arXiv subjects

Pascal Van Hentenryck

Publications and source records attributed to Pascal Van Hentenryck.

At least 73 records · Page 4Linked to original sources

arXiv2025

PROPEL: Supervised and Reinforcement Learning for Large-Scale Supply Chain Planning

This paper considers how to fuse Machine Learning (ML) and optimization to solve large-scale Supply Chain Planning (SCP) optimization problems. These problems can be formulated as MIP models which feature both integer (non-binary) and continuous variables, as well as flow balance and capacity constraints. This raises fundamental challenges for existing integrations of ML and optimization that have focused on binary MIPs and graph problems. To address these, the paper proposes PROPEL, a new framework that combines optimization with both supervised and Deep Reinforcement Learning (DRL) to reduce the size of search space significantly. PROPEL uses supervised learning, not to predict the values of all integer variables, but to identify the variables that are fixed to zero in the optimal solution, leveraging the structure of SCP applications. PROPEL includes a DRL component that selects which fixed-at-zero variables must be relaxed to improve solution quality when the supervised learning step does not produce a solution with the desired optimality tolerance. PROPEL has been applied to industrial supply chain planning optimizations with millions of variables. The computational results show dramatic improvements in solution times and quality, including a 60% reduction in primal integral and an 88% primal gap reduction, and improvement factors of up to 13.57 and 15.92, respectively.

cs.LG↗

arXiv2025

A Deep Neural Network-based Frequency Predictor for Frequency-Constrained Optimal Power Flow

Rate of change of frequency (RoCoF) and frequency nadir should be considered in real-time frequency-constrained optimal power flow (FCOPF) to ensure frequency stability of the modern power systems. Since calculating the frequency response is complex, deep neural network (DNN) could be adopted to capture the nonlinearities and estimate those two metrics accurately. Therefore, in this paper, a DNN-based frequency predictor is developed with the training data obtained from time-domain simulations using PSCAD/EMTDC. Subsequently, it is reformulated using a set of mixed-integer linear programming formulations and then embedded into the FCOPF framework as constraints to ensure grid frequency stability, creating the proposed DNN-FCOPF model. Two benchmark models, a traditional OPF without any frequency constraints and a linear system-wide RoCoF-constrained FCOPF, are also implemented to gauge the proposed DNN-FCOPF. Finally, the solutions obtained with these three models are compared and evaluated with time-domain simulations using PSCAD under various load profiles, demonstrating the effectiveness of the proposed DNN-FCOPF.

eess.SY↗

arXiv2025

Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality

Constrained Markov Decision Processes (CMDPs) are critical in many high-stakes applications, where decisions must optimize cumulative rewards while strictly adhering to complex nonlinear constraints. In domains such as power systems, finance, supply chains, and precision robotics, violating these constraints can result in significant financial or societal costs. Existing Reinforcement Learning (RL) methods often struggle with sample efficiency and effectiveness in finding feasible policies for highly and strictly constrained CMDPs, limiting their applicability in these environments. Stochastic dual dynamic programming is often used in practice on convex relaxations of the original problem, but they also encounter computational challenges and loss of optimality. This paper introduces a novel approach, Two-Stage Deep Decision Rules (TS-DDR), to efficiently train parametric actor policies using Lagrangian Duality. TS-DDR is a self-supervised learning algorithm that trains general decision rules (parametric policies) using stochastic gradient descent (SGD); its forward passes solve {\em deterministic} optimization problems to find feasible policies, and its backward passes leverage duality theory to train the parametric policy with closed-form gradients. TS-DDR inherits the flexibility and computational performance of deep learning methodologies to solve CMDP problems. Applied to the Long-Term Hydrothermal Dispatch (LTHD) problem using actual power system data from Bolivia, TS-DDR is shown to enhance solution quality and to reduce computation times by several orders of magnitude when compared to current state-of-the-art methods.

cs.LG↗

arXiv2025

Dual Interior Point Optimization Learning

In many practical applications of constrained optimization, scale and solving time limits make traditional optimization solvers prohibitively slow. Thus, the research question of how to design optimization proxies -- machine learning models that produce high-quality solutions -- has recently received significant attention. Orthogonal to this research thread which focuses on learning primal solutions, this paper studies how to learn dual feasible solutions that complement primal approaches and provide quality guarantees. The paper makes two distinct contributions. First, to train dual linear optimization proxies, the paper proposes a smoothed self-supervised loss function that augments the objective function with a dual penalty term. Second, the paper proposes a novel dual completion strategy that guarantees dual feasibility by solving a convex optimization problem. Moreover, the paper derives closed-form solutions to this completion optimization for several classes of dual penalties, eliminating the need for computationally-heavy implicit layers. Numerical results are presented on large linear optimization problems and demonstrate the effectiveness of the proposed approach. The proposed dual completion outperforms methods for learning optimization proxies which do not exploit the structure of the dual problem. Compared to commercial optimization solvers, the learned dual proxies achieve optimality gaps below $1\%$ and several orders of magnitude speedups.

