Optimal scheduling for wind farms power generation based on partial information

This paper aims to solve the coupled problem of wind farms modeling and wind power generation optimal scheduling. The salient features of the proposed method are as follows: First, the multi-agent model of wind farms power generation is obtained, which consider the influence among wind turbines. Second, the task is formulated as an optimization scheduling problem in terms of wind power generation. Third, the controller is designed by considering the partial system information, and solved based on the Forward & Backward Stochastic Different Equations (FBSDE) and adjoint equations. Numerical simulations are adopted to verify the proposed optimization method for partial information cases.

[1]  Chongqing Kang,et al.  Modeling Conditional Forecast Error for Wind Power in Generation Scheduling , 2014, IEEE Transactions on Power Systems.

[2]  Xun Yu Zhou,et al.  Relationship Between Backward Stochastic Differential Equations and Stochastic Controls: A Linear-Quadratic Approach , 2000, SIAM J. Control. Optim..

[3]  Wang Kunpeng,et al.  Wind Farm Power Optimum Dispatching Strategy for Variable-Speed Wind Turbine Based on Rotating Energy Storage , 2013 .

[4]  H. Siahkali,et al.  Fuzzy based generation scheduling of power system with large scale wind farms , 2009, 2009 IEEE Bucharest PowerTech.

[5]  Liu Chu.  An Annual Wind Power Planning Method Based on Time Sequential Simulations , 2014 .

[6]  T. J. Overbye,et al.  Optimal storage scheduling for minimizing schedule deviations considering variability of generated wind power , 2011, 2011 IEEE/PES Power Systems Conference and Exposition.

[7]  Chen Qijuan.  Wind Power Dispatch Model Based on Constraints , 2010 .

[8]  Sajad Tabatabaei.  A new stochastic framework for optimal generation scheduling considering wind power sources , 2014, J. Intell. Fuzzy Syst..

[9]  Enrique Kremers,et al.  An agent-based multi-scale wind generation model , 2009 .

[10]  Thomas Bak,et al.  Multi-Agent Model for Fatigue Control in Large Offshore Wind Farm , 2008, 2008 International Conference on Computational Intelligence and Security.

[11]  Takashi Hiyama,et al.  Reinforcement Learning based multi-agent LFC design concerning the integration of wind farms , 2010, 2010 IEEE International Conference on Control Applications.