Voltage control method and device, terminal equipment and storage medium

The embodiment of the invention discloses a voltage control method and device, terminal equipment and a storage medium. The method comprises the following steps: establishing a power distribution network voltage control model for cooperative voltage regulation of a distributed roof photovoltaic inverter; establishing a distributed partially observable Markov decision model according to the power distribution network voltage control model; a graph convolutional neural network is embedded in a multi-agent actor-attention-commentator algorithm, and the multi-agent actor-attention-commentator algorithm is utilized to solve the Markov decision model so as to perform offline centralized training; and the online intelligent agent executes a real-time reactive power scheduling strategy in a distributed manner. State information and topological information in a power grid environment can be better captured; the optimal strategy is mined through a large number of samples in the off-line learning stage and stored in the