A New False Data Injection Attack Detection Model for Cyberattack Resilient Energy Forecasting

Ahmadi, Amirhossein; Nabipour, Mojtaba; Taheri, Saman; Mohammadi‐Ivatloo, Behnam; Vahidinasab, Vahid

doi:10.1109/tii.2022.3151748

Cited by 27 publications

(7 citation statements)

References 40 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these algorithms often require environment-dependent hyper parameter adjustments, which can limit their effectiveness [1]. In contrast, deep learning-based methods, such as Point Instance Network (PINet) [2] and LaneATT [5], have shown precise and robust performance in diverse scenarios with different lighting conditions and occlusions [6]. Consequently, deep learning-based approaches are considered a more promising choice for practical applications due to their improved accuracy and reliability.…”

Section: Figure 3: Sgdepth Heatmapmentioning

confidence: 99%

“…The history of road accidents in India can be traced back to various factors, including rapid urbanization, population growth, inadequate infrastructure, lack of proper enforcement of traffic laws, poor road design, and insufficient driver training and education. Autonomous vehicles have been proposed as a potential alternative to human driving by some companies [2]. However, their widespread adoption is hindered by high costs and limited public use.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Autonomous Vehicle Perception and Platooning

2023

IRJMETS

View full text Add to dashboard Cite

Human errors and non-compliance with local driving regulations contribute significantly to driving hazards. As a result, the implementation of an intelligent assistance system can provide valuable benefits in mitigating these risks. Autonomous vehicles have gained momentum as a promising solution for transforming transportation systems. In this research paper, we provide a comprehensive overview of autonomous vehicles, including their past developments, current status, and future prospects. We then focus on perception algorithms used in autonomous vehicles, including computer vision, machine learning, and deep learning techniques, for tasks such as lane detection, object detection, and segmentation, while addressing challenges like diverse environmental conditions and real-time performance. We also discuss the challenges and limitations of autonomous vehicle perception and platooning, including regulatory considerations and societal acceptance. Finally, we highlight potential future directions for research and development in sensor technologies, perception algorithms, and communication systems to shape the future of autonomous vehicle perception and platooning.

show abstract

Section: Figure 3: Sgdepth Heatmapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Autonomous Vehicle Perception and Platooning

2023

IRJMETS

View full text Add to dashboard Cite

show abstract

“…is for high wind velocities. Here, the thermal conductivity of air is denoted by k f as expressed by Equation (5).…”

Section: Overhead Line Thermal Modellingmentioning

confidence: 99%

“…A Dynamic Line Rating (DLR) may be used instead of SLR. In comparison to SLR, DLR produces a more accurate line rating because it employs real‐time tracking systems, mounted directly on the conductor or nearby weather stations, to measure line capacities based on changes in meteorological variables such as solar radiation, air temperature, and wind profile [5]. DLR‐based system operations ensure a stable conductor temperature, sufficient clearance to the field, and reduced conductor aging [6].…”

Section: Introductionmentioning

confidence: 99%

A dagging‐based deep learning framework for transmission line flexibility assessment

Morteza

Sadipour

Fard

et al. 2022

IET Renewable Power Gen

Self Cite

View full text Add to dashboard Cite

Uncertainty in renewable energy generation, energy consumption, and electricity prices, as well as transmission congestion, pose a number of problems in modern power grids, necessitating stability on the supply, grid, and demand sides. Grid-side stability can be achieved by dynamic line rating (DLR) forecasting, which reliably predicts the overall current carrying potential of overhead transmission lines. Long short-term memory proved beneficiary in this field, owing to its ability to learn highly variable and uncertain data. To empower this network to tackle the non-stationary nature of meteorological parameters, a novel machine learning (ML) architecture based on Dagging technique is proposed and tested on the data collected from a 400 kV overhead transmission line. Simulation results corroborate that the proposed Dagging-based stacked LSTM can successfully handle the non-stationary issue and outperform the decomposition-based technique, as the state-ofthe-art algorithm, for various forecasting horizons. The results confirm the generalizability of models with an application in forecasting DLR over the line without utilizing additional sensors and communication networks. Moreover, the proposed model is compared to several ML architectures, including support vector machines (SVM), random forest (RF), and multi-layer perceptron (MLP) in a comprehensive benchmark study. The introduced algorithm outperforms MLP by 3.4%, RF by 9.4%, and SVM by 6.7% in terms of average prediction accuracy.

show abstract

“…Thus, the primary drawback of both conventional and intelligence methods used in previous forecasting models is the need for centralized data. The centralized data is very sensitive since it may readily be utilized to infer critical/private information or conduct cybersecurity attacks [19], [20]. For example, reference [21] examined the effect of data integrity attacks on the physical system of a wind farm.…”

Section: Introductionmentioning

confidence: 99%

Deep Federated Learning-Based Privacy-Preserving Wind Power Forecasting

et al. 2023

View full text Add to dashboard Cite

Given the growing installed capacity, wind energy will exert a profound impact on the flexibility of modern energy systems. Wind power forecasting is a practical solution for dealing with the attributed variations and uncertainties, balancing supply and demand, and improving the reliability of the system. To achieve more accurate and generalizable forecast models, comprehensive data sets, supplied by multiple wind farms owing to their spatio-temporal dependencies, are required. In addition, data aggregation/collaboration across many wind farms scattered around a country is difficult, if not impossible, due to complex administrative processes, industry competition, and data privacy and security concerns. This article offers federated learning-based wind energy forecasting as a novel decentralized collaborative modeling method capable of training a single model on data from many wind farms without jeopardizing the privacy or security of data. To this end, rather than sending private data across sites, local model parameters are securely transmitted. A comparison between the proposed private distributed model and non-private centralized and fully private localized models indicates the high performance of the proposed federated learning-based wind power forecasting with 87.96% accuracy. Enjoying the smoothing effect, the higher generalizability of the proposed model with 83.63% accuracy is also substantiated in comparison to localized and centralized approaches while the privacy of the underlying data is preserved.

show abstract

A New False Data Injection Attack Detection Model for Cyberattack Resilient Energy Forecasting

Cited by 27 publications

References 40 publications

Autonomous Vehicle Perception and Platooning

Autonomous Vehicle Perception and Platooning

A dagging‐based deep learning framework for transmission line flexibility assessment

Deep Federated Learning-Based Privacy-Preserving Wind Power Forecasting

Contact Info

Product

Resources

About