Integrating Cybersecurity in Predictive Cost-Benefit Power Scheduling: A DeepStack Model with Dynamic Defense Mechanism

TL;DR

This paper presents a deep learning-based predictive model for wind power forecasting that integrates cybersecurity measures via a Dynamic Defense Mechanism, improving operational efficiency and system security in power grids.

Contribution

It introduces a novel deep learning architecture combined with a cybersecurity strategy to enhance wind power prediction and system security in power grid management.

Findings

Achieved 98% forecasting accuracy.

Reduced operational costs by over 3.8%.

Enhanced cybersecurity through network reactance modification.

Abstract

This paper introduces a novel, deep learning-based predictive model tailored to address wind curtailment in contemporary power systems, while enhancing cybersecurity measures through the implementation of a Dynamic Defense Mechanism (DDM). The augmented BiLSTM architecture facilitates accurate short-term predictions for wind power. In addition, a ConvGAN-driven step for stochastic scenario generation and a hierarchical, multi-stage optimization framework, which includes cases with and without Battery Energy Storage (BES), significantly minimizes operational costs. The inclusion of DDM strategically alters network reactances, thereby obfuscating the system's operational parameters to deter cyber threats. This robust solution not only integrates wind power more efficiently into power grids, leveraging BES potential to improve the economic efficiency of the system, but also boosting the cyber security of the system. Validation using the Illinois 200-bus system demonstrates the model's potential, achieving a 98% accuracy in forecasting and substantial cost reductions of over 3.8%. The results underscore the dual benefits of enhancing system reliability and security through advanced deep learning architectures and the strategic application of cybersecurity measures.