arXiv subjects

Ning Lu

Publications and source records attributed to Ning Lu.

At least 91 records · Page 5Linked to original sources

arXiv2021

A Meta-learning based Distribution System Load Forecasting Model Selection Framework

This paper presents a meta-learning based, automatic distribution system load forecasting model selection framework. The framework includes the following processes: feature extraction, candidate model labeling, offline training, and online model recommendation. Using user load forecasting needs as input features, multiple meta-learners are used to rank the available load forecast models based on their forecasting accuracy. Then, a scoring-voting mechanism weights recommendations from each meta-leaner to make the final recommendations. Heterogeneous load forecasting tasks with different temporal and technical requirements at different load aggregation levels are set up to train, validate, and test the performance of the proposed framework. Simulation results demonstrate that the performance of the meta-learning based approach is satisfactory in both seen and unseen forecasting tasks.

eess.SY↗

arXiv2021

MASTER: Multi-Aspect Non-local Network for Scene Text Recognition

Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-decoder architecture. However, such methods suffer from attention-drift problem because high similarity among encoded features leads to attention confusion under the RNN-based local attention mechanism. Moreover, RNN-based methods have low efficiency due to poor parallelization. To overcome these problems, we propose the MASTER, a self-attention based scene text recognizer that (1) not only encodes the input-output attention but also learns self-attention which encodes feature-feature and target-target relationships inside the encoder and decoder and (2) learns a more powerful and robust intermediate representation to spatial distortion, and (3) owns a great training efficiency because of high training parallelization and a high-speed inference because of an efficient memory-cache mechanism. Extensive experiments on various benchmarks demonstrate the superior performance of our MASTER on both regular and irregular scene text. Pytorch code can be found at https://github.com/wenwenyu/MASTER-pytorch, and Tensorflow code can be found at https://github.com/jiangxiluning/MASTER-TF.

cs.CV↗

arXiv2021

EMS and DMS Integration of the Coordinative Real-time Sub-Transmission Volt-Var Control Tool under High DER Penetration

This paper proposes an applicable approach to deploy the Coordinative Real-time Sub-Transmission Volt-Var Control Tool (CReST-VCT), and a holistic system integration framework considering both the energy management system (EMS) and distribution system management system (DMS). This provides an architectural basis and can serve as the implementation guideline of CReST-VCT and other advanced grid support tools, to co-optimize the operation benefits of distributed energy resources (DERs) and assets in both transmission and distribution networks. Potential communication protocols for different physical domains of a real application is included. Performance and security issues are also discussed, along with specific considerations for field deployment. Finally, the paper presents a viable pathway for CReST-VCT and other advanced grid support tools to be integrated in an open-source standardized-based platform that supports distribution utilities.

eess.SY↗

arXiv2021

A Zonal Volt/VAR Control Mechanism for High PV Penetration Distribution Systems

This paper presents a zonal Volt/VAR control scheme that coordinates Photovoltaic (PV) inverters for providing voltage regulation on 3-phase unbalanced distribution feeders. Voltage sensitivity studies are conducted to uncover the dependency between nodal voltage changes and the reactive power injections at nodes with smart PV inverters. A fast incremental clustering method is developed to divide the distribution feeder into weakly coupled zones based on correlations of nodal voltage sensitivities. Because each zone is weakly coupled, voltage of each zone can be controlled independently. Thus, in each zone, a rule-based voltage controller will dispatch PV smart inverters to provide reactive power control for correcting the over/under voltages. An actual distribution feeder in North Carolina is used as a test bed. Simulation results show that the proposed zonal based Volt/VAR control mechanism can maintain the voltage in the distribution system within limits and solves faster than the centralized controller.

eess.SY↗

arXiv2021

Hierarchical Multi-timescale Framework For Operation of Dynamic Community Microgrid

Distribution system integrated community microgrids (CMGs) can restore loads during extended outages. The CMG is challenged with limited resource availability, absence of a robust grid-support, and demand-supply uncertainty. To address these challenges, this paper proposes a three-stage hierarchical multi-timescale framework for scheduling and real-time (RT) dispatch of CMGs. The CMG's ability to dynamically expand its boundary to support the neighboring grid sections is also considered. The first stage solves a stochastic day-ahead (DA) scheduling problem to obtain referral plans for optimal resource rationing. The intermediate near real-time scheduling stage updates the DA schedule closer to the dispatch time, followed by the RT dispatch stage. The proposed methodology is validated via numerical simulations on a modified IEEE 123-bus system, which shows superior performance in terms of RT load supplied under different forecast error cases, outage duration scenarios, and against the traditionally used two-stage approach.

