Bayesian adversarial multi-node bandit for optimal smart grid protection against cyber attacks
This addresses cybersecurity for smart grids, a critical issue in modern power systems, but appears incremental as it adapts existing bandit methods to a specific domain.
The paper tackles the problem of optimal smart grid protection against cyber attacks by introducing a non-stationary adversarial cost model and a Bayesian multi-node bandit framework, resulting in a Thompson-Hedge algorithm with proven superior performance in terms of regret convergence rate.
The cybersecurity of smart grids has become one of key problems in developing reliable modern power and energy systems. This paper introduces a non-stationary adversarial cost with a variation constraint for smart grids and enables us to investigate the problem of optimal smart grid protection against cyber attacks in a relatively practical scenario. In particular, a Bayesian multi-node bandit (MNB) model with adversarial costs is constructed and a new regret function is defined for this model. An algorithm called Thompson-Hedge algorithm is presented to solve the problem and the superior performance of the proposed algorithm is proven in terms of the convergence rate of the regret function. The applicability of the algorithm to real smart grid scenarios is verified and the performance of the algorithm is also demonstrated by numerical examples.