基于Tukey围栏的非侵入式负荷监测事件检测
Event Detection for Non-intrusive Load Monitoring using Tukey s Fences
AI总结：
本文提出基于Tukey围栏的事件检测器TFED，结合快速傅里叶变换检测聚合电流信号变化，实现99%的检测准确率，优于倒谱和χ²拟合优度统计方法。
摘要：
非侵入式负荷监测（NILM）技术的主要目标是监测和跟踪住宅建筑内的电力消耗。这是通过从聚合能量测量中近似每个独立电器的消耗来实现的。基于事件的NILM解决方案通常比其他方法更准确。本文提出了一种新颖的事件检测算法，称为基于Tukey围栏的事件检测器（TFED）。该算法使用快速傅里叶变换结合Tukey围栏规则来检测聚合电流信号中的变化。TFED的主要优势在于其卓越的能力，能够准确定位事件的开始时间，这一点已通过仿真得到证明。我们的研究结果表明，所提出的算法拥有令人印象深刻的99%准确率，超越了文献中其他近期工作的准确率，例如基于倒谱和$χ^2$拟合优度统计的分析，这些方法仅达到98%的准确率。
英文摘要：
The primary objective of non-intrusive load monitoring (NILM) techniques is to monitor and track power consumption within residential buildings. This is achieved by approximating the consumption of each individual appliance from the aggregate energy measurements. Event-based NILM solutions are generally more accurate than other methods. Our paper introduces a novel event detection algorithm called Tukey's Fences-based event detector (TFED). This algorithm uses the fast Fourier transform in conjunction with the Tukey fences rule to detect variations in the aggregated current signal. The primary benefit of TFED is its superior ability to accurately pinpoint the start times of events, as demonstrated through simulations. Our findings reveal that the proposed algorithm boasts an impressive 99% accuracy rate, surpassing the accuracy of other recent works in the literature such as the Cepstrum and $χ^2$ GOF statistic-based analyses, which only achieved 98% accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
