Maintaining transient stability is a core requirement for ensuring safe operation of power systems. Hence, quick and accurate assessment of the transient stability of power systems is particularly critical. As the deployment of wide area measurement systems (WAMS) expands, transient stability assessment (TSA) based on machine learning with data of phasors measurement units (PMUs) also develops rapidly. However, unstable samples of the power system are rarely seen in practice which affects greatly the effectiveness of transient instability recognition. To address this problem, we propose a deep imbalanced learning-based TSA framework. First, an improved denoising autoencoder (DAE) is constructed to map the training set to hidden space for dimension reduction. Then, adaptive synthetic sampling (ADASYN) is further used to synthesize unstable samples in hidden space to balance the proportion of different classes. Third, the synthesized data are decoded into the original space to enhance the training set. Finally, an ensemble cost-sensitive classifier based on a stacked denoising autoencoder (SDAE) is designed to extract different feature patterns, and the SDAEs are merged with a fusion layer to classify the status of the power system. The simulation results of two benchmark power systems indicate that the proposed method can effectively improve the recognition accuracy of unstable cases by combining nonlinear data synthesis with ensemble cost-sensitive learning methods. Compared with other imbalanced learning methods, the proposed framework enjoys superiority both in accuracy and G-mean. INDEX TERMS Deep imbalanced learning, transient stability of power system, denoising autoencoder (DAE), ensemble cost-sensitive SDAE, feature patterns, G-mean.

No abstract

Abstract:With the popularization of electric vehicles (EVs), the out-of-order charging behaviors of large numbers of EVs will bring new challenges to the safe and economic operation of power systems. This paper studies an optimal charging strategy for EVs. For that a typical urban zone is divided into four regions, a regional time-of-use (RTOU) electricity price model is proposed to guide EVs when and where to charge considering spatial and temporal characteristics. In light of the elastic coefficient, the user response to the RTOU electricity price is analyzed, and also a bilayer optimization charging strategy including regional-layer and node-layer models is suggested to schedule the EVs. On the one hand, the regional layer model is designed to coordinate the EVs located in different time and space. On the other hand, the node layer model is built to schedule the EVs to charge in certain nodes. According to the simulations of an IEEE 33-bus distribution network, the performance of the proposed optimal charging strategy is verified. The results demonstrate that the proposed bilayer optimization strategy can effectively decrease the charging cost of users, mitigate the peak-valley load difference and the network loss. Besides, the RTOU electricity price shows better performance than the time-of-use (TOU) electricity price.

No abstract

No abstract