Title: Effect of forecasting on the multi-echelon distribution inventory supply chain cost using neural network, genetic algorithm and particle swarm optimisation

Authors: A. Noorul Haq, G. Kannan

Addresses: Department of Production Engineering and Dean Administration, National Institute of Technology, Tiruchirappalli 620015, India. ' Department of Production Engineering, National Institute of Technology, Tiruchirappalli 620015, India

Abstract: Supply Chain Management (SCM) is an emerging field that has commanded attention and support from the industrial community. Forecasting activities are widely performed in various areas of supply chains for predicting important SCM measurements such as demand volume in order management, capacity usage in production management, traffic costs in transportation management and so on. Firstly, the demand is forecast using Neural Networks (NN) and different forecasting methods. The Multi-Echelon Distribution Inventory Supply Chain Model (MEDISCM) is formulated using Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO). This paper considers the impact of forecasting methods on the total cost of the multi-echelon distribution inventory supply chain. In this paper, the proposed model is validated by considering the case study in a tyre industry located in southern part of India. To solve the iterative procedure involved, the algorithm involved in GA and PSO model is coded in C++.

Keywords: multi-echelon distribution inventory; supply chain models; MEDISCM; neural networks; genetic algorithms; particle swarm optimisation; PSO; forecasting; supply chain management; SCM.

DOI: 10.1504/IJSOI.2006.010186

International Journal of Services Operations and Informatics, 2006 Vol.1 No.1/2, pp.1 - 22

Published online: 08 Jul 2006 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article