HYBRID-NEURAL-NETWORK-BASED ESTIMATION OF LINE OVERLOADING

Abstract

Since the modern power systems are being operated under heavily stressed conditions, the cases of voltage limit violation and power system line overloading are occurring frequently. These events are responsible for several incidents of major network collapses leading to partial or even complete blackouts. Alleviation of line overloads is the suitable corrective action in this regard and for this, fast and accurate identification of overloaded lines is essential along with the estimation of the overloading amount in these lines. In this paper, an approach based on hybrid neural network (HNN) is presented for identification and estimation of line overloading in an efficient manner. The effectiveness of the proposed HNN-based approach is demonstrated by estimation of line overloading for different loading conditions in IEEE 14-bus system. The developed HNN provides accurate and quick results for previously unseen operating condition during testing phase.