Multi-agent model predictive control for transportation networks: Serial versus parallel schemes


Reference:
R.R. Negenborn, B. De Schutter, and J. Hellendoorn, "Multi-agent model predictive control for transportation networks: Serial versus parallel schemes," Engineering Applications of Artificial Intelligence, vol. 21, no. 3, pp. 353-366, Apr. 2008.

Abstract:
We consider the control of large-scale transportation networks, like road traffic networks, power distribution networks, water distribution networks, etc. Control of these networks is often not possible from a single point by a single intelligent control agent; instead control has to be performed using multiple intelligent agents. We consider multi-agent control schemes in which each agent employs a model-based predictive control approach. Coordination between the agents is used to improve decision making. This coordination can be in the form of parallel or serial schemes. We propose a novel serial coordination scheme based on Lagrange theory and compare this with an existing parallel scheme. Experiments by means of simulations on a particular type of transportation network, viz., an electric power network, illustrate the performance of both schemes. It is shown that the serial scheme has preferable properties compared to the parallel scheme in terms of the convergence speed and the quality of the solution.


Downloads:
 * Online version of the paper
 * Corresponding technical report: pdf file (306 KB)
      Note: More information on the pdf file format mentioned above can be found here.


Bibtex entry:

@article{NegDeS:07-024,
        author={R.R. Negenborn and B. {D}e Schutter and J. Hellendoorn},
        title={Multi-agent model predictive control for transportation networks: Serial versus parallel schemes},
        journal={Engineering Applications of Artificial Intelligence},
        volume={21},
        number={3},
        pages={353--366},
        month=apr,
        year={2008},
        doi={10.1016/j.engappai.2007.08.005}
        }



Go to the publications overview page.


This page is maintained by Bart De Schutter. Last update: December 22, 2015.