Guarding the Grid: Enhancing Resilience in Automated Residential Demand Response Against False Data Injection Attacks

TL;DR

This paper proposes a comprehensive framework that enhances the resilience of residential demand response systems against false data injection attacks by integrating optimization, anomaly detection, and mitigation strategies, validated with real-world data.

Contribution

It introduces a novel integrated framework combining DR optimization, anomaly detection, and attack mitigation for resilient residential demand response systems.

Findings

Framework effectively detects false data injections

Resilient scheduling maintains system performance under attack

Validated with real-world data demonstrating robustness

Abstract

Utility companies are increasingly leveraging residential demand flexibility and the proliferation of smart/IoT devices to enhance the effectiveness of residential demand response (DR) programs through automated device scheduling. However, the adoption of distributed architectures in these systems exposes them to the risk of false data injection attacks (FDIAs), where adversaries can manipulate decision-making processes by injecting false data. Given the limited control utility companies have over these distributed systems and data, the need for reliable implementations to enhance the resilience of residential DR schemes against FDIAs is paramount. In this work, we present a comprehensive framework that combines DR optimisation, anomaly detection, and strategies for mitigating the impacts of attacks to create a resilient and automated device scheduling system. To validate the robustness of our framework against FDIAs, we performed an evaluation using real-world data sets, highlighting its effectiveness in securing residential DR systems.