arXiv subjects

Wenbo Chen

Publications and source records attributed to Wenbo Chen.

At least 37 records · Page 2Linked to original sources

arXiv2024

Compact Optimality Verification for Optimization Proxies

Recent years have witnessed increasing interest in optimization proxies, i.e., machine learning models that approximate the input-output mapping of parametric optimization problems and return near-optimal feasible solutions. Following recent work by (Nellikkath & Chatzivasileiadis, 2021), this paper reconsiders the optimality verification problem for optimization proxies, i.e., the determination of the worst-case optimality gap over the instance distribution. The paper proposes a compact formulation for optimality verification and a gradient-based primal heuristic that brings substantial computational benefits to the original formulation. The compact formulation is also more general and applies to non-convex optimization problems. The benefits of the compact formulation are demonstrated on large-scale DC Optimal Power Flow and knapsack problems.

math.OC↗

arXiv2024

Optimization-based Learning for Dynamic Load Planning in Trucking Service Networks

The load planning problem is a critical challenge in service network design for parcel carriers: it decides how many trailers to assign for dispatch over time between pairs of terminals. Another key challenge is to determine a flow plan, which specifies how parcel volumes are assigned to planned loads. This paper considers the Outbound Load Planning Problem (OLPP) that considers flow and load planning challenges jointly in order to adjust loads and flows as the demand forecast changes over time before the day of operations in a terminal. The paper aims at developing a decision-support tool to inform planners making these decisions at terminals across the network. The paper formulates the OLPP as a mixed-integer programming model and shows that it admits a large number of symmetries in a network where each commodity can be routed through primary and alternate terminals. As a result, an optimization solver may return fundamentally different solutions to closely related problems, confusing planners and reducing trust in optimization. To remedy this limitation, this paper proposes a lexicographical optimization approach that eliminates those symmetries by generating optimal solutions staying close to a reference plan. Moreover, this paper designs an optimization proxy that addresses the computational challenges of the optimization model. The optimization proxy combines a machine-learning model and a repair procedure to find near-optimal solutions that satisfy real-time constraints imposed by planners in the loop. An extensive computational study on industrial instances shows that the optimization proxy is orders of magnitude faster for generating solutions that are consistent with each other. The proposed approach also demonstrates the benefits of the OLPP for load consolidation and the significant savings obtained from combining machine learning and optimization.

cs.AI↗

arXiv2023

Real-Time Risk Analysis with Optimization Proxies

The increasing penetration of renewable generation and distributed energy resources requires new operating practices for power systems, wherein risk is explicitly quantified and managed. However, traditional risk-assessment frameworks are not fast enough for real-time operations, because they require numerous simulations, each of which requires solving multiple economic dispatch problems sequentially. The paper addresses this computational challenge by proposing proxy-based risk assessment, wherein optimization proxies are trained to learn the input-to-output mapping of an economic dispatch optimization solver. Once trained, the proxies make predictions in milliseconds, thereby enabling real-time risk assessment. The paper leverages self-supervised learning and end-to-end-feasible architecture to achieve high-quality sequential predictions. Numerical experiments on large systems demonstrate the scalability and accuracy of the proposed approach.

math.OC↗

arXiv2023

End-to-End Feasible Optimization Proxies for Large-Scale Economic Dispatch

The paper proposes a novel End-to-End Learning and Repair (E2ELR) architecture for training optimization proxies for economic dispatch problems. E2ELR combines deep neural networks with closed-form, differentiable repair layers, thereby integrating learning and feasibility in an end-to-end fashion. E2ELR is also trained with self-supervised learning, removing the need for labeled data and the solving of numerous optimization problems offline. E2ELR is evaluated on industry-size power grids with tens of thousands of buses using an economic dispatch that co-optimizes energy and reserves. The results demonstrate that the self-supervised E2ELR achieves state-of-the-art performance, with optimality gaps that outperform other baselines by at least an order of magnitude.

math.OC↗

arXiv2023

Confidence-Aware Graph Neural Networks for Learning Reliability Assessment Commitments

Reliability Assessment Commitment (RAC) Optimization is increasingly important in grid operations due to larger shares of renewable generations in the generation mix and increased prediction errors. Independent System Operators (ISOs) also aim at using finer time granularities, longer time horizons, and possibly stochastic formulations for additional economic and reliability benefits. The goal of this paper is to address the computational challenges arising in extending the scope of RAC formulations. It presents RACLearn that (1) uses a Graph Neural Network (GNN) based architecture to predict generator commitments and active line constraints, (2) associates a confidence value to each commitment prediction, (3) selects a subset of the high-confidence predictions, which are (4) repaired for feasibility, and (5) seeds a state-of-the-art optimization algorithm with feasible predictions and active constraints. Experimental results on exact RAC formulations used by the Midcontinent Independent System Operator (MISO) and an actual transmission network (8965 transmission lines, 6708 buses, 1890 generators, and 6262 load units) show that the RACLearn framework can speed up RAC optimization by factors ranging from 2 to 4 with negligible loss in solution quality.

