Kernel Function Selection for FISVDD Applied to Outliers Detection Application for Energy Time Series Datasets

Abstract

Forecasting energy consumption is crucial for maintaining stability in the energy supply-demand balance. This process requires accurate data, necessitating deep preprocessing steps, with outlier detection being a pivotal task. While most existing methods are tailored for batch learning, smart grid data collection operates continuously, demanding online algorithms for effective data cleaning. This paper proposes an analytical study emphasizing the significance of selecting an appropriate kernel function for data description methods and its impact on forecasting efficiency. The Fast Incremental Support Vector Data Description (FISVDD) algorithm is chosen as a kernel-based approach for outlier detection in time series datasets. The evaluation involves different kernel functions on two datasets: Electrical Grid Stability Simulated Data and Individual Household Electric Power Consumption Dataset. Criteria such as the objective function and data distribution are considered to determine the most suitable kernel function. FISVDD's performance with the right kernel function is compared with other outlier detection methods, and the results are fed into a Gated Recurrent Unit model to visualize the impact on forecasting. Mean Squared Error evaluation reveals that FISVDD with the appropriate kernel function yields the best results, underscoring the strength of data description methods with the appropriate kernel function.