This study investigates scheduling strategies for the stochastic resource-constrained project scheduling problem with maximal time lags (SRCPSP/max). Recent advances in Constraint Programming (CP) and Temporal Networks have re-invoked interest in evaluating the advantages and drawbacks of various proactive and reactive scheduling methods. First, we present a new, CP-based fully proactive method. Second, we show how a reactive approach can be constructed using an online rescheduling procedure. A third contribution is based on partial order schedules and uses Simple Temporal Networks with Uncertainty (STNUs). Our statistical analysis shows that the STNU-based algorithm performs best in terms of solution quality, while also showing good relative offline and online computation time.

Smart “predict, then optimize” (SPO) (Elmachtoub in Manag Sci 68(1): 9–26, 2022) is an end-to-end learning strategy for models that predict parameters in optimization problems. Unlike minimizing mean squared error (MSE) which cares about prediction accuracies, SPO aims to ensure that predictions lead to the best possible decisions. The associated loss function, termed SPO loss, measures the decision’s regret from optimal outcomes with parameter realizations. Existing literature has demonstrated the viability of SPO, however, these studies often focus on classical optimization problems and employ a limited set of models for benchmarking. In this study, we tackled a decision-making task inspired by real-world challenges across a wide range of neural network models. Unlike classical problems, our task requires a unique approach: collaboratively training two models to predict different variables. On top of that, one of the decision variables also affects the feasibility of the decisions, further increasing the complexity. While our implementation validates the benefits of SPO, we were surprised to find that models trained exclusively on SPO loss do not consistently attain the minimum regret. Our further investigation into hyperparameters illustrates that the well-tuned models learned very similar patterns from the feature set, irrespective of whether MSE or SPO loss was used. In other words, the change from MSE to SPO loss in training primarily affected the layer biases. Therefore, to improve the learning efficacy with SPO loss, we propose prioritizing learning feature patterns as the fundamental step. Possible strategies include using specialized neural network layers to capture deeper patterns more effectively or simply warming up by training with MSE. Specifically, a warming-up process is particularly advantageous for model(s) where the outputs are closely tied to constraints, as their prediction accuracy significantly impacts the decision feasibility. The insights are investigated empirically through two real-world trading scenarios. By leveraging datasets with diverse properties, we demonstrate the novelty and generalizability of our investigation.

Exposure to research is an important component of undergraduate university education, cultivating critical thinking, problem-solving, and preparation for advanced study. However, providing individual research experiences for large cohorts of undergraduate students poses significant logistical challenges. This paper demonstrates how an undergraduate research experience can be achieved at scale for a large computer science program. Our approach integrates individual research projects into the undergraduate computer science curriculum for up to almost 400 students within a single 10-week course. We describe three key features of our approach: (1) a matching algorithm that assigns students to research projects based on their preferences, (2) peer-group collaboration, and (3) a distributed supervision and assessment model to guide students through key research activities that include reformulating research questions, designing experiments/user studies, and presenting research. Results and feedback indicate that both students and supervisors are satisfied, demonstrating the feasibility and effectiveness of this scalable approach for integrating research experiences into large undergraduate computer science programs.

With a dense infrastructure and limited space, the opportunities for increasing the capacity of the railway network in the Netherlands are limited. One of the bottlenecks is optimally using the available space around stations and in shunting yards. Many details must be considered, increasing the complexity of the problem. Human planners can benefit from computational support to ensure efficient use of the infrastructure. We introduce a framework for positioning previous research in terms of abstractions and highlight a promising future direction: the development of a new approach that combines different methods and uses the relations between the abstractions to create more efficient solutions.

To achieve climate goals by 2050, accurate energy system optimization (MIP) models are needed to help decision-makers make investment plans. To increase accuracy, a high resolution in the temporal and spatial dimensions is needed, as well as many details on the operational capabilities of energy generators. However, this results in large-scale models that do not scale well. Thus, researchers often seek the right trade-off between computational tractability and accuracy. Here, we present a tighter formulation for optimal storage operation and investment problems, including reserves, along with the methodology we used to obtain it, based on the work of [2]. Additionally, we present some preliminary work aiming to provide tight and compact unit commitment models with different levels of detail. These models can be included in large-scale energy system optimization models to increase model accuracy while keeping the models computationally tractable.

Research in railway operations has mostly focused on operations research methods. However, these real-world problems have a state-based nature, which makes them very suitable for AI models, such as the Multi-Agent Pathfinding problem, where agents move in a grid and need to be routed from their start to their goal location without colliding with each other. The core aspect of problems like train shunting and train dispatching is routing, which is often not the main focus of current mathematical formulations. Therefore, we apply the state-of-the-art algorithms to the railway problems of shunting and dispatching and study their usability for routing trains. The Multi-Agent Pathfinding problem is often solved with one of two algorithms: conflict-based search (a two-stage algorithm detecting conflicts between individual paths and using A* search to find new conflict-free paths), and branch-cut-and-price (a linear program adding cuts (row generation) based on problem-specific constraints, and finding new paths to be selected that satisfy all constraints using a pricer). We modify these algorithms to include more railway details. First, we allow for the matching of train units (i.e., ensure the necessary train units of a certain type are available for departure) by specifying goals for agent (type) groups instead of single agent goals. Moreover, we add goal sequences for servicing stations and agents of different sizes, and we study specific aspects of the railway infrastructure to exploit in the algorithm. Finally, we show the use of Multi-Agent Pathfinding solvers in different railway settings and analyze the conditions for success.

