arXiv subjects

Pierre Pinson

Publications and source records attributed to Pierre Pinson.

At least 19 recordsLinked to original sources

arXiv2026

Control-Oriented Scenario Tree Construction through Reinforcement Learning

Multistage stochastic model predictive control (MPC) handles uncertainty by optimizing over a scenario tree, a finite branching approximation of future outcomes constructed from sampled forecasts. To build such a tree, conventional methods focus on matching the underlying probability distribution---e.g., via Wasserstein-based scenario reduction---but improved distributional accuracy does not necessarily yield better control performance. We propose a control-oriented approach that learns scenario tree construction directly from its impact on downstream decisions. Fixing the tree topology, we formulate tree construction as a sequential assignment of sampled scenarios to leaves. This assignment is parameterized by an attention-based policy over the scenario set and trained using reinforcement learning, with closed-loop control profit as the objective. Training is stabilized by an asymmetric critic that leverages realized future trajectories. We evaluate the method on a risk-averse battery arbitrage problem. Across a range of forecast set sizes, the learned construction consistently achieves the highest profit, outperforming classical forward and backward reduction methods and certainty-equivalent (single-trajectory forecast) control. The learned policy also exhibits greater robustness on challenging instances, consistently demonstrating better tail-risk characteristics. Analysis of the resulting trees indicates that our method constructs compact, selectively branching structures that capture high-impact events while keeping most trajectories nearly deterministic. These findings highlight that the value of a scenario tree depends critically on the decisions it supports, and provide an effective framework to train scenario tree constructors merely based on the closed-loop control optimization signal.

cs.AI↗

arXiv2026

QueryMarket: Cost-Aware Online Active Learning in Data Markets

Data acquisition is a major bottleneck for learning in real-time streams: analysts must decide on the fly which labels to purchase while respecting a rolling budget. However, existing online active learning rarely unifies pricing, information gain, and rolling budget constraints under concept drift. We introduce QueryMarket, a market-inspired framework that queries each incoming data point based on its estimated utility to the model and its price. Within this framework, we propose OVBAL (online variance-based active learning), which integrates data pricing with information-driven selection by estimating each sample's marginal utility via a D-optimality criterion with exponential forgetting and executing cost-aware purchases under rolling budget constraints. OVBAL yields a simple, fully online decision rule that adapts to nonstationary streams and heterogeneous label costs. Experiments on synthetic data and a real-world solar power generation forecasting task show that OVBAL is particularly effective under seller-centric pricing and yields a more favorable long-run error-cost trade-off in the real-world task under both pricing schemes.

cs.LG↗

arXiv2026

Decision-calibrated prediction sets for robust power system operations

Robust optimization offers a tractable approach to balance operating costs and reliability in power systems dominated by weather-dependent renewable uncertainty, but its performance depends critically on the uncertainty set. Standard data-driven approaches often calibrate uncertainty sets to attain predictive coverage, which can produce unnecessarily large sets and costly operating decisions. In contrast, we introduce decision-calibrated prediction sets and embed them as uncertainty sets in robust optimization problems; these are conditional multivariate prediction sets where calibration is defined in terms of the reliability of downstream decisions, rather than in terms of the coverage. First, we learn these conditional prediction sets as sub-level sets of norm-based score functions represented by partially input-convex neural networks, capturing contextual information and multivariate dependence while preserving convexity and tractability in downstream robust formulations. Second, inspired by conformal risk control, we calibrate a score-threshold parameter that sets the volume of the uncertainty set, thereby controlling the expected violations of downstream operational constraints. We apply our approach to 15-minute-ahead reserve scheduling with network-constrained deliverability, which we formulate as a robust DC optimal power flow problem with affine recourse. Numerical experiments show that decision-calibrated sets attain prescribed constraint-satisfaction targets within about three percentage points, whereas standard coverage-based calibration systematically exceeds these targets by more than eleven percentage points, leading to larger sets and higher operating costs.

