This research paper investigates the vulnerability of industrial demand response programs to adversarial attacks that manipulate electricity price forecasts. The study designs specific attacks to degrade the accuracy of price forecasting models and analyzes their impact on energy-intensive production scheduling. Findings indicate that while adversarial attacks can reduce demand response profits, the programs retain a significant portion of their financial benefits when perturbations are subtle and difficult to detect. The effectiveness of these attacks is shown to depend not only on the magnitude of the data manipulation but also on its orientation relative to the sensitivities of the scheduling optimization models. AI
IMPACT Highlights potential security vulnerabilities in energy systems that rely on AI for forecasting and optimization.
RANK_REASON The cluster contains a single academic paper discussing a novel research finding. [lever_c_demoted from research: ic=1 ai=1.0]
- Adversarial Data Modifications
- arXiv
- Cyber Attacks
- Demand Response
- electricity grid
- electricity price forecasting models
- energy-intensive production processes
- false data injection attacks
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
