计算机辅助诊断算法在用电异常识别中的应用

Application of Computer-aided Diagnosis Algorithms in Abnormal Electricity Consumption Identification

摘要:

电力系统用电异常识别是保障电网安全稳定运行的关键环节。计算机辅助诊断算法结合用电负荷曲线特征、时间序列统计特征与频域特征参数,构建智能诊断模型,可实现异常模式自动识别,提高了用电管理的智能化水平。实验表明,深度神经网络与支持向量机、随机森林与集成学习等算法在异常检测中呈现出不同的性能特点,其中集成学习算法准确率达到95.8%,显著优于单一算法识别效果。

Abstract:

Identifying abnormal electricity consumption in power systems is a critical component of ensuring the safe and stable operation of the power grid. By combining computer-aided diagnostic algorithms with load curve characteristics, time-series statistical features, and frequency-domain parameters, an intelligent diagnostic model can be constructed to automatically identify abnormal patterns, thereby enhancing the intelligence of electricity consumption management. Experiments demonstrate that algorithms such as deep neural networks, support vector machines, random forests, and ensemble learning exhibit distinct performance characteristics in anomaly detection. Among these, ensemble learning algorithms achieved an accuracy rate of 95.8%, significantly outperforming the recognition results of individual algorithms.