math.OC↗

arXiv2026

S3TS: Stochastic Scenario-Structured Tree Search for Advanced Planning Under Uncertainty

Effective scheduling in the energy sector is essential to ensure the reliable operation of electrical grids and their connected assets by, for instance, optimizing the dispatch of generation units and storage systems. An effective planning strategy must (a) accommodate advanced and potentially non-linear system models -- exploiting the increasing data availability of modern grids, and (b) explicitly handle uncertainties arising, for instance, from the integration of renewable energy sources. While existing approaches can address either non-linearity (e.g., Monte Carlo Tree Search) or uncertainty (e.g., stochastic mathematical optimization), there is a lack of planning techniques capable of addressing both challenges simultaneously. To bridge this gap, we propose a Stochastic Scenario-Structured Tree Search (S3TS) algorithm that explicitly represents uncertainty through scenario trees while enabling the integration of advanced non-linear models. We evaluate S3TS on a simulated demand response signal publication problem, largely mimicking the imbalance settlement mechanism in Belgium. The results demonstrate near-optimal performance in linear, analytically tractable settings, with costs within 14% of the mathematically optimal solution conditioned to the scenario trees. In highly non-linear scenarios, S3TS significantly outperforms baseline methods, achieving cost reductions of up to 51% and 5.4% compared to a myopic algorithm and deterministic MCTS, respectively.

cs.AI↗

arXiv2026

Stabilizing distribution-free probabilistic forecasts

Multi-step-ahead forecasts are often updated as new observations become available, since shorter forecast horizons typically improve forecast quality. However, such improvements come at the cost of forecast instability, i.e., variability in forecasts for the same target period. This instability can trigger costly changes to plans formulated based on the forecasts and may erode trust in the forecasting system. In this work, we integrate forecast stability alongside forecast quality into the training of distribution-free probabilistic time-series forecasting models, allowing us to control this trade-off. We propose a method for generating stabilized forecasted conditional quantile functions using regression splines parameterized by a neural network. This approach enables joint optimization of quality and stability, as it allows us to directly penalize dissimilarities arising from forecast updates. Furthermore, it allows assigning varying importance to stabilizing different parts of the forecast distributions (e.g., central parts vs. tails) to focus on the parts most relevant for the intended downstream use (e.g., the upper tail for inventory management). We empirically evaluate the proposed method on two datasets with different statistical properties and show that it can effectively reduce forecast instability without a substantial loss in forecast quality, and that it can target stabilization effort toward specific parts of the forecast distributions.

cs.LG↗

arXiv2026

Counter-Dyna: Data-Efficient RL-Based HVAC Control using Counterfactual Building Models

Model-based reinforcement learning (MBRL) offers a promising approach for data-efficient energy management in buildings, combining the strengths of predictive modeling and reinforcement learning. While previous MBRL methods applied to HVAC control have reduced training data requirements, they still require several months of interaction with the building to learn a satisfactory control policy. A key reason is that existing surrogate models attempt to predict the entire state-space, including weather and electricity prices that are unaffected by control actions, or completely ignore these variables. Addressing these issues, we propose Counter-Dyna, a method that enhances the data-efficiency of Dyna, an MBRL method. We create data-efficient counterfactual surrogate models (CSM) by leveraging invariances in the state-space. Using a CSM in Dyna speeds up RL training measured in environment interaction data compared to previous results. In comparison with previous state-of-the-art that used 6-12 months of environment interactions, our method needs only 5 weeks. We evaluate our method in a large simulation study using the literature standard BOPTEST framework and proximal policy algorithm (PPO) as the RL algorithm. Our results show cost-saving potentials of 5.3% to 17.0% in a hypothetical deployment scenario. Our work is a significant step towards making real-world deployment of RL algorithms in HVAC control practically viable.

cs.LG↗

arXiv2025

Synergies between AI Computing and Power Systems: Metrics, Scheduling, and Resilience

