Exploiting Vulnerabilities of Load Forecasting Through Adversarial Attacks

2019/04/13 by Yize Chen, Chen, Yize, Yushi Tan +3 · 2 citations
Engineering · #FOS: Electrical engineering #FOS: Mathematics #Optimization and Control (math.OC) #Power System Optimization and Stability #Power System Reliability and Maintenance #Smart Grid Security and Resilience #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1904.06606

openalex publication_date 2019/04/13 · openalex created_date 2019/04/25 · openalex updated_date 2026/07/28

Abstract

Load forecasting plays a critical role in the operation and planning of power systems. By using input features such as historical loads and weather forecasts, system operators and utilities build forecast models to guide decision making in commitment and dispatch. As the forecasting techniques becomes more sophisticated, however, they also become more vulnerable to cybersecurity threats. In this paper, we study the vulnerability of a class of load forecasting algorithms and analyze the potential impact on the power system operations, such as load shedding and increased dispatch costs. Specifically, we propose data injection attack algorithms that require minimal assumptions on the ability of the adversary. The attacker does not need to have knowledge about the load forecasting model or the underlying power system. Surprisingly, our results indicate that standard load forecasting algorithms are quite vulnerable to the designed black-box attacks. By only injecting malicious data in temperature from online weather forecast APIs, an attacker could manipulate load forecasts in arbitrary directions and cause significant and targeted damages to system operations.

Citations

• Cyber–Physical System Security for the Electric Power Grid
• Short-term load forecasting
• 25 years of time series forecasting
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Blocking Transferability of Adversarial Examples in Black-Box Learning Systems

Cited by

• Cyber Resilience Assessment of Unbalanced Distribution System Restoration under Sparse Load Forecasting Attacks
• Adversarial Attacks on Deep Learning-Based False Data Injection Detection in Differential Relays

Related

• Vulnerabilities of Power System Operations to Load Forecasting Data Injection Attacks
• Exploring Physical-Based Constraints in Short-Term Load Forecasting: A Defense Mechanism Against Cyberattack
• Availability Adversarial Attack and Countermeasures for Deep Learning-based Load Forecasting
• Enabling Cyberattack-Resilient Load Forecasting through Adversarial Machine Learning
• Cyber Resilience Assessment of Unbalanced Distribution System Restoration under Sparse Load Forecasting Attacks