The paper presents a network partitioning strategy for the optimal voltage control of Active Distribution Networks (ADNs) actuated by means of a limited number of Distributed Energy Storage Systems (DESSs). The proposed partitioning uses a linear programming approach by means of the known concept of voltage sensitivities. Then, two decentralized optimal control algorithms are proposed relying, respectively, on the Thévenin equivalents and a recursive approach. These algorithms are developed using the Multi- Agent System (MAS) concept. With respect to a centralized control algorithm, the aim of the network clustering is to reduce the number of exchanged messages among the clusters when one of the two proposed decentralized control algorithms is adopted. The effectiveness of the two proposed controls is assessed with respect to the performances of the equivalent centralized control using numerical examples composed by the IEEE 13 and IEEE 123 buses distribution test feeders adapted to include stochastic generation and DESSs.