``A Self-Scheduling Model Using Agent-Base,
Peer-to-Peer Negotiation and Open Common Schema''
C. Hsu and C. D. Carothers
In Proceedings of the 17th International Conference on
Production Research (ICPR '03), August 2003.
ABSTRACT
Research has shown that market-style self-scheduling is a promising
approach to achieving real-time online resources allocation. However,
the field still lacks sufficient results in areas such as control,
inter-operation of heterogeneous data semantics, and qualitative
performance measurement, to satisfy large scale distributed
operations, especially today's information enterprises.
We propose a new agent-based, peer-to-peer publish and subscribe model
for enterprise resource allocation under the above conditions. We use
the proven industrial exchange technology to develop a full-fledged
artificial market to self-schedule information tasks (resources
offerings and requests) across a potentially extended enterprise, with
a comprehensive performance-feedback-re-allocation mechanism. New
results also include an Agent-Base for creating and managing large
number of custom agents online, a peer-to-peer negotiation method, and
an open common schema design, to enable the model. It also provides an
implementation scheme for developing the basic architecture, the
pricing model, and the data interchange required of the artificial
market.