cs.LG↗

arXiv2025

Enhanced Renewable Energy Forecasting and Operations through Probabilistic Forecast Aggregation

Accurate and reliable forecasting of renewable energy generation is crucial for the efficient integration of renewable sources into the power grid. In particular, probabilistic forecasts are becoming essential for managing the intrinsic variability and uncertainty of renewable energy production, especially wind and solar generation. This paper considers the setting where probabilistic forecasts are provided for individual renewable energy sites using, e.g., quantile regression models, but without any correlation information between sites. This setting is common if, e.g., such forecasts are provided by each individual site, or by multiple vendors. However, to effectively manage a fleet of renewable generators, it is necessary to aggregate these individual forecasts to the fleet level, while ensuring that the aggregated probabilistic forecast is statistically consistent and reliable. To address this challenge, this paper presents the integrated use of Copula and Monte-Carlo methods to aggregate individual probabilistic forecasts into a statistically calibrated, probabilistic forecast at the fleet level. The proposed framework is validated using synthetic data from several large-scale systems in the United States. This work has important implications for grid operators and energy planners, providing them with better tools to manage the variability and uncertainty inherent in renewable energy production.

stat.AP↗

arXiv2025

Optimization Learning

This article introduces the concept of optimization learning, a methodology to design optimization proxies that learn the input/output mapping of parametric optimization problems. These optimization proxies are trustworthy by design: they compute feasible solutions to the underlying optimization problems, provide quality guarantees on the returned solutions, and scale to large instances. Optimization proxies are differentiable programs that combine traditional deep learning technology with repair or completion layers to produce feasible solutions. The article shows that optimization proxies can be trained end-to-end in a self-supervised way. It presents methodologies to provide performance guarantees and to scale optimization proxies to large-scale optimization problems. The potential of optimization proxies is highlighted through applications in power systems and, in particular, real-time risk assessment and security-constrained optimal power flow.

math.OC↗

arXiv2024

Contextual Stochastic Optimization for School Desegregation Policymaking

Most US school districts draw geographic "attendance zones" to assign children to schools based on their home address, a process that can replicate existing neighborhood racial/ethnic and socioeconomic status (SES) segregation in schools. Redrawing boundaries can reduce segregation, but estimating expected rezoning impacts is often challenging because families can opt-out of their assigned schools. This paper seeks to alleviate this societal problem by developing a joint redistricting and choice modeling framework, called Redistricting with Choices (RWC). The RWC framework is applied to a large US public school district to estimate how redrawing elementary school boundaries might realistically impact levels of socioeconomic segregation. The main methodological contribution of RWC is a contextual stochastic optimization model that aims to minimize district-wide segregation by integrating rezoning constraints with a machine learning-based school choice model. The study finds that RWC yields boundary changes that might reduce segregation by a substantial amount (23%) -- but doing so might require the re-assignment of a large number of students, likely to mitigate re-segregation that choice patterns could exacerbate. The results also reveal that predicting school choice is a challenging machine learning problem. Overall, this study offers a novel practical framework that both academics and policymakers might use to foster more diverse and integrated schools.

cs.CY↗

arXiv2024

High-Spatial Resolution Transmission and Storage Expansion Planning for High Renewable Grids: A Case Study

Transmission Expansion Planning (TEP) is the process of optimizing the development and upgrade of the power grid to ensure reliable, efficient, and cost-effective electricity delivery while addressing grid constraints. To support growing demand and renewable energy integration, energy storage is emerging as a pivotal asset that provides temporal flexibility and alleviates congestion. This paper presents a TEP model that incorporates the sizing and siting of short-duration storage. With a focus on high spatial resolution, the model is applied to a 2,000-bus synthetic Texas power system, offering detailed insights into geographic investment and operational patterns. To maintain computational feasibility, a simple yet effective storage candidates (SC) method is introduced, significantly reducing the search space. Results highlight that transmission investments are primarily driven by renewable energy expansion, while storage investments are shaped by renewable curtailment and load-shedding events, with their primary function being peak load shaving. The findings underscore the importance of co-optimizing transmission and storage to minimize costs and enhance grid reliability. However, limitations in the ability of the SC method to identify optimal storage locations to meet long-term needs suggest opportunities for future research, including dynamic candidate selection and hybrid optimization techniques.

eess.SY↗

arXiv2024

Confidence-Aware Deep Learning for Load Plan Adjustments in the Parcel Service Industry