In this paper, we first clarify the concepts of green AI versus frugal AI, positioning frugality as efficiency by design and green AI as transparency and accountability. We then argue that these approaches, while complementary, are insufficient without a shared quantitative foundation that links AI computing to power system contexts. This motivates the development of standardized carbon metrics as a bridge between algorithmic decisions and their physical consequences. We next embed these signals into scheduling and planning frameworks, presenting two architectures: (i) an iterative signal-response loop for real-time operations, and (ii) an integrated optimization that learns and encodes flexible-load behavior for long-term planning. Finally, we show how the same coordination stack supports resilience, enabling signals to shift from emissions-first to stability-first during stress events, providing targeted relief and faster restoration.

eess.SY↗

arXiv2025

How to Purchase Labels? A Cost-Effective Approach Using Active Learning Markets

We introduce and analyse active learning markets as a way to purchase labels, in situations where analysts aim to acquire additional data to improve model fitting, or to better train models for predictive analytics applications. This comes in contrast to the many proposals that already exist to purchase features and examples. By originally formalising the market clearing as an optimisation problem, we integrate budget constraints and improvement thresholds into the label acquisition process. We focus on a single-buyer-multiple-seller setup and propose the use of two active learning strategies (variance based and query-by-committee based), paired with distinct pricing mechanisms. They are compared to benchmark baselines including random sampling and a greedy knapsack heuristic. The proposed strategies are validated on real-world datasets from two critical application domains: real estate pricing and energy forecasting. Results demonstrate the robustness of our approach, consistently achieving superior performance with fewer labels acquired compared to conventional methods. Our proposal comprises an easy-to-implement practical solution for optimising data acquisition in resource-constrained environments.

cs.LG↗

arXiv2025

Probabilistic Prediction Markets with Intermittent Contributions

Although both data availability and the demand for accurate forecasts are increasing, collaboration between stakeholders is often constrained by data ownership and competitive interests. In contrast to recent proposals within cooperative game-theoretical frameworks, we place ourselves in a more general framework, based on prediction markets. There, independent agents trade forecasts of uncertain future events in exchange for rewards. We introduce and analyse a prediction market that (i) accounts for the historical performance of the agents, (ii) adapts to time-varying conditions, while (iii) permitting agents to enter and exit the market at will. The proposed design employs robust regression models to learn the optimal forecasts' combination whilst handling missing submissions. Moreover, we introduce a pay-off allocation mechanism that considers both in-sample and out-of-sample performance while satisfying several desirable economic properties. Case-studies using simulated and real-world data allow demonstrating the effectiveness and adaptability of the proposed market design.

cs.LG↗

arXiv2025

Pooling Probabilistic Forecasts for Cooperative Wind Power Offering

Wind power producers can benefit from forming coalitions to participate cooperatively in electricity markets. To support such collaboration, various profit allocation rules rooted in cooperative game theory have been proposed. However, existing approaches overlook the lack of coherence among producers regarding forecast information, which may lead to ambiguity in offering and allocations. In this paper, we introduce a ``reconcile-then-optimize'' framework for cooperative market offerings. This framework first aligns the individual forecasts into a coherent joint forecast before determining market offers. With such forecasts, we formulate and solve a two-stage stochastic programming problem to derive both the aggregate offer and the corresponding scenario-based dual values for each trading hour. Based on these dual values, we construct a profit allocation rule that is budget-balanced and stable. Finally, we validate the proposed method through empirical case studies, demonstrating its practical effectiveness and theoretical soundness.

eess.SY↗

arXiv2025

Sufficient A Priori Conditions for the Linear Relaxation of the Energy Storage Scheduling Problem

