An expert-system approach to the unit commitment problem

An expert system plays a key role in the better conservation and management of electrical energy in a power station having a number of units that have to be committed for a given load. This paper presents a hybrid expert system dynamic programming approach to the unit commitment problem. Here, the scheduling output of the usual dynamic programming is enhanced by supplementing it with the rule based expert system. The proposed system limits the number of constraints and also checks the possible constraint violations in the generated schedule. The expert system communicates with the operator in a friendly manner, and hence, the various program parameters can be adjusted to have a optimal, operationally acceptable schedule.