arXiv subjects

Hui Song

Publications and source records attributed to Hui Song.

24 records · Page 2Linked to original sources

arXiv2021

Multi-objective Scheduling of Electric Vehicle Charging/Discharging with Time of Use Tariff

The increased uptake of electric vehicles (EVs) leads to increased demand for electricity, and sometimes pressure on power grids. Uncoordinated charging of EVs may result in stress on distribution networks, and often some form of optimization is required in the charging process. Optimal coordinated charging is a multi-objective optimization problem (MOOP) in nature, with objective functions such as minimum price charging and minimum disruptions to the grid. In this manuscript, we propose a general multi-objective EV charging/discharging schedule (MOEVCS) framework, where the time of use (TOU) tariff is designed according to the load request at each time stamp. To obtain the optimal scheduling scheme and balance the competing benefits from different stakeholders, such as EV owners, EV charging stations (EVCS), and the grid operator, we design three competing objective functions including EV owner cost, EVCS profit, and the network impact. Moreover, we create four application scenarios with different charging request distributions over the investigated periods. Due to different types of decision variables in this MOOP, we develop a constraint mixed-variable multi-objective evolutionary algorithm (MVMOEA) to implement the proposed MOEVCS framework. Our results demonstrate the effectiveness of MOEVCS in making a balance between three competing objectives.

eess.SY↗

arXiv2021

Evolutionary Ensemble Learning for Multivariate Time Series Prediction

Multivariate time series (MTS) prediction plays a key role in many fields such as finance, energy and transport, where each individual time series corresponds to the data collected from a certain data source, so-called channel. A typical pipeline of building an MTS prediction model (PM) consists of selecting a subset of channels among all available ones, extracting features from the selected channels, and building a PM based on the extracted features, where each component involves certain optimization tasks, i.e., selection of channels, feature extraction (FE) methods, and PMs as well as configuration of the selected FE method and PM. Accordingly, pursuing the best prediction performance corresponds to optimizing the pipeline by solving all of its involved optimization problems. This is a non-trivial task due to the vastness of the solution space. Different from most of the existing works which target at optimizing certain components of the pipeline, we propose a novel evolutionary ensemble learning framework to optimize the entire pipeline in a holistic manner. In this framework, a specific pipeline is encoded as a candidate solution and a multi-objective evolutionary algorithm is applied under different population sizes to produce multiple Pareto optimal sets (POSs). Finally, selective ensemble learning is designed to choose the optimal subset of solutions from the POSs and combine them to yield final prediction by using greedy sequential selection and least square methods. We implement the proposed framework and evaluate our implementation on two real-world applications, i.e., electricity consumption prediction and air quality prediction. The performance comparison with state-of-the-art techniques demonstrates the superiority of the proposed approach.

cs.NE↗

arXiv2020

On Loss Functions and Recurrency Training for GAN-based Speech Enhancement Systems

Recent work has shown that it is feasible to use generative adversarial networks (GANs) for speech enhancement, however, these approaches have not been compared to state-of-the-art (SOTA) non GAN-based approaches. Additionally, many loss functions have been proposed for GAN-based approaches, but they have not been adequately compared. In this study, we propose novel convolutional recurrent GAN (CRGAN) architectures for speech enhancement. Multiple loss functions are adopted to enable direct comparisons to other GAN-based systems. The benefits of including recurrent layers are also explored. Our results show that the proposed CRGAN model outperforms the SOTA GAN-based models using the same loss functions and it outperforms other non-GAN based systems, indicating the benefits of using a GAN for speech enhancement. Overall, the CRGAN model that combines an objective metric loss function with the mean squared error (MSE) provides the best performance over comparison approaches across many evaluation metrics.

eess.AS↗

arXiv2019

DELTA: A DEep learning based Language Technology plAtform

In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech processing problems. It integrates most popular neural network models for training as well as comprehensive deployment tools for production. DELTA aims to provide easy and fast experiences for using, deploying, and developing natural language processing and speech models for both academia and industry use cases. We demonstrate the reliable performance with DELTA on several natural language processing and speech tasks, including text classification, named entity recognition, natural language inference, speech recognition, speaker verification, etc. DELTA has been used for developing several state-of-the-art algorithms for publications and delivering real production to serve millions of users.

cs.CL↗

arXiv2013

Automated Small-Cell Deployment for Heterogeneous Cellular Networks

Optimizing the cellular network's cell locations is one of the most fundamental problems of network design. The general objective is to provide the desired Quality-of-Service (QoS) with the minimum system cost. In order to meet a growing appetite for mobile data services, heterogeneous networks have been proposed as a cost- and energy-efficient method of improving local spectral efficiency. Whilst unarticulated cell deployments can lead to localized improvements, there is a significant risk posed to network-wide performance due to the additional interference. The first part of the paper focuses on state-of-the-art modelling and radio-planning methods based on stochastic geometry and Monte-Carlo simulations, and the emerging automatic deployment prediction technique for low-power nodes (LPNs) in heterogeneous networks. The technique advises a LPN where it should be deployed, given certain knowledge of the network. The second part of the paper focuses on algorithms that utilize interference and physical environment knowledge to assist LPN deployment. The proposed techniques can not only improve network performance, but also reduce radio-planning complexity, capital expenditure, and energy consumption of the cellular network. The theoretical work is supported by numerical results from system-level simulations that employ real cellular network data and physical environments.

cs.NI↗

arXiv2007

Levitation and percolation in quantum Hall systems with correlated disorder

We investigate the integer quantum Hall system in a two dimensional lattice model with spatially correlated disorder by using the efficient method to calculate the Chern number proposed by Fukui \textit{et al}. Distribution of charge density indicates that the extended states at the center of each Landau band have percolating current paths, which are topologically equivalent to the edge states that exist in a system with boundaries. As increasing the strength of disorder, floating feature is observed in an averaged Hall conductance as a function of filling factor. Its relation to the observed experiments is also discussed.

cond-mat.mes-hall↗