A multi-agent and big data self-healing scheme for active distribution network with inverter-based distributed generators

In this paper, a self-healing scheme in active distribution network (ADN) with inverter-based distributed generators (IBDGs) based on multi-agent and big data is proposed. The multi-agent system (MAS), big data storage and mining technology are used to accomplish fault discrimination, fault localization, isolation and service restoration. In this paper, the use of a new type of the relay which takes advantage of the enhanced processing techniques, which are recently becoming available for power networks application. There are 4 types of agents proposed for ADN service restoration: Regulator Agent (RA), Bus Agent (BA), State Agent (SA) and State Subset Agent (SSA). The proposed MAS was implemented based on Java programming language and Java agent development framework (JADE). The simulation result indicates that the developed MAS and big data technology for ADN service restoration can provide an effective and timely solution.