Heuristic-based neural networks for stochastic dynamic lot sizing problem

Multi-period single-item lot sizing problem under stochastic environment has been tackled by few researchers and remains in need of further studies. It is mathematically intractable due to its complex structure. In this paper, an optimum lot-sizing policy based on minimum total relevant cost under price and demand uncertainties was studied by using various artificial neural networks trained with heuristic-based learning approaches; genetic algorithm (GA) and bee algorithm (BA). These combined approaches have been examined with three domain-specific costing heuristics comprising revised silver meal (RSM), revised least unit cost (RLUC), cost benefit (CB). It is concluded that the feed-forward neural network (FF-NN) model trained with BA outperforms the other models with better prediction results. In addition, RLUC is found the best operating domain-specific heuristic to calculate the total cost incurring of the lot-sizing problem. Hence, the best paired heuristics to help decision makers are suggested as RLUC and FF-NN trained with BA.

[1]  Marco Taisch,et al.  Neural networks in production planning and control , 1999 .

[2]  D.T. Pham,et al.  Application of the Bees Algorithm to the Training of Learning Vector Quantisation Networks for Control Chart Pattern Recognition , 2006, 2006 2nd International Conference on Information & Communication Technologies.

[3]  Brian G. Kingsman,et al.  Production, Manufacturing and Logistics Modelling and computing (R n ,S n ) policies for inventory systems with non-stationary stochastic demand , 2005 .

[4]  Chao-Ton Su,et al.  Selection of optimal parameters in gas‐assisted injection moulding using a neural network model and the Taguchi method , 1997 .

[5]  Graham K. Rand,et al.  Decision Systems for Inventory Management and Production Planning , 1979 .

[6]  Subhash C. Sarin,et al.  Integrated lot sizing and dispatching in wafer fabrication , 2010 .

[7]  Armagan Tarim,et al.  Constraint programming for computing non-stationary (R, S) inventory policies , 2008, Eur. J. Oper. Res..

[8]  D. Pham,et al.  THE BEES ALGORITHM, A NOVEL TOOL FOR COMPLEX OPTIMISATION PROBLEMS , 2006 .

[9]  Mark E. Ferguson,et al.  BlueLinx can benefit from innovative inventory management methods for commodity forward buys , 2009 .

[10]  P. Brandimarte.  Multi-item capacitated lot-sizing with demand uncertainty , 2006 .

[11]  Lotfi K. Gaafar,et al.  A neural network model for solving the lot-sizing problem , 2000 .

[12]  Jatinder N. D. Gupta,et al.  Determining lot sizes and resource requirements: A review , 1987 .

[13]  Muddassar Farooq.  Bee-Inspired Protocol Engineering: From Nature to Networks , 2008 .

[14]  Hacer Güner Gören,et al.  A review of applications of genetic algorithms in lot sizing , 2010, J. Intell. Manuf..

[15]  Habibollah Haron,et al.  Lot Sizing using Neural Network Approach , 2006 .

[16]  Ş. Tarim,et al.  The stochastic dynamic production/inventory lot-sizing problem with service-level constraints , 2004 .

[17]  Ercan Oztemel,et al.  Neural Network Based Experimental Design Method and an Industrial Application , 1996 .

[18]  Jatinder N. D. Gupta,et al.  OR Practice - Determining Lot Sizes and Resource Requirements: A Review , 1987, Oper. Res..

[19]  Emile H. L. Aarts,et al.  A novel decomposition approach for on-line lot-sizing , 2000, Eur. J. Oper. Res..

[20]  John J. DeMatteis.  An Economic Lot-Sizing Technique I: The Part-Period Algorithm , 1968, IBM Syst. J..

[21]  Kit Yan Chan,et al.  A new orthogonal array based crossover, with analysis of gene interactions, for evolutionary algorithms and its application to car door design , 2010, Expert Syst. Appl..

[22]  Kit Yan Chan,et al.  Improved orthogonal array based simulated annealing for design optimization , 2009, Expert Syst. Appl..

[23]  James H. Bookbinder,et al.  Strategies for the Probabilistic Lot-Sizing Problem with Service-Level Constraints , 1988 .

[24]  Zeger Degraeve,et al.  Meta-heuristics for dynamic lot sizing: A review and comparison of solution approaches , 2004, Eur. J. Oper. Res..

[25]  N. Jawahar,et al.  Genetic algorithm and Hopfield neural network for a dynamic lot sizing problem , 2006 .

[26]  Dervis Karaboga,et al.  A survey: algorithms simulating bee swarm intelligence , 2009, Artificial Intelligence Review.

[27]  Ge Xiurun,et al.  An improved PSO-based ANN with simulated annealing technique , 2005, Neurocomputing.

[28]  E. Şenyiğit,et al.  New lot sizing heuristics for demand and price uncertainties with service-level constraint , 2010 .

[29]  J. DeMatteisJ..  An economic lot-sizing technique , 1968 .

[30]  Fei Liu,et al.  A stochastic dynamic programming based model for uncertain production planning of re-manufacturing system , 2009 .

[31]  Xin Yao,et al.  A review of evolutionary artificial neural networks , 1993, Int. J. Intell. Syst..

[32]  Harvey M. Wagner,et al.  Dynamic Version of the Economic Lot Size Model , 2004, Manag. Sci..