Situational awareness in complex systems is important for their reliable and efficient operations. Complex systems consist of components/nodes and subsystems. Functional situational awareness (FSA) is focused on provi...
Situational awareness in complex systems is important for their reliable and efficient operations. Complex systems consist of components/nodes and subsystems. Functional situational awareness (FSA) is focused on providing qualitative and quantitative functional capabilities of components, subsystems, and the system over time. Safe-/mission-critical systems require FSA in real-time. The development of an artificial intelligence (AI)-based FSA system inferencing tool, herein, referred to as an FSA inference system development engine (FIDE), tailored to hybrid military ground vehicles (HMGVs) is presented. FIDE can be utilized to generate preliminary designs, virtual prototyping of FSA and its evaluation on actual HMGVs as well virtual vehicle testbeds. FIDE consists of four modules, namely, i) intelligent knowledge acquisition, ii) FSA topology model, iii) FSA engine and iv) human-computer interface (HCI). The development and operation of these modules is presented. FIDE generated FSA systems can ensure reliable and efficient operation of Vehicle Power systems (VPSs). Case studies are presented for virtual prototypes of an FSA engines and HCIs using FIDE.
Reconfigurable holographic surfaces (RHSs) have been proposed as a cost-effective and power-efficient solution for extremely large-scale arrays, where the amplitude of electromagnetic waves radiated at each element is...
详细信息
ISBN:
(数字)9798350351255
ISBN:
(纸本)9798350351262
Reconfigurable holographic surfaces (RHSs) have been proposed as a cost-effective and power-efficient solution for extremely large-scale arrays, where the amplitude of electromagnetic waves radiated at each element is controlled to achieve high directive gain. However, the complexity of acquiring real-time channel state information (CSI) required for beamforming is prohibitively high, especially when the near-field expansion brought by the large-scale RHS is considered. In this paper, we propose a codebook-based beam training scheme for a large-scale RHS-enabled communication system to bypass CSI estimation. Unlike traditional phase-controlled arrays, the amplitude-controlled property of the RHS implies that each RHS element can be selectively activated. This motivates an array reconfiguration method where a scale-changeable RHS array is constructed to generate gain-flat beams with different coverage in the angle-range domain. A hierarchical RHS codebook is then proposed where the coverage of the codewords in each layer is progressively refined. To address the substantial beam search overhead in the near-far field, a two-stage beam training scheme is performed in the proposed codebook, thereby reducing the overhead to a logarithmic level of the element number. The simulation results show that the proposed scheme performs better than phased arrays given the same input power in terms of sum rate, and it also approaches the upper bound achieved by the exhaustive search at a significantly reduced overhead.
作者:
Cao, GanghuiWang, JinzhiPolycarpou, Marios M.Peking University
State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Beijing100871 China University of Cyprus
KIOS Research and Innovation Center of Excellence and the Department of Electrical and Computer Engineering Nicosia1678 Cyprus
This paper investigates the design of distributed observers for a class of nonlinear systems. The designed distributed observers reside in a network of sensor nodes. The communication links in the network enable each ...
详细信息
Stability problems arise when large utility-scale solar photovoltaic (PV) plants are integrated into bulk power systems. The intermittent nature of solar radiation results in PV power generation variations, which must...
详细信息
Stability problems arise when large utility-scale solar photovoltaic (PV) plants are integrated into bulk power systems. The intermittent nature of solar radiation results in PV power generation variations, which must be compensated by the conventional power plants (synchronous generators) to regulate the frequency of the power system by balancing generation-load. The compensation involves generation dispatch changes of the synchronous generators. The PV plant variations and synchronous generators' dispatch changes could give rise to electromechanical oscillations (EMOs) in the power system. Severe EMOs can lead to power system instability, and this can be avoided by intelligently modulating the rate of change of dispatch of the synchronous generators during PV plant output variations. The intelligent modulation of the rate of change of dispatch can be implemented via an adaptive automatic generation control (A-AGC). This paper presents the development of an A-AGC based on an EMO index derived from phasor measurement units to ensure the stability of the power system. Typical results are presented to illustrate the operation and performance of A-AGC during PV power variations.
Amidst the challenges posed by the high penetration of distributed energy resources (DERs), particularly a number of distributed photovoltaic plants (DPVs), in modern electric power distribution systems (MEPDS), the i...
Amidst the challenges posed by the high penetration of distributed energy resources (DERs), particularly a number of distributed photovoltaic plants (DPVs), in modern electric power distribution systems (MEPDS), the integration of new technologies and frameworks become crucial for addressing operation, management, and planning challenges. Situational awareness (SA) and situational intelligence (SI) over multi-time scales is essential for enhanced and reliable PV power generation in MEPDS. In this paper, data-driven digital twins (DTs) are developed using AI paradigms to develop actual and/or virtual models of DPV s, These DTs are then applied for estimating and forecasting the power outputs of physical and virtual PV plants. Virtual weather stations are used to estimate solar irradiance and temperature at user-selected locations in a localized region, using inferences from physical weather stations. Three case studies are examined based on data availability: physical PV plant, hybrid PV plants, and virtual PV plants, generating real-time estimations and short-term forecasts of PV power production that can support distribution system studies and decision-making.
