information required to perform a task and the information that
address the problem of developing a coordinated link in a supply is actually available. Uncertainty has a great influence on the
chain (SC) was performed by [1], managing SC performance has effectiveness of SCs’ configuration and coordination in SCP
been a main challenge among enterprises. Supply chain planning processes [6]. In this paper, we provide a review on various
(SCP), as one of the most important processes within the supply SCP methods which are being exploited to develop an
chain management (SCM) concept, has a great impact on firms’ integrated SC network in which the overall performance of the
success or failure. SCP decision has been greatly influenced by entire enterprise has been optimized. Furthermore, a
the presence of uncertainty from the intricate nature and classification framework based on the following elements is
dynamic relationship among various stages involved in the SC
defined as a new taxonomy: (a) problem types handled within
network. This paper aims to present an extensive review of the
SCP, (b) sources of uncertainty that the analyzed model is
existing literature to acquire a deep understanding of modelling
approaches used in the area of SCP under uncertainty. The
dealing with, (c) performance measures addressed, and (d)
research main objective is to provide a classification framework modelling approaches used.
based on the following elements: problem types, sources of This paper is organized as follows. In the next section, the
uncertainty, performance measures, and modelling approaches methodology of reviewing the literature is defined and a new
that were exploited by previous researchers. We have conducted taxonomy is undertaken. Then, the classification of modelling
a survey of various journal papers dated from 1993 to 2012. In approaches for SCP is described and classified. Finally,
conclusion, some guidelines regarding future areas of research
conclusions are drawn and potential future extension of the
have been identified.
research is discussed.
Keywords: Supply chain management;Supply chain planning;
II. REVIEW METHODOLOGY
Uncertainty modelling
In order to conduct this review on scientific literatures
I. INTRODUCTION related to SCP under uncertainty, a wide search on
A supply chain (SC) is an integrated process in which a bibliography references was performed using key words like
group of several organizations, such as suppliers, “supply chain planning”, “uncertainty”, “procurement,
manufacturers, distributors and retailers, work together with production distribution planning”, and “supply chain network
both a forward flow of materials and a backward flow of design”. Having exploited these criteria, a group of 84 journal
information, to acquire raw materials with a view of converting papers were initially obtained. To acquire more relevant
them into final products, and deliver the final products to literature in accordance with the research objective, a detailed
customers [2]. Today, individual firms compete as an integral analysis was carried out by considering various research
part of SC links rather than independent entities with unique criteria of the classification framework. Once this procedure
brand names [3]. A firm success has been greatly influenced by was completed, 47 final references were selected.
its managerial ability to integrate and coordinate the
III. TAXONOMY
complicated network of business relationship among SC
members. One of the most important processes within the SCM We have developed our taxonomy based on the initial
concept is the supply chain planning (SCP) process which is model presented by [7]. These authors identified two
about the coordination and integration of key business dimensions of classification including: (a) the problem types
activities undertaken by an enterprise, from the procurement of and (b) the modelling approaches in their taxonomy for SCM
raw materials to the distribution of the final products to the models. We incorporated two more criteria into the previous
customer [4]. However, a large degree of uncertainty arises taxonomy which comprised (c) the sources of uncertainty and
from the intricate nature and dynamic relationship among (d) the performance measures. To have a better understanding
various stages involved in a SC network. According to [5], regarding various classifications, a comprehensive review of
uncertainty is defined as the difference between the amount of the former effort in the area of modelling SCP problems has

978-1-4577-2025-3/12/$26.00 ©2011 IEEE 197


been done. Our focus is on providing a categorized framework frequently mentioned. First, the distribution-based approach,
based on different dimensions of classification. where the normal distribution with specified mean and standard
deviation is widely invoked for modelling uncertain demands
A. Criterion: Problem Types and/or parameters; second, the fuzzy-based approach, therein
Considering the wide range of SC decisions, the SCP the forecast parameters are considered as fuzzy numbers with
problem can be decomposed based on three levels of decisions accompanied membership functions; and third, the scenario-
according to the time horizons contemplated: (a) The strategic based approach, in which several discrete scenarios with
level (long-term), (b) the tactical level (mid-term), and (c) the associated probability levels are used to describe the expected
operational level (short-term) [8]. In the SC design phase, occurrence of particular outcomes. In our research, we have
strategic planning such as location decisions for manufacturing added two more categories to the initial definition of SCP
and distribution facilities and technology selection decisions modelling approach including, simulation-based approach and
play major roles. Strategic planning models affect SC design hybrid-based approach. Our classification in assigning
and configuration over a relatively long time, somewhere modelling approaches is solely based on the solution method.
