arXiv subjects

Lin Cheng

Publications and source records attributed to Lin Cheng.

At least 37 records · Page 2Linked to original sources

arXiv2026

Quantum Learning and Estimation for Coordinated Operation between Distribution Networks and Energy Communities

Price signals from distribution networks (DNs) guide energy communities (ECs) in adjusting their energy usage, enabling effective coordination for reliable power system operation. However, this coordinated operation faces significant challenges due to the limited availability of ECs' internal information (i.e., only the aggregated energy usage of ECs is available to DNs), and the high computational burden of accounting for uncertainties and the associated risks through numerous scenarios. To address these challenges, we propose a quantum learning and estimation approach to enhance coordinated operation between DNs and ECs. Specifically, by leveraging advanced quantum properties such as quantum superposition and entanglement, we develop a hybrid quantum temporal convolutional network-long short-term memory (Q-TCN-LSTM) model to establish an end-to-end mapping between ECs' responses and the price incentives from DNs. Moreover, we develop a quantum estimation method based on quantum amplitude estimation (QAE) and two phase-rotation circuits to significantly accelerate the optimization process under numerous uncertainty scenarios. Numerical experiments demonstrate that, compared to classical neural networks, the proposed Q-TCN-LSTM model improves the mapping accuracy by 69.2\% while reducing the model size by 99.75\%. Compared to classical Monte Carlo simulation, QAE achieves comparable accuracy with a substantial reduction in computational resources. In addition, the estimated computation time for quantum learning and estimation on ideal quantum devices is over 90\% shorter than that of traditional methods.

math.OC↗

arXiv2025

BubbleOKAN: A Physics-Informed Interpretable Neural Operator for High-Frequency Bubble Dynamics

In this work, we employ physics-informed neural operators to map pressure profiles from an input function space to the corresponding bubble radius responses. Our approach employs a two-step DeepONet architecture. To address the intrinsic spectral bias of deep learning models, our model incorporates the Rowdy adaptive activation function, enhancing the representation of high-frequency features. Moreover, we introduce the Kolmogorov-Arnold network (KAN) based two-step DeepOKAN model, which enhances interpretability (often lacking in conventional multilayer perceptron architectures) while efficiently capturing high-frequency bubble dynamics without explicit utilization of activation functions in any form. We particularly investigate the use of spline basis functions in combination with radial basis functions (RBF) within our architecture, as they demonstrate superior performance in constructing a universal basis for approximating high-frequency bubble dynamics compared to alternative formulations. Furthermore, we emphasize on the performance bottleneck of RBF while learning the high frequency bubble dynamics and showcase the advantage of using spline basis function for the trunk network in overcoming this inherent spectral bias. The model is systematically evaluated across three representative scenarios: (1) bubble dynamics governed by the Rayleigh-Plesset equation with a single initial radius, (2) bubble dynamics governed by the Keller-Miksis equation with a single initial radius, and (3) Keller-Miksis dynamics with multiple initial radii. We also compare our results with state-of-the-art neural operators, including Fourier Neural Operators, Wavelet Neural Operators, OFormer, and Convolutional Neural Operators. Our findings demonstrate that the two-step DeepOKAN accurately captures both low- and high-frequency behaviors, and offers a promising alternative to conventional numerical solvers.

cs.LG↗

arXiv2025

Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning

Large language models (LLMs) offer strong high-level planning capabilities for reinforcement learning (RL) by decomposing tasks into subgoals. However, their practical utility is limited by poor planning-execution alignment, which reflects a critical gap between abstract plans and actionable, environment-compatible behaviors. This misalignment arises from two interrelated limitations: (1) LLMs often produce subgoals that are semantically plausible but infeasible or irrelevant in the target environment due to insufficient grounding in environment-specific knowledge, and (2) single-LLM planning conflates generation with self-verification, resulting in overconfident yet unreliable subgoals that frequently fail during execution. To address these challenges, we propose Subgoal Graph-Augmented Actor-Critic-Refiner (SGA-ACR), a framework that integrates an environment-specific subgoal graph and structured entity knowledge with a multi-LLM planning pipeline that explicitly separates generation, critique, and refinement to produce executable and verifiable subgoals. A subgoal tracker further monitors execution progress, provides auxiliary rewards, and adaptively updates the subgoal graph to maintain alignment between plans and actions. Experimental results on 22 diverse tasks in the open-world game "Crafter" demonstrate the effectiveness of our proposed method.

