With the increasing complexity of power system structures and the increasing penetration of renewable energy, driven primarily by the need for decarbonization, power system operation and control become challenging. Changes are resulting in an enormous increase in system complexity, wherein the number of active control points in the grid is too high to be managed manually and provide an opportunity for the application of artificial intelligence technology in the power system. For power flow control, many studies have focused on using generation redispatching, load shedding, or demand side management flexibilities. This paper presents a novel reinforcement learning (RL)-based approach for the secure operation of power system via autonomous topology changes considering various constraints. The proposed agent learns from scratch to master power flow control purely from data. It can make autonomous topology changes according to current system conditions to support grid operators in making effective preventive control actions. The state-of-the-art RL algorithm—namely, dueling double deep Q-network with prioritized replay—is adopted to train effective agent for achieving the desired performance. The IEEE 14-bus system is selected to demonstrate the effectiveness and promising performance of the proposed agent controlling power network for up to a month with only nine actions affecting substation configuration.

Simultaneous optimization of controllers in power systems is a challenging research due to the inherent nonlinearity of such a system. Multi-objective optimization is a useful tool for tuning excitation controllers and minimizing oscillations that ar...

The increase in renewable energy sources (RESs) in power systems is causing significant changes in their dynamic behavior. To ensure the safe operation of these systems, it is necessary to develop new methods for preserving transient stability that follow the new system dynamics. Fast-response devices such as flexible AC transmission systems (FACTSs) can improve the dynamic response of power systems. One of the most frequently used FACTS devices is the Static Var Compensator (SVC), which can improve a system’s transient stability with a proper control strategy. This paper presents a reactive power control strategy for an SVC using synchronized voltage phasor measurements and particle swarm optimization (PSO) to improve the transient stability of a multimachine power system. The PSO algorithm is based on the sensitivity analysis of bus voltage amplitudes and angles to the reactive power of the SVC. It determines the SVC reactive power required for damping active power oscillations of synchronous generators in fault conditions. The sensitivity coefficients can be determined in advance for the characteristic switching conditions of the influential part of the transmission network, and with the application of the PSO algorithm, enable quick and efficient finding of a satisfactory solution. This relatively simple and fast algorithm can be applied in real time. The proposed control strategy is tested on the IEEE 14-bus system using DIgSILENT PowerFactory. The simulation results show that an SVC with the proposed control strategy effectively minimizes the rotor angle oscillations of generators after large disturbances.

The integration of renewable energy sources into the power grid presents significant challenges and opportunities for grid planners. Renewable energy sources such as wind and solar are variable and intermittent, leading to fluctuations in power outpu...

State estimation is an important part of control functions and power system management. Correct insight and interpretation of the network topology are a crucial step of any state estimator. In order to improve state estimators accuracy...