Optimizing power flows using harmony search with machine learning

摘要

Systems and methods for optimizing power flows using a harmony search, including decoupling phases in a multi-phase power generation system into individual phase agents in a multi-phase power flow model for separately controlling at least one of phase variables or parameters. One or more harmony segments from harmony memory are ranked and selected based on a utility value determined for each of the decoupled phases. A harmony search with gradient descent learning is performed to move the selected harmony segments to a better local neighborhood. A new utility value for each of the selected segments is determined based on historical performance, and the harmony memory is iteratively updated if one or more of the new utility values are higher than a utility value of a worst harmony segment stored in the harmony memory.