Spatiotemporal Optimization Through Gaussian Process-Based Model Predictive Control: A Case Study in Airborne Wind Energy
Spatiotemporal Optimization Through Gaussian Process-Based Model Predictive Control: A Case Study in Airborne Wind Energy
复制标题
通过基于高斯过程的模型预测控制进行时空优化：机载风能案例研究
DOI：
--
复制
发表时间：
2019
影响因子：
4.8
通讯作者：
C. Vermillion
中科院分区：
文献类型：
--
作者：
Shamir Bin;A. Bafandeh;Ali Baheri;C. Vermillion
提出了一种基于模型预测控制(MPC)的时空优化策略，并将其应用于某型机载风能(AWE)系统，特别是浮空式机载涡轮机的高度优化问题。AWE系统的高度优化是一个具有挑战性的问题，在这种情况下，风速随时间和高度变化，只能在AWE系统运行的高度瞬时观测，并决定系统产生的净功率。建议的MPC策略避免了用于表征风速的计算代价高昂的马尔可夫过程模型，并且其结构使得对瞬时功率最大化的需求(称为开发)与维护风速与高度的准确地图(称为探索)的需求相平衡。MPC策略通过高斯过程回归框架进行校准。实际风速与海拔的关系数据已经被用来验证该策略。
This brief presents a model predictive control (MPC)-based spatiotemporal optimization strategy that is applied to the problem of optimizing the altitude of a type of airborne wind energy (AWE) system, specifically a buoyant airborne turbine. Altitude optimization for AWE systems represents a challenging problem under which the wind speed varies with both time and altitude, is only instantaneously observable at the altitude where the AWE system is operating, and dictates the net power produced by the system. The proposed MPC strategy avoids the need for a computationally expensive Markov process model for characterizing the wind speed and is structured in a way that the need for instantaneous power maximization (termed exploitation) is balanced with the need to maintain an accurate map of wind speed versus altitude (termed exploration). The MPC strategy is calibrated through a Gaussian process regression framework. Real wind speed versus altitude data have been used to validate the strategy.