arXiv subjects

Zhiwei Wang

Publications and source records attributed to Zhiwei Wang.

At least 235 records · Page 13Linked to original sources

arXiv2019

Automatic Short Answer Grading via Multiway Attention Networks

Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads. However, ASAG is a very challenging task due to two reasons: (1) student answers are made up of free text which requires a deep semantic understanding; and (2) the questions are usually open-ended and across many domains in K-12 scenarios. In this paper, we propose a generalized end-to-end ASAG learning framework which aims to (1) autonomously extract linguistic information from both student and reference answers; and (2) accurately model the semantic relations between free-text student and reference answers in open-ended domain. The proposed ASAG model is evaluated on a large real-world K-12 dataset and can outperform the state-of-the-art baselines in terms of various evaluation metrics.

cs.AI↗

arXiv2019

Deep Knowledge Tracing with Side Information

Monitoring student knowledge states or skill acquisition levels known as knowledge tracing, is a fundamental part of intelligent tutoring systems. Despite its inherent challenges, recent deep neural networks based knowledge tracing models have achieved great success, which is largely from models' ability to learn sequential dependencies of questions in student exercise data. However, in addition to sequential information, questions inherently exhibit side relations, which can enrich our understandings about student knowledge states and has great potentials to advance knowledge tracing. Thus, in this paper, we exploit side relations to improve knowledge tracing and design a novel framework DTKS. The experimental results on real education data validate the effectiveness of the proposed framework and demonstrate the importance of side information in knowledge tracing.

cs.AI↗

arXiv2019

A Deep Reinforcement Learning Based Approach for Optimal Active Power Dispatch

The stochastic and dynamic nature of renewable energy sources and power electronic devices are creating unique challenges for modern power systems. One such challenge is that the conventional mathematical systems models-based optimal active power dispatch (OAPD) method is limited in its ability to handle uncertainties caused by renewables and other system contingencies. In this paper, a deep reinforcement learning-based (DRL) method is presented to provide a near-optimal solution to the OAPD problem without system modeling. The DRL agent undergoes offline training, based on which, it is able to obtain the OAPD points under unseen scenarios, e.g., different load patterns. The DRL-based OAPD method is tested on the IEEE 14-bus system, thereby validating its feasibility to solve the OAPD problem. Its utility is further confirmed in that it can be leveraged as a key component for solving future model-free AC-OPF problems.

math.OC↗

arXiv2019

Generalized Anderson's theorem for superconductors derived from topological insulators

A well-known result in unconventional superconductivity is the fragility of nodal superconductors against nonmagnetic impurities. Despite this common wisdom, Bi$_2$Se$_3$-based topological superconductors have recently displayed unusual robustness against disorder. Here we provide a theoretical framework which naturally explains what protects Cooper pairs from strong scattering in complex superconductors. Our analysis is based on the concept of superconducting fitness and generalizes the famous Anderson's theorem into superconductors having multiple internal degrees of freedom. For concreteness, we report on the extreme example of the Cu$_x$(PbSe)$_5$(Bi$_2$Se$_3$)$_6$ superconductor, where thermal conductivity measurements down to 50 mK not only give unambiguous evidence for the existence of nodes, but also reveal that the energy scale corresponding to the scattering rate is orders of magnitude larger than the superconducting energy gap. This provides a most spectacular case of the generalized Anderson's theorem protecting a nodal superconductor.

cond-mat.supr-con↗

arXiv2019

Recommender Systems with Heterogeneous Side Information

In modern recommender systems, both users and items are associated with rich side information, which can help understand users and items. Such information is typically heterogeneous and can be roughly categorized into flat and hierarchical side information. While side information has been proved to be valuable, the majority of existing systems have exploited either only flat side information or only hierarchical side information due to the challenges brought by the heterogeneity. In this paper, we investigate the problem of exploiting heterogeneous side information for recommendations. Specifically, we propose a novel framework jointly captures flat and hierarchical side information with mathematical coherence. We demonstrate the effectiveness of the proposed framework via extensive experiments on various real-world datasets. Empirical results show that our approach is able to lead a significant performance gain over the state-of-the-art methods.