Deadlock resolution strategies based on siphon control are widely *** computational efficiency largely depends on siphon ***-integer programming(MIP)can be utilized for the computation of an emptiable siphon in a Petr...
详细信息
Deadlock resolution strategies based on siphon control are widely *** computational efficiency largely depends on siphon ***-integer programming(MIP)can be utilized for the computation of an emptiable siphon in a Petri net(PN).Based on it,deadlock resolution strategies can be designed without requiring complete siphon enumeration that has exponential *** to this reason,various MIP methods are proposed for various subclasses of *** work proposes an innovative MIP method to compute an emptiable minimal siphon(EMS)for a subclass of PNs named S^(4)*** particular,many particular structural characteristics of EMS in S4 PR are formalized as constraints,which greatly reduces the solution *** results show that the proposed MIP method has higher computational ***,the proposed method allows one to determine the liveness of an ordinary S^(4)PR.
Renewable energy generation sources (RESs) are gaining increased popularity due to global efforts to reduce carbon emissions and mitigate effects of climate change. Planning and managing increasing levels of RESs, spe...
Renewable energy generation sources (RESs) are gaining increased popularity due to global efforts to reduce carbon emissions and mitigate effects of climate change. Planning and managing increasing levels of RESs, specifically solar photovoltaic (PV) generation sources is becoming increasingly challenging. Estimations of solar PV power generations provide situational awareness in distribution system operations. A digital twin (DT) can replicate PV plant behaviors and characteristics in a virtual platform, providing realistic solar PV estimations. Furthermore, neural networks, a popular paradigm of artificial intelligence may be used to adequately learn and replicate the relationship between input and output variables for data-driven DTs (DD-DTs). In this paper, DD-DTs are developed for Clemson University's 1 MW solar PV plant located in South Carolina, USA to perform realistic solar PV power estimations. The DD-DTs are implemented utilizing multilayer perceptron (MLP) and Elman neural networks. Typical practical results for two DD-DT architectures are presented and validated.
Lithium-ion batteries are playing a critical role in many applications nowadays, from small-scale electronic devices to grid-scale storage systems. To maintain its continuous operation and increase its life span, the ...
Lithium-ion batteries are playing a critical role in many applications nowadays, from small-scale electronic devices to grid-scale storage systems. To maintain its continuous operation and increase its life span, the state of charge of the battery should be determined to ensure safe operating conditions. Among the existing charge estimation methods, data-driven models are flourishing these days. This work presents a state of charge estimation for the eFlex 52.8V/5.4 kWh lithium iron phosphate battery pack at the Energy systems Research laboratory (ESRL) at FIU. Three different machine learning models were implemented and trained through Python code to achieve the most accurate SoC estimation. Although the three proposed models can efficiently estimate the battery’s SoC with an acceptable error percentage, the random forest regression model has proven its outperformance among the selected models with a percentage mean square error less than 0.01.
Recently, applying data-independent random feature extraction methods has been promising for time-series classifications. However, a large portion of the features generated by these methods is redundant. To address th...
Recently, applying data-independent random feature extraction methods has been promising for time-series classifications. However, a large portion of the features generated by these methods is redundant. To address this problem, we propose a robust feature selection method that applies a maximin optimization to a weight cost function that makes a trade-off between dimension reduction and preserving the classification accuracy. It can be shown that the weight cost is discrete midpoint convex with respect to the sparsity parameter, and at the same time is concave with respect to the regularization parameter. Based on these findings, we propose an efficient implementation for feature selection with maximin optimization. Our empirical results show that for large classification tasks with a small sample size per class, our feature selection method removes more redundancies than the state-of-the-art methods, while preserving the classification accuracy.
DC microgrids are becoming more and more popular, however there are still difficulties involving ongoing instability that are mostly caused by imbalances in energy supply and demand, particularly in situations with pu...
DC microgrids are becoming more and more popular, however there are still difficulties involving ongoing instability that are mostly caused by imbalances in energy supply and demand, particularly in situations with pulse load or variable pulse load patterns. Innovative solutions are required since these disruptive load dynamics significantly decrease the effectiveness of conventional PV-Battery control systems. conventional Proportional-Integral (PI) controllers, although widely employed, may encounter limitations when confronted with the unique challenges posed by specific load patterns, notably pulse load scenarios. These dynamic load profiles, characterized by rapid and unpredictable changes. The inherent non-linearity and variability in such load conditions can result in suboptimal control performance, potentially leading to voltage instability and transients within the microgrid. To overcome these issues and improve control performance, the introduction of Neural Network (NN) controllers promises to be a potential approach. NN controllers have a remarkable capacity to learn and adapt from data, making them particularly well-suited for situations characterized by non-linear and dynamic load behavior. In this study, a hybrid PI-NN (Proportional-Integral Neural Network) controller is introduced to reduce load effects, especially pulsed loads, in PV systems with batteries and supercapacitors. This method efficiently optimizes energy storage. For voltage control, it utilizes a PI system, which divides the reference current into low and high-frequency components for battery and supercapacitor control. For enhanced sensitivity and dynamic responsiveness, neural network control replaces conventional PIs. The performance of the hybrid PI-NN controller is evaluated in this work, with an emphasis on its potential to improve PV system efficiency in severe load circumstances.
暂无评论