arXiv subjects

Yongfeng Li

Publications and source records attributed to Yongfeng Li.

12 recordsLinked to original sources

arXiv2025

Applying Ensemble Models based on Graph Neural Network and Reinforcement Learning for Wind Power Forecasting

Accurately predicting the wind power output of a wind farm across various time scales utilizing Wind Power Forecasting (WPF) is a critical issue in wind power trading and utilization. The WPF problem remains unresolved due to numerous influencing variables, such as wind speed, temperature, latitude, and longitude. Furthermore, achieving high prediction accuracy is crucial for maintaining electric grid stability and ensuring supply security. In this paper, we model all wind turbines within a wind farm as graph nodes in a graph built by their geographical locations. Accordingly, we propose an ensemble model based on graph neural networks and reinforcement learning (EMGRL) for WPF. Our approach includes: (1) applying graph neural networks to capture the time-series data from neighboring wind farms relevant to the target wind farm; (2) establishing a general state embedding that integrates the target wind farm's data with the historical performance of base models on the target wind farm; (3) ensembling and leveraging the advantages of all base models through an actor-critic reinforcement learning framework for WPF.

cs.LG↗

arXiv2022

Completely Spin-Decoupled Geometric Phase of Metasurface

Metasurfaces have provided unprecedented degree of freedom (DOF) in manipulating electromagnetic (EM) waves. Geometric phase can be readily obtained by rotating the meta-atom of metasurfaces. Nevertheless, such geometric phases are usually spin-coupled, with the same magnitude but opposite signs for left_ and right_handed circularly polarized (LCP,RCP) waves. To achieve independent control on LCP and RCP waves, it is crucial to obtain spin-decoupled geometric phases. In this paper, we propose to obtain completely spin-decoupled geometric phases by engineering surface current paths on meta-atoms. Based on the rotational Doppler effect, the rotation manner is firstly analyzed and it is found that the essence of generating geometric phase lies in the rotation of surface current paths on meta-atoms. Since the induced surface currents paths under LCP and RCP waves always start oppositely and are mirror-symmetrical with each other, it is natural that the geometric phases be with the same magnitude and opposite signs when the meta-atoms are rotated. To obtain spin-decoupled geometric phases, the start point of induced surface current under one spin should be rotated by an angle while that under the other spin by another different angle. In this way, LCP and RCP waves can acquire different geometric phase changes and spin-decoupled geometric phase can be imparted by metasurfaces. Proof-of-principle prototypes were designed, fabricated and measured. Both the simulation and experiment results verify spin-decoupled geometric phases. This work provides a robust means of obtaining spin-dependent geometric phase and will further adds up to the metasurface DOF in manipulating EM waves.

physics.class-ph↗

arXiv2021

A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning

In this paper, we consider the linear programming (LP) formulation for deep reinforcement learning. The number of the constraints depends on the size of state and action spaces, which makes the problem intractable in large or continuous environments. The general augmented Lagrangian method suffers the double-sampling obstacle in solving the LP. Namely, the conditional expectations originated from the constraint functions and the quadratic penalties in the augmented Lagrangian function impose difficulties in sampling and evaluation. Motivated from the updates of the multipliers, we overcome the obstacles in minimizing the augmented Lagrangian function by replacing the intractable conditional expectations with the multipliers. Therefore, a deep parameterized augment Lagrangian method is proposed. Furthermore, the replacement provides a promising breakthrough to integrate the two steps in the augmented Lagrangian method into a single constrained problem. A general theoretical analysis shows that the solutions generated from a sequence of the constrained optimizations converge to the optimal solution of the LP if the error is controlled properly. A theoretical analysis on the quadratic penalty algorithm under neural tangent kernel setting shows the residual can be arbitrarily small if the parameter in network and optimization algorithm is chosen suitably. Preliminary experiments illustrate that our method is competitive to other state-of-the-art algorithms.

