Negotiations for agent-based concurrent process scheduling of resources in highly dynamic environments

Abstract

An important and complex process in the mining industry is the material handling process. In this process, trucks must transport materials extracted by shovels to different places at the mine. To enable efficient material handling processes, the decision on the destination of a truck is crucial. Currently, this process is supported by an approach based on centralized systems that apply dispatching criteria. A disadvantage of this approach is not providing a precise dispatching solution because of missing knowledge about potentially changed external conditions and the dependency on a central node.

This thesis addresses the improvement of the material handling process in an open-pit mine by utilizing a multiagent system. A multiagent system is a distributed system compound of intelligent agents that have to interact with each other to achieve their own objectives. Besides, they can react to dynamic changes both caused by the environment and in the equipment respective states.

The thesis investigates how a multiagent approach can improve the material handling process in an open-pit mine specifically, how agents can negotiate efficiently to organize the activities of the equipment in a dynamic environment. The research is focused on the following three major research questions: 1. How can a material handling process in an open-pit mine be supported more efficiently? 2. Which communication and interaction mechanism among agents allows for generating schedules? 3. How can an agent make an efficient decision during concurrent negotiations in dynamic environments?

The developed multiagent system is evaluated by comparing it against other centralized methods. In the evaluation, simulated scenarios based on actual data from a Chilean open-pit mine were used. The results show that the multiagent systems solve the truck dispatching problem in open-pit mines efficiently.