Effects of multi-objective genetic rule selection on short-term load forecasting for anomalous days

One advantage of multi-objective genetic optimization algorithms over classical approaches is that many non-dominated solutions can be simultaneously obtained by their single run. In this paper, we proposed a fuzzy rule-based classifier for electrical load pattern classification by using multi-objective genetic algorithm and fuzzy association rule mining. Multi-objective genetic algorithm is used to automatically select the rules with better classification accuracy and interpretability, and the key concepts of fuzzy association rule mining are the bases of heuristic rule selection for improving the performance of genetic algorithm searching. Through computation experiments on a real power system, it is shown that the generated fuzzy rule-based classifier leads to high classification performance, and can supply more sufficient historical data for load forecasting of anomalous days, better performance of load forecasting is gained accordingly