Dynamic Security Margin Estimation with Preventive Control Using Artificial Neural Networks

On-line dynamic security assessment (DSA) is challenging using conventional techniques because most DSA approaches use detailed mathematical models of the system that are computationally intensive and time-consuming. In this paper, a method based on Artificial Neural Networks (ANN) is developed to estimate the security margin. The security margin for a given power system is obtained by applying standard operations criteria for transient response to off-line time simulations. These simulations then form a database that can be used to train a pattern matching approach, such as, ANNs. Feature selection using statistical approaches is applied to overcome the dimensional problem of applying the ANN to larger systems. This method provides a fast and accurate tool to evaluate dynamic security. If the estimated security margin is less than requirements, then preventive control actions that guarantee dynamic security of the power system are needed. This is achieved by optimal rescheduling of the generation with given constraints on the network power flows and system security margins as estimated by the ANN. This requires a modified Optimal Power Flow (OPF) solution that allows the trained ANN to act as a security objective function. Numerical results on the New England 39-bus system validate the methodology.