Pre-emergency power system security assessment and control using artificial intelligence approaches

Abstract

Modern electricity grids continue to be vulnerable to large-scale blackouts. During the past ten years events in North America, Europe and Asia have clearly demonstrated an increasing likelihood of large blackouts. If pre-emergency conditions are identified, preventive actions can be taken, and large-scale blackouts avoided. In the current competitive environment, such conditions may not be easily detected because different problems may simultaneously occur in different parts of a large network within different jurisdictions. In the paper a novel viable approach is proposed to minimise the threat of large-scale blackouts. The proposed system consist of two main parts: the alarm trigger, an intelligent neural network-based system for early detection of possible alarm states in a power system, and the competitive-collaborative multi-agent control system. We demonstrated the approach on the modified 53-bus IEEE power system. Results are presented and discussed.