In this paper a simple novel approach is presented to construct the Bayesian Network (BN) associated with a power system. In the approach, assuming independent outage events, a general structure is considered for BN which is then modified by using the Mutual Information (MI). Therefore the BN associated with the system is constructed easily and it is not required to use the common structure learning algorithms or use from the physical topology and cause-effect relations that their using for complex and large systems is intractable. The required training data is provided by the state sampling method of Monte Carlo (MC) simulation. Most of the transmission system components have relatively low failure probabilities and so their outages are rare events. Thus, for a more accurate impact analysis of transmission system components the Importance Sampling (IS) scheme is employed in the generation of data. The proposed method that is applicable to large and complex power systems is employed for detailed reliability assessment of IEEE Reliability Test System (IEEE-RTS) and its usability and efficiency is verified.
Adverse weather has considerable effects on reliability of electric power systems. On the other hand, using the Bayesian networks (BN) in reliability studies provides the possibility of analyzing different factors, especially the importance evaluation of system components. In this paper, a novel approach is presented to consider the weather conditions and load level variation in construction and implementation of the BN associated with the composite power systems. In this approach, the geographical division model is used to model weather conditions in various regions of the given power system and also different sections of overhead transmission lines. The obtained BN provides an effective framework for comprehensive reliability study of composite power systems.
Controlled islanding is the last remedial action to prevent cascading outages or blackouts in power systems. Conventional methods presented for controlled islanding strategy determination, particularly those calculating load shedding values using optimization methods, are not fast enough in online applications for modern power systems. In this paper, a novel learning-based approach is introduced for online coherency-based controlled islanding in transmission systems. The proposed approach presents a prediction and optimization model, which is faster than conventional optimization-based models in two ways. Firstly, the proposed approach uses a classification model to predict the splitting scheme in a short time following the occurrence of a disturbance, and secondly in the proposed approach, a simpler optimization problem with fewer variables is solved to find the load shedding amount required in each area. In the proposed load shedding approach, some candidate system partitioning schemes are calculated beforehand and therefore, the load shedding optimization problem is simplified significantly compared to similar optimization-based approaches. Note that appropriate features, which are used in this paper as the input of the classifier, are acquired by processing post-disturbance phase angle variations, which are measured across the network. The proposed approach is simulated on the 16-machine, 68-bus system, and its accuracy and efficacy have been demonstrated.
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.