基于决策融合的非侵入式电力负荷辨识方法及应用

Non-intrusive power load disaggregation method based on decision fusion and its applications

在非侵入式负荷分解与辨识中,单独一种算法的辨识决策方法容易受算法自身的局限性以及电网对用电设备而降低辨识精度,使得不能准确获得用电设备投切情况。为此,基于多种不同算法得到的分解与辨识结果,提出了一种非侵入式电力负荷分解与辨识决策融合方法。首先,提取每个用电设备平稳状态下的负荷特征,并采用3种常用的模式识别方法进行分解与辨识。然后将得到的辨识结果,进一步采用一种加权方法对投切结果进行决策。最后采用案例分析,对决策融合方法进行了合理验证。结果证明,辨识决策方法可以有效地提高设备辨识的准确性。

In the non-intrusive load disaggregating, the result of one type of algorithms is often affected by the serious issues like voltage fluctuation and the limitations of recognition algorithms, which make it difficult to obtain high precision of load disaggregation. A decision fusion method is presented for non-intrusive load disaggregation, which is based on the results by using several types of algorithms. Firstly, in this method, the robust feature is extracted according to the information of current and power in the bus line. Then, three common recognition algorithms are used to recognize the state of device whether it works or not. The decision is then made according the results of those algorithms, thus obtaining the promising results. In the final part of the paper, a real case study is adopted to verify the decision fusion method. The results show that the proposed method provides better performance for identifying the open or close state of home loads than that of one type of the algorithm.