家用负荷辨识准确性受数据采样速率制约显著,过高的采样速率虽然能够解决数据问题但也带来成本提高、系统设计复杂等问题。基于此,本文提出了一种仅依赖常规采样速率有功功率量测的非侵入式负荷辨识方法,该方法对传统的降噪自动编码器算法滑动窗的重叠部分计算进行了改进,使用中值滤波器对重叠窗的数据结果进行处理,能够较好的克服辨识结果偏高的问题。同过在REDD(Reference Energy Disaggregation Dataset)和TraceBase两个家庭用电数据集开展测试,证明了所提方法在辨识设备功率和判断设备所处状态两个方面都具有较好的效果,且各项指标均好于经典的基于因子隐马尔科夫模型(FHMM)算法。另外所提算法的通用性较好,能够对不同型号、品牌的同种设备进行有效辨识,具有较好的实用价值。
英文摘要:
In order to solve the problem of high data requirement for household appliance load identification, this paper proposes a non-invasive load identification method which only relies on the conventional sampling rate active power measurement. This method is based on the denoising automatic encoder algorithm, and can accurately identify various types of loads. The test results of REDD and TraceBase datassets show that the proposed method has good results in identifying the power of the equipment and judging the state of the equipment, and its indexes are better than the classical factor Hidden Markov model (FHMM) algorithm. In addition, the proposed algorithm has good versatility and can effectively identify the same equipment of different models and brands.