cs.LG↗

arXiv2025

Parameter Optimization in Trajectory Planning via Differentiable Convex Programming

Sequential convex programming has been established as an effective framework for solving nonconvex trajectory planning problems. However, its performance is highly sensitive to problem parameters, including trajectory variables, algorithmic hyperparameters, and physical vehicle parameters. This paper introduces a differentiable sequential convex programming framework that integrates differentiable convex optimization with sequential convex programming to enable end-to-end parameter optimization. By deriving first-order sensitivity relations of second-order cone programming solutions with respect to problem data, exact gradients of trajectory performance metrics with respect to arbitrary parameters are obtained and propagated through iterations. The effectiveness of the proposed framework is validated through three representative applications: optimal terminal-time prediction for powered landing, trust-region penalty optimization in subproblems, and surface-to-mass ratio optimization for hypersonic gliding vehicles. Simulation results show that the proposed framework enables reliable gradient-based parameter learning and significantly improves numerical performance, convergence behavior, and design efficiency. These results indicate that the differentiable sequential convex programming framework provides a powerful and general tool for vehicle design, mission optimization, and hyperparameter selection in aerospace trajectory planning.

math.OC↗

arXiv2025

Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning

Sparse dynamics identification is an essential tool for discovering interpretable physical models and enabling efficient control in engineering systems. However, existing methods rely on batch learning with full historical data, limiting their applicability to real-time scenarios involving sequential and partially observable data. To overcome this limitation, this paper proposes an online Sparse Kalman Identification (SKI) method by integrating the Augmented Kalman Filter (AKF) and Automatic Relevance Determination (ARD). The main contributions are: (1) a theoretically grounded Bayesian sparsification scheme that is seamlessly integrated into the AKF framework and adapted to sequentially collected data in online scenarios; (2) an update mechanism that adapts the Kalman posterior to reflect the updated selection of the basis functions that define the model structure; (3) an explicit gradient-descent formulation that enhances computational efficiency. Consequently, the SKI method achieves accurate model structure selection with millisecond-level efficiency and higher identification accuracy, as demonstrated by extensive simulations and real-world experiments (showing an 84.21\% improvement in accuracy over the baseline AKF).

eess.SY↗

arXiv2025

Recursive Gaussian Process State Space Model

Learning dynamical models from data is not only fundamental but also holds great promise for advancing principle discovery, time-series prediction, and controller design. Among various approaches, Gaussian Process State-Space Models (GPSSMs) have recently gained significant attention due to their combination of flexibility and interpretability. However, for online learning, the field lacks an efficient method suitable for scenarios where prior information regarding data distribution and model function is limited. To address this issue, this paper proposes a recursive GPSSM method with adaptive capabilities for both operating domains and Gaussian process (GP) hyperparameters. Specifically, we first utilize first-order linearization to derive a Bayesian update equation for the joint distribution between the system state and the GP model, enabling closed-form and domain-independent learning. Second, an online selection algorithm for inducing points is developed based on informative criteria to achieve lightweight learning. Third, to support online hyperparameter optimization, we recover historical measurement information from the current filtering distribution. Comprehensive evaluations on both synthetic and real-world datasets demonstrate the superior accuracy, computational efficiency, and adaptability of our method compared to state-of-the-art online GPSSM techniques.

cs.LG↗

arXiv2025

An Iterative Problem-Driven Scenario Reduction Framework for Stochastic Optimization with Conditional Value-at-Risk

Scenario reduction (SR) alleviates the computational complexity of scenario-based stochastic optimization with conditional value-at-risk (SBSO-CVaR) by identifying representative scenarios to depict the underlying uncertainty and tail risks. Existing distribution-driven SR methods emphasize statistical similarity but often exclude extreme scenarios, leading to weak tail-risk awareness and insufficient problem-specific representativeness. Instead, this paper proposes an iterative problem-driven scenario reduction framework. Specifically, we integrate the SBSO-CVaR problem structure into SR process and project the original scenario set from the distribution space onto the problem space. Subsequently, to minimize the SR optimality gap with acceptable computation complexity, we propose a tractable iterative problem-driven scenario reduction (IPDSR) method that selects representative scenarios that best approximate the optimality distribution of the original scenario set while preserving tail risks. Furthermore, the iteration process is rendered as a mixed-integer program to enable scenario partitioning and representative scenarios selection. And ex-post problem-driven evaluation indices are proposed to evaluate the SR performance. Numerical experiments show IPDSR significantly outperforms existing SR methods by achieving an optimality gap of less than 1% within an acceptable computation time.

