Comparative Performance Study of Different Filtering Techniques with LSTM for the Prediction of Power Consumption in Smart Grid

Abstract

Smart Grid (SG) has smart instruments which can communicate using Advanced Metering Infrastructure (AMI). This will require SG a large storage space for storing the time-series data. The veracity of data increases with respect to time and becomes a challenging task for data managers. For managing large data sets, preprocessing is a fundamental part of the data management system, and often it is called Intelligent Compression (IC). IC is a method for removing redundant or repeated data from a disk or any other storage device. In this paper, various filtering techniques are used to compress and preprocess large data set of power consumption in SG. Filtering eliminates abnormal or unwanted components, signals, or features from a data set. Here, five filtering techniques have been used as Butterworth, Smoothing, Kalman, Frequency swept, and Filtfilt with Long Short-Term Memory (LSTM) to predict Power Consumption in the Smart Grid. The results are compared with different evaluation metrics for five different datasets. It is found that Filtfilt filtering techniques with LSTM provide better performance and accuracy over other filtering techniques.