In a smart city, Mobile Edge Computing (MEC) are generally deployed in static fashion base stations (BSs). While moving vehicles with advanced on-board equipment can be regarded as dynamic computing resource transporters ignoring geographical limitations. Thus Internet of Vehicle (IoV) could assist the city to achieve flexible demand response (DR) via paid sharing idle vehicle resources. Motivated by this, we propose Peer-to-Peer (P2P) trading system balance spatio-temporal demands...

Nowadays, benefit from more powerful edge computing devices and artificial intelligence (edge-AI) could be introduced into Internet of Things (IoT) to find the knowledge derived massive sensory data, such as cyber results or models classification, detection prediction physical environments. Heterogeneous edge-AI in IoT will generate isolated distributed slices, thus collaboration exchange are required complete complex tasks intelligent applications with numerous selfish nodes. Therefore,...

Currently, blockchain technology has been widely used due to its support of transaction trust and security in next generation society. Using Internet Things (IoT) mine makes more ubiquitous decentralized, which become a main development trend blockchain. However, the limited resources existing IoT cannot satisfy high requirements on-demand energy consumption mining process through decentralized way. To address this, we propose supply approach based on microgrids provide for devices. First,...

Recently, edge artificial intelligence techniques (e.g., federated learning) are emerged to unleash the potential of big data from Internet Things (IoT). By learning knowledge on local devices, privacy preserving and Quality Service (QoS) guaranteed. Nevertheless, dilemma between limited on-device battery capacities high energy demands in is not resolved. When exhausted, process will have be interrupted. In this article, we propose a novel wirelessly powered (WPEG) framework, which aims...

Vehicle-to-everything (V2X) aims to make transportation system more intelligent through linking everything with the moving vehicles, but it brings geographical dynamic intrusions. However, existing intrusion detection systems (IDSs) of vehicles just deploy preset statics strategies. As a novel security technology, blockchain can realize decentralized tamper- resistance. has not been used for IDSs because its rigid structure. In this article, we propose Micro-Blockchain based Intrusion...

Traffic speed forecasting plays an increasingly essential role in successful intelligent transportation systems. However, this still remains a challenging task when the accuracy requirement is demanding. To improve prediction and achieve timely performance, capture of intrinsically spatio-temporal dependencies creation parallel model architecture are required. Accordingly, we propose novel end-to-end deep learning framework named Graph Attention Temporal Convolutional Network (GATCN). The...

The emergence of Digital Twin Edge Networks (DTENs) achieves the mapping real physical entities to digital models cyberspace. By offloading real-time mobile data Mobile Computing (MEC) servers for processing and modeling, communication-efficient (DT) services could be achieved. However, spatio-temporal dynamic DT service demand stochastically generated by users easily causes congestion, which challenges long-term stability. Meanwhile, current still lack effective incentive designs...

Recently, wireless edge networks have realized intelligent operation and management with artificial intelligence (AI) techniques (i.e., federated learning). However, the trustworthiness effective incentive mechanisms of learning (FEL) not been fully studied. Thus, current FEL framework will still suffer untrustworthy or low-quality parameters from malicious inactive learners, which undermines viability stability FEL. To address these challenges, potential social attributes among devices...

Abstract Lysine glutarylation (Kglu) is a newly discovered post-translational modification of proteins with important roles in mitochondrial functions, oxidative damage, etc. The established biological experimental methods to identify sites are often time-consuming and costly. Therefore, there an urgent need develop computational for efficient accurate identification sites. Most the existing only utilize handcrafted features construct prediction model do not consider positive impact...

This paper describes a method of developing wide-band multi-port system equivalents for use with real-time digital power simulators. The proposed equivalent combines frequency dependent network (FDNE) the high electromagnetic transients and transient stability analysis (TSA) type simulation block electromechanical transients. characteristic FDNE is obtained by curve-fitting domain admittance characteristics using vector fitting method. also introduces an approach approximating large networks...

A grid dynamic segmentation technique based on fault current limiter (FCL) is presented in this paper. The basic concept of to install the FCLs appropriate ac lines according network structure and segment multi-infeed HVDC systems into a number sectors interconnected by these FCLs. Under normal conditions, equivalent impedence zero does not affect power flow bus voltage system. When short-circuit faults occur system, are activated limit obstruct propagation among sectors. As result, for dc...

The increasing uncertainty level caused by growing renewable energy sources (RES) and aging transmission networks poses a great challenge in the assessment of total transfer capability (TTC) available (ATC). In this paper, novel data-driven sparse polynomial chaos expansion (DDSPCE) method is proposed for estimating probabilistic characteristics (e.g., mean, variance, probability distribution) TTC (PTTC). Specifically, method, requiring no pre-assumed distributions random inputs, exploits...

The cybertwin and 6G-enabled Industrial Internet of Things (6G-IIoT) are the critical technologies that create digital counterparts for physical systems enable near-instant interconnectivity in industrial domain. It is demand but challenging to conduct integrated design 6G-IIoT, which intertwines cyber subsystems, such as control, communication, computing (3C), factories plants. Therefore, cybertwin, synchronizes between its entities during system runtime, ideal proving ground conducting on...

The Internet of Vehicles (IoV) connects a massive amount smart vehicles for inter/intra-vehicle information sharing. Data privacy issues, such as leakage and cost are the key challenges that hinder vehicle operators from sharing their data safely. Traditional privacy-preserving techniques, including Federated Learning (FL) Differential Privacy (DP) can protect security, but high severely limits learning performance. In addition, IoV services place demands on low communication latency, which...

Credit scoring is an important tool for financial institutions to assess customer credit risk, and its accuracy directly affects the effectiveness of risk management decision-making. With development big data artificial intelligence technology, application machine learning methods in field has gradually become a research hotspot. This study explores scoring, specifically use random forest models analyze real data. By conducting feature importance analysis on public sets from Kaggle,...

This paper introduces an approach which enables very large power systems to be modeled on real-time electro-magnetic transients (EMT) digital simulators. is achieved using improved wide-band multi-port equivalent, reduces a network into small manageable equivalent model that preserves behaviors. The low-frequency or electromechanical are captured with transient stability analysis (TSA) type derived coherency-based reduction techniques. high-frequency behavior accurately by placing in...