Semi-Supervised Disaggregation of Load Profiles at Transmission Buses with Significant Behind-the-Meter Solar Generations
Semi-Supervised Disaggregation of Load Profiles at Transmission Buses with Significant Behind-the-Meter Solar Generations
复制标题
具有大量表后太阳能发电的输电总线负载曲线的半监督分解
DOI：
10.1109/ecce50734.2022.9948155
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Liang Du
中科院分区：
文献类型：
--
作者：
Zhenyu Zhao;Daniel Moscovitz;Shengyi Wang;Xiaoyuan Fan;Liang Du
区域输电组织（RTO）迫切需要有效地提取输电节点的日负荷分布，这仍然是现有技术范式中的一个空白。本摘要提出了一个明确而有效的线性估计器，以数据驱动的方式分解具有重要的表后（BTM）太阳能发电的总线上的计量负载曲线。所提出的估计是基于公用事业分区负荷配置文件和代理太阳辐照度配置文件，这在现实中是在每个传输总线的聚合波形，相当于混合的总负荷配置文件减去实际的BTM太阳能发电。为了克服缺乏“地面实况”的技术挑战并验证监督学习算法的性能，我们提出了具有参数调整的半监督机制，并利用BTM太阳能峰值行为中零交叉点的独特特性。
It is of imperative interests for regional transmission organizations (RTOs) to effectively extract daily load profiles at transmission buses, which remains a gap in existing technology paradigm. This digest proposes an explicit yet efficient linear estimator, to disaggregate metered load profiles at buses with significant behind-the-meter (BTM) solar generations in a data-driven manner. The proposed estimator is based on utility zonal load profiles and proxy solar irradiance profiles, which in reality is the aggregated waveform at each transmission bus and equivalent to the mix of summed load profiles minus actual BTM solar generation. To overcome technical challenges in the lack of “ground truth” and validate the performance of supervised learning algorithms, we propose semi-supervised mechanisms with parameter tuning, and leverage the unique characteristics of zero-crossing points in BTM solar peaking behaviors.
通过不确定性建模对变电站进行贝叶斯能量分解
影响因子：
6.6
作者：
Yi, Ming;Wang, Meng
通讯作者：
Wang, Meng