math.OC↗

arXiv2019

A Stochastic Trust-Region Framework for Policy Optimization

In this paper, we study a few challenging theoretical and numerical issues on the well known trust region policy optimization for deep reinforcement learning. The goal is to find a policy that maximizes the total expected reward when the agent acts according to the policy. The trust region subproblem is constructed with a surrogate function coherent to the total expected reward and a general distance constraint around the latest policy. We solve the subproblem using a preconditioned stochastic gradient method with a line search scheme to ensure that each step promotes the model function and stays in the trust region. To overcome the bias caused by sampling to the function estimations under the random settings, we add the empirical standard deviation of the total expected reward to the predicted increase in a ratio in order to update the trust region radius and decide whether the trial point is accepted. Moreover, for a Gaussian policy which is commonly used for continuous action space, the maximization with respect to the mean and covariance is performed separately to control the entropy loss. Our theoretical analysis shows that the deterministic version of the proposed algorithm tends to generate a monotonic improvement of the total expected reward and the global convergence is guaranteed under moderate assumptions. Comparisons with the state-of-the-art methods demonstrate the effectiveness and robustness of our method over robotic controls and game playings from OpenAI Gym.

math.OC↗

arXiv2019

Low-rank Matrix Optimization Using Polynomial-filtered Subspace Extraction

In this paper, we study first-order methods on a large variety of low-rank matrix optimization problems, whose solutions only live in a low dimensional eigenspace. Traditional first-order methods depend on the eigenvalue decomposition at each iteration which takes most of the computation time. In order to reduce the cost, we propose an inexact algorithm framework based on a polynomial subspace extraction. The idea is to use an additional polynomial-filtered iteration to extract an approximated eigenspace, and project the iteration matrix on this subspace, followed by an optimization update. The accuracy of the extracted subspace can be controlled by the degree of the polynomial filters. This kind of subspace extraction also enjoys the warm start property: the subspace of the current iteration is refined from the previous one. Then this framework is instantiated into two algorithms: the polynomial-filtered proximal gradient method and the polynomial-filtered alternating direction method of multipliers. We give a theoretical guarantee to the two algorithms that the polynomial degree is not necessarily very large. They share the same convergence speed as the corresponding original methods if the polynomial degree grows with an order $Ω(\log k)$ at the $k$-th iteration. If the warm-start property is considered, the degree can be reduced to a constant, independent of the iteration $k$. Preliminary numerical experiments on several low-rank matrix optimization problems show that the polynomial filtered algorithms usually provide multi-fold speedups.

math.OC↗

arXiv2017

A Semi-smooth Newton Method for Solving Semidefinite Programs in Electronic Structure Calculations

The ground state energy of a many-electron system can be approximated by an variational approach in which the total energy of the system is minimized with respect to one and two-body reduced density matrices (RDM) instead of many-electron wavefunctions. This problem can be formulated as a semidefinite programming problem. Due the large size of the problem, the well-known interior point method can only be used to tackle problems with a few atoms. First-order methods such as the the alternating direction method of multipliers (ADMM) have much lower computational cost per iteration. However, their convergence can be slow, especially for obtaining highly accurate approximations. In this paper, we present a practical and efficient second-order semi-smooth Newton type method for solving the SDP formulation of the energy minimization problem. We discuss a number of techniques that can be used to improve the computational efficiency of the method and achieve global convergence. Extensive numerical experiments show that our approach is competitive to the state-of-the-art methods in terms of both accuracy and speed.

math.OC↗

arXiv2016

A Regularized Semi-Smooth Newton Method With Projection Steps for Composite Convex Programs

