This paper proposes a novel intelligent fault diagnosis method to automatically identify different health conditions of wind turbine (WT) gearbox. Unlike traditional approaches, where feature extraction and classification are separately designed performed, this aims learn effective features directly from raw vibration signals while classify the type faults in single framework, thus providing an end-to-end learning-based system for WT gearbox without additional signal processing diagnostic...

The smart grid is arguably one of the most complex cyber-physical systems (CPS). Complex security challenges have been revealed in both physical and cyber parts grid, an integrative analysis on (CP) emerging. This paper provides a comprehensive systematic review critical attack threats defence strategies grid. We start this survey with overview from CP perspective, then focuses prominent schemes significant impact operation corresponding defense solutions. With in-depth attacks defences, we...

Data-driven approaches have gained increasing interests in the fault detection of wind turbines (WTs) due to difficulty system modeling and availability sensor data. However, nonlinearity WTs, uncertainty disturbances measurement noise, temporal dependence time-series data still pose grand challenges effective detection. To this end, paper proposes a new detector based on recently developed unsupervised learning method, denoising autoencoder (DAE), which offers robust nonlinear...

Recent studies on sequential attack schemes revealed new smart grid vulnerability that can be exploited by attacks the network topology. Traditional power systems contingency analysis needs to expanded handle complex risk of cyber-physical attacks. To analyze transmission under topology attacks, this paper proposes a Q-learning-based approach identify critical sequences with consideration physical system behaviors. A realistic flow cascading outage model is used simulate behavior, where...

When the modern electrical infrastructure is undergoing a migration to Smart Grid, vulnerability and security concerns have also been raised regarding cascading failure threats in this interconnected transmission system with complex communication control challenge. The DC power flow-based model has popular study problem due its efficiency, simplicity scalability simulations of such failures. However, nature failures, underlying assumptions simulators (CFS) may fail hold during development...

Security issues related to power grid networks have attracted the attention of researchers in many fields. Recently, a new network model that combines complex theories with flow models was proposed. This model, referred as extended is suitable for investigating vulnerabilities networks. In this paper, we study cascading failures grids under model. Particularly, discover attack strategies select target nodes (TNs) based on load and degree do not yield strongest attacks. Instead, propose novel...

In power systems, although the inertia energy in sources can partly cover unbalances caused by load disturbance or renewable fluctuation, it is still hard to maintain frequency deviation within acceptable ranges. However, with vehicle-to-grid (V2G) technique, electric vehicles (EVs) act as mobile storage units, which could be a solution for control (LFC) an isolated grid. this paper, LFC model of micro-grid EVs, distributed generations and their constraints developed. addition, controller...

The modern society increasingly relies on electrical service, which also brings risks of catastrophic consequences, e.g., large-scale blackouts. In the current literature, researchers reveal vulnerability power grids under assumption that substations/transmission lines are removed or attacked synchronously. reality, however, it is highly possible such removals can be conducted sequentially. Motivated by this idea, we discover a new attack scenario, called sequential attack, assumes...

The threat of false data injection (FDI) attacks have raised wide interest in the research and development smart grid security. This paper presents a comparative study on utilization supervised learning classifiers to detect direct stealth FDI grid. A detailed formulation problem for detection with is first described proper assumptions justifications. Three widely used (SL) based are chosen design corresponding detectors. performance tested against measurement (direct attack) state (stealth...

The security issue of complex networks has drawn significant concerns recently. While pure topological analyzes from a network perspective provide some effective techniques, their inability to characterize the physical principles requires more comprehensive model approximate failure behavior in reality. In this paper, based on an extended metric, we proposed approach examine vulnerability specific type network, i.e., power system, against cascading threats. adopts called betweenness that...

Integrated energy systems (IES) with cooling, heat, electricity, and natural gas have drawn significant interest recently as we embrace more sustainable a midst climate change. However, the uncertain outputs of distributed generators (DGs) make it challenging for IES planning while maintaining low-cost installation operation under carbon emission constraints. To tackle challenge, this work proposes an optimal model considering both DG output uncertainties punishments. reduce conservatism...

The transition to electric vehicles (EVs) has prodigious plausibility in reducing green house gas (GHG). But EVs acceptance is, however, hindered by several challenges; among them is their avidity for quicker charging at lower price. This article considers a photovoltaic (PV)-powered station equipped with an energy storage system (ESS), which assumed be capable of assigning variable rates different fulfill demands inside declared deadlines minimum To ensure fairness, rate-dependent pricing...

In recent years, with the rapid development of distributed photovoltaic systems (DPVS), shortage data monitoring devices and difficulty comprehensive coverage measurement equipment has become more significant, bringing great challenges to efficient management maintenance DPVS. Virtual collection is a new DPVS scheme cost-effectiveness computational efficiency that meets needs energy but lacks attention research. To fill gap in current research field, this paper provides systematic review...

The penetration of distributed energy resources (DERs) in smart grids significantly increases the number field devices owned and controlled by consumers, aggregators, third parties, utilities. As interface between DER power grids, inverters are becoming smarter with various grid-support functions communication capabilities. Meanwhile, cybersecurity risks also on rise due to extensive utilization information technologies. potential negative impacts cyberattacks have attracted significant...

In the study of power grid security, cascading failure analysis in multi-contingency scenarios has been a challenge due to its topological complexity and computational cost. Both network analyses load ranking methods have their own limitations. this paper, based on self-organizing map (SOM), we propose an integrated approach combining spatial feature (distance)-based clustering with electrical characteristics (load) assess vulnerability effect multiple component sets grid. Using result from...

This paper presents a functional model predictive control (MPC) approach based on an adaptive dynamic programming (ADP) algorithm with the abilities of handling constraints and disturbances for optimal nonlinear discrete-time systems. In proposed ADP-based MPC (NMPC) structure, neural-network-based identification is established first to reconstruct unknown system dynamics. Then, actor-critic scheme adopted critic network estimate index performance function action approximate input....

High-precision day-ahead short-term photovoltaic (PV) output forecasting is essential in PV integration to the smart distribution networks and multi-energy system, provides foundation for security, stability, economic operation of systems. This paper proposes a hybrid model based on principal component analysis, grey wolf optimization generalized regression neural network (PCA-GWO-GRNN) forecasting, considering features multiple influencing factors strong uncertainty. first uses PCA reduce...

The operation of smart grids heavily relies on secure and accurate meter measurements provided by phasor measurement units (PMUs). Therefore, the optimal PMU placement (OPP) aiming to achieve complete system observability with as few PMUs possible has been extensively investigated. Although many existing studies have focused OPP, them are concerned order PMUs. To protect buses in when installing stages owing high cost, this paper proposes attack-resilient OPP strategy which places using...

False data injection attacks (FDIAs) can bypass conventional bad detection methods. Recently developed FDIA methods based on statistical consistency of measurement values may not work effectively when false do significantly deviate from historical trends. They also mistakenly treat actual power grid events as FDIAs. In this paper, a highly discriminative detector named the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math...

This article proposes a novel deep-learning-based ORB-SLAM-feature filtering framework to monitor, detect the occurrence, and estimate distance of early wildfire through an integrated design image processing aerial onboard visual-infrared sensor measurements real-time navigation unmanned vehicle (UAV). The proposed uses DJI ZenMuse H20T integrating with both visual infrared cameras mounted on M300 UAV. It consists three main functional modules support fighting management missions: 1) smoke...