eess.SY↗

arXiv2020

A Load Switching Group based Feeder-level Microgrid Energy Management Algorithm for Service Restoration in Power Distribution System

This paper presents a load switching group based energy management system (LSG-EMS) for operating microgrids on a distribution feeder powered by one or multiple grid-forming distributed energy resources. Loads on a distribution feeder are divided into load switching groups that can be remotely switched on and off. The LSG-EMS algorithm, formulated as a mixed-integer linear programming (MILP) problem, has an objective function of maximizing the served loads while minimizing the total number of switching actions. A new set of topology constraints are developed for allowing multiple microgrids to be formed on the feeder and selecting the optimal supply path. Customer comfort is accounted for by maximizing the supply duration in the customer preferred service period and enforcing a minimum service duration. The proposed method is demonstrated on a modified IEEE 33-bus system using actual customer data. Simulation results show that the LSG-EMS successfully coordinates multiple grid-forming sources by selecting an optimal supply topology that maximizes the supply period of both the critical and noncritical loads while minimizing customer service interruptions in the service restoration process.

eess.SY↗

arXiv2020

ACDER: Augmented Curiosity-Driven Experience Replay

Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic manipulation tasks with high dimensional continuous state and action space. In this paper, we propose a novel method, called Augmented Curiosity-Driven Experience Replay (ACDER), which leverages (i) a new goal-oriented curiosity-driven exploration to encourage the agent to pursue novel and task-relevant states more purposefully and (ii) the dynamic initial states selection as an automatic exploratory curriculum to further improve the sample-efficiency. Our approach complements Hindsight Experience Replay (HER) by introducing a new way to pursue valuable states. Experiments conducted on four challenging robotic manipulation tasks with binary rewards, including Reach, Push, Pick&Place and Multi-step Push. The empirical results show that our proposed method significantly outperforms existing methods in the first three basic tasks and also achieves satisfactory performance in multi-step robotic task learning.

cs.RO↗

arXiv2020

A Regression-based Voltage Estimation Method for Distribution Volt-Var Control with Limited Data

This paper presents a regression-based method for estimating voltages and voltage sensitivities for volt-var control on distribution circuits with limited data. The estimator uses power flow results for representative load and PV output scenarios as training data. Using linear regressions on power flow results, the voltages at critical nodes are calculated online based on power measurements at the feeder head and at each PV plant. The voltage sensitivity to changes in reactive power injection by each PV plant is also found online using regressions on power flow results. The estimator thus provides the estimated critical voltages and their sensitivities to each possible control action. The estimator is tested in conjunction with a volt-var optimization on real, unbalanced rural distribution feeder. The optimal control actions and voltage results using the estimator are compared to the optimal results assuming full visibility of the distribution system. Results show that the estimator can estimate voltages and sensitivities with adequate accuracy for successful centralized volt-var control.

eess.SY↗

arXiv2020

Diesel Generator Model Parameterization for Microgrid Simulation Using Hybrid Box-Constrained Levenberg-Marquardt Algorithm

Existing generator parameterization methods, typically developed for large turbine generator units, are difficult to apply to small kW-level diesel generators in microgrid applications. This paper presents a model parameterization method that estimates a complete set of kW-level diesel generator parameters simultaneously using only load-step-change tests with limited measurement points. This method provides a more cost-efficient and robust approach to achieve high-fidelity modeling of diesel generators for microgrid dynamic simulation. A two-stage hybrid box-constrained Levenberg-Marquardt (H-BCLM) algorithm is developed to search the optimal parameter set given the parameter bounds. A heuristic algorithm, namely Generalized Opposition-based Learning Genetic Algorithm (GOL-GA), is applied to identify proper initial estimates at the first stage, followed by a modified Levenberg-Marquardt algorithm designed to fine tune the solution based on the first-stage result. The proposed method is validated against dynamic simulation of a diesel generator model and field measurements from a 16kW diesel generator unit.

