Reinforcement learning based backstepping control of power system oscillations

Karimi, Ali; Eftekharnejad, Sara; Feliachi, A.

doi:10.1016/j.epsr.2009.05.005

Cited by 20 publications

(12 citation statements)

References 16 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [8], RL is applied to adaptively tune the gain of the conventional PSS. The use of RL to adjust the gains of adaptive decentralized backstepping controllers has been demonstrated in [11]. Wide-area stabilizing control, exploiting real-time measurements provided by WAMS, using RL has been introduced in [7].…”

Section: Model-based Vs Model-free Solution Methodsmentioning

confidence: 99%

“…While Q-learning based approaches have been proposed in previous works about oscillations damping [7]- [11], in the present work we propose to use a model-free tree-based batch mode RL algorithm to optimize supplementary inputs to existing damping controllers [14]. This choice is motivated by the following reasons [12]- [14]:…”

Section: Model-based Vs Model-free Solution Methodsmentioning

confidence: 99%

“…Different with other works using RL for oscillations damping [7]- [11] where Q-learning or some of its variants have been suggested, we use a model-free tree-based batch mode RL algorithm [12]- [14]. Furthermore, we propose to design a multi-agent system of heterogeneous non-communicating RLbased agents through separate sequential learning of individual agents [15], [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Trajectory-Based Supplementary Damping Control for Power System Electromechanical Oscillations

Wang

Glavić

Wehenkel

2014

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

Abstract-This paper considers a trajectory-based approach to determine control signals superimposed to those of existing controllers so as to enhance the damping of electromechanical oscillations. This approach is framed as a discrete-time, multi-step optimization problem which can be solved by model-based and/or by learning-based methods. This paper proposes to apply a model-free tree-based batch mode Reinforcement Learning (RL) algorithm to perform such a supplementary damping control based only on information collected from observed trajectories of the power system. This RL-based supplementary damping control scheme is first implemented on a single generator and then several possibilities are investigated for extending it to multiple generators. Simulations are carried out on a 16-generators medium size power system model, where also possible benefits of combining this RL-based control with Model Predictive Control (MPC) are assessed.

show abstract

Section: Model-based Vs Model-free Solution Methodsmentioning

confidence: 99%

Section: Model-based Vs Model-free Solution Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Trajectory-Based Supplementary Damping Control for Power System Electromechanical Oscillations

Wang

Glavić

Wehenkel

2014

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

show abstract

“…In [6] the model of the synchronous machine used is a 7-order model and the feedback system is globally asymptotically stable in the sense of the Lyapunov stability theory. The combination of nonlinear controllers has been designed through a backstepping technique with the tuning and adaptation of their gains using reinforcement learning to power system stability enhancement in [8]. In these literatures, equations of power system of SMIB with the single input (excitation input) have been used.…”

Section: Iintroductionmentioning

confidence: 99%

Application of a new multivariable sliding mode controller for the single machine infinite bus systems

Pamsari

Bidgoli

Rajabzadeh

et al. 2011

2011 2nd Power Electronics, Drive Systems and Technologies Conference

View full text Add to dashboard Cite

This paper presents two multivariable nonlinear stabilizers, designed for a single machine infinite bus (SMIB) modeled by a standard ninth-order model. Multivariable feedback linearization (MFBL) and multivariable sliding mode control (MSMC) are proposed to regulate the output voltage and track the reference rotor angle at post-fault conditions. It is the first time that The MSMC method is designed and simulated to ensure both the stability of power system and voltage regulation despite of model uncertainties. An appropriate sliding surface has been found to achieve the desired aims. The proposed sliding mode controller has been simulated on the SMIB in the presence of a large disturbance, namely, a symmetrical three-phase short circuit fault at the terminal of the machine, and compared to the performance of the MFBL controller. Simulation results show that the MSMC technique has better performance to improve transient stability and voltage regulation in comparison with the MFBL controller.

show abstract

“…Backstepping method has also been employed with great success [24,25]. In [24], backstepping with Particle Swarm Optimization tuning technique is presented.…”

Section: Literature Surveymentioning

confidence: 99%

Decentralized Synergetic Control of Power Systems

Ademoye¹

View full text Add to dashboard Cite

Reinforcement learning based backstepping control of power system oscillations

Cited by 20 publications

References 16 publications

Trajectory-Based Supplementary Damping Control for Power System Electromechanical Oscillations

Trajectory-Based Supplementary Damping Control for Power System Electromechanical Oscillations

Application of a new multivariable sliding mode controller for the single machine infinite bus systems

Decentralized Synergetic Control of Power Systems

Contact Info

Product

Resources

About