Future energy markets for low voltage AC and DC distribution systems will facilitate prosumer participation in the market. To comply with market regulations and grid constraints, a tailored market design reflecting (DC) operational requirements is needed. Our previous work identified a locational energy market design. However, its real-life implementation faces challenges due to uncertainties in system operation, prosumer preferences, and bidding strategies. This article tests the market design under uncertain scenarios. To this end, we develop an agent-based model that simulates typical electric vehicle user preferences and bidding strategies, influenced by varying degrees of range anxiety. The market design is tested in challenging scenarios with a high share of solar panels and electric vehicles, modelled using the high-resolution Pecan Street database. Simulations indicate that the proposed market design maintains both economic efficiency and system reliability under real-life uncertainties. This in turn indicates the practical feasibility of locational energy markets in helping to integrate renewable generation sources and bidirectional power flows.

Because the energy transition is a critical and urgent issue that is increasingly reliant on data, the Center for Energy System Intelligence (CESI), a Convergence collaboration between TU Delft and Erasmus University Rotterdam, has developed a platform where researchers on the energy transition can share, publish, and/or find energy-related datasets and algorithms: EnergySHR. This platform aims to accelerate energy transition research into intelligent, data-driven algorithms. In this demonstration, we present the EnergySHR platform as both a platform for storing, accessing, managing, and archiving datasets as well as a tool to conduct empirical research about platformization and data-driven decision-making about the energy transition.

The project “Real-time data-driven maintenance logistics” was initiated with the purpose of bringing innovations in data-driven decision making to maintenance logistics, by bringing problem owners in the form of three innovative companies together with researchers at two leading knowledge institutions. This paper reviews innovations in three related areas: How the innovations were inspired by practice, how they materialized, and how the results impact practice.

Train routing is sensitive to delays that occur in the network. When a train is delayed, it is imperative that a new plan be found quickly, or else other trains may need to be stopped to ensure safety, potentially causing cascading delays. In this paper, we consider this class of multi-agent planning problems, which we call Multi-Agent Execution Delay Replanning. We show that these can be solved by reducing the problem to an any-start-time safe interval path planning problem. When an agent has an any-start-time plan, it can react to a delay by simply looking up the precomputed plan for the delayed start time. We identify crucial real-world problem characteristics like the agent's speed, size, and safety envelope, and extend the any-start-time planning to account for them. Experimental results on real-world train networks show that any-start-time plans are compact and can be computed in reasonable time while enabling agents to instantly recover a safe plan.

People want to rely on optimization algorithms for complex decisions but verifying the optimality of the solutions can then become a valid concern, particularly for critical decisions taken by non-experts in optimization. One example is the shortest-path problem on a network, occurring in many contexts from transportation to logistics to telecommunications. While the standard shortest-path problem is both solvable in polynomial time and certifiable by duality, introducing side constraints makes solving and certifying the solutions much harder. We propose a proof system for constrained shortest-path problems, which gives a set of logical rules to derive new facts about feasible solutions. The key trait of the proposed proof system is that it specifically includes high-level graph concepts within its reasoning steps (such as connectivity or path structure), in contrast to using linear combinations of model constraints. Using our proof system, we can provide a step-by-step, human-auditable explanation showing that the path given by an external solver cannot be improved. Additionally, to maximize the advantages of this setup, we propose a proof search procedure that specifically aims to find small proofs of this form using a procedure similar to A* search. We evaluate our proof system on constrained shortest path instances generated from real-world road networks and experimentally show that we may indeed derive more interpretable proofs compared to an integer programming approach, in some cases leading to much smaller proofs.

When optimizing problems with uncertain parameter values in a linear objective, decision-focused learning enables end-to-end learning of these values. We are interested in a stochastic scheduling problem, in which processing times are uncertain, which brings uncertain values in the constraints, and thus repair of an initial schedule may be needed. Historical realizations of the stochastic processing times are available. We show how existing decision-focused learning techniques based on stochastic smoothing can be adapted to this scheduling problem. We include an extensive experimental evaluation to investigate in which situations decision-focused learning outperforms the state of the art, i.e., scenario-based stochastic optimization.