math.OC↗

arXiv2025

Recursive Inference for Heterogeneous Multi-Output GP State-Space Models with Arbitrary Moment Matching

Accurate learning of system dynamics is becoming increasingly crucial for advanced control and decision-making in engineering. However, real-world systems often exhibit multiple channels and highly nonlinear transition dynamics, challenging traditional modeling methods. To enable online learning for these systems, this paper formulates the system as Gaussian process state-space models (GPSSMs) and develops a recursive learning method. The main contributions are threefold. First, a heterogeneous multi-output kernel is designed, allowing each output dimension to adopt distinct kernel types, hyperparameters, and input variables, improving expressiveness in multi-dimensional dynamics learning. Second, an inducing-point management algorithm enhances computational efficiency through independent selection and pruning for each output dimension. Third, a unified recursive inference framework for GPSSMs is derived, supporting general moment matching approaches, including the extended Kalman filter (EKF), unscented Kalman filter (UKF), and assumed density filtering (ADF), enabling accurate learning under strong nonlinearity and significant noise. Experiments on synthetic and real-world datasets show that the proposed method matches the accuracy of SOTA offline GPSSMs with only 1/100 of the runtime, and surpasses SOTA online GPSSMs by around 70% in accuracy under heavy noise while using only 1/20 of the runtime.

stat.ML↗

arXiv2025

Grid-Aware Real-Time Dispatch of Microgrid with Generalized Energy Storage: A Prediction-Free Online Optimization Approach

This paper proposes a novel prediction-free two-stage coordinated dispatch framework for the real-time dispatch of grid-connected microgrid with generalized energy storages (GES). The proposed framework explicitly addresses grid awareness, non-anticipativity constraints, and the time-coupling characteristics of GES, providing microgrid operators with a near-optimal, reliable, and adaptable dispatch tool. In the offline stage, we generate the hindsight state-of-charge (SoC) trajectories of GES by solving the multi-period economic dispatch with historical scenarios. Subsequently, leveraging this historical information (SoC trajectories, net loads, and electricity prices), we synthesize and dynamically update online references for both SoC and opportunity cost through kernel regression. We propose an adaptive Lagrange multiplier-based online convex optimization algorithm, which innovatively incorporates reference tracking for global vision and expert-tracking for step-size updates. We provide theoretical proof to show that the proposed OCO algorithm achieves a sublinear bound of both dynamic regret and time-varying hard constraint violation. Numerical studies using ground-truth data from the Australian Energy Market Operator demonstrate that the proposed method outperforms state-of-the-art methods, reducing operational costs by 5.0-6.2% and voltage violations by 0.8-9.1%. These improvements mainly result from mitigating myopia by reference tracking and the adaptive capability provided by dynamically updated references and adaptive Lagrange multipliers. Sensitivity analysis demonstrates the robustness, computational efficiency, and scalability of the proposed method.

eess.SY↗

arXiv2025

A Weighted Predict-and-Optimize Framework for Power System Operation Considering Varying Impacts of Uncertainty

Prediction deviations of different uncertainties have varying impacts on downstream decision-making. Improving the prediction accuracy of critical uncertainties with significant impacts on decision-making quality yields better optimization results. Motivated by this observation, this paper proposes a novel weighted predict-and-optimize (WPO) framework for decision-making under multiple uncertainties. Specifically, we incorporate an uncertainty-aware weighting mechanism into the predictive model to capture the relative impact of each uncertainty on specific optimization tasks, and introduce a problem-driven prediction loss (PDPL) to quantify the suboptimality of the weighted predictions relative to perfect predictions in downstream optimization. By optimizing the uncertainty weights to minimize the PDPL, the proposed WPO framework enables adaptive assessment of uncertainty impacts and joint learning of prediction and optimization. Furthermore, to facilitate weight optimization, we develop a surrogate model that establishes a direct mapping between the uncertainty weights and the PDPL, where enhanced graph convolutional networks and multi-task learning are adopted for efficient surrogate model construction and training. Numerical experiments on the modified IEEE 33-bus and 123-bus systems demonstrate that the proposed WPO framework outperforms the traditional predict-then-optimize paradigm, reducing the PDPL by an average of 55% within acceptable computational time.

eess.SY↗

arXiv2025

Real-Time Peer-to-Peer Energy Trading for Multi-Microgrids: Improved Double Auction Mechanism and Prediction-Free Online Trading Approach

