A large portion of the available power generation of a photovoltaic (PV) array could be wasted due to partial shading, temperature and irradiance effects, which create current/voltage imbalance between the PV modules....A large portion of the available power generation of a photovoltaic (PV) array could be wasted due to partial shading, temperature and irradiance effects, which create current/voltage imbalance between the PV modules. Partial shading is a phenomenon which occurs when some modules in a PV array receive non-uniform irradiation due to dust, cloudy weather or shadows of nearby objects such as buildings, trees, mountains, birds etc. Maximum power point tracking (MPPT) techniques are designed in order to deal with this problem. In this research, a Markov Decision Process (MDP) based MPPT technique is proposed. MDP consists of a set of states, a set of actions in each state, state transition probabilities, reward function, and the discount factor. The PV system in terms of the MDP framework is modelled first and once the states, actions, transition probabilities, and reward function, and the discount factor are defined, the resulting MDP is solved for the optimal policy using stochastic dynamic programming. The behavior of the resulting optimal policy is analyzed and characterized, and the results are compared to existing MPPT control methods.展开更多
文摘A large portion of the available power generation of a photovoltaic (PV) array could be wasted due to partial shading, temperature and irradiance effects, which create current/voltage imbalance between the PV modules. Partial shading is a phenomenon which occurs when some modules in a PV array receive non-uniform irradiation due to dust, cloudy weather or shadows of nearby objects such as buildings, trees, mountains, birds etc. Maximum power point tracking (MPPT) techniques are designed in order to deal with this problem. In this research, a Markov Decision Process (MDP) based MPPT technique is proposed. MDP consists of a set of states, a set of actions in each state, state transition probabilities, reward function, and the discount factor. The PV system in terms of the MDP framework is modelled first and once the states, actions, transition probabilities, and reward function, and the discount factor are defined, the resulting MDP is solved for the optimal policy using stochastic dynamic programming. The behavior of the resulting optimal policy is analyzed and characterized, and the results are compared to existing MPPT control methods.
