基于多目标粒子群优化算法的短期电力负荷预测法

An Algorithm for Short-term Electrical Load Forecasting Based on Multi-objective Particle Swarm Optimization

针对短期负荷预测的特点,提出一种基于多目标粒子群优化算法的短期电力负荷预测法。该算法充分利用了历史数据集的基本知识,利用多目标粒子群优化算法挑选出Pareto最优模式分类规则集,在考虑规则的分类准确性和可解释性的情况下,建立一个基于模糊规则的电力负荷模式分类系统。在仿真试验表明此分类系统具有较好的分类性能,可为电力负荷预测提供更为充分有效的历史数据,从而改善其负荷预测性能。

Aimed at the characteristics of short-term electrical load forecasting, an algorithm based on multi-objective particle swarm optimization is proposed in the paper. Considering with the accuracy and interpretation of fuzzy rules, a fuzzy rule-based classifier for electrical load pattern classification is set up, in which multi-objective particle swarm optimization is applied to choose the Pareto optimum rules. In the computation experiments, the results show that it leads to high classification performance, and it can supply more sufficient and effective historical data for load forecasting, better performance of load forecasting is gained accordingly.