Search

The cyber–physical infrastructure of a smart grid requires data-dependent artificial intelligence (AI)-based forecasting schemes for predicting different aspects for the short- to long-term, where AI-based schemes include machine learning (ML), deep learning (DL), and hybrid models. These forecasting schemes in different application areas of a smart grid can be vulnerable to cyber-attacks, which is yet to be addressed from a broad perspective. This work reviews the literature addressing the vulnerability of forecasting schemes in smart grids with a categorization of application areas. The existing research works addressing cyber-security or cyber resiliency are reviewed and then presented in an organized manner according to application areas to highlight their advantages and disadvantages. The findings of this review indicate a critical need to develop accurate and robust AI-based forecasting schemes capable of withstanding diverse attack scenarios in each sector, while addressing unsymmetrical attention to different sectors of smart grids. Hence, this review provides a comprehensive overview of the current literature and emphasizes the necessity for the research community to advance toward developing attack-resilient AI-based forecasting schemes designed explicitly for smart grids. • Categorized the application areas of forecasting models in smart grids. • Summarized presentation of forecasting models for each application area. • Organized discussion on usages and robustness of forecasting models during cyber-attacks. • Presented future directions to develop attack-resilient forecasting models. [ABSTRACT FROM AUTHOR]

Predictive maintenance, facilitated by smart devices and cyber infrastructure, is used for essential equipment like power transformers, enhancing power grid stability and reducing operating costs. As part of predictive maintenance, machine learning (ML) methods are employed to predict the remaining useful life (RUL) of power transformers, which can be vulnerable to cyber-attacks, especially data contamination attacks. Hence, this work introduces false data injection (FDI) attacks in ML-based RUL prediction and investigates the impacts on lifetime prediction. Three different attack templates of FDI attacks are implemented to corrupt the input data of extreme gradient boosting (XGBoost), extra trees (ETs) and random forest (RF)-based lifetime predictor models, where single attack templates are found severe compared to a mixed attack template of FDI attacks. Also, adversarial training is presented as a countermeasure, where the adversarially trained XGBoost model outperforms the other two models under normal conditions and cyber-attacks. Experiment results indicate that the lifetime prediction errors of the proposed model in all scenarios can be maintained at about 6 and 3 in terms of RMSE and MAE, respectively. • Introducing cyber-attacks on ML-based power transformer lifetime predictors. • Investigating the severity of single and mixed models of FDI attacks on predictors. • Presenting a comparative analysis of predictors under normal cases and cyber-attacks. • Proposing an adversarial training-based countermeasure to mitigate the severity. [ABSTRACT FROM AUTHOR]

Machine learning provides a probabilistic framework for metabolic pathway inference from genomic sequence information at different levels of complexity and completion. However, several challenges, including pathway features engineering, multiple mapping of enzymatic reactions, and emergent or distributed metabolism within populations or communities of cells, can limit prediction performance. In this article, we present triUMPF (triple non-negative matrix factorization [NMF] with community detection for metabolic pathway inference), which combines three stages of NMF to capture myriad relationships between enzymes and pathways within a graph network. This is followed by community detection to extract a higher-order structure based on the clustering of vertices that share similar statistical properties. We evaluated triUMPF performance by using experimental datasets manifesting diverse multi-label properties, including Tier 1 genomes from the BioCyc collection of organismal Pathway/Genome Databases and low complexity microbial communities. Resulting performance metrics equaled or exceeded other prediction methods on organismal genomes with improved precision on multi-organismal datasets. [ABSTRACT FROM AUTHOR]