In order to improve the utilization rate of power resources,a non invasive strategy for monitoring the electric appliances in smart grid based on genetic algorithm is proposed. Firstly,the mixing characteristics of the appliances parameters based on load is extracted, including the transient characteristics of the transient voltage and current as well as the cumulative characteristics of the high-order statistics. Secondly, the genetic algorithm is used to select the most discriminating features and reduce the computational complexity. Finally,artificial neural network and decision tree algorithm is adopted to classify the characteristics after filtering by the genetic algorithm,distinguishing different electric appliances and classifying the information of the power consumption of of various electric appliances. The experimental results show that the genetic algorithm can significantly improve the classification performance of classifier and meet the real-time requirements.%为提高电力资源的利用率,提出了一种基于遗传算法的智能电网非侵入式电器监控策略.首先,提取出基于负荷瞬态电压电流的瞬态特征和基于高阶统计的累积特征的电器参数混合特征;然后使用遗传算法选出最具判别能力的特征,并降低计算复杂度;最后使用人工神经网络和决策树算法对遗传算法过滤后的特征进行分类,区分出不同的用电设备以分类计量各种电器的用电信息.试验结果表明,使用遗传算法后能明显提高分类器的分类性能,并可满足实时性需求.
展开▼
