Operating Rule Classification System of Water Supply Reservoir Based on Learning Classifier System

An operating rule classification system based on lesrning classifier system (LCS), which learns through credit assignment (bucket brigade algorithm, BBA) and rule discovery (genetic algorithm, GA), is established to extract water-supply reservoir operating rules. The proposed system acquires an online identification rate of 95% for training samples and an offline rate of 85% for testing samples in a case study. The performances of the rule classification system are discussed from the rationality of the obtained rules, the impact of training samples on rule extraction, and a comparison between the rule classification system and the artificial neural network (ANN). The results indicate that the LCS is feasible and effective for the system to obtain the reservoir supply operating rules.