Multi-user Augmented Reality (MuAR) allows multiple users to interact with shared virtual objects, facilitated by exchanging environment information. Current MuAR systems rely on 3D point clouds for real-world analysi...
详细信息
Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the a...
详细信息
Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the adopted datasets for training have correct labeling information. However, such an assumption is not always valid as training data might include measurement samples that are incorrectly labeled as benign, namely, adversarial data poisoning samples, which have not been detected before. Neglecting such an aspect makes detectors susceptible to data poisoning. Our investigations revealed that detection rates (DRs) of existing detectors significantly deteriorate by up to 9-29% when subject to data poisoning in generalized and topology-specific settings. Thus, we propose a generalized graph neural network-based anomaly detector that is robust against FDIAs and data poisoning. It requires only benign datasets for training and employs an autoencoder with Chebyshev graph convolutional recurrent layers with attention mechanism to capture the spatial and temporal correlations within measurement data. The proposed convolutional recurrent graph autoencoder model is trained and tested on various topologies (from 14, 39, and 118-bus systems). Due to such factors, it yields stable generalized detection performance that is degraded by only 1.6-3.7% in DR against high levels of data poisoning and unseen FDIAs in unobserved topologies. Impact Statement-Artificial Intelligence (AI) systems are used in smart grids to detect cyberattacks. They can automatically detect malicious actions carried out bymalicious entities that falsifymeasurement data within power grids. Themajority of such systems are data-driven and rely on labeled data for model training and testing. However, datasets are not always correctly labeled since malicious entities might be carrying out cyberattacks without being detected, which leads to training on mislabeled datasets. Such actions might degrade the d
We studied the weekly number and the growth/decline rates of COVID-19 deaths of the period from October 31, 2022, to February 9, 2023, in Italy. We found that the COVID-19 winter wave reached its peak during the three...
详细信息
We propose a method to reconstruct a personalized hand avatar, representing the user's hand shape and appearance, from a monocular RGB-D video of a hand performing unknown hand poses under unknown illumination. Ou...
详细信息
Summarizing lengthy text involves distilling crucial information into a concise form by covering the key events in the source text. Previous researchers mostly explored the supervised approaches for the task, but due ...
详细信息
The transition from traditional energy or electrical grids to smart energy or electrical grids has significantly transformed energy management. This evolution emphasizes decentralization, efficiency, and sustainabilit...
详细信息
The transition from traditional energy or electrical grids to smart energy or electrical grids has significantly transformed energy management. This evolution emphasizes decentralization, efficiency, and sustainability in energy systems. However, it also introduces numerous risks, including cyber-physical system vulnerabilities and challenges in energy trading. The application of blockchain and Machine Learning (ML) offers potential solutions to these issues. Blockchain enhances energy transactions by making them safer, more transparent, and tamper-proof, while ML optimizes grid performance by improving predictions, fault detection, and anomaly identification. This systematic review examines the application of blockchain and ML in peer-to-peer (P2P) energy trading within smart grids and analyzes how these technologies complement each other in mitigating risks and enhancing the efficiency of smart grids. Blockchain enhances security by providing privacy for transactions and maintaining immutable records, while ML predicts market trends, identifies fraudulent activities, and ensures efficient energy use. The paper identifies critical challenges in smart grids, such as unsecured communication channels and vulnerabilities to cyber threats, and discusses how blockchain and ML address these issues. Furthermore, the study explores emerging trends, such as lightweight blockchain systems and edge computing, to overcome implementation challenges. A new architecture is proposed, integrating blockchain with ML algorithms to create resilient, secure, and efficient energy trading markets. The paper underscores the need for global standardization, improved cybersecurity measures, and further research into how blockchain and ML can revolutionize smart grids. This study integrates current knowledge with a forward-looking perspective, providing valuable insights for researchers, policymakers, and stakeholders in the energy sector to collaboratively build a future of efficient and int
Community question answering (CQA) forums are Internet-based platforms where users ask questions about a topic and other expert users try to provide solutions. Many CQA forums such as Quora, Stackoverflow, Yahoo!Answe...
详细信息
This work focuses on the problem of distributed optimization in multi-agent cyberphysical systems, where a legitimate agent's iterates are influenced both by the values it receives from potentially malicious neigh...
详细信息
The holomorphic embedding method(HEM)stands as a mathematical technique renowned for its favorable convergence properties when resolving algebraic systems involving complex *** key idea behind the HEM is to convert th...
详细信息
The holomorphic embedding method(HEM)stands as a mathematical technique renowned for its favorable convergence properties when resolving algebraic systems involving complex *** key idea behind the HEM is to convert the task of solving complex algebraic equations into a series expansion involving one or multiple embedded complex *** transformation empowers the utilization of complex analysis tools to tackle the original problem *** the 2010s,the HEM has been applied to steady-state and dynamic problems in power systems and has shown superior convergence and robustness compared to traditional numerical *** paper provides a comprehensive review on the diverse applications of the HEM and its variants reported by the literature in the past *** paper discusses both the strengths and limitations of these HEMs and provides guidelines for practical *** also outlines the challenges and potential directions for future research in this field.
The growing integration of renewable energy sources manifests as an effective strategy for reducing carbon emissions. This paper strives to efficiently approximate the set of optimal scheduling plans(OSPs) to enhance ...
详细信息
The growing integration of renewable energy sources manifests as an effective strategy for reducing carbon emissions. This paper strives to efficiently approximate the set of optimal scheduling plans(OSPs) to enhance the performance of the steady-state adaptive cruise method(SACM) of power grid, improving the ability of dealing with operational uncertainties. Initially, we provide a mathematical definition of the exact boxconstrained economic operating region(EBC-EOR) for the power grid and its dispatchable components. Following this, we introduce an EBC-EOR formulation algorithm and the corresponding bi-level optimization models designed to explore the economic operating boundaries. In addition, we propose an enhanced big-M method to expedite the computation of the EBCEOR. Finally, the effectiveness of the EBC-EOR formulation, its economic attributes, correlation with the scheduling plan underpinned by model predictive control, and the significant improvement in computational efficiency(over twelvefold) are verified through case studies conducted on two test systems..
暂无评论