eess.SY↗

arXiv2020

FeederGAN: Synthetic Feeder Generation via Deep Graph Adversarial Nets

This paper presents a novel, automated, generative adversarial networks (GAN) based synthetic feeder generation mechanism, abbreviated as FeederGAN. FeederGAN digests real feeder models represented by directed graphs via a deep learning framework powered by GAN and graph convolutional networks (GCN). Information of a distribution feeder circuit is extracted from its model input files so that the device connectivity is mapped onto the adjacency matrix and the device characteristics, such as circuit types (i.e., 3-phase, 2-phase, and 1-phase) and component attributes (e.g., length and current ratings), are mapped onto the attribute matrix. Then, Wasserstein distance is used to optimize the GAN and GCN is used to discriminate the generated graphs from the actual ones. A greedy method based on graph theory is developed to reconstruct the feeder using the generated adjacency and attribute matrices. Our results show that the GAN generated feeders resemble the actual feeder in both topology and attributes verified by visual inspection and by empirical statistics obtained from actual distribution feeders.

eess.SY↗

arXiv2020

Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild

Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are unavailable. Exploiting synthetic data is a very promising solution except for domain distribution mismatches between synthetic datasets and real datasets. To address the severe domain distribution mismatch, we propose a synthetic-to-real domain adaptation method for scene text detection, which transfers knowledge from synthetic data (source domain) to real data (target domain). In this paper, a text self-training (TST) method and adversarial text instance alignment (ATA) for domain adaptive scene text detection are introduced. ATA helps the network learn domain-invariant features by training a domain classifier in an adversarial manner. TST diminishes the adverse effects of false positives~(FPs) and false negatives~(FNs) from inaccurate pseudo-labels. Two components have positive effects on improving the performance of scene text detectors when adapting from synthetic-to-real scenes. We evaluate the proposed method by transferring from SynthText, VISD to ICDAR2015, ICDAR2013. The results demonstrate the effectiveness of the proposed method with up to 10% improvement, which has important exploration significance for domain adaptive scene text detection. Code is available at https://github.com/weijiawu/SyntoReal_STD

cs.CV↗

arXiv2020

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks

Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large number of use scenarios in real-world, remains a challenge because documents not only have textual features extracting from OCR systems but also have semantic visual features that are not fully exploited and play a critical role in KIE. Too little work has been devoted to efficiently make full use of both textual and visual features of the documents. In this paper, we introduce PICK, a framework that is effective and robust in handling complex documents layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features and global layout without ambiguity. Extensive experiments on real-world datasets have been conducted to show that our method outperforms baselines methods by significant margins. Our code is available at https://github.com/wenwenyu/PICK-pytorch.

cs.CV↗

arXiv2020

Impacts of PV Capacity Allocation Methods on Distribution Planning Studies

This paper presents a new method for assessing the amount of photovoltaics that can be accommodated on a distribution feeder before disrupting the normal operational conditions, commonly referred to hosting capacity. An optimal-capacity-based (OCB) PV allocation method is proposed to evaluate PV hosting capacity. We fist use load allocation method to allocate realistic load profiles to each load node down to each household. Instead of randomly assigning the installed capacity of PV to each household, the optimal size of PV for each house is first calculated based on the annual load profiles. Different PV allocation methods for hosting capacity calculation are first compared using the IEEE 123-bus system as a benchmark. An actual distribution feeder in North Carolina area is used to validate the results in realistic distribution systems. The simulation results show that the impact of PV capacity allocation methods on hosting capacity assessment is significant. We also investigate the zonal allocation method for weak zone identification to address the cluster phenomena in technology diffusion.

eess.SY↗

arXiv2020

Time Series Classification for Locating Forced Oscillation Sources

Forced oscillations are caused by sustained cyclic disturbances. This paper presents a machine learning (ML) based time-series classification method that uses the synchrophasor measurements to locate the sources of forced oscillations for fast disturbance removal. Sequential feature selection is used to identify the most informative measurements of each power plant so that multivariate time series (MTS) can be constructed. By training the Mahalanobis matrix, we measure and compare the distance between the MTSs. Templates for representing each class is constructed to reduce the size of training datasets and improve the online matching efficiency. Dynamic time warping (DTW) algorithm is used to align the out-of-sync MTSs to account for oscillation detection errors. The algorithm is validated on two test systems: the IEEE 39-bus system and the WECC 179-bus system. When a forced oscillation occurs, MTSs will be constructed by designated PMU measurements. Then, the MTSs will be classified by the trained classifiers, the class membership of which corresponds to the location of each oscillation source. Simulation results show that the proposed method can be used online to identify the forced oscillation sources with high accuracy. The robustness of the proposed algorithm in the presence of oscillation detection errors is also quantified.