between five and ten years. At the tactical level, the main issue
is the determination of procurement, production and IV. CLASSIFICATION OF SUPPLY CHAIN PLANNING
distribution quantities for the facilities in different echelons of MODELLING APPROACHES UNDER UNCERTAINTY
a SC with planning time lasting one or two years. Coordinating Since variable data are inherent in almost all of the real
the procurement, production and distribution plans in an world problems, we have provided a review of various
integrated framework considering capacity limitations at modelling approaches to deal with the uncertain environment
different echelons is of particular interest in tactical planning of the SC networks. Likewise, works are presented in
decisions. Operational planning models are related to the chronological order.
detailed scheduling definition, sequencing, lot sizing, assigning
loads and vehicle routes, etc. These models use time periods A. Distribution-based approach
which last from one to two weeks. With the aim of minimizing total cost over the presence of
B. Criterion: Sources of Uncertainty service level constraint, [9] developed a stochastic model of an
integrated production-distribution system under demand
The intricate nature of SC networks and dynamic uncertainty. They also proposed an optimization algorithm for
relationships of different sectors among a SC indicate that an finding the near-optimal solution. [10] presented a two-stage
inevitable degree of uncertainty exists in SCP decisions. stochastic programming framework to measure cost with the
Deterministic optimization approaches either completely scenario analysis based approach over a mid-term planning
ignore uncertainty or use historical data to forecast the future. horizon to solve a manufacturing, assembly, distribution
In real-world situations, most of the SCs operate in a somehow (MAD) planning problem under demand, supply cost and lead
uncertain environment and their related parameters are not time delivery uncertainties. Researchers in [11] developed a
known with certainty because of incompleteness and/or two-stage stochastic programming approach based on the
unavailability of required data over the planning horizon. There deterministic mixed-integer linear programming model
are three distinct sources of uncertainty in SCs including, proposed by [12]. The authors’ objective was to minimize cost.
supply uncertainty, process/manufacturing uncertainty, and They incorporated demand uncertainty into multisite midterm
demand uncertainty. Supply uncertainty is related to the SCP problems. Developing a hierarchical decision-making
variability of the suppliers’ performance due to late or framework, they classified the variables and constraints into
defective deliveries. Process uncertainty results from the production decision and supply chain decision.
unreliability of the production process. Finally, demand
uncertainty, which is the most serious of the three based on [6], Reference [13] extended their previous work [11] by
arises from rapidly changing demand or inaccurate forecasting integrating the previous two-stage stochastic programming
of demand. methodology with a chance constraint programming approach
to capture the trade-offs between customer demand satisfaction
C. Criterion: Performance Measures and production cost under demand uncertainty. The authors
SCP literature is very rich in terms of modelling then extended their work again to develop a bi-level
frameworks and problem formulation approaches. While the optimization framework with the basic objective of
efficiency and effectiveness of most proposed SC models were maximizing customer service level and minimizing total cost
generally evaluated by means of quantitative performance [4].
measures such as cost or lead time minimization, some studies
concentrated on qualitative ones like maximization of Developing a stochastic programming model for solving
flexibility or customer service level, for instance. However, large-scale problems, [14] proposed an integration of a
only a few researchers jointly incorporated qualitative and sampling strategy with an accelerated Benders decomposition
quantitative performance measures into their effort. Previous algorithm. Considering a strategic planning horizon, they
literatures could be classified based on the type of performance incorporated supply, process, and demand uncertainties into the
measures they utilize to develop the model. model. Reference [15] developed a mixed integer linear goal
programming (MILGP) model for an integrated multi-objective
D. Criterion: Modelling Approaches procurement, production and distribution problem. The authors
According to [4], in order to handle the uncertainty inherent proposed different time-grids and planning horizons for
in the real world problems, three distinct methods were aggregate and detailed planning. They presented a single

198
formulation for different levels of decisions with the objective proposed two-phase fuzzy method was tested through a
of minimization of the following elements: storage constraints numerical experiment.
