Chapter 13 - Stability assessment using Bayesian network control for inverters in smart grid

Abstract

The transmission capacity of long-distance transmission lines has continued to increase, and the integration of a large amount of distributed power generation systems into the power system reduces the stability of the power system. The stability assessment of the power system and the study of control measures to improve its stability are significant. In this chapter, an AdaBoost-based tree augmented naive Bayesian (ATAN) classifier is adopted in the power system transient stability assessment. When the power system is unstable, the grid-connected energy storage system can improve the stability of the power system when the appropriate control method is used. The inverter serves as the interface between the energy storage system in the smart grid and the power system, the performance of inverter control determines the degree to which the energy storage grid-connected system improves the stability of the power system. The traditional linear control method for the inverter requires complex processes including decoupling and control parameter tuning and relies on a pulse width modulation module. A data-driven method using the dynamic Bayesian network-based model predictive control (DBN-MPC) is proposed, which takes advantage of the predictive ability of the dynamic Bayesian networks to implement the model predictive control strategy. Using the proposed DBN-MPC method, the predictive model implements parameter learning online, providing more accurate prediction signals for further optimization and feedback correction. In addition, the control law of the proposed controller can update over time, which enables the grid-connected inverter system to achieve optimal control, which makes the energy storage grid-connected system based on the DBN-MPC control method more effective for improving the stability of the power system.