Adaptive optimal control of a grid-independent photovoltaic system

被引:33
作者
Henze, GP
Dodier, RH
机构
[1] Univ Nebraska, Peter Kiewit Inst, Omaha, NE 68182 USA
[2] Univ Colorado, Boulder, CO 80309 USA
来源
JOURNAL OF SOLAR ENERGY ENGINEERING-TRANSACTIONS OF THE ASME | 2003年 / 125卷 / 01期
关键词
D O I
10.1115/1.1532005
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
This paper investigates adaptive optimal control of a grid-independent photovoltaic system consisting of a collector storage, and a load. The control algorithm is based on Q-Learning, a model-free reinforcement learning algorithm, which optimizes control performance through exploration. Q-Learning is used in a simulation study to find a policy which performs better than a conventional control strategy with respect to a cost function which places more weight on meeting a critical base load than on those non-critical loads exceeding the base load.
引用
收藏
页码:34 / 42
页数:9
相关论文
共 8 条
[1]  
Bellman R., 1957, DYNAMIC PROGRAMMING
[2]  
Bertsekas D. P., 1996, Neuro Dynamic Programming, V1st
[3]  
CARDINALE J, 1994, MODEL RMSE PHOTOVOLT
[4]  
CYBENKO G, 1995, MATH ARTIFICIAL NEUR
[5]   A STOCHASTIC REINFORCEMENT LEARNING ALGORITHM FOR LEARNING REAL-VALUED FUNCTIONS [J].
GULLAPALLI, V .
NEURAL NETWORKS, 1990, 3 (06) :671-692
[6]  
SHEPPARD M, 1993, 9 INT C MATH COMP MO
[7]  
Sutton R. S., 1998, Reinforcement Learning: An Introduction, V22447
[8]  
WATKINS CJCH, 1992, MACH LEARN, V8, P279, DOI 10.1007/BF00992698