deviation, forward cover constraint deviation, and total cost
With the aim of minimizing total SC cost, [23] developed
deviation. An illustrative case of a consumer goods company
an approach to derive the membership function of a fuzzy SC
was also presented. With the aim of minimizing total cost, [16]
network model over a tactical planning horizon. The authors
developed an analytical framework based on mixed-integer
considered demand, raw material cost and transportation cost
linear programming to address a dynamic planning process of a
as fuzzy parameters. Reference [24] modelled an integrated
production unit under demand uncertainty. Researchers in [17]
production–distribution planning problem based on fuzzy
formulated the supply chain network design (SCND) problem
mathematical programming with a fuzzy objective function
as a multi-objective stochastic mixed-integer nonlinear
solved by genetic algorithm. Considering uncertainties of
programming model, which was solved by using the goal
customer demand and production capacity, the authors’
attainment technique. Developing a stochastic programming
objective was to provide a sound trade-off between
approach under the uncertainties of demand, supply, and
maximization of profit and maximization of customer service
process, they proposed a research work addressing strategic
level. A numerical example of a general appliance company
and tactical planning levels to measure total cost, variance of
demonstrated the model. Researchers in [25] developed a fuzzy
total cost and financial risk of not meeting a certain budget.
mathematical programming model of integrated production-
Reference [18] developed a two-stage stochastic supply distribution planning in a build-to-order (BTO) environment
chain network design model under customer demand, over both short-term and mid-term planning horizons. They
operational cost and facility capacity uncertainties. Considering used mixed-integer fuzzy programming (MIFP) with the aim of
both strategic and tactical planning levels, the authors’ minimizing the total operating cost while improving customer
objective was to minimize total cost of the system. The sample service level under the uncertainties of raw material and
average approximation technique was exploited to solve the inventory holding cost and customer demand. Developing a
problem. collaborative production-distribution planning model, [26]
employed a fuzzy goal programming (FGP) approach to
B. Fuzzy-based approach incorporate the collaborative planning issues together with a
One of the first attempts to develop a fuzzy model and realistic model structure into the model to handle the problem
simulation for modelling a procurement, production and of both centralized and decentralized SC structures under
distribution SC network over a short-term planning horizon demand uncertainty. The authors fulfilled multiple objectives
was performed by [19]. Considering the uncertainty of demand related to maximizing total system profit, minimizing cost of
and external supply of raw material, the authors’ objective was retailers, and minimizing delays in demand in retailers.
to determine the stock levels and order quantities for each
inventory during a finite time horizon to obtain an acceptable Integrating procurement, production and distribution into a
delivery performance at a reasonable total cost for the entire unified framework, [27] formulated a multi-objective supply
SC. The authors then extended their work and proposed a chain master planning (SCMP) problem. Considering the
production SC with all facilities in a serial link, including all uncertain nature of market demand, cost/time coefficients and
kinds of inventories along a SC and their related production capacity levels, they proposed a possibilistic mixed integer
facilities except distribution and retailer [20]. A fuzzy model linear programming model (PMILP) considering a wide range
incorporated into a simulator was developed for investigating of conflicting objectives such as minimization of total cost and
the dynamics of SC and measuring its performance within a maximization of customer service level. The authors proposed
short-term time horizon. Their objective was to reach a a novel fuzzy approach as a solution method. Extending their
satisfactory level of service at a reasonable total cost through previous effort, [28] then developed a fuzzy goal programming
determining order-up-to levels of inventories under demand, approach to construct an integrated procurement, production
supply and delivery uncertainties. and distribution planning framework in a tactical planning
level. They incorporated four objectives including
Researchers in [21] constructed a production-distribution minimization of total cost, defective items, and late deliveries
planning model. Taking several performance measures such as and maximization of total purchasing value under uncertain
maximizing each enterprise profit, maximizing customer market demand and production capacity. Extending the