cs.LG↗

arXiv2023

Compact Optimization Learning for AC Optimal Power Flow

This paper reconsiders end-to-end learning approaches to the Optimal Power Flow (OPF). Existing methods, which learn the input/output mapping of the OPF, suffer from scalability issues due to the high dimensionality of the output space. This paper first shows that the space of optimal solutions can be significantly compressed using principal component analysis (PCA). It then proposes Compact Learning, a new method that learns in a subspace of the principal components before translating the vectors into the original output space. This compression reduces the number of trainable parameters substantially, improving scalability and effectiveness. Compact Learning is evaluated on a variety of test cases from the PGLib with up to 30,000 buses. The paper also shows that the output of Compact Learning can be used to warm-start an exact AC solver to restore feasibility, while bringing significant speed-ups.

cs.LG↗

arXiv2023

Two-Stage Learning For the Flexible Job Shop Scheduling Problem

The Flexible Job-shop Scheduling Problem (FJSP) is an important combinatorial optimization problem that arises in manufacturing and service settings. FJSP is composed of two subproblems, an assignment problem that assigns tasks to machines, and a scheduling problem that determines the starting times of tasks on their chosen machines. Solving FJSP instances of realistic size and composition is an ongoing challenge even under simplified, deterministic assumptions. Motivated by the inevitable randomness and uncertainties in supply chains, manufacturing, and service operations, this paper investigates the potential of using a deep learning framework to generate fast and accurate approximations for FJSP. In particular, this paper proposes a two-stage learning framework 2SLFJSP that explicitly models the hierarchical nature of FJSP decisions, uses a confidence-aware branching scheme to generate appropriate instances for the scheduling stage from the assignment predictions and leverages a novel symmetry-breaking formulation to improve learnability. 2SL-FJSP is evaluated on instances from the FJSP benchmark library. Results show that 2SL-FJSP can generate high-quality solutions in milliseconds, outperforming a state-of-the-art reinforcement learning approach recently proposed in the literature, and other heuristics commonly used in practice.

cs.AI↗

arXiv2022

FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting

Time series forecasting is a long-standing challenge due to the real-world information is in various scenario (e.g., energy, weather, traffic, economics, earthquake warning). However some mainstream forecasting model forecasting result is derailed dramatically from ground truth. We believe it's the reason that model's lacking ability of capturing frequency information which richly contains in real world datasets. At present, the mainstream frequency information extraction methods are Fourier transform(FT) based. However, use of FT is problematic due to Gibbs phenomenon. If the values on both sides of sequences differ significantly, oscillatory approximations are observed around both sides and high frequency noise will be introduced. Therefore We propose a novel frequency enhanced channel attention that adaptively modelling frequency interdependencies between channels based on Discrete Cosine Transform which would intrinsically avoid high frequency noise caused by problematic periodity during Fourier Transform, which is defined as Gibbs Phenomenon. We show that this network generalize extremely effectively across six real-world datasets and achieve state-of-the-art performance, we further demonstrate that frequency enhanced channel attention mechanism module can be flexibly applied to different networks. This module can improve the prediction ability of existing mainstream networks, which reduces 35.99% MSE on LSTM, 10.01% on Reformer, 8.71% on Informer, 8.29% on Autoformer, 8.06% on Transformer, etc., at a slight computational cost ,with just a few line of code. Our codes and data are available at https://github.com/Zero-coder/FECAM.

cs.AI↗

arXiv2022

Just-In-Time Learning for Operational Risk Assessment in Power Grids

In a grid with a significant share of renewable generation, operators will need additional tools to evaluate the operational risk due to the increased volatility in load and generation. The computational requirements of the forward uncertainty propagation problem, which must solve numerous security-constrained economic dispatch (SCED) optimizations, is a major barrier for such real-time risk assessment. This paper proposes a Just-In-Time Risk Assessment Learning Framework (JITRALF) as an alternative. JITRALF trains risk surrogates, one for each hour in the day, using Machine Learning (ML) to predict the quantities needed to estimate risk, without explicitly solving the SCED problem. This significantly reduces the computational burden of the forward uncertainty propagation and allows for fast, real-time risk estimation. The paper also proposes a novel, asymmetric loss function and shows that models trained using the asymmetric loss perform better than those using symmetric loss functions. JITRALF is evaluated on the French transmission system for assessing the risk of insufficient operating reserves, the risk of load shedding, and the expected operating cost.

