Time Series Analysis of Big Data for Electricity Price and Demand to Find Cyber-Attacks part 2: Decomposition Analysis
This work addresses cyber-security in energy grids, but it is incremental as it builds on prior methods without introducing new techniques.
The paper tackles cyber-attack detection in electricity systems by applying time series decomposition analysis to big data on price and demand, using additive and multiplicative methods to isolate error terms and testing them for predictable patterns to identify potential attacks.
In this paper, in following of the first part (which ADF tests using ACI evaluation) has conducted, Time Series (TSs) are analyzed using decomposition analysis. In fact, TSs are composed of four components including trend (long term behavior or progression of series), cyclic component (non-periodic fluctuation behavior which are usually long term), seasonal component (periodic fluctuations due to seasonal variations like temperature, weather condition and etc.) and error term. For our case of cyber-attack detection, in this paper, two common ways of TS decomposition are investigated. The first method is additive decomposition and the second is multiplicative method to decompose a TS into its components. After decomposition, the error term is tested using Durbin-Watson and Breusch-Godfrey test to see whether the error follows any predictable pattern, it can be concluded that there is a chance of cyber-attack to the system.