Predicting Automated Negotiation Bandwidth Usage at the Edge of the Network

Abstract Automated negotiation can be an efficient method for resolving conflict and redistributing resources in a coalition setting. Automated negotiation has already seen increased usage in fields such as e-commerce and power distribution in smart girds. However, significant barriers to more widespread adoption remain. For example, consumption of bandwidth, which can be problematic in real environments, especially at the edge of a network. The ultimate outcome of this research is to develop a negotiation agent that can leverage exchanging constraints during a negotiation to reduce the number of messages needed to be exchanged before the negotiation terminates (either successfully or unsuccessfully). In this paper we take a probabalistic approach and show that the probability that a proposal is acceptable to both of the agents can predict the number of messages necessary for the negotiation. This can provide valuable insight into the difficulty of negotiations and a measure for effectiveness that is under-explored in the current literature.
  • Daniel Vente (Cardiff)
  • Angelika Kimmig (Cardiff)
  • Alun Preece (Cardiff)
  • Federico Cerutti (Cardiff)
Date Sep-2019
Venue Annual Fall Meeting of the DAIS ITA, 2019