RNN-Assisted Feature-Extraction VMD for Load Classification in Cloud Computing Platform

Abstract

Cloud computing can improve the calculation and data storage ability for the control center in the power system. A new framework of the cloud-based control center is proposed in this paper. This cloud computing system can collect the load data from smart meters of the grid and classify demand-side management (DSM) loads that meet the specific requirements. The selected loads belong to the off-peak period (from 21:00 to 07:00 next day) and can contribute to shifting the night peak load. A feature extraction combined with Variational Mode Decomposition (FE-VMD) of the loads which can be trained in recurrent neural network (RNN) is proposed in this paper. Using the feature value to replace the actual load data, input data can be significantly reduced which is suitable for a vast amount of load in the power system. A case study of real load data from 200,000 customers has been classified with this method, and the accuracy is compared with the other methods. From simulation with MATLAB, it can be seen that the FE-VMD combined with the RNN method provides the best result of 89.8% recognition accuracy among these methods.