This study develops a deep learning-based approach to automate inbound load plan adjustments for a large transportation and logistics company. It addresses a critical challenge for the efficient and resilient planning of E-commerce operations in presence of increasing uncertainties. The paper introduces an innovative data-driven approach to inbound load planning. Leveraging extensive historical data, the paper presents a two-stage decision-making process using deep learning and conformal prediction to provide scalable, accurate, and confidence-aware solutions. The first stage of the prediction is dedicated to tactical load-planning, while the second stage is dedicated to the operational planning, incorporating the latest available data to refine the decisions at the finest granularity. Extensive experiments compare traditional machine learning models and deep learning methods. They highlight the importance and effectiveness of the embedding layers for enhancing the performance of deep learning models. Furthermore, the results emphasize the efficacy of conformal prediction to provide confidence-aware prediction sets. The findings suggest that data-driven methods can substantially improve decision making in inbound load planning, offering planners a comprehensive, trustworthy, and real-time framework to make decisions. The initial deployment in the industry setting indicates a high accuracy of the proposed framework.

cs.LG↗

arXiv2024

Decision Making with Differential Privacy under a Fairness Lens

Agencies, such as the U.S. Census Bureau, release data sets and statistics about groups of individuals that are used as input to a number of critical decision processes. To conform to privacy and confidentiality requirements, these agencies are often required to release privacy-preserving versions of the data. This paper studies the release of differentially private data sets and analyzes their impact on some critical resource allocation tasks under a fairness perspective. {The paper shows that, when the decisions take as input differentially private data}, the noise added to achieve privacy disproportionately impacts some groups over others. The paper analyzes the reasons for these disproportionate impacts and proposes guidelines to mitigate these effects. The proposed approaches are evaluated on critical decision problems that use differentially private census data.

cs.AI↗

arXiv2024

Differential Privacy Overview and Fundamental Techniques

This chapter is meant to be part of the book "Differential Privacy in Artificial Intelligence: From Theory to Practice" and provides an introduction to Differential Privacy. It starts by illustrating various attempts to protect data privacy, emphasizing where and why they failed, and providing the key desiderata of a robust privacy definition. It then defines the key actors, tasks, and scopes that make up the domain of privacy-preserving data analysis. Following that, it formalizes the definition of Differential Privacy and its inherent properties, including composition, post-processing immunity, and group privacy. The chapter also reviews the basic techniques and mechanisms commonly used to implement Differential Privacy in its pure and approximate forms.

cs.CR↗

arXiv2024

On the Viability of Stochastic Economic Dispatch for Real-Time Energy Market Clearing

Over the past decade, the rapid adoption of intermittent renewable energy sources (RES), especially wind and solar generation, has posed challenges in managing real-time uncertainty and variability. In the U.S., Independent System Operators (ISOs) solve a security-constrained economic dispatch (SCED) every five minutes to clear real-time electricity markets, co-optimizing energy dispatch and reserve to minimize costs while meeting physical and reliability constraints. All SCED formulations in the U.S. are deterministic and mostly consider a single time period, limiting their effectiveness in managing real-time operational uncertainty from RES intermittency. This limitation is highlighted by the recent introduction of multiple short-term ramping products in U.S. markets, aiming to bridge the gap between deterministic and stochastic SCED formulations. While stochastic formulations address uncertainty in a unified and endogenous manner, their adoption has been hindered by high computational costs and, to a lesser extent, the availability of probabilistic forecasts. This paper revisits these concerns and demonstrates that stochastic economic dispatch is now a viable technology for real-time market clearing. It introduces the stochastic look-ahead dispatch (SLAD) formulation for real-time market clearing and presents an accelerated Benders' decomposition to solve it efficiently. Extensive experiments on a real, industry-sized transmission grid demonstrate the computational scalability of the proposed approach, with SLAD instances being solved in under 5 minutes. Furthermore, results show that SLAD provides more than 50% additional savings compared to flexiramp products and is more robust to the forecasting methodology. Therefore, SLAD is a promising approach for uncertainty management in real-time electricity markets.

math.OC↗

arXiv2024

Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systems

The integration of renewable energy sources (RES) into power grids presents significant challenges due to their intrinsic stochasticity and uncertainty, necessitating the development of new techniques for reliable and efficient forecasting. This paper proposes a method combining probabilistic forecasting and Gaussian copula for day-ahead prediction and scenario generation of load, wind, and solar power in high-dimensional contexts. By incorporating weather covariates and restoring spatio-temporal correlations, the proposed method enhances the reliability of probabilistic forecasts in RES. Extensive numerical experiments compare the effectiveness of different time series models, with performance evaluated using comprehensive metrics on a real-world and high-dimensional dataset from Midcontinent Independent System Operator (MISO). The results highlight the importance of weather information and demonstrate the efficacy of the Gaussian copula in generating realistic scenarios, with the proposed weather-informed Temporal Fusion Transformer (WI-TFT) model showing superior performance.

