Research Article
Fault Diagnosis of Data-Driven Photovoltaic Power Generation System Based on Deep Reinforcement Learning
(1) | All parameters of the Q network are initialized randomly with the corresponding value Q | (2) | Clear set D of experience playback | (3) | for episode = 1, M do | (4) | Initialization status , then get the eigenvector | (5) | for t = 1, T do | (6) | Use ε−greedy selection action | (7) | Execute action to get return value and next state | (8) | Sets and gets | (9) | Stores back to experience pool | (10) | Randomly collect a sample from the experience pool | (11) | Update: | (12) | Perform gradient descent steps: | (13) | End |
|