eess.SY↗

arXiv2020

An Networked HIL Simulation System for Modeling Large-scale Power Systems

This paper presents a network hardware-in-the-loop (HIL) simulation system for modeling large-scale power systems. Researchers have developed many HIL test systems for power systems in recent years. Those test systems can model both microsecond-level dynamic responses of power electronic systems and millisecond-level transients of transmission and distribution grids. By integrating individual HIL test systems into a network of HIL test systems, we can create large-scale power grid digital twins with flexible structures at required modeling resolution that fits for a wide range of system operating conditions. This will not only significantly reduce the need for field tests when developing new technologies but also greatly shorten the model development cycle. In this paper, we present a networked OPAL-RT based HIL test system for developing transmission-distribution coordinative Volt-VAR regulation technologies as an example to illustrate system setups, communication requirements among different HIL simulation systems, and system connection mechanisms. Impacts of communication delays, information exchange cycles, and computing delays are illustrated. Simulation results show that the performance of a networked HIL test system is satisfactory.

eess.SY↗

arXiv2019

Non-local spin valve interferometer: Observation of superconducting spin current and Aharonov-Anandan's non-adiabatic geometric phase

An electron interferometer was designed and fabricated via a normal metal/insulator/ferromagnet non-local lateral spin valve with a ring-shaped normal metal/insulator spacer, and spin current interference was observed. A very high spin signal of 200 m$Ω$ was found in a device with 2 $μ$m injector-detector distance and magnetic field swept parallel to the plane. With a perpendicular magnetic field sweep, a Hanle effect measurement showed both spin precession and $h/e$ oscillation. Because of the non-adiabatic nature of the precessing spins at low fields as they traverse the normal metal ring, this is an experimental observation of Aharonov-Anandan's non-adiabatic geometric phase. In addition, our observation of identical spin resistance for normal and superconducting Aluminum is inconsistent with theoretical predictions based on the quasiparticle picture. To explain the superconducting spin current we suggest that spin triplet Cooper pairs may exist in thin films of Aluminum for direct spin injection.

cond-mat.mes-hall↗

arXiv2018

Air-Ground Integrated Mobile Edge Networks: Architecture, Challenges and Opportunities

The ever-increasing mobile data demands have posed significant challenges in the current radio access networks, while the emerging computation-heavy Internet of things (IoT) applications with varied requirements demand more flexibility and resilience from the cloud/edge computing architecture. In this article, to address the issues, we propose a novel air-ground integrated mobile edge network (AGMEN), where UAVs are flexibly deployed and scheduled, and assist the communication, caching, and computing of the edge network. In specific, we present the detailed architecture of AGMEN, and investigate the benefits and application scenarios of drone-cells, and UAV-assisted edge caching and computing. Furthermore, the challenging issues in AGMEN are discussed, and potential research directions are highlighted.

eess.SP↗

arXiv2018

A New Two-Dimensional Functional Material with Desirable Bandgap and Ultrahigh Carrier Mobility

Two-dimensional (2D) semiconductors with direct and modest bandgap and ultrahigh carrier mobility are highly desired functional materials for nanoelectronic applications. Herein, we predict that monolayer CaP3 is a new 2D functional material that possesses not only a direct bandgap of 1.15 eV (based on HSE06 computation), and also a very high electron mobility up to 19930 cm2 V-1 s-1, comparable to that of monolayer phosphorene. More remarkably, contrary to the bilayer phosphorene which possesses dramatically reduced carrier mobility compared to its monolayer counterpart, CaP3 bilayer possesses even higher electron mobility (22380 cm2 V-1 s-1) than its monolayer counterpart. The bandgap of 2D CaP3 can be tuned over a wide range from 1.15 to 0.37 eV (HSE06 values) through controlling the number of stacked CaP3 layers. Besides novel electronic properties, 2D CaP3 also exhibits optical absorption over the entire visible-light range. The combined novel electronic, charge mobility, and optical properties render 2D CaP3 an exciting functional material for future nanoelectronic and optoelectronic applications.

cond-mat.mtrl-sci↗