A Deep Learning-Based Method for Non-Intrusive Load Monitoring and Load Disaggregation of 11kV/400V Electrical Substations

An Artificial Intelligence-based method has been developed to achieve Non-Intrusive Load Monitoring (NILM) at 11kV/400V electrical substations, accomplished using the aggregate load measured at the substation and separating it by property. This allows Utility & Power Distribution companies better electricity demand forecasts and aids demand-side response. There has been extensive research of NILM at household-level using household “smart meter” data. However, substation-level disaggregation offers a cost-effective alternative and streamlined approach as only the substation requires monitoring devices rather than every house in the distribution region. A deep learning eventless NILM approach was taken, using Recurrent Neural Networks with Long Short-Term Memory and Gated Recurrent Unit layers. Disaggregation was achieved using a synthetic dataset for Low-Carbon Technology devices such as Electric vehicles (EVs), Heat Pumps (HP) and Photo-Voltaic Solar (PV) with the relationship with substation load. The accuracies for unseen data compared to the ground truth were 99.20% (EV), 99.39% (PV), 81.39% (HP) and 92.16% for other household loads. This method proposed in this paper is foundational to future substation-level NILM research, allowing for an evaluation of a scenario-based uptake in low-carbon technologies and an analysis of the required change of the power distribution network.