Exploring Physical-Based Constraints in Short-Term Load Forecasting: A Defense Mechanism Against Cyberattack

TL;DR

This paper investigates physical system constraints as a defense mechanism against cyberattacks in short-term load forecasting, analyzing regional load data to identify anomalies caused by malicious data injections.

Contribution

It introduces a method to model physical constraints in load forecasting to detect anomalies and potential cyberattacks, highlighting the limitations of static similarity measures.

Findings

Variation in similarity measures indicates potential malicious actions.

Static measures are insufficient for consistent anomaly detection across scenarios.

Physical constraints can help identify anomalies in load forecasting data.

Abstract

Short-term load forecasting is an essential task that supports utilities to schedule generating sufficient power for balancing supply and demand, and can become an attractive target for cyber attacks. It has been shown that the power system state estimation is vulnerable to false data injection attacks. Similarly, false data injection on input variables can result in large forecast errors. The load forecasting system should have a protective mechanism to mitigate such attacks. One approach is to model physical system constraints that would identify anomalies. This study investigates possible constraints associated with a load forecasting application. Looking at regional forecasted loads, we analyze the relation between each zone through similarity measures used in time series in order to identify constraints. Comprehensive results for historical ERCOT load data indicate variation in the measures recognizing the existence of malicious action. Still, these static measures can not be considered an efficient index across different scenarios.