Title :
Optimization of power and its variability with an artificial immune network algorithm
Author :
Kusiak, Andrew ; Zhang, Zijun
Author_Institution :
Dept. of Mech. & Ind. Eng., Univ. of Iowa, Iowa City, IA, USA
Abstract :
A bi-objective optimization model of power and power changes generated by a wind turbine is discussed in this paper. The model involves two objectives, power maximization and power ramp rate (PRR) minimization. A new constraint for power maximization based on physics and process control theory is introduced. Data-mining algorithms were used to identify the model of power generation from the industrial data collected at a wind farm. The models and constraints derived from the data were integrated to optimize the power itself and the power variability, expressed as the power ramp rate. Due to the nonlinearity and complexity of the optimization model, an artificial immune network algorithm was used to solve it. The optimization results, such as computed operation strategies and the corresponding outputs, are demonstrated and discussed.
Keywords :
artificial immune systems; data mining; optimisation; process control; wind turbines; artificial immune network algorithm; bi-objective optimization model; data mining algorithm; industrial data collection; operation strategy; power generation model; power optimization; power ramp rate; power ramp rate minimization; power variability; process control theory; wind turbine; Cloning; Computational modeling; Control charts; Mathematical model; Optimization; Prediction algorithms; Wind turbines; artificial immune network algorithm; bi-objective optimization; blade pitch angle; data mining; generator torque; power prediction; power ramp rate; wind turbine operation strategy;
Conference_Titel :
Power Systems Conference and Exposition (PSCE), 2011 IEEE/PES
Conference_Location :
Phoenix, AZ
Print_ISBN :
978-1-61284-789-4
Electronic_ISBN :
978-1-61284-787-0
DOI :
10.1109/PSCE.2011.5772600