Title :
Multi-agent system based intelligent distributed control system for power plants
Author :
Lee, Kwang Y. ; Head, Jason D. ; Gomes, Jason R. ; Williams, Craig S.
Author_Institution :
Dept. of Electr. & Comput. Eng., Baylor Univ., Waco, TX, USA
Abstract :
This paper presents an approach for intelligent distributed control of power plants using the concept of multi-agent systems (MAS). Solving the problem of optimally controlling a power plant based on multiple objectives, such as minimizing pollution, maximizing equipment life, etc., and coordinating each of the involved tasks that must be performed in distributed environments is a challenge, which involves many individual computationally intensive tasks. These tasks include calculating feasible control valve operating ranges based on unit load demand, multi-objective optimization, training neural networks, monitoring and managing real-time input/output data, and task delegation, among others. Since each of these tasks requires such computational overhead and these systems need to be coordinated among distributed environments, it is necessary to divide them up into multiple agents. The presented method of design of the multi-agent system is a continuation of research to develop a multi-agent system to implement a technique for computing optimal multi-objective power plant controls.
Keywords :
distributed control; intelligent control; multi-agent systems; optimisation; power generation control; power plants; MAS; computing optimal multi-objective power plant controls; multiagent system based intelligent distributed control system; multiobjective optimization; task delegation; training neural networks; Control systems; Feedforward neural networks; Mathematical model; Message systems; Multiagent systems; Optimization; Power generation; Power plant control; automatic gain tuning; distributed control; intelligent control; model predictive control; multi-agent systems; multi-objective optimization; parallel algorithms; real-time control; reference governor;
Conference_Titel :
Power and Energy Society General Meeting, 2011 IEEE
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4577-1000-1
Electronic_ISBN :
1944-9925
DOI :
10.1109/PES.2011.6039500