Abstract
This paper presents a model tree (MT) based approach for fast voltage contingency ranking, of most severe contingencies for online applications in energy management systems. To measure the severity of contingencies, a bus voltage violation based scalar performance index is used. Model trees are developed to estimate the real value of voltage performance index (VPI) and rank the single line outage contingencies, according to their severity. Full AC power flow is performed, to generate the training and testing patterns for the proposed MT under each contingency. The effectiveness of the proposed approach is tested on IEEE test systems. Once trained, the MT method gives fast and accurate ranking of contingencies for unknown load patterns, hence it is suitable for online applications in energy management systems.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call