cs.IR↗

arXiv2019

R-Transformer: Recurrent Neural Network Enhanced Transformer

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation procedure. Therefore, many non-recurrent sequence models that are built on convolution and attention operations have been proposed recently. Notably, models with multi-head attention such as Transformer have demonstrated extreme effectiveness in capturing long-term dependencies in a variety of sequence modeling tasks. Despite their success, however, these models lack necessary components to model local structures in sequences and heavily rely on position embeddings that have limited effects and require a considerable amount of design efforts. In this paper, we propose the R-Transformer which enjoys the advantages of both RNNs and the multi-head attention mechanism while avoids their respective drawbacks. The proposed model can effectively capture both local structures and global long-term dependencies in sequences without any use of position embeddings. We evaluate R-Transformer through extensive experiments with data from a wide range of domains and the empirical results show that R-Transformer outperforms the state-of-the-art methods by a large margin in most of the tasks. We have made the code publicly available at \url{https://github.com/DSE-MSU/R-transformer}.

cs.LG↗

arXiv2019

Evidence for bulk nodal loops and universality of Dirac-node arc surface states in ZrGeXc (Xc = S, Se, Te)

We have performed angle-resolved photoemission spectroscopy (ARPES) on layered ternary compounds ZrGeXc (Xc = S, Se, and Te) with square Ge lattices. ARPES measurements with bulk-sensitive soft-x-ray photons revealed a quasi-two-dimensional bulk-band structure with the bulk nodal loops protected by glide mirror symmetry of the crystal lattice. Moreover, high-resolution ARPES measurements near the Fermi level with vacuum-ultraviolet photons combined with first-principles band-structure calculations elucidated a Dirac-node-arc surface state traversing a tiny spin-orbit gap associated with the nodal loops. We found that this surface state commonly exists in ZrGeXc despite the difference in the shape of nodal loops. The present results suggest that the spin-orbit coupling and the multiple nodal loops cooperatively play a key role in creating the exotic Dirac-node-arc surface states in this class of topological line-node semimetals.

cond-mat.mes-hall↗

arXiv2019

Asymptotic estimate of cohomology groups valued in pseudo-effective line bundles

In this paper, we study questions of Demailly and Matsumura on the asymptotic behavior of dimensions of cohomology groups for high tensor powers of (nef) pseudo-effective line bundles over non-necessarily projective algebraic manifolds. By generalizing Siu's $\partial\overline{\partial}$-formula and Berndtsson's eigenvalue estimate of $\overline{\partial}$-Laplacian and combining Bonavero's technique, we obtain the following result: given a holomorphic pseudo-effective line bundle $(L, h_L)$ on a compact Hermitian manifold $(X,ω)$, if $h_L$ is a singular metric with algebraic singularities, then $\dim H^{q}(X,L^k\otimes E\otimes \mathcal{I}(h_L^{k}))\leq Ck^{n-q}$ for $k$ large, with $E$ an arbitrary holomorphic vector bundle. As applications, we obtain partial solutions to the questions of Demailly and Matsumura.

math.CV↗

arXiv2019

Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learning

Modern power grids are experiencing grand challenges caused by the stochastic and dynamic nature of growing renewable energy and demand response. Traditional theoretical assumptions and operational rules may be violated, which are difficult to be adapted by existing control systems due to the lack of computational power and accurate grid models for use in real time, leading to growing concerns in the secure and economic operation of the power grid. Existing operational control actions are typically determined offline, which are less optimized. This paper presents a novel paradigm, Grid Mind, for autonomous grid operational controls using deep reinforcement learning. The proposed AI agent for voltage control can learn its control policy through interactions with massive offline simulations, and adapts its behavior to new changes including not only load/generation variations but also topological changes. A properly trained agent is tested on the IEEE 14-bus system with tens of thousands of scenarios, and promising performance is demonstrated in applying autonomous voltage controls for secure grid operation.

eess.SY↗

arXiv2019

A Neural-Network-Based Optimal Control of Ultra-Capacitors with System Uncertainties