Peer-to-peer energy trading offers a promising solution for enhancing renewable energy utilization and economic benefits within interconnected microgrids. However, existing real-time P2P markets face two key challenges: high computational complexity in trading mechanisms, and suboptimal participant decision-making under diverse uncertainties. Existing prediction-based decision-making methods rely heavily on accurate forecasts, which are typically unavailable for microgrids, while prediction-free methods suffer from myopic behaviors. To address these challenges, this paper proposes an improved double auction mechanism combined with an adaptive step-size search algorithm to reduce computational burden, and a data-driven dual-reference online optimization (DDOO) framework to enhance participant decision-making. The improved mechanism simplifies bidding procedures, significantly reducing computational burden and ensuring rapid convergence to the market equilibrium. Additionally, the prediction-free DDOO framework mitigates myopic decision-making by introducing two informative reference signals. Case studies on a 20-microgrid system demonstrate the effectiveness and scalability of the proposed mechanism and approach. The improved mechanism significantly decreases the computational time while increasing local energy self-sufficiency periods from 0.01% to 29.86%, reducing reverse power flow periods from 24.51% to 3.96%, and lowering average operating costs by 19.20%. Compared with conventional approaches such as Lyapunov optimization and model predictive control, the DDOO framework achieves a 10%-13% reduction in operating costs with an optimality gap of only 5.76%.

eess.SY↗

arXiv2025

Representation of tensor functions using lower-order structural tensor set: two-dimensional point group

The representation theory of tensor functions is essential to constitutive modeling of materials including both mechanical and physical behaviors. Generally, material symmetry is incorporated in the tensor functions through a structural or anisotropic tensor that characterizes the corresponding point group. The general mathematical framework was well-established in the 1990s. Nevertheless, the traditional theory suffers from a grand challenge that many point groups involve fourth or sixth order structural tensors that hinder its practical applications in engineering. Recently, researchers have reformulated the representation theory and opened up opportunities to model anisotropic materials using low-order (i.e., 2nd-order and lower) structural tensors only, although the theory was not fully established. This work aims to fully establish the reformulated representation theory of tensor functions for all two-dimensional point groups. It was found that each point group needs a structural tensor set to characterize the symmetry. For each two-dimensional point group, the structural tensor set is proposed and the general tensor functions are derived. Only low-order structural tensors are introduced so researchers can readily apply these tensor functions for their modeling applications. The theory presented here is useful for constitutive modeling of materials in general, especially for composites, nanomaterials, soft tissues, etc.

math.RT↗

arXiv2025

Comparison of Droop-Based Single-Loop Grid-Forming Wind Turbines: High-Frequency Open-Loop Unstable Behavior and Damping

The integration of inverter-interfaced generators introduces new instability phenomena into modern power systems. This paper conducts a comparative analysis of two widely used droop-based grid-forming controls, namely droop control and droop-I control, in wind turbines. Although both approaches provide steady-state reactive power-voltage droop characteristics, their impacts on high-frequency (HF) stability differ significantly. Firstly, on open-loop (OL) comparison reveals that droop-I control alters HF pole locations. The application of Routh's Stability Criterion further analytically demonstrates that such pole shifts inevitably lead to OL instability. This HF OL instability is identified as a structural phenomenon in purely inductive grids and cannot be mitigated through control parameter tuning. As a result, droop-I control significantly degrades HF stability, making conventional gain and phase margins insufficient for evaluating robustness against parameter variations. Then, the performance of established active damping (AD) is assessed for both control schemes. The finding indicates that AD designs effective for droop control may fail to suppress HF resonance under droop-I control due to the presence of unstable OL poles. Case studies performed on the IEEE 14-Bus Test System validate the analysis and emphasize the critical role of HF OL instability in determining the overall power system stability.

eess.SY↗

arXiv2025

A Heuristic Method for Simplified Resource Allocation based on Comparative Advantage in Wireless Access Systems

This paper presents a heuristic method for simplifying resource allocation in access systems, leveraging the concept of comparative advantage to reduce computational complexity while maintaining near-optimal performance. Using power-division non-orthogonal multiple access (PD-NOMA) as an example, we demonstrate how this approach mitigates the challenge of power allocation in multi-cell networks. Our method reduces the search space for optimization, significantly decreasing computational overhead while ensuring efficient spectrum utilization. In principle, the method reduces the dimensions of search space by half. Extensive analysis and simulations validate its effectiveness, highlighting its potential for practical deployment in next-generation wireless networks. The proposed framework can help streamline resource allocation in complex communication environments, enhancing system performance and scalability.

