In this paper we show the application of multi-agent modeling and simulation with distributed reinforcement learning to one of the major problems in power system operations, i.e. voltage control. In this research some agents in the power network work together to provide a desirable voltage profile, using a combination of multi-agent system (MAS) technology and some of the reinforcement learning approaches. In this schema, individual agents who are assigned to voltage controller devices in the power system learn from their experiences to control the system voltage, and also cooperate and communicate with each other to satisfy the whole team goals. A detailed evaluation of methods for controlling voltage in power systems, including multi-agent coordination and distributed reinforcement learning (DRL), demonstrates that this framework yields effective plans, good agent coordination, and successful implementation. In the proposed approach, agent development and communication simulation have been carried out in the Java Agent Development (JADE) framework.

In this paper, a new voltage coordination model based on agent technology is proposed. In this work, communication simulation of peer-to-peer device coordination has been developed based on the Java Agent DEvelopment (JADE) platform which provides a FIPA-compliant agent platform and a package to development of multi-agent systems. In this paper each STATCOM has been modeled as an intelligent agent and join to a container to form a multi agent system for voltage coordination. The results of the proposed method in the IEEE 39-Bus Test System show that using coordinated voltage control of STATCOMs, lead to better elimination of voltage violations in power system.

No abstract

No abstract

No abstract