The goal of this paper is to study approaches to bridge the gap between first-order and second-order type methods for composite convex programs. Our key observations are: i) Many well-known operator splitting methods, such as forward-backward splitting (FBS) and Douglas-Rachford splitting (DRS), actually define a fixed-point mapping; ii) The optimal solutions of the composite convex program and the solutions of a system of nonlinear equations derived from the fixed-point mapping are equivalent. Solving this kind of system of nonlinear equations enables us to develop second-order type methods. Although these nonlinear equations may be non-differentiable, they are often semi-smooth and their generalized Jacobian matrix is positive semidefinite due to monotonicity. By combining with a regularization approach and a known hyperplane projection technique, we propose an adaptive semi-smooth Newton method and establish its convergence to global optimality. Preliminary numerical results on $\ell_1$-minimization problems demonstrate that our second-order type algorithms are able to achieve superlinear or quadratic convergence.

math.OC↗

arXiv2016

Circulator based on spoof surface plasmon polaritons

Circulators based on spoof surface plasmon polaritons are designed and analyzed. In the letter, we use blade structure to realize the propagation of SSPPs wave and a matching transition is used to feed energy from coplanar waveguide to the SSPPs. And the circulator shows good nonreciprocal transmission characteristics. The simulation results indicate that in the frequency band from 5 to 6.6 GHz, the isolation degree and return loss basically reaches 15dB and the insertion loss is less than 0.5dB. Moreover, the use of confinement electromagnetic waves can decrease the size of the ferrite and show a broadband characteristic.

cond-mat.other↗

arXiv2015

A review of plasma liquid interactions for nanomaterial synthesis

In this review, we have summarized the recent advances and present conditions of the nanomaterials synthesis from the plasma-liquid interactions. A theoretical analysis for the nanomaterials synthesis process is presented by analyzing the experimental data. Besides the theoretical analysis, the practical applications in several nanomaterials syntheses of the the plasma-liquid interactions are also presented.

physics.plasm-ph↗

arXiv2014

Three-Dimensional Nanoporous Graphene Substrate for Surface-Enhanced Raman Scattering

We synthesized three-dimensional nanoporous graphene films by a chemical vapor deposition method with nanoporous copper as a catalytic substrate. The resulting nanoporous graphene has the same average pore size as the underlying copper substrate. Our surface-enhanced Raman scattering (SERS) investigation indicates that the nanoporosity of graphene significantly improves the SERS efficiency of graphene as a substrate as compared to planar graphene substrates.

cond-mat.mtrl-sci↗

arXiv2014

Controllable growth of 1-7 layers of graphene by chemical vapour deposition

We report that graphene films with thickness ranging from 1 to 7 layers can be controllably synthesized on the surface of polycrystalline copper by a chemical vapour deposition method. The number of layers of graphene is controlled precisely by regulating the flow ratio of CH4 and H2, the reaction pressure, the temperature and the reaction time. The synthesized graphene films were characterized by scanning electron microscopy, transmission electron microscopy, selected area electron diffraction, X-ray diffraction and Raman spectroscopy. In addition, the graphene films transferred from copper to other substrates are found to have a good optical transmittance that makes them suitable for transparent conductive materials.

cond-mat.mtrl-sci↗

arXiv2014

Controllable synthesis of single-, double- and triple-walled carbon nanotubes from asphalt

Single-, double- and triple-walled carbon nanotubes (SWNTs, DWNTs and TWNTs) have been controlla- bly synthesized by an arc discharge method using asphalt as carbon source. The morphology and struc- ture of three kinds of products synthesized with Fe as catalyst were characterized by scanning electron microscopy (SEM), high-resolution transmission electron microscopy (HRTEM), Raman spectroscopy and energy dispersive X-ray spectroscopy (EDX). It was found that different buffer gases strongly affect the number layers in the synthesized nanotubes. In the He gas atmosphere only SWNTs were found to be synthesized by arc discharge in contrast to the case in Ar gas atmosphere in which only TWNTs were formed. In N2 atmosphere both SWNTs and DWNTs were synthesized. Our findings indicate that asphalt is a suitable industrial carbon source for the growth of different type nanotubes.

cond-mat.mtrl-sci↗