service level, and maximizing safe inventory level into formulation presented by [12], a fuzzy mixed-integer linear
account, they formulated the model as a mixed-integer programming model was constructed by [29] to demonstrate
nonlinear programming (MINLP) problem under demand the usefulness of the fuzzy mathematical programming
uncertainty. To achieve an overall accepted solution, a two- approach to model a SC production planning problem under
phase fuzzy method was exploited. A numerical example demand uncertainty. The basic objective of the proposed model
demonstrated the effectiveness of the proposed model. was to minimize total cost of the entire system. Researchers in
Reference [22] constructed a SC scheduling model as a mixed- [30] proposed a fuzzy mathematical programming model for a
integer nonlinear programming (MINLP) problem. With the tactical SCP problem considering supply, demand and process
aim of attaining the maximization of total supply chain profit, uncertainties. To obtain the objective of minimizing total SC
customer service level, and safe inventory level, the authors cost, the authors formulated a fuzzy mixed-integer linear
adopted the scenario based approach for modelling the programming model where data were modelled by triangular
uncertain market demand, and the fuzzy set theory was applied fuzzy numbers. Their model was evaluated by using data from
for forming product price uncertainty. The effectiveness of the a real-world automobile SC. The authors, then, extended their

199
work by presenting trapezoidal fuzzy numbers in [31] and demand. With the aim of minimizing total losses of SC while
combined linear programming with fuzzy set theory to propose maximizing customer satisfaction, the authors developed a
a novel fuzzy mixed-integer linear programming (FMILP) novel robust multi-objective mixed-integer nonlinear
model for a tactical SCP problem. With the aim of centralizing programming model for a medium-term planning horizon. The
multi-node decisions to acquire the best utilization of resources authors then proposed an efficient algorithm in [38], which was
along the time horizon in order to meet customer demand at the a combination of an augmented ε-constraint method and
lowest possible cost, the authors contemplated all the genetic algorithm to solve the same problem. They extended
uncertainty sources of demand, process and supply in an their previous model objectives to fulfil the conflicting
integrated manner. The model was illustrated using an objectives of total cost of SC, customer service level and
automobile SC. worker productivity. Finally, they formulated a multi-objective
two-stage stochastic programming model in [39] to deal with a
C. Scenario-based approach multi-period, multi-product, multi-site tactical production-
In an attempt to reduce variability and show the distribution planning problem. Providing a set of discrete
overemphasis of feasibility in optimization models of real- scenarios to handle the uncertainties of cost parameters and
world problems, decision makers are always faced with noisy, customer demand, a robust stochastic mixed-integer nonlinear
inaccurate, or unspecific data. To handle the difficulty of such programming model was formulated. The authors’ objective
data and to deal with sensitivity analysis problems or stochastic was to minimize total cost coupled with total cost variance
programming formulations, [32] developed a general model minimization and workers productivity maximization. To solve
formulation framework, called Robust Optimization (RO). the presented model, a hybrid algorithm composed of the
They constructed their novel approach based on the integration extended Monte Carlo sampling method, modified ε-constraint
of goal programming formulation with scenario-based technique and L-shaped method was exploited.
description of a problem.
D. Simulation-based approach
To demonstrate the effect of uncertainty on demand chain Reference [40] investigated the effect of different strategic
planning (DCP), [33] proposed a robust planning model for a and operational performance measures on SC performance.
tactical SCP problem. The authors introduced various sources Developing a discrete event simulation model, the authors
of uncertainties inherent in SCP decisions and the best level to studied the behaviour of a conjoined web-based retail SC. It
provide buffers against those uncertainties. Using Monte Carlo was indicated in their research that inventory system stock-out
simulation as a solution method, they illustrated their proposed risk, probability distribution of demand, and transportation time
model through a case study of a chemical enterprise. were most important in determining the effectiveness of the
Reference [34] proposed a mathematical programming chain. Researchers in [41] developed a multi-objective
model contemplating a scenario based approach to formulate a simulation-based optimization model that comprised the
procurement-production planning problem. With the aim of Taguchi technique and response surface methodology.
