POWER FLOW INTELLIGENT ADJUSTMENT METHOD BASED ON Q-LEARNING ALGORITHM

摘要

A power flow intelligent adjustment method based on a Q-Learning algorithm, comprising: step 1. converting a variable, an action, and a target in a power grid into a state, an action, and a reward in an algorithm, respectively; step 2. selecting an action from an action space, giving an immediate return according to a power flow calculation result, and correcting the next state; step 3. observing the next exploration action according to a strategy in the Q-Learning; step 4. updating a Q value of a corresponding position in a Q value table according to the obtained reward; step 5. if a final state is not reached, returning to step 2, and if the final state is reached, incrementing the number of iterations by one; step 6. if the number of iterations does not reach a set value K, i.e., Episode