Blackout around the world generally manifests due to the voltage instability on distribution networks following major overloads, therefore the activation of the protection devices via a load shedding strategy is necessary to avoid severe contingencies. This article aims is to develop a new approach for under voltage load shedding (UVLS) ensuring two primordial parameters of shedding strategy, its amount and its load priority. The main contribution of this work lies in the application of a neuroevolution algorithm to enhance the UVLS relays decisions in the distribution network, under a decentralized process. The proposed algorithm adapts the amount of the shed loads in each bus, in a cooperative manner, in order to maintain the voltage stability of the system, and in where the priority of UVLS is defined by two voltage stability indices (SI): voltage SI and voltage electrical distance in addition to the measured voltage deviation. The efficiency of the proposed approach is validated for several overload scenarios performed in 33‐bus IEEE distribution system, in where the performance of the proposed adaptive Load shedding outperforms the conventional scheme.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.