When modeling energy storage systems, an essential question is how to account for the physical infeasibility of simultaneous charge and discharge. The use of complementarity constraints or of binary variables is common, but these formulations do not scale well. Alternatively, assumptions such as perfect efficiencies or positive prices are often used to justify the choice of a linear model. In this paper, we establish new a priori conditions that guarantee the existence of an optimal solution without simultaneous charge and discharge when solving the linear relaxation of the storage scheduling problem. They are based on the characteristics of the storage system, in particular, the duration of charge. They can be valid for negative prices and with inefficiencies, thereby enlarging the set of conditions for which the complementarity constraints can be relaxed. We prove mathematically the validity of these conditions and illustrate them with practical examples. We also introduce a refined mixed-integer linear equivalent, in which the number of binary variables can be drastically reduced.

math.OC↗

arXiv2025

Generalizable simulation framework for the request-to-order process in the procurement of onboard vessel requisitions

Procurement in maritime logistics faces challenges due to uncertainties in demand and fluctuating market conditions. To address these complexities, we introduce a flexible discrete-event simulation framework that models the request-to-order process. This framework captures critical stages, including the generation of onboard vessel requisitions, requisition handling, and order allocation. Through numerical analysis, we compare two order allocation policies: a naive practice, which relies heavily on contracts, and a dynamic supplier selection approach that explores cost opportunities in the spot market. Our findings reveal trade-offs between cost efficiency and contract compliance, particularly in meeting volume commitments to contracted suppliers. Excessive reliance on spot market opportunities can yield significant savings but at the expense of contract compliance. Additionally, when spot rates are highly sensitive to order quantities, both policies tend to overutilize contracts, highlighting the need for larger volume commitments in such cases. These results offer actionable insights for improving procurement practices, while the framework's adaptability makes it a powerful decision-support tool across diverse procurement contexts.

stat.AP↗

arXiv2025

Integrated optimization of operations and capacity planning under uncertainty for drayage procurement in container logistics

We present an integrated framework for truckload procurement in container logistics, bridging strategic and operational aspects that are often treated independently in existing research. Drayage, the short-haul trucking of containers, plays a critical role in intermodal container logistics. Using dynamic programming, we identify optimal operational policies for allocating drayage volumes among capacitated carriers under uncertain container flows and spot rates. The computational complexity of optimization under uncertainty is mitigated through sample average approximation. These optimal policies serve as the basis for evaluating specific capacity arrangements. To optimize capacity reservations with strategic and spot carriers, we employ an efficient quasi-Newton method. Numerical experiments demonstrate significant cost-efficiency improvements, including a 21.2% cost reduction in a four-period scenario. Monte Carlo simulations further highlight the strong generalization capabilities of the proposed joint optimization method across out-of-sample scenarios. These findings underscore the importance of integrating strategic and operational decisions to enhance cost efficiency in truckload procurement under uncertainty.

math.OC↗

arXiv2025

Multistage stochastic optimization for drayage procurement in container logistics using stochastic dual dynamic programming

Truckload procurement plays a vital role in integrated container logistics, particularly under the uncertainties of container flow and market conditions. We formulate the operational volume allocation problem in drayage procurement as a multistage stochastic transportation problem and solve it using stochastic dual dynamic programming (SDDP). We employ a multivariate count time series approach from the literature to model cargo flow dynamics, relaxing independence assumptions and capturing complex correlations. Our numerical experiments demonstrate the scalability of SDDP and its effectiveness in approximating high-quality policies across realistic problem instances. Sensitivity analyses highlight the significant impact of inflow uncertainties on costs, while spot market variability has a comparatively minor effect. Additionally, we propose an alternative stopping rule for SDDP iterations, balancing computational efficiency and solution fidelity.

math.OC↗

arXiv2025

Selling Information in Games with Externalities

A competitive market is modeled as a game of incomplete information. One player observes some payoff-relevant state and can sell (possibly noisy) messages thereof to the other, whose willingness to pay is contingent on their own beliefs. We frame the decision of what information to sell, and at what price, as a product versioning problem. The optimal menu screens buyer types to maximize profit, which is the payment minus the externality induced by selling information to a competitor, that is, the cost of refining a competitor's beliefs. For a class of games with binary actions and states, we derive the following insights: (i) payments are necessary to provide incentives for information sharing amongst competing firms; (ii) the optimal menu benefits both the buyer and the seller; (iii) the seller cannot steer the buyer's actions at the expense of social welfare; (iv) as such, as competition grows fiercer it can be optimal to sell no information at all.

