Fault location in DC microgrids (DCMGs) is a critical challenge due to the system’s inherent complexities and the demand for high reliability in modern power systems. This study proposes an explainable artificial intelligence (XAI)-based quantum deep neural network (QDNN) framework to address fault localization challenges in DCMGs. First, voltage signals from the DCMG are collected and analyzed using high-order synchrosqueezing transform to detect traveling waves (TWs) and extract critical fault parameters such as time of arrival, magnitude, and polarity of the first and second TWs. These features are fed into the proposed QDNN model that integrates advanced learning techniques for accurate fault localization. The cumulative distance from the fault point to the bus connecting the DCMG to the power network is considered the output vector. The model uses a combination of deep learning and quantum computing techniques to extract features and improve accuracy. To ensure transparency, an XAI technique called Shapley additive explanations (SHAP) is applied, enabling system operators to identify critical fault features. The SHAP-based explainability framework plays a critical role in translating the model’s predictions into actionable insights, ensuring that the proposed solution is not only accurate but also practically implementable in real-world scenarios. The results demonstrate the QDNN framework’s superior accuracy in fault localization even in noisy environments and with high-resistance faults, independent of voltage levels and DCMG configurations, making it a robust solution for modern power systems.

Weighted least-square support vector machine (WLS-SVM) is proposed in this research as a real-time transient stability evaluation method using the synchrophasor measurement received from phasor measurement units (PMUs). This method considers the directional overcurrent relays (DOCRs) for the transmission system, whereas in previous studies, the effect of protective mechanisms on the transient stability was largely ignored. When protective relays are activated in power system, the configuration of the power system is altered to mitigate the risk of the power system becoming unstable. The present study considers the operation of DOCRs in transmission lines for the transient stability so that the proposed method can respond to changes in the configuration of the case study system. In addition, WLS-SVM is employed for an online assessment of the transient stability. WLS-SVM not only is effective in response due to its faster speed, but also is resistant to noise and has excellent performance against the measurement errors of PMUs. To extract the characteristics of the vectors that are fed into the WLS-SVM algorithm, principal component analysis is used. The findings of the suggested technique reveal that it has higher accuracy and optimum performance, as compared to the extreme learning machine method, the adaptive neuro-fuzzy inference system method, and the back-propagation neural network method. The proposed technique is validated in the New England 39-bus system and the IEEE 118-bus system.