Agent-based restoration approach for reliability with load balancing on smart grids

Reliability and load balancing are essential techniques for smart grids that enable reliable electricity delivery to end customers. A smart grid needs configuration and restoration approaches that can react to blackouts in an economical way. However, the present approaches primarily focus on maximization of the restoration efficiency and the effect of function, while the trade-off between reliability and load balancing is usually ignored. In this paper, an agent-based approach is proposed to optimize the reliability of a system in the restoration process, considering load balancing as a constraint. A modified restoration strategy based on reinforcement learning, namely, the wolf pack algorithm (WPA), is proposed under the multi-agent framework and communication architecture. First, considering the constraints of the grid network and the dynamic load of the system, several types of agents are defined and abstracted to imitate physical entities. In addition, integrated with the WPA, the multi-agent system (MAS)is subsequently utilized to optimize the reliability of the system while considering the trade-off of load balancing. To verify the practicality of the approach, two cases based on a complex radial power network developed in Java are proposed. Ultimately, the sensitivity, effectiveness and expandability of the approach are analyzed.