An expert system for power generation scheduling

Abstract

A prototype of an expert system is presented which assists planners in making power generation schedules. The system takes advantage of knowledge engineering to overcome some drawbacks of conventional methods. Since the scheduling problem is too large to solve, it is divided into several subscheduling problems. To solve the subscheduling problems efficiently, the system adopts heuristic solution methods in addition to mathematical programming methods. The architecture of the system allows easy changes and additions of constraints, planning strategies, and heuristic and numerical solution methods, ensuring a flexible scheduling environment. The system effectiveness is verified using several sets of small-scale model data.<>