determining the optimal sourcing, transportation and allocation Considering the uncertainty of demand, the authors’ objective
of an enterprise’s limited resources in the least costly manner, was to determine the proper plant capacity and adopt the right
the authors developed a multi-stage stochastic programming level of delayed differentiation strategy for products of a PC
model for SCP under demand uncertainty. The significance of manufacturing company to achieve the optimal performance of
the model was illustrated through a numerical example. With the SC.
the aim of developing a global SC network to measure the Proposing an object-oriented approach, [42] modeled a
effect of government regulation on the entire network, [35] production planning and inventory replenishment system in a
proposed an integrated production-distribution planning model pharmaceutical SC. Developing a group of interconnected
based on the scenario based approach. The authors nodes to model a SC network, the influence of various
simultaneously considered strategic and operational planning uncertainties in the entire chain was evaluated through Monte-
decisions in a global SC under uncertain parameters of Carlo simulation. Finally, the authors studied the effect of
customer demand, cost of product, and transportation lead replenishment policy change on SC performance through a
time. The authors’ objective in the strategic level was to numerical example. Investigating the optimal level of safety
maximize total network profit, while minimizing total cost was stock in a petrochemical company, [43] developed a linear
considered as the operational level’s objective. programming formulation with the aim of minimizing total
Researchers in [36] developed a robust optimization model expected on-hand inventory across the entire chain.
incorporating demand uncertainty for integrated aggregate and Considering demand uncertainty, discrete-event simulation was
detailed planning of a multi-site procurement-production proposed to evaluate the performance functions of the SC,
distribution problem. In their proposed model, procurement while the safety stock variables and customer service level
and production plans were presented as “here and now” were determined through a linear programming model.
decisions, while distribution plans are scenario based and were With the aim of achieving the optimal operation plan for
proposed as “wait and see” strategies until the realization of SC network, [44] developed a general framework by
demand. With the aim of minimizing total cost, the model was combining an optimization model and discrete-event
demonstrated using a numerical example of a consumer goods simulation. Contemplating the minimization of total SC cost as
company. Reference [37] considered an aggregate production the model objective, the authors investigated the interaction
planning (APP) problem of a manufacturing supply chain between the optimization model solutions and simulation
under the uncertain nature of cost parameters and consumer

200
results. Reference [45] developed a multi-echelon production- modelling to investigate order fulfillment scheduling of a
distribution SC model to deal with the problem of clinical trial manufacturing company in a SC environment. Considering
materials management through proposing a simulation-based both tactical and operational planning levels, the main goal of
optimization approach. The authors combined mathematical the proposed model was to determine the best order promising
programming-based planning with discrete event simulation in time together with optimal production, inventory and
the proposed model. Considering different sources of distribution plans at the tactical level and optimal scheduling
uncertainty, the research objective was to minimize the entire decision at the operational level. Contemplating various kinds
SC cost. of uncertain factors, the model objective was to minimize total
SC cost.
E. Hybrid-based approach
Researchers in [46] proposed a hybrid approach combining V. ANALYSIS AND DISCUSSION
mathematical programming and simulation models to solve a Based on the result of reviewed literature, most of the
multi-period multi-product (MPMP) production planning models considered only one source of uncertainty, which was
problem. With the aim of keeping the lowest possible inventory demand uncertainty. This is a considerable drawback of the
in the entire chain, their objective was to find the capacity- existing models, since although demand is the most important
feasible production plan. To demonstrate the effectiveness of source of uncertainty according to [6], other sources of
the proposed model, a case study of a manufacturing system uncertainty such as supply and process greatly influence the SC
was examined. Reference [47] proposed a hybrid approach to performance, which triggers the need for jointly considering
model an integrated production-distribution planning problem them.
with the aim of satisfying retailer’s demand through keeping
the lowest possible inventories on hand. Considering the Most of the proposed models were developed over a mid-
stochastic nature of machine capacity and distribution capacity term planning horizon while some researchers considered a
constraints, the authors’ objective was to minimize the entire multi-level planning approach. Minimization of total cost and,
SC cost over a short-term planning horizon. to a lesser extent, maximization of the entire chain profit, as a
single objective, was often the objective function of most of the
Combining analytic and simulation models, [48] presented proposed models. Moreover, qualitative performance measures
a hybrid approach to develop an integrated production- in addressing multi-objective SCP problems were greatly
distribution planning model. Considering machine operation ignored. Finally, the most widely used modelling approach was
time and distribution operation time as uncertain parameters, distribution based followed by fuzzy-based model, along with
the authors’ objective was to minimize the overall production, scenario-based approach.
