Agent-based demand forecast in multi-echelon supply chain

Supply chain management (SCM) is an emerging field that has commanded attention and support from the industrial community. Demand forecast taking inventory into consideration is an important issue in SCM. There are many diverse inventory systems, in theory or practice, which are operated by entities (companies) in a supply chain. In order to increase supply chain effectiveness, minimize total cost, and reduce the bullwhip effect, integration and coordination of these different systems in the supply chain (SC) are required using information technology and effective communication. The paper develops a multi-agent system to simulate a supply chain, where agents operate these entities with different inventory systems. Agents are coordinated to control inventory and minimize the total cost of a SC by sharing information and forecasting knowledge. The demand is forecasted with a genetic algorithm (GA) and the ordering quantity is offered at each echelon incorporating the perspective of “systems thinking”. By using this agent-based system, the results show that total cost decreases and the ordering variation curve becomes smooth.