Multiple Object Tracking (MOT) is a rapidly developing research field that targets precise and reliable tracking of objects. Unfortunately, most available MOT datasets typically contain short video clips only, disregarding the indispensable requirement for adequately capturing substantial long-term variations in real-world scenarios. Long-term MOT poses unique challenges due to changes in both the objects and the environment, which remain relatively unexplored. To fill the gap, we propose a time-lapse image dataset inspired by the growth monitoring of strawberries, dubbed The Growing Strawberries Dataset (GSD). The data was captured hourly by six cameras, covering a span of 16 months in 2021 and 2022. During this time, it encompassed a total of 24 plants in two separate greenhouses. The changes in appearance, weight, and position during the ripening process, along with variations in the illumination during data collection, distinguish the task from previous MOT research. These practical issues resulted in a drastic performance downgrade in the track identification and association tasks of state-of-the-art MOT algorithms. We believe The Growing Strawberries will provide a platform for evaluating such long-term MOT tasks and inspire future research. The dataset is available at https://doi.org/10.4121/e3b31ece-cc88-4638-be10-8ccdd4c5f2f7.v1.

In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the task efficiently. Choosing a good reward function is hence an extremely important yet challenging problem. In this paper, we explore an alternative approach for using rewards for learning. We introduce max-reward RL, where an agent optimizes the maximum rather than the cumulative reward. Unlike earlier works, our approach works for deterministic and stochastic environments and can be easily combined with state-of-the-art RL algorithms. In the experiments, we study the performance of max-reward RL algorithms in two goal-reaching environments from Gymnasium-Robotics and demonstrate its benefits over standard RL. The code is available at https://github.com/veviurko/To-the-Max.

Surrogate algorithms such as Bayesian optimisation are especially designed for black-box optimisation problems with expensive objectives, such as hyperparameter tuning or simulation-based optimisation. In the literature, these algorithms are usually evaluated with synthetic benchmarks which are well established but have no expensive objective, and only on one or two real-life applications which vary wildly between papers. There is a clear lack of standardisation when it comes to benchmarking surrogate algorithms on real-life, expensive, black-box objective functions. This makes it very difficult to draw conclusions on the effect of algorithmic contributions and to give substantial advice on which method to use when. A new benchmark library, EXPObench, provides first steps towards such a standardisation. The library is used to provide an extensive comparison of six different surrogate algorithms on four expensive optimisation problems from different real-life applications. This has led to new insights regarding the relative importance of exploration, the evaluation time of the objective, and the used model. We also provide rules of thumb for which surrogate algorithm to use in which situation. A further contribution is that we make the algorithms and benchmark problem instances publicly available, contributing to more uniform analysis of surrogate algorithms. Most importantly, we include the results of the six algorithms on all evaluated problem instances. This unique new dataset lowers the bar for researching new methods as the number of expensive evaluations required for comparison and for the creation of new surrogate models is significantly reduced.

The Train Unit Shunting Problem concerns the parking of trains outside their scheduled use on so-called shunting yards. This is an NP-hard problem, and the current algorithm used by the Netherlands Railways cannot detect whether an instance is infeasible. So, infeasible instances can cause needlessly long computation times. Therefore, this paper fills the gap by providing novel approaches to determine the feasibility. For this, the Pebble Motion problem is considered which moves pebbles from their starting node to their goal node in the graph, such that no two pebbles occupy a node at the same time. A variant of the Pebble Motion problem is proposed to model the Train Unit Shunting Problem, where train units are represented by pebbles and the arrival and departure of train unit combinations are also included. This paper specifically looks at dead-end track shunting yards, as they can be abstractly represented by trees, such that trains arrive and depart at the root node. Furthermore, trains cannot be reallocated between arrival and departure in the tree, since reallocation in practice is a very costly process as moves need to be performed by a small set of drivers. The conditions for realizing the departure order of trains are studied, and an efficient method to (partially) determine the feasibility of problem instances is given, which can find the minimal number of tracks required to park the trains. Furthermore, a special case with tracks of length two is shown to be polynomially solvable, while another subset of problem instances with tracks of length six or more is demonstrated to be NP-complete.

Global optimization of decision trees has shown to be promising in terms of accuracy, size, and consequently human comprehensibility. However, many of the methods used rely on general-purpose solvers for which scalability remains an issue. Dynamic programming methods have been shown to scale much better because they exploit the tree structure by solving subtrees as independent subproblems. However, this only works when an objective can be optimized separately for subtrees. We explore this relationship in detail and show necessary and sufficient conditions for such separability and generalize previous dynamic programming approaches into a framework that can optimize any combination of separable objectives and constraints. Experiments on five application domains show the general applicability of this framework, while outperforming the scalability of general-purpose solvers by a large margin.

The integration of Distributed Energy Resources (DERs) in distribution networks comes with challenges, like power quality concerns, but also opens up new opportunities, e.g., DERs can offer competitive energy prices for final users by leveraging time arbitrage. A suitable method to fully exploit such opportunities is to compute the optimal DER schedule, either with a full three-phase network model or a more computationally efficient single-line equivalent. This paper presents under which conditions a single-line equivalent can and cannot be used to properly represent a modern and unbalanced power distribution network able to dispatch high levels of DER integration optimally. Results show that single-line equivalents might be helpful when the problem objective function limits counterflows, for example, when minimizing active power losses. Moreover, single-line equivalents might be helpful for low levels of DER integration. However, enabling single-line equivalents results in a lower hosting capacity for high levels of DER integration.