Probability, stochastic processes, and queueing theory: the mathematics of computer performance modeling
An architecture for Real-Time Reasoning and System Control
IEEE Expert: Intelligent Systems and Their Applications
The Belief-Desire-Intention Model of Agency
ATAL '98 Proceedings of the 5th International Workshop on Intelligent Agents V, Agent Theories, Architectures, and Languages
A Flexible BDI Architecture Supporting Extensibility
IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Are Parallel BDI Agents Really Better?
Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Hi-index | 0.01 |
A performance mark of a BDI agent is how fast it can react to and process incoming event sequences. To the best of our knowledge, few papers have been published about predicting an agent's average response time for an event sequence before the agent is applied in a real project. In this paper, we first introduce a simulation method. In simulation, a sequence of events with attributes, such as priorities and amounts of time needed to process the events, is input to the agent at designed insertion time. The events are processed by the agent according to the attributes. The statistics of processing time can be recorded. Then we make some theoretical analysis to estimate the average response time when an agent processes a sequence of events based on probability and queueing theory. Comparison experiments show that the results from analysis are quite matching with the results from simulation experiments. The analysis suggests a way to quickly estimate the performance of an agent if the attributes of the incoming event sequence are known in advance. The predicted average response time can help construct efficient BDI agents for various environments.