stat.ML↗

arXiv2024

Learning Joint Models of Prediction and Optimization

The Predict-Then-Optimize framework uses machine learning models to predict unknown parameters of an optimization problem from exogenous features before solving. This setting is common to many real-world decision processes, and recently it has been shown that decision quality can be substantially improved by solving and differentiating the optimization problem within an end-to-end training loop. However, this approach requires significant computational effort in addition to handcrafted, problem-specific rules for backpropagation through the optimization step, challenging its applicability to a broad class of optimization problems. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by joint predictive models. The approach is generic, and based on an adaptation of the Learning-to-Optimize paradigm, from which a rich variety of existing techniques can be employed. Experimental evaluations show the ability of several Learning-to-Optimize methods to provide efficient and accurate solutions to an array of challenging Predict-Then-Optimize problems.

cs.LG↗

arXiv2024

Optimizing Autonomous Transfer Hub Networks: Quantifying the Potential Impact of Self-Driving Trucks

Autonomous trucks are expected to fundamentally transform the freight transportation industry. In particular, Autonomous Transfer Hub Networks (ATHNs), which combine autonomous trucks on middle miles with human-driven trucks on the first and last miles, are seen as the most likely deployment pathway for this technology. This paper presents a framework to optimize ATHN operations and evaluate the benefits of autonomous trucking. By exploiting the problem structure, this paper introduces a flow-based optimization model for this purpose that can be solved by blackbox solvers in a matter of hours. The resulting framework is easy to apply and enables the data-driven analysis of large-scale systems. The power of this approach is demonstrated on a system that spans all of the United States over a four-week horizon. The case study quantifies the potential impact of autonomous trucking and shows that ATHNs can have significant benefits over traditional transportation networks.

math.OC↗

arXiv2024

Defining 'Good': Evaluation Framework for Synthetic Smart Meter Data

Access to granular demand data is essential for the net zero transition; it allows for accurate profiling and active demand management as our reliance on variable renewable generation increases. However, public release of this data is often impossible due to privacy concerns. Good quality synthetic data can circumnavigate this issue. Despite significant research on generating synthetic smart meter data, there is still insufficient work on creating a consistent evaluation framework. In this paper, we investigate how common frameworks used by other industries leveraging synthetic data, can be applied to synthetic smart meter data, such as fidelity, utility and privacy. We also recommend specific metrics to ensure that defining aspects of smart meter data are preserved and test the extent to which privacy can be protected using differential privacy. We show that standard privacy attack methods like reconstruction or membership inference attacks are inadequate for assessing privacy risks of smart meter datasets. We propose an improved method by injecting training data with implausible outliers, then launching privacy attacks directly on these outliers. The choice of $ε$ (a metric of privacy loss) significantly impacts privacy risk, highlighting the necessity of performing these explicit privacy tests when making trade-offs between fidelity and privacy.

cs.LG↗

arXiv2024

Bucketized Active Sampling for Learning ACOPF

This paper considers optimization proxies for Optimal Power Flow (OPF), i.e., machine-learning models that approximate the input/output relationship of OPF. Recent work has focused on showing that such proxies can be of high fidelity. However, their training requires significant data, each instance necessitating the (offline) solving of an OPF. To meet the requirements of market-clearing applications, this paper proposes Bucketized Active Sampling (BAS), a novel active learning framework that aims at training the best possible OPF proxy within a time limit. BAS partitions the input domain into buckets and uses an acquisition function to determine where to sample next. By applying the same partitioning to the validation set, BAS leverages labeled validation samples in the selection of unlabeled samples. BAS also relies on an adaptive learning rate that increases and decreases over time. Experimental results demonstrate the benefits of BAS.

cs.LG↗

arXiv2024

Privacy-Preserving Convex Optimization: When Differential Privacy Meets Stochastic Programming

Convex optimization finds many real-life applications, where--optimized on real data--optimization results may expose private data attributes (e.g., individual health records, commercial information), thus leading to privacy breaches. To avoid these breaches and formally guarantee privacy to optimization data owners, we develop a new privacy-preserving perturbation strategy for convex optimization programs by combining stochastic (chance-constrained) programming and differential privacy. Unlike standard noise-additive strategies, which perturb either optimization data or optimization results, we express the optimization variables as functions of the random perturbation using linear decision rules; we then optimize these rules to accommodate the perturbation within the problem's feasible region by enforcing chance constraints. This way, the perturbation is feasible and makes different, yet adjacent in the sense of a given distance function, optimization datasets statistically similar in randomized optimization results, thereby enabling probabilistic differential privacy guarantees. The chance-constrained optimization additionally internalizes the conditional value-at-risk measure to model the tolerance towards the worst-case realizations of the optimality loss w.r.t. the non-private solution. We demonstrate the privacy properties of our perturbation strategy analytically and through optimization and machine learning applications.

math.OC↗