distribution, inventory holding and shortage costs. Reference
[49] extended their previous work in [46] by developing a VI. CONCLUSION
capacity feasible production plan model considering workload In this work, a comprehensive literature survey of various
of jobs to present a hybrid model combining linear modelling methods for supply chain planning (SCP) under
programming and simulation. Incorporating JIT approach, the uncertainty has been conducted. A classification based on the
model objective was to minimize the entire SC cost. various modelling approaches to model SCP under uncertainty
Researchers in [50] provided a hybrid method to solve a has been presented. To the best of our knowledge, this is the
production-distribution planning problem taking replenishment first time that this kind of classification has been presented.
policy into account. The authors developed a mathematical Researchers employed different methods and techniques to
programming model to specify the capacities of facilities. With solve the problem of SCP over different planning horizons. The
the aim of determining the optimal production-distribution plan problem types, sources of uncertainty, performance measures
a simulation model was constructed. The objective of the and modelling approaches were the taxonomy criteria exploited
proposed model was to minimize the total SC cost which was in this research. Although extensive research on SCP methods
demonstrated through a numerical example. Incorporating risk under uncertainty has been performed, a new modelling
measures into their stochastic programming model, [51] approach in this wide area of planning can be investigated as a
proposed a mid-term planning of a global SC under demand future research.
and freight rate uncertainties. With the aim of minimizing total
cost, they combined their model with a Monte Carlo sampling REFERENCES
approach to achieve an optimal solution. Considering the [1] Hanssmann, F., 1959. Optimal inventory location and control in
production-planning problem of a crop farm, [52] developed a production and distribution networks, Operations Research 7, 483-498.
hybrid approach combining Monte Carlo simulation (to [2] Beamon, B.M., 1998. Supply chain design and analysis: models and
methods. International Journal of Production Economics, 55, 3, 281-94.
accommodate probabilistic information of various kinds) and
genetic algorithm (to solve the constrained maximization [3] Min H. and Zhou G.G., 2002. Supply chain modeling: past, present and
future. Computer and Industrial Engineering, 43(1–2):231-249.
problem). Incorporating various kinds of stochastic information
[4] Gupta A. and Maranas C.D., 2003. Managing demand uncertainty in
into the model, the research objective was to maximize total supply chain planning. Computers and Chemical Engineering, 27, 1219-
gross margin of the system. One of the drawbacks of the 1227.
proposed model is it does not consider the cost parameters [5] Galbraith J., 1973. Designing complex organizations. Addison- Wesley,
associated with adopting the method. Massachusetts.
[6] Davis T., 1993. Effective supply chain management. Sloan Management
Reference [53] developed a three-step hybrid approach Review 34, 35-46.
integrating mathematical programming and simulation

201
[7] Giannoccaro I. and Pontrandolfo P., 2001. Models for supply chain [28] Torabia S.A., Hassini E., 2009. Multi-site production planning
management: a taxonomy. Proceedings of the Production and Operations integrating procurement and distribution plans in multi-echelon supply
Management. Conference POMS mastery in the new millennium, chains: an interactive fuzzy goal programming approach. International
Orlando, Florida, USA. Journal of Production Research, 47, 19, 5475-5499.
[8] chopra S. and Meindl P., 2010. Supply chain management; strategy, [29] Mula J., Peidro D., Poler R., 2010b. The effectiveness of a fuzzy
planning and operation. Pearson education, inc. publishing at prentice mathematical programming approach for supply chain production
hall, One Lake Street, Upper Saddle River, Nnew Jersey. planning with fuzzy demand. International Journal of Production
[9] Pyke D.F. and Cohen M.A., 1994. Multiproduct integrated production- Economics 128, 136-143.
distribution systems. European Journal of Operational Research 74, 18- [30] Peidro D., Mula J., Poler R., Verdegay J.L., 2009. Fuzzy optimization
49 North-Holland. for supply chain planning under supply, demand and process
[10] Escudero L.F., Galindo E., Garcia G., Gomez E., Sabau V., 1999. Case uncertainties. Fuzzy Sets and Systems 160, 2640-2657.
