Multiagent approach to solve project team work allocation problems

Abstract

In today's fiercely competitive market, embedded software development teams are driven to do more with less: reduce time to market, costs and risk, while improving quality and predictability. There is also an increasing need to deliberately organise the teams that initially involves the division of the project into tasks; the selection of the right people; and the correct allocation of those tasks for the selected people. Team configuration process is typically performed by a project manager based on his/her past experience and the available (though frequently scarce, uncertain and dynamic) information about the cognitive, emotion and social characteristics of the potential team members. To support this decision-making process we propose the Fuzzy Belief-Desire-Intention architecture, a multiagent approach that given an initial team configuration and a set of tasks, simulates the most possible team performance. Its architecture bases are fuzzy set theory and fuzzy logic and it is implemented using Multiagent Systems technology in Java and Jadex. Tests have been carried out in which the architecture has been applied to a set of tasks involving the embedded software development. The result predicted by our architecture with the performance of an engineering team in a real industrial project is made.