eess.SY↗

arXiv2022

Spurious currents suppression by accurate difference schemes in multiphase lattice Boltzmann method

Spurious currents, which are often observed near a curved interface in the multiphase simulations by diffuse interface methods, are unphysical phenomena and usually damage the computational accuracy and stability. In this paper, the origination and suppression of spurious currents are investigated by using the multiphase lattice Boltzmann method driven by chemical potential. Both the difference error and insufficient isotropy of discrete gradient operator give rise to the directional deviations of nonideal force and then originate the spurious currents. Nevertheless, the high-order finite difference produces far more accurate results than the high-order isotropic difference. We compare several finite difference schemes which have different formal accuracy and resolution. When a large proportional coefficient is used, the transition region is narrow and steep, and the resolution of finite difference indicates the computational accuracy more exactly than the formal accuracy. On the contrary, for a small proportional coefficient, the transition region is wide and gentle, and the formal accuracy of finite difference indicates the computational accuracy better than the resolution. Furthermore, numerical simulations show that the spurious currents calculated in the 3D situation are highly consistent with those in 2D simulations; especially, the two-phase coexistence densities calculated by the high-order accuracy finite difference are in excellent agreement with the theoretical predictions of the Maxwell equal-area construction till the reduced temperature 0.2.

physics.comp-ph↗

arXiv2022

Risk-Aware Control and Optimization for High-Renewable Power Grids

The transition of the electrical power grid from fossil fuels to renewable sources of energy raises fundamental challenges to the market-clearing algorithms that drive its operations. Indeed, the increased stochasticity in load and the volatility of renewable energy sources have led to significant increases in prediction errors, affecting the reliability and efficiency of existing deterministic optimization models. The RAMC project was initiated to investigate how to move from this deterministic setting into a risk-aware framework where uncertainty is quantified explicitly and incorporated in the market-clearing optimizations. Risk-aware market-clearing raises challenges on its own, primarily from a computational standpoint. This paper reviews how RAMC approaches risk-aware market clearing and presents some of its innovations in uncertainty quantification, optimization, and machine learning. Experimental results on real networks are presented.

math.OC↗

arXiv2021

Learning Optimization Proxies for Large-Scale Security-Constrained Economic Dispatch

The Security-Constrained Economic Dispatch (SCED) is a fundamental optimization model for Transmission System Operators (TSO) to clear real-time energy markets while ensuring reliable operations of power grids. In a context of growing operational uncertainty, due to increased penetration of renewable generators and distributed energy resources, operators must continuously monitor risk in real-time, i.e., they must quickly assess the system's behavior under various changes in load and renewable production. Unfortunately, systematically solving an optimization problem for each such scenario is not practical given the tight constraints of real-time operations. To overcome this limitation, this paper proposes to learn an optimization proxy for SCED, i.e., a Machine Learning (ML) model that can predict an optimal solution for SCED in milliseconds. Motivated by a principled analysis of the market-clearing optimizations of MISO, the paper proposes a novel ML pipeline that addresses the main challenges of learning SCED solutions, i.e., the variability in load, renewable output and production costs, as well as the combinatorial structure of commitment decisions. A novel Classification-Then-Regression architecture is also proposed, to further capture the behavior of SCED solutions. Numerical experiments are reported on the French transmission system, and demonstrate the approach's ability to produce, within a time frame that is compatible with real-time operations, accurate optimization proxies that produce relative errors below $0.6\%$.

cs.LG↗

arXiv2021

Numerical simulation of pulmonary airway reopening by the EOS-based multiphase lattice Boltzmann method

The aerosol formation is associated with the rupture of the liquid plug during the pulmonary airway reopening. The fluid dynamics of this process is difficult to predict because the rupture involved complex liquid-gas transition. Equation of state (EOS) plays a key role in the thermodynamic process of liquid-gas transition. Here, we propose an EOS-based multiphase lattice Boltzmann model, in which the nonideal force is directly evaluated by EOSs. This multiphase model is used to model the pulmonary airway reopening and study aerosol formation during exhalation. The numerical model is first validated with the simulations of Fujioka et al.(2008). and the result is in reasonable agreement with their study. Furthermore, two rupture cases with and without aerosol formation are contrasted and analyzed. It is found that the injury on the epithelium in the case with aerosol formation is essentially the same that of without aerosol formation even while the pressure drop in airway increases by about 67%. Then extensive simulations are performed to investigate the effects of pressure drop, thickness of liquid plug and film on aerosol size and the mechanical stresses. The results show that aerosol size and the mechanical stresses increase as the pressure drop enlarges and thickness of liquid plug become thicken, while aerosol size and the mechanical stresses decrease as thickness of liquid film is thicken. The present multiphase model can be extended to study the generation and transmission of bioaerosols which can carry the bioparticles of influenza or coronavirus.

