Reinforcement learning tuned decentralized synergetic control of power systems

Improved synergetic excitation control for transient stability enhancement and voltage regulation of power systems

“…It can be seen that the value of w rapidly increases to 0.1 after the disturbance occurs and then decays exponentially to 0.005 at 1.3 s. As expected, these transient decays in a time equal to 3T = 0.3 s. Once this transient period is over, the second transient follows that satisfies Eq. (22). This transient lasts approximately 1s until the system reaches the equilibrium point.…”

“…The conventional synergetic theory-based PSS is designed for a single-machine infinite-bus system in [20] and a multi-machine power system to enhance its stability in [21], respectively. Moreover, a decentralized synergetic damping controller, which employs reinforcement learning to update the controller parameters online in order to improve the damping performance, is proposed for a multimachine system in [22]. In [23,24], an adaptive synergetic PSS is designed, in which a type-2 fuzzy logic system is used to approximate the unknown system dynamics.…”

“…In recent years, the synergetic control theory, which has the advantages of order reduction and is similar to sliding mode control but without its disadvantage of chattering [16,17], has been successfully applied in designing controllers for power electronics devices [18,19] and synchronous generator [20][21][22][23][24]. The conventional synergetic theory-based PSS is designed for a single-machine infinite-bus system in [20] and a multi-machine power system to enhance its stability in [21], respectively.…”

“…To solve this problem, a nonlinear variable structure excitation controller is proposed in [14] and a new load angle reference is calculated from a dynamic term given by a PI voltage regulator in [15] to maintain the voltage profile. However, it is usually difficult to fulfil the global asymptotic stability of rotor angle while achieving satisfactory voltage profile due to the high nonlinearity and complexity of the power systems.In recent years, the synergetic control theory, which has the advantages of order reduction and is similar to sliding mode control but without its disadvantage of chattering [16,17], has been successfully applied in designing controllers for power electronics devices [18,19] and synchronous generator [20][21][22][23][24]. The conventional synergetic theory-based PSS is designed for a single-machine infinite-bus system in [20] and a multi-machine power system to enhance its stability in [21], respectively.…”

Development of System Identification Fault in Gas Turbine Using Neural Network

“…Pao have reported identification and control of nonlinear systems using FLANN [13]. Chen and Billings [5] have reported nonlinear system modeling and identification using ANN structures. They have studied this problem using an MLP structure and a radial basis function network and have obtained satisfactory results with networks.…”