State estimation plays a critical role in monitoring and managing operation of smart grid. Nonetheless, recent research efforts demonstrate that data integrity attacks are able to bypass the bad detection mechanism make system operator obtain misleading states system, leading massive economic losses. Particularly, have become threats power In this paper, we propose deep-Q-network (DQND) scheme defend against alternating current (AC) systems. DQND is deep reinforcement learning scheme, which...

In this paper, to address the issue of demand response in smart grid with island MicroGrids (MGs), we introduce an effective and secure auction market that allows electric vehicles (EVs) having surplus energy act as sellers, EVs insufficient MGs buyers. There are two primary challenges designing grid. First, scheme shall be online, allowing buyers sellers enter at any time, satisfy several critical economic properties (individual rationality, incentive compatibility, so on.). Second,...

An efficient energy scheduling strategy of a charging station is crucial for stabilizing the electricity market and accommodating demand electric vehicles (EVs). Most existing studies on strategies fail to coordinate process purchasing distribution and, thus, cannot balance supply demand. Besides, existence multiple stations in complex scenario makes it difficult develop unified schedule different stations. In order solve these problems, we propose multiagent reinforcement learning (MARL)...

The existing multi-agent reinforcement learning methods (MARL) for determining the coordination between agents focus on either global-level or neighborhood-level agents. However problem of individual is remain to be solved. It crucial an optimal coordinated policy in unknown environments analyze agent's roles and correlation To this end, paper we propose agent-level based MARL method. Specifically, it includes two parts our first analysis Pearson, Spearman, Kendall coefficients; And second...

The conventional method of optimizing the aerodynamic performance an airfoil heavily depends on confines design space. variables create a non-normalized space that is fragmented into several different clusters airfoils. An approach data-driven and deforms airfoils over Grassmannian submanifold utilized in work being presented here. affine deformation, which includes camber thickness, can be uncoupled from currently use, operations are performed shape made smooth enough to prevent...

With the introduction of “carbon peaking and carbon neutralizing” initiative, China is undergoing a positive energy transition, emphasizing replacement traditional fossil fuels with clean sources. As part this numerous megacities are progressively endorsing electric vehicles (EVs) as substitutes for fuel‐based vehicles. The expanding use EVs, however, has presented challenges related to randomness volatility EV charging. In response this, many regions in have mandated implementation...

The accumulation of ice on aircraft is a typical meteorological issue. accretion the wing’s leading edge can cause an earlier stall and significantly increase safety risks. Because equivalent shape wing will change based pattern edge, it crucial to predict design anti-icing device. predicted in present work through multi-shot approach. In current study, bio-inspired that generate multiple pairs counter-rotating vortices used alter trajectory water droplets. This results lowering ratio...

For energy management problems in smart grid, a hybrid intelligent hierarchical controller based on simulated annealing (SA) and reinforcement learning (RL) is proposed. The SA used to adjust the parameters of controller. RL algorithm shows particular superiority, which independent mathematic model just needs simple fuzzy information obtained through trial-and-error interaction with environment. By means procedures, proposed can learn take best actions regulate usage for equipments features...

According to the data described by "Global EV Outlook 2017" re-leased International Energy Agency, China has become world's largest market for electric vehicles. The explosive growth of vehicles led rapid development charging facilities. App related pile is current standard configuration new energy vehicle owner. en- ergy owner performs finding, charging, and payment through APP pile. statistics, users who installed pile-related accounted about 8.8 points in 10,000 nation's mobile Internet...

In this paper, a novel packaging method which features wirebond-less structure by using flexible printed circuit board (FPCB) are presented. Detailed comparisons also conducted with the wirebonding hybrid in half-bridge (HB) module. The results reveal better performances of FPCB smaller parasitic inductances, less switching losses, thermal stability. Compared structure, inductances power loop and gate decrease 52% 76% respectively. double pulse test (DPT) was established simulation to...