physics.flu-dyn↗

arXiv2020

SemanticVoxels: Sequential Fusion for 3D Pedestrian Detection using LiDAR Point Cloud and Semantic Segmentation

3D pedestrian detection is a challenging task in automated driving because pedestrians are relatively small, frequently occluded and easily confused with narrow vertical objects. LiDAR and camera are two commonly used sensor modalities for this task, which should provide complementary information. Unexpectedly, LiDAR-only detection methods tend to outperform multisensor fusion methods in public benchmarks. Recently, PointPainting has been presented to eliminate this performance drop by effectively fusing the output of a semantic segmentation network instead of the raw image information. In this paper, we propose a generalization of PointPainting to be able to apply fusion at different levels. After the semantic augmentation of the point cloud, we encode raw point data in pillars to get geometric features and semantic point data in voxels to get semantic features and fuse them in an effective way. Experimental results on the KITTI test set show that SemanticVoxels achieves state-of-the-art performance in both 3D and bird's eye view pedestrian detection benchmarks. In particular, our approach demonstrates its strength in detecting challenging pedestrian cases and outperforms current state-of-the-art approaches.

cs.RO↗

arXiv2015

Theoretical study of terahertz generation from atoms and aligned molecules driven by two-color laser fields

We study the generation of terahertz radiation from atoms and molecules driven by an ultrashort fundamental laser and its second harmonic field by solving time-dependent Schrödinger equation (TDSE). The comparisons between one-, two-, and three- dimensional TDSE numerical simulations show that initial ionized wave-packet and its subsequent acceleration in the laser field and rescattering with long-range Coulomb potential play key roles. We also present the dependence of the optimum phase delay and yield of terahertz radiation on the laser intensity, wavelength, duration, and the ratio of two-color laser components. Terahertz wave generation from model hydrogen molecules are further investigated by comparing with high harmonic emission. It is found that the terahertz yield is following the alignment dependence of ionization rate, while the optimal two-color phase delays varies by a small amount when the alignment angle changes from 0 to 90 degrees, which reflects alignment dependence of attosecond electron dynamics. Finally we show that terahertz emission might be used to clarify the origin of interference in high harmonic generation from aligned molecules by coincidently measuring the angle-resolved THz yields.

physics.atom-ph↗

arXiv2014

Rydberg states generation of Hydrogen atoms with intense laser pulses: the roles of Coulomb force and initial lateral momentum

We investigate the Rydberg states generation of Hydrogen atoms with intense laser pulses, by solving the time-dependent Schrödinger equation and by means of classical trajectory monte-carlo simulations. Both linearly polarized multi-cycle pulses and pairs of optical half cycle pulses are used. Comparisons between these methods show that both the Coulomb force and initial lateral momentum, which have effects on the $n$-distribution and $l$-distribution of the population of excited states, are important in the generation of Rydberg states.

physics.atom-ph↗

arXiv2013

Nonlinear theory of intense laser-plasma interactions modified by vacuum-polarization effects

The classical nonlinear laser-plasma interaction theory is corrected. Given the effects of vacuum polarization (induced by extreme laser) as nonlinear media response, one-dimensional wave equations of a monochromatic laser field are derived from the Heisenberg-Euler Lagrangian density and a derivative correction with the first order quantum electrodynamic (QED) effects. A more suitable model to formulate the interactions of extreme laser and high-energy-density plasma is developed. In the results, the enhanced effect of vacuum polarization will be discussed and shown.

physics.plasm-ph↗

arXiv2013

Modified surface redshift of pulsars and magnetars by magnetized plasmas and vacuum polarization

The propagation of emissions in the relativistic streaming pair plasmas of pulsars and magnetars is studied within the framework of Gordon effective metric theory, and the effect of vacuum polarization on the radiation spectra is examined particularly. It is found that the electromagnetic and kinetic effects of streaming magnetized plasmas and the vacuum polarization effect can shift the radiation spectra of stars. The modification of redshifts of spectra can reach the same magnitude as the gravitational redshift in particular cases. Moreover, the redshifts induced by the media are anisotropic and associated with wave modes. For the O-mode, the modification of redshifts is dependent on the frequency of the radiation. For lower-frequency radiation, the modification is dominated by the plasma effect, while for higher-frequency radiations, by the vacuum polarization effect. For the X-mode, the modification is non-dispersive and dominated by the vacuum polarization effect. The vacuum polarization also has a significant effect on the redshifts of X-ray emissions in magnetars.

physics.plasm-ph↗