We have designed and realized decentralized multiagent optimization for solving different real-world problems in supply chain and transportation networks. Each system consists of a network of loosely-coupled computational autonomous agents who can perform actions, each has local resources at their disposal and they possess local knowledge and limited capabilities. Without any strong centralized supervision, they can interact through a set of operations, namely an interaction protocol. A well-designed decentralized system would possess the advantages of Scalability, Robustness, and Situatedness, although it is challenging to achieve coherent, coordinated & efficient system behaviour while avoiding harmful interactions. We have achieved successes in the following applications.

Smart and scalable urban traffic control is a real-time, adaptive traffic control system that improves highly dynamic traffic flows in urban road networks.

The core control engine (the brain) includes schedule-driven intersection control on each intersection and decentralized coordination mechanisms among neighbors. It also needs a few strengthening strategies to enable its operations by coping with real-world traffic challenges in urban environment.

Our goal is to analyze the relative performance of alternative route choice models as different assumptions are made about the type of traffic control in use in the urban road network. To this end, we define a unified agent-based framework for formulating different route choice models, and integrate this framework with a microscopic traffic simulation environment. Within this framework, each agent’s memory is updated repeatedly (daily) to reflect available prior individual and social experience, and then a route is chosen by a probabilistic sequential decision-making process that is a function of the agent’s updated current memory.

We have designed an agent-mediated approach to on-demand e-business supply chain integration. Each agent works as a service broker, exploring individual service decisions as well as interacting with each other for achieving compatibility and coherence among the decisions of all agents. Based on the multi-agent constraint-based framework, a prototype has been implemented with experiments highlighting the effectiveness of the approach.