In this paper, a novel co-optimization model is proposed for integrated electricity-gas-heat urban energy systems to improve resilience during extreme events. This paper modelled and analysed data centres' optimal operation, workload redistribution, waste heat reuse. addition guaranteeing power supply as critical loads, centres also provide the generated customers via heating network. Meanwhile, considers complex interactions of multiple recovery decisions distribution system. Energy...

The effective acquisition of multi-source information promotes the development fusion-based methods for power grid fault diagnosis. These method have addressed problem low fault-tolerance diagnosis using switching to a certain extent. However, existing increase complexity and weaken applicability by centrally utilizing information. Given this background, an effort is made present hierarchical information, which takes into account use electrical at different stages. adopts two layer...

Federated learning (FL) has nourished a promising scheme to solve the data silo, which enables multiple clients construct joint model without centralizing data. The critical concerns for flourishing FL applications are that build security and privacy-preserving environment. It is thus highly necessary comprehensively identify classify potential threats utilize under guarantees. This paper starts from perspective of launched attacks with different computing participants unique classification,...

This paper proposes a co-optimal strategy using line hardening, mobile devices (mobile ice-melting device, emergency generator, energy storage system), and repair crew dispatching to improve distribution system resilience during ice storms.A multi-stage defender-attacker-defender model is established take into account interactions coupling relationships between different measures.In our proposed model, storms will attack the transportation in worst-case scenario, affecting performance from...

Abstract In order to solve the related problems of detection and tracking shallow marine organisms, this paper designs a YOLO v5 multi‐target algorithm with attention mechanism. When working underwater, authors usually encounter many difficulties. Different luminosity complex coral background affect organisms. At same time, unrestricted movement ability hide behind rocks algae, their mutual occlusion while swimming pose additional challenges task. Considering characteristics organisms...

The element extraction from network security condition is the foundation awareness. Its excellence directly disturbsentire system performance. In this paper we introduce fuzzy logic based rough set theory for extracting conditional factors. traditional method of situation elements relies on a lot prior knowledge. With purpose solving issue, in proposed featurerank matrix neighborhood set. Additionally, propose reduction parallel algorithm that uses concept entropy order to constructs feature...

In this study, new multicomponent Fe54M5Cr15Mo6Si2B4P10C4 (M = Fe, Co, and Ni, denoted as Fe59, Fe54Co5, Fe54Ni5, respectively) bulk metallic glasses (BMGs) with excellent corrosion wear resistances were synthesized using the J-quenching technique fluxing treatment. The Fe-based BMGs possessed a large glass-forming ability, maximum diameters of Fe54Ni5 glassy alloy rods reached 5.5, 4.5, 4.0 mm, respectively. Fe59 BMG had wide supercooled liquid region 65 K. Potentiodynamic tests in 3.5 wt.%...

Large-scale wind power synchronization will do harm to the system safety, stable operation and electricity quality thus limiting development scale of generation. Wind forecast is one effective measures solve these problems. In this paper, categories major methods are introduced changing regularities factors which influence output analyzed. Besides, parameters choosing, data capturing processing put forward.

With the increasing attention of clean and efficient use energy, regional integrated energy system (RIES), as an measure to improve efficiency, is tending play important role in field supply. The configuration multiple storage equipment RIES can greatly economy system, which research direction planning. However, at present on optimization electric-gas-thermal multi-energy devices insufficient. Under this background, a method for configuring rated capacity power various under both off-grid...

Federated Learning (FL) allows clients to keep local datasets and train collaboratively by uploading model gradients, which achieves the goal of learning from fragmented sensitive data. Although FL prevents clients' being shared directly, private information may be leaked through gradients. To mitigate this problem, we combine game theory design an scheme (IMFL) based on incentive mechanism differential privacy (DP). Firstly, explore three DP variants, all are resistant deep leakage...

The micro-grid technology that integrates distributed generations, energy storage element and loads is an effective approach to solve the interconnection of large-scale generations with power grid. Wind solar can be complementary each other in time, therefore wind PV hybrid system could make full use clean have high reliability. Smooth switching between grid-connected mode islanding important stable operation. In this paper a model based on built DigSILENT/PowerFactory. improved control...

The biggest difficulty of hidden Markov model applied to multistep attack is the determination observations. Now research observations still lacking, and it shows a certain degree subjectivity. In this regard, we integrate intentions (HMM) support method forecasting based on model. Firstly, train existing model(s) by Baum-Welch algorithm HMM. Then recognize alert belonging scenarios with Forward Finally, forecast next possible sequence Viterbi results simulation experiments show that models...

With the development of smart meters, a real-time pricing (RTP) demand response is becoming possible for households in distribution networks. The power flow can be bidirectional networks which become smarter with distributed generators (DGs). It expensive to import electricity from generation far load centers because cost loss and network use, so that it more economical use generated by local generators. Therefore, order curtail operating costs networks, this paper proposes model economic...

In the previous research of risk assessment, AHP method and Fuzzy logical used are obvious subjectivity limitation. this paper, improved, formula degree entropy-weight coefficient put forward to estimation information security. Firstly, hierarchy structure assessment is constructed fuzzy comprehensive judgment improved according actual condition Secondly, likelihood probability, impact severity uncontrollability. Finally, for determination weight vector factor, a applied objective...

A risk assessment method is introduced to the estimation of network security. The method, which combines AHP and fuzzy logical applied assessment. are improved according actual condition Each factor estimated in aspect probability, impact severity uncontrollability. important degree each obtained. By comparing factor, risks will be controlled by some means known. On other hand, applying entropy-weight coefficient, whole system obtained, coefficient objective computation, subjective judgment...

Traditionally, the economic operation of a microgrid (MG) is independent with that distribution network (DN), and electricity trade between them simply based on contract prices or wholesale market prices. In order to coordinate benefits DNs MGs more effectively, new model for MG proposed in this paper modeled as bilevel programming problem (BLPP). At upper level, electric power from gird price are control variables. A DN seeks least cost by optimizing these lower variables dispatchable...

Convolutional neural networks have been widely used in intrusion detection and proactive network defense strategies such as security situation prediction (NSSP). The interaction between cross-channel features the dependencies elements input data are essential factors that affect model's performance. However, existing works ignored these, resulting performance needs to be improved. To this end, we propose a GResNeSt model combines advantages of global context block ResNeSt improve NSSP...

In the case of ensuring reliability power supply, in order to improve economy distributed generation systems, it should be based on different resource conditions optimize design system. This paper constructs system structure multiple supply. The main factors affecting optimal are discussed qualitatively. minimum net present cost (NPC) is optimization goal. was optimized by using Homer software, scheme given this paper. addition, according natural resources, load level and fuel price, article...