In this paper, a neural-network (NN)-based online optimal control method (NN-OPT) is proposed for ultra-capacitors (UCs) energy storage system (ESS) in hybrid AC/DC microgrids involving multiple distributed generations (e.g., Photovoltaic (PV) system, battery storage, diesel generator). Conventional control strategies usually produce large disturbances to buses during charging and discharging (C&D) processes of UCs, which significantly degrades the power quality and system performance, especially under fast C&D modes. Therefore, the optimal control theory is adopted to optimize the C&D profile as well as to suppress the disturbances caused by UCs implementation. Specifically, an NN-based intelligent algorithm is developed to learn the optimal control policy for bidirectional-converter-interfaced UCs. The inaccuracies of system modeling are also considered in the control design. Since the designed NN-OPT method is decentralized that only requires the local measurements, plug & play of UCs can be easily realized with minimal communication efforts. In addition, the PV system is under the maximum power point tracking (MPPT) control to extract the maximum benefit. Both islanded and grid-tied modes are considered during the controller design. Extensive case studies have been conducted to evaluate the effectiveness of the proposed method.

math.OC↗

arXiv2019

A High-Performance Energy Management System based on Evolving Graph

As the fast growth and large integration of distributed generation, renewable energy resource, energy storage system and load response, the modern power system operation becomes much more complicated with increasing uncertainties and frequent changes. Increased operation risks are introduced to the existing commercial Energy Management System (EMS), due to its limited computational capability. In this paper, a high-performance EMS analysis framework based on the evolving graph is developed. A power grid is first modeled as an evolving graph and then the power system dynamic analysis applications, like network topology processing (NTP), state estimation (SE), power flow (PF), and contingency analysis (CA), are efficiently implemented on the system evolving graph to build a high-performance EMS analysis framework. Its computation performance is field tested using a 2749-bus power system in Sichuan, China. The results illustrate that the proposed EMS remarkably speeds up the computation performance and reaches the goal of real-time power system analysis.

cs.DC↗

arXiv2019

Graph Computing based Fast Screening in Contingency Analysis

During last decades, contingency analysis has been facing challenges from significant load demand increase and high penetrations of intermittent renewable energy, fluctuant responsive loads and non-linear power electronic interfaces. It requires an advanced approach for high-performance contingency analysis as a safeguard of the power system operation. In this paper, a graph-based method is employed for N-1 contingency analysis (CA) fast screening. At first, bi-directional breadth-first search (BFS) is proposed and adopted on graph model to detect the potential shedding component in contingency analysis. It implements hierarchical parallelism of the graph traverse and speedup its process. Then, the idea of evolving graph is introduced in this paper to improve computation performance. For each contingency scenario, N-1 contingency graph quickly derives from system graph in basic status, and parallelly analyzes each contingency scenario using graph computing. The efficiency and effectiveness of the proposed approach have been tested and verified by IEEE 118-bus system and a practical case SC 2645-bus system.

cs.DC↗

arXiv2019

Adaptive Robust Energy Management Strategy for Campus-Based Commercial Buildings Considering Comprehensive Comfort Levels

Neglecting consumers' comfort always leads to failure or slow-response to demand response request. In this paper, we propose several comprehensive comfort level models for various appliances in campus-based commercial buildings (CBs). The objective of the proposed system is to minimize O\&M costs of campus-based CBs and maximize various comfort levels simultaneously under the worst-case scenarios. Adaptive robust optimization (ARO) is leveraged to handle various uncertainties within the proposed system: (i) demand response signals sending from the distribution system operator (DSO); (ii) arrival state-of-charge (SoC) conditions of plug-in electric vehicles (PEVs); (iii) power outputs of renewable energy sources (RESs); and (iv) load demand of other appliances. Benders decomposition, such as column-and-constraint generation (C\&CG) algorithm, is used to solve the reformulated NP-hard min-max problem. Extensive simulation results demonstrate the effectiveness of the proposed optimal energy management strategy for campus-based CBs in both minimizing O\&M costs and maximizing comprehensive comfort levels.