eess.SP↗

arXiv2025

Morpheus: A Neural-driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control

Previous animatronic faces struggle to express emotions effectively due to hardware and software limitations. On the hardware side, earlier approaches either use rigid-driven mechanisms, which provide precise control but are difficult to design within constrained spaces, or tendon-driven mechanisms, which are more space-efficient but challenging to control. In contrast, we propose a hybrid actuation approach that combines the best of both worlds. The eyes and mouth-key areas for emotional expression-are controlled using rigid mechanisms for precise movement, while the nose and cheek, which convey subtle facial microexpressions, are driven by strings. This design allows us to build a compact yet versatile hardware platform capable of expressing a wide range of emotions. On the algorithmic side, our method introduces a self-modeling network that maps motor actions to facial landmarks, allowing us to automatically establish the relationship between blendshape coefficients for different facial expressions and the corresponding motor control signals through gradient backpropagation. We then train a neural network to map speech input to corresponding blendshape controls. With our method, we can generate distinct emotional expressions such as happiness, fear, disgust, and anger, from any given sentence, each with nuanced, emotion-specific control signals-a feature that has not been demonstrated in earlier systems. We release the hardware design and code at https://github.com/ZZongzheng0918/Morpheus-Hardware and https://github.com/ZZongzheng0918/Morpheus-Software.

cs.RO↗

arXiv2025

RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control

Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges, as users often struggle to provide precise camera parameters when working with arbitrary real-world images without knowledge of their depth nor scene scale. To address these real-world application issues, we propose RealCam-I2V, a novel diffusion-based video generation framework that integrates monocular metric depth estimation to establish 3D scene reconstruction in a preprocessing step. During training, the reconstructed 3D scene enables scaling camera parameters from relative to metric scales, ensuring compatibility and scale consistency across diverse real-world images. In inference, RealCam-I2V offers an intuitive interface where users can precisely draw camera trajectories by dragging within the 3D scene. To further enhance precise camera control and scene consistency, we propose scene-constrained noise shaping, which shapes high-level noise and also allows the framework to maintain dynamic and coherent video generation in lower noise stages. RealCam-I2V achieves significant improvements in controllability and video quality on the RealEstate10K and out-of-domain images. We further enables applications like camera-controlled looping video generation and generative frame interpolation. Project page: https://zgctroy.github.io/RealCam-I2V.

cs.CV↗

arXiv2025

Learning-Based Stable Optimal Control for Infinite-Time Nonlinear Regulation Problems

Infinite-time nonlinear optimal regulation control is widely utilized in aerospace engineering as a systematic method for synthesizing stable controllers. However, conventional methods often rely on linearization hypothesis, while recent learning-based approaches rarely consider stability guarantees. This paper proposes a learning-based framework to learn a stable optimal controller for nonlinear optimal regulation problems. First, leveraging the equivalence between Pontryagin Maximum Principle (PMP) and Hamilton-Jacobi-Bellman (HJB) equation, we improve the backward generation of optimal examples (BGOE) method for infinite-time optimal regulation problems. A state-transition-matrix-guided data generation method is then proposed to efficiently generate a complete dataset that covers the desired state space. Finally, we incorporate the Lyapunov stability condition into the learning framework, ensuring the stability of the learned optimal policy by jointly learning the optimal value function and control policy. Simulations on three nonlinear optimal regulation problems show that the learned optimal policy achieves near-optimal regulation control and the code is provided at https://github.com/wong-han/PaperNORC

eess.SY↗

arXiv2025

SkyMemory: A LEO Edge Cache for Transformer Inference Optimization and Scale Out

We expand the scope of cache memory to include LEO constellations, which are highly distributed systems with thousands of satellites connected with free-space optics inter-satellite links (ISL) always only one hop from any point on earth. We show how to increase the number of cache hits and improve the speed of inference for the important use case of LLMs. These benefits apply not only to LLMs, both terrestrially hosted and on satellites, but also generalize to any cache distributed over multiple locations that needs to be accessed in a timely manner. We show the benefit of our key value cache (KVC) protocol in simulations and present a proof-of-concept implementation of the protocol for KVCs on a testbed comprising 5 Intel NUC Linux mini PCs hosting a 19x5 constellation, with an NVIDIA Jetson Nano 8GB GPU hosting the LLM.

cs.DC↗