study schumann, a modeling framework for supply chain management [31] Peidro D., Mula J., Jimenez M., Botella M.d.M., 2010. A fuzzy linear
under uncertainty. European Journal of Operational Research 119, 14- programming based approach for tactical supply chain planning in an
34. uncertain environment. European Journal of Operational Research, 205,
[11] Gupta A. and Maranas C.D., 2000. A two-stage modeling and solution 65-80.
framework for multisite midterm planning under demand uncertainty. [32] Mulvey, J.M., Vanderbei, R.J., Zenios, S.J., 1995. Robust optimization
Industrial Engineering and Chemistery Research, 39, 3799-3813. of large-scale systems. Operations Research 43 (2), 264-281.
[12] McDonald C.M., Karimi I., 1997, A planning and scheduling of parallel [33] Landeghem H.V., Vanmaele H., 2002. Robust planning: a new paradigm
semi continuous processes. 1. Production Planning. Industrial for demand chain planning. Journal of Operations Management 20, 769-
Engineering and Chemistery Research, 36, 2691. 783.
[13] Gupta A., Maranas C.D., McDonald C.M., 2000. Mid-term supply chain [34] Nagar L. and Jain K., 2008. Supply chain planning using multi-stage
planning under demand uncertainty: customer demand satisfaction and stochastic programming. Supply Chain Management: An International
inventory management. Computers and Chemical Engineering, 24, Journal, 13/3, 251-256.
2613-2621. [35] Das K. and Sengupta S., 2009. A hierarchical process industry
[14] Santoso T., Ahmed S., Goetschalckx M., Shapiro A., 2005. A stochastic production–distribution planning model. International Journal of
programming approach for supply chain network design under Production Economics 117, 402-419.
uncertainty. European Journal of Operational Research 167, 96-115. [36] Kanyalkar A.P. and Adil G.K., 2010. A robust optimisation model for
[15] Kanyalkar A.P. and Adil G.K., 2007. Aggregate and detailed production aggregate and detailed planning of a multi-site procurement-production-
planning integrating procurement and distribution plans in a multi-site distribution system. International Journal of Production Research, 48, 3,
environment. International Journal of Production Research, 45, 22, 635-656.
5329-5353. [37] Mirzapour Al-e-hashem S.M.J., Malekly H., Aryanezhad M.B., 2011. A
[16] Galassoab F., Merce C., Grabot B., 2008. Decision support for supply multi-objective robust optimization model for multi-product multi-site
chain planning under uncertainty. International Journal of Systems aggregate production planning in a supply chain under uncertainty.
Science, 39, 7, 667-675. International Journal of Production Economics 134, 28-42.
[17] Azaron A., Brown K.N., Tarim S.A., Modarres M., 2008. A multi- [38] Mirzapour Al-e-hashem S.M.J., Aryanezhad M.B., Sadjadi S.J., 2011.
objective stochastic programming approach for supply chain design An efficient algorithm to solve a multi-objective robust aggregate
considering risk. International Journal of Production Economics, 116, production planning in an uncertain environment, International Journal
129-138. of Advanced Manufacturing Technology, In Press.
[18] Mohammadi Bidhandi H., Yusuff R.M., 2011. Integrated supply chain [39] Mirzapour Al-e-hashem S.M.J., Baboli A., Sadjadi S.J., Aryanezhad
planning under uncertainty using an improved stochastic approach. M.B., 2011. A Multiobjective Stochastic Production-Distribution
Applied Mathematical Modelling 35, 2618-2630. Planning Problem in an Uncertain Environment Considering Risk and
[19] Petrovic D., Roy R., Petrovic R., 1998. Modelling and simulation of a Workers Productivity. Mathematical Problems in Engineering, Volume
supply chain in an uncertain environment. European Journal of 2011.