math.OC↗

arXiv2019

Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis

Short-term load forecasting (STLF) is essential for the reliable and economic operation of power systems. Though many STLF methods were proposed over the past decades, most of them focused on loads at high aggregation levels only. Thus, low-aggregation load forecast still requires further research and development. Compared with the substation or city level loads, individual loads are typically more volatile and much more challenging to forecast. To further address this issue, this paper first discusses the characteristics of small-and-medium enterprise (SME) and residential loads at different aggregation levels and quantifies their predictability with approximate entropy. Various STLF techniques, from the conventional linear regression to state-of-the-art deep learning, are implemented for a detailed comparative analysis to verify the forecasting performances as well as the predictability using an Irish smart meter dataset. In addition, the paper also investigates how using data processing improves individual-level residential load forecasting with low predictability. Effectiveness of the discussed method is validated with numerical results.

cs.LG↗

arXiv2019

Probabilistic Load Forecasting via Point Forecast Feature Integration

Short-term load forecasting is a critical element of power systems energy management systems. In recent years, probabilistic load forecasting (PLF) has gained increased attention for its ability to provide uncertainty information that helps to improve the reliability and economics of system operation performances. This paper proposes a two-stage probabilistic load forecasting framework by integrating point forecast as a key probabilistic forecasting feature into PLF. In the first stage, all related features are utilized to train a point forecast model and also obtain the feature importance. In the second stage the forecasting model is trained, taking into consideration point forecast features, as well as selected feature subsets. During the testing period of the forecast model, the final probabilistic load forecast results are leveraged to obtain both point forecasting and probabilistic forecasting. Numerical results obtained from ISO New England demand data demonstrate the effectiveness of the proposed approach in the hour-ahead load forecasting, which uses the gradient boosting regression for the point forecasting and quantile regression neural networks for the probabilistic forecasting.

cs.LG↗

arXiv2019

Bayesian Estimation Based Parameter Estimation for Composite Load

Accurate identification of parameters of load models is essential in power system computations, including simulation, prediction, and stability and reliability analysis. Conventional point estimation based composite load modeling approaches suffer from disturbances and noises and provide limited information of the system dynamics. In this work, a statistic (Bayesian Estimation) based distribution estimation approach is proposed for both static (ZIP) and dynamic (Induction Motor) load modeling. When dealing with multiple parameters, Gibbs sampling method is employed. In each iteration, the proposal samples each parameter while keeps others fixed. The proposed method provides a distribution estimation of load models coefficients and is robust to measurement errors.

eess.SY↗

arXiv2019

Adaptive Online Learning with Momentum for Contingency-based Voltage Stability Assessment

Voltage stability refers to the ability of a power system to maintain acceptable voltages among all buses under normal operating conditions and after a disturbance. In this paper, a measurement-based voltage stability assessment (VSA) framework using online deep learning is developed. Since the topology changes induced by transmission contingencies may significantly reduce the voltage stability margin, different network topologies under different operating conditions are involved in our training dataset. To achieve high accuracy in the training process, a gradient-based adaptive learning algorithms is adopted. Numerical results based on the NETS-NYPS 68-bus system demonstrate the effectiveness of the proposed VSA approach. Moreover, with the proximal function modified adaptively, the adaptive algorithm with momentum outperforms traditional nonadaptive algorithms whose learning rate is constant.

eess.SY↗

arXiv2019

Submodular Load Clustering with Robust Principal Component Analysis

Traditional load analysis is facing challenges with the new electricity usage patterns due to demand response as well as increasing deployment of distributed generations, including photovoltaics (PV), electric vehicles (EV), and energy storage systems (ESS). At the transmission system, despite of irregular load behaviors at different areas, highly aggregated load shapes still share similar characteristics. Load clustering is to discover such intrinsic patterns and provide useful information to other load applications, such as load forecasting and load modeling. This paper proposes an efficient submodular load clustering method for transmission-level load areas. Robust principal component analysis (R-PCA) firstly decomposes the annual load profiles into low-rank components and sparse components to extract key features. A novel submodular cluster center selection technique is then applied to determine the optimal cluster centers through constructed similarity graph. Following the selection results, load areas are efficiently assigned to different clusters for further load analysis and applications. Numerical results obtained from PJM load demonstrate the effectiveness of the proposed approach.

cs.LG↗