cs.GT↗

arXiv2025

Value-oriented forecast reconciliation for renewables in electricity markets

Forecast reconciliation is considered an effective method to achieve coherence (within a forecast hierarchy) and to improve forecast quality. However, the value of reconciled forecasts in downstream decision-making tasks has been mostly overlooked. In a multi-agent setup with heterogeneous loss functions, this oversight may lead to unfair outcomes, hence resulting in conflicts during the reconciliation process. To address this, we propose a value-oriented forecast reconciliation approach that focuses on the forecast value for all individual agents. Fairness is ensured through the use of a Nash bargaining framework. Specifically, we model this problem as a cooperative bargaining game, where each agent aims to optimize their own gain while contributing to the overall reconciliation process. We then present a primal-dual algorithm for parameter estimation based on empirical risk minimization. From an application perspective, we consider an aggregated wind energy trading problem, where profits are distributed using a weighted allocation rule. We demonstrate the effectiveness of our approach through several numerical experiments, showing that it consistently results in increased profits for all agents involved.

stat.ML↗

arXiv2025

Do we actually understand the impact of renewables on electricity prices? A causal inference approach

The energy transition is profoundly reshaping electricity market dynamics. It makes it essential to understand how renewable energy generation actually impacts electricity prices, among all other market drivers. These insights are critical to design policies and market interventions that ensure affordable, reliable, and sustainable energy systems. However, identifying causal effects from observational data is a major challenge, requiring innovative causal inference approaches that go beyond conventional regression analysis only. We build upon the state of the art by developing and applying a local partially linear double machine learning approach. Its application yields the first robust causal evidence on the distinct and non-linear effects of wind and solar power generation on UK wholesale electricity prices, revealing key insights that have eluded previous analyses. We find that, over 2018-2024, wind power generation has a U-shaped effect on prices: at low penetration levels, a 1 GWh increase in energy generation reduces prices by up to 7 GBP/MWh, but this effect gets close to none at mid-penetration levels (20-30%) before intensifying again. Solar power places substantial downward pressure on prices at very low penetration levels (up to 9 GBP/MWh per 1 GWh increase in energy generation), though its impact weakens quite rapidly. We also uncover a critical trend where the price-reducing effects of both wind and solar power have become more pronounced over time (from 2018 to 2024), highlighting their growing influence on electricity markets amid rising penetration. Our study provides both novel analysis approaches and actionable insights to guide policymakers in appraising the way renewables impact electricity markets.

stat.AP↗

arXiv2024

How long is long enough? Finite-horizon approximation of energy storage scheduling problems

Energy storage scheduling problems, where a storage is operated to maximize its profit in response to a price signal, are essentially infinite-horizon optimization problems as storage systems operate continuously, without a foreseen end to their operation. Such problems can be solved to optimality with a rolling-horizon approach, provided that the planning horizon over which the problem is solved is long enough. Such a horizon is termed a forecast horizon. However, the length of the planning horizon is usually chosen arbitrarily for such applications. We introduce an easy-to-check condition that confirms whether a planning horizon is a forecast horizon, and which can be used to derive a bound on suboptimality when it is not the case. By way of an example, we demonstrate that the existence of forecast horizons is not guaranteed for this problem. We also derive a lower bound on the length of the minimum forecast horizon. We show how the condition introduced can be used as part of an algorithm to determine the minimum forecast horizon of the problem, which ensures the determination of optimal solutions at the lowest computational and forecasting costs. Finally, we provide insights into the implications of different planning horizons for a range of storage system characteristics.

math.OC↗