Operational Research 109, 299-309. [40] Beamon B.M., Chen V.C.P., 2001. Performance analysis of conjoined
[20] Petrovic D., Roy R., Petrovic R., 1999. Supply chain modelling using supply chains. International Journal of Production Research,
fuzzy sets. International Journal of Production Economics 59, 443-453. 39(14):3195-3218
[21] Chen C.L., Wang B.W., Lee W.C., 2003. Multi objective Optimization [41] Shang J.S., Li S., Tadikamalla P., 2004. Operational design of a supply
for a Multi enterprise Supply Chain Network. Industrial Engineering and chain system using the Taguchi method, response surface methodology,
Chemistry Reearch, 42(9), 1879-1889. simulation, and optimization, International Journal of Production
Research, 42:18, 3823-3849.
[22] Chen C.L., Lee W.C., 2004. Multi-objective optimization of multi-
echelon supply chain networks with uncertain product demands and [42] Hung W.Y., Samsatli N.J., Shah N., 2006. Object-oriented dynamic
prices. Computers and Chemical Engineering 28, 1131-1144. supply-chain modelling incorporated with production scheduling.
European Journal of Operational Research, 169(3):1064-1076.
[23] Chen S.P. and Chang P.C., 2006. A mathematical programming
approach to supply chain models with fuzzy parameters, Engineering [43] Jung J.Y., Blau G., Pekny J.F., Reklaitis G.V., Eversdyk D., 2008.
Optimization, 38:6, 647-669. Integrated safety stock management for multi-stage supply chains under
production capacity constraints. Computers and Chemical Engineering,
[24] Aliev R.A., Fazlollahi B., Guirimov B.G., Aliev R.R., 2007. Fuzzy- 32, 2570-2581.
genetic approach to aggregate production – distribution planning in
supply chain management. Information Sciences 177, 4241-4255. [44] Almeder C., Preusser M., Hartl R.F., 2009. Simulation and optimization
of supply chains: alternative or complementary approaches? OR
[25] Demirli K. and Yimer A.D., 2008. Fuzzy scheduling of a build-to-order Spectrum, 31:95-119.
supply chain. International Journal of Production Research, 46, 14,
3931-3958. [45] Chen Y., Mockus L., Orcun S., Reklaitis G.V., 2010. Simulation-based
Optimization Approach to Clinical Trial Supply Chain Management.
[26] Selim H., Araz C., Ozkarahan I., 2008. Collaborative production – 20th European Symposium on Computer Aided Process Engineering
distribution planning in supply chain: A fuzzy goal programming (ESCAPE20).
approach. Transportation Research Part E Logistic Transportation, 44,
396-419. [46] Byrne M.D. and Bakir M.A., 1999. Production planning using a hybrid
simulation_analytical approach. International Journal of Production
[27] Torabia S.A. and Hassini E., 2008. An interactive possibilistic Economics, 59, 305-311.
programming approach for multiple objective supply chain master
planning. Fuzzy Sets and Systems 159, 193-214.

202
[47] Lee Y.H., Kim S.H., Moon C., 2002. Production-distribution planning in replenishment policies. International Journal of Advance Manufacturing
supply chain using a hybrid approach, Production Planning & Control, Technology, 27: 593-603.
13:1, 35-46. [51] You F., Wassick J.M., Grossmann I.E., 2009. Risk management for a
[48] Lee Y.H. and Kim S.H., 2002. Production-distribution planning in global supply chain planning under uncertainty: models and algorithms.
supply chain considering capacity constraints. Computer & Industrial American Institute of Chemical Engineers Journal, 55: 931-946.
Engineering 43, 169-190. [52] Musshoff O. and Hirschauer N., 2009. Optimizing production decisions
[49] Byrne M.D. and Hossain M.M., 2005. Production planning: An using a hybrid simulation–genetic algorithm approach. Canadian Journal
improved hybrid approach. International Journal of Production of Agricultural Economics, 57, 35-54.
Economics 93–94, 225-229. [53] Tunali S., Ozfirat P.M., Ay G., 2011. Setting order promising times in a
[50] Lim S.J., Jeong S.J., Kim K.S., Park M.W., 2006. A simulation approach supply chain network using hybrid simulation-analytical approach: An
for production-distribution planning with consideration given to industrial case study. Simulation Modelling Practice and Theory, 19,
1967-1982.

203

View publication stats

Anda mungkin juga menyukai