Nowadays, the method of simple-feature extraction has been extensively studied and is used in PPG biometric recognition; some promising results have been reported. However, some useful information is often lost in the process of PPG signal denoising; the time-domain, frequency-domain, or wavelet feature extracted is often partial, which cannot fully express the raw PPG signal; and it is also difficult to choose the appropriate matching method. Therefore, to make up for these shortcomings, a method of PPG biometric recognition based on multifeature extraction and naive Bayes classifier is proposed. First, in the preprocessing of the raw PPG data, the sliding window method is used to rerepresent the raw data. Second, the feature-extraction methods based on time-domain, frequency-domain, and wavelet are analysed in detail, then these methods are used to extract the time-domain, frequency-domain, and wavelet features, and the features are concatenated into a multifeature. Finally, the multifeature is normalized and combined with classifiers and Euclidean distance for matching and decision-making. Extensive experiments are conducted on three PPG datasets, it is found that the proposed method can achieve a recognition rate of 98.65%, 97.76%, and 99.69% on the respective sets, and the results demonstrate that the proposed method is not inferior to several state-of-the-art methods.
Electric power substations, as critical components of modern power grids, are increasingly becoming targets for intentional physical attacks, including vandalism, theft, and sabotage. These threats, coupled with the potential for cyber-attacks and the weaponization of technologies, necessitate robust security measures and comprehensive auditing practices. Despite utilities providers’ focus on understanding grid vulnerability and implementing physical security upgrades, there is a recognized gap in evaluating the effectiveness and long-term usability of these measures. This paper addresses the need for regular security audits to identify vulnerabilities and ensure the overall resilience of substations against evolving threats. The rationale behind this study is to propose a conventional auditing method that includes an auditing framework, checklists, inspections, and post-inspection suggestions. Through the systematic identification and addressing of vulnerabilities via security auditing, the framework aims to significantly enhance the resilience of substations against physical threats. This paper provides a comprehensive guideline for the physical security auditing procedure, which is essential for the reliable operation of the power grid.
This paper introduces an Enhanced-Dueling Deep Q-Network (EDDQN) specifically designed to bolster the physical security of electric power substations. We model the intricate substation security challenge as a Markov Decision Process (MDP), segmenting the facility into three zones, each with potential normal, suspicious, or attacked states. The EDDQN agent learns to strategically select security actions, aiming for optimal threat prevention while minimizing disruptive errors and false alarms. This methodology integrates Double DQN for stable learning, Prioritized Experience Replay (PER) to accelerate the learning process, and a sophisticated neural network architecture tailored to the complexities of multi-zone substation environments. Empirical evaluation using synthetic data derived from historical incident patterns demonstrates the significant advantages of EDDQN over other standard DQN variations, yielding an average reward of 7.5, a threat prevention success rate of 91.1%, and a notably low false alarm rate of 0.5%. The learned action policy exhibits a proactive security posture, establishing EDDQN as a promising and reliable intelligent solution for enhancing the physical resilience of power substations against evolving threats. This research directly addresses the critical need for adaptable and intelligent security mechanisms within the electric power infrastructure.
1 January 2025 in IET Science, Measurement & Technology
Arc faults in low‐voltage distribution networks significantly threaten power system safety due to their randomness and concealment. Traditional arc fault detection methods, which rely on time‐domain and frequency‐domain features, often struggle with accuracy and robustness in variable load environments. To address these challenges, this paper introduces Visibility Graph Convolutional Learning (VisGCL), a novel approach that segments current signals into visibility graphs and employs hierarchical graph convolutional networks for analysis. This method directly learns arc failure modes from the graphical representation of current signals, simplifying the detection process and enhancing both accuracy and robustness. Experimental results demonstrate that the proposed method achieves an accuracy of 98.58 ± 0.14%, with precision, recall, and F1‐score reaching 98.05 ± 0.25%, 98.36 ± 0.47%, and 98.16 ± 0.23%, respectively. Extensive experiments validate the effectiveness of VisGCL, confirming its superiority in detecting arc faults under diverse load conditions, and offering a new efficient and reliable solution for arc fault detection in low‐voltage distribution networks.
Ensuring the physical security of electric power substations is crucial for maintaining a reliable supply of electricity. The increasing prevalence of physical threats, such as physical attacks, vandalism, sabotage, etc., on electric power substations worldwide has resulted in widespread power outages. To enhance physical security in light of these high-impact, low-probability events, this paper proposes a physical security threat assessment approach to evaluate and enhance substation security against physical attacks utilizing the Substation Criticality Index (SCI) and the Threat–Vulnerability–Consequences Index (TVCI) on risk-based security-constrained economic dispatch. The primary objective is to provide power utilities with actionable insights to proactively strengthen their defenses within budgetary constraints by considering the criticality level of each substation. By incorporating social, economic, and electrical factors, this study simulated a physical attack (specifically a bus-isolating attack), on an IEEE 39-bus test system, and evaluated the resultant consequences and load loss. Upon computation of the SCI, substations are ordered according to their criticality, and computing the TVCI gives the risk of each substation which is used to obtain an optimized physical security investment based on substation vulnerability and the consequences of attacks. Thus, based on these results, decisions for prioritizing substation physical security and investments for hardening physical security are made. Furthermore, the experimentation showed that with the physical security investment, the overall TVCI score has significantly decreased with certain budgetary constant.
To address the challenges of multivariate signal coupling, noise interference, and load adaptability in arc fault detection within low-voltage distribution systems, this paper introduces a novel arc fault detection architecture, termed Multivariate Data Joint Analysis with Transformer (MDJA-Trans) architecture. The architecture employs Noise-Suppressing Time Convolutional Learning (NS-TCL) to dynamically mitigate noise and extract multiscale arc features through frequency-domain masking. Load-Aware Cross-Variate Attention Fusion (CVAF) facilitates dynamic alignment of voltage and current features, while Dynamic Gating Decision (DGD) integrates electrical features with load attribute embeddings for robust arc fault classification. This approach enhances physical interpretability and load generalization. Extensive experiments demonstrate superior noise immunity and cross-load adaptability, achieving an arc fault detection accuracy and F1-Score of 98.55%. The proposed solution will provide technical support for improving household safety and reducing electrical fire risks.