References of "Wehenkel, Louis"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailTrajectory-Based Supplementary Damping Control for Power System Electromechanical Oscillations
Wang, Da ULg; Glavic, Mevludin ULg; Wehenkel, Louis ULg

in IEEE Transactions on Power Systems (in press)

This paper considers a trajectory-based approach to determine control signals superimposed to those of existing controllers so as to enhance the damping of electromechanical oscillations. This approach is ... [more ▼]

This paper considers a trajectory-based approach to determine control signals superimposed to those of existing controllers so as to enhance the damping of electromechanical oscillations. This approach is framed as a discrete-time, multi-step optimization problem which can be solved by model-based and/or by learning-based methods. This paper proposes to apply a model-free tree-based batch mode Reinforcement Learning (RL) algorithm to perform such a supplementary damping control based only on information collected from observed trajectories of the power system. This RL-based supplementary damping control scheme is first implemented on a single generator and then several possibilities are investigated for extending it to multiple generators. Simulations are carried out on a 16-generators medium size power system model, where also possible benefits of combining this RL-based control with Model Predictive Control (MPC) are assessed. [less ▲]

Detailed reference viewed: 58 (5 ULg)
Full Text
Peer Reviewed
See detailRandom forests with random projections of the output space for high dimensional multi-label classification
Joly, Arnaud ULg; Geurts, Pierre ULg; Wehenkel, Louis ULg

in Machine Learning and Knowledge Discovery in Databases (2014, September 15)

We adapt the idea of random projections applied to the out- put space, so as to enhance tree-based ensemble methods in the context of multi-label classification. We show how learning time complexity can ... [more ▼]

We adapt the idea of random projections applied to the out- put space, so as to enhance tree-based ensemble methods in the context of multi-label classification. We show how learning time complexity can be reduced without affecting computational complexity and accuracy of predictions. We also show that random output space projections may be used in order to reach different bias-variance tradeoffs, over a broad panel of benchmark problems, and that this may lead to improved accuracy while reducing significantly the computational burden of the learning stage. [less ▲]

Detailed reference viewed: 2 (0 ULg)
Full Text
Peer Reviewed
See detailAn AC OPF-based Heuristic Algorithm for Optimal Transmission Switching
Capitanescu, Florin; Wehenkel, Louis ULg

in Proceedings of the 18th Power Systems Computation Conference (2014, August)

This paper focuses on reducing generators dispatch cost by means of transmission line switching. The problem is formulated as a mixed-integer nonlinear program (MINLP) optimal power flow (OPF). A scalable ... [more ▼]

This paper focuses on reducing generators dispatch cost by means of transmission line switching. The problem is formulated as a mixed-integer nonlinear program (MINLP) optimal power flow (OPF). A scalable heuristic algorithm is proposed to break-down the complexity of the problem due to the huge combinatorial space. The algorithm aims at providing the sequence of lines to be removed from service, one at the time, until no further decrease in the dispatch cost can be obtained. It identifies the line candidate for removal at each step by exploiting the (continuously relaxed values of) lines breaker statuses at the solution of a relaxed OPF problem. The algorithm thus relies on solving a sequence of OPF problems formulated as nonlinear programs (NLPs). The effectiveness of the approach is demonstrated on the IEEE118-bus system. Results show that the approach can provide good quality sub-optimal solutions with relatively small computational effort and by removing only few lines from service. [less ▲]

Detailed reference viewed: 13 (0 ULg)
Full Text
See detailAdvanced optimization methods for power systems
Panciatici, Patrick; Campi, M.C.; Garatti, S. et al

in Proceedings of the 18th Power Systems Computation Conference (2014, August)

Power system planning and operation offers multitudinous opportunities for optimization methods. In practice, these problems are generally large-scale, non-linear, subject to uncertainties, and combine ... [more ▼]

Power system planning and operation offers multitudinous opportunities for optimization methods. In practice, these problems are generally large-scale, non-linear, subject to uncertainties, and combine both continuous and discrete variables. In the recent years, a number of complementary theoretical advances in addressing such problems have been obtained in the field of applied mathematics. The paper introduces a selection of these advances in the fields of non-convex optimization, in mixedinteger programming, and in optimization under uncertainty. The practical relevance of these developments for power systems planning and operation are discussed, and the opportunities for combining them, together with high-performance computing and big data infrastructures, as well as novel machine learning and randomized algorithms, are highlighted. [less ▲]

Detailed reference viewed: 13 (1 ULg)
Full Text
Peer Reviewed
See detailComparison of centralized, distributed and hierarchical model predictive control schemes for electromechanical oscillations damping in large-scale power systems
Wang, Da ULg; Glavic, Mevludin ULg; Wehenkel, Louis ULg

in International Journal of Electrical Power & Energy Systems (2014), 58

The paper investigates the feasibility of applying Model Predictive Control (MPC) as a viable strategy to damp wide-area electromechanical oscillations in large-scale power systems. First a fully ... [more ▼]

The paper investigates the feasibility of applying Model Predictive Control (MPC) as a viable strategy to damp wide-area electromechanical oscillations in large-scale power systems. First a fully centralized MPC scheme is considered, and its performances are evaluated first in ideal conditions and then by considering state estimation errors and communication delays. This scheme is further extended into a distributed scheme with the aim of making it more viable for very large-scale or multi-area systems. Finally, a robust hierarchical multi-area MPC scheme is proposed, introducing a second layer of MPC based controllers at the level of individual power plants and transmission lines. Simulations are carried out using a 70-bus test system. The results reveal all three MPC schemes as viable solutions to supplement existing controllers in order to improve the system performance in terms of damping. The hierarchical scheme is the one combining the best performances in nominal conditions and the best robustness with respect to partial component failures and various modeling and measurement errors. [less ▲]

Detailed reference viewed: 51 (7 ULg)
Full Text
Peer Reviewed
See detailA generic approach for solving nonlinear-discrete security-constrained power flow problems in large-scale systems
Platbrood, Ludovic; Capitanescu, Florin; Crisciu, Horia et al

in IEEE Transactions on Power Systems (2014), 29(3), 1194-1203

This paper proves the practicality of an iterative algorithm for solving realistic large-scale SCOPF problems. This algorithm is based on the combination of a contingency filtering scheme, used to ... [more ▼]

This paper proves the practicality of an iterative algorithm for solving realistic large-scale SCOPF problems. This algorithm is based on the combination of a contingency filtering scheme, used to identify the binding contingencies at the optimum, and a network compression method, used to reduce the complexity of the post-contingency models included in the SCOPF formulation. We show that by combining these two complementary ideas, it is possible to solve in a reasonable time SCOPF problems on large power system models with a large number of contingencies. Unlike most results reported for large-scale SCOPF problems, our algorithm uses a non-linear AC network model in both pre-contingency and post-contingency states, optimizes both active/reactive powers flows jointly, and treats the discrete variables. The proposed algorithm is implemented with state-of-the-art solvers and applied to two systems: a national grid with 2563 buses and 1297 contingencies, and a model of the European transmission network with 9241 buses and 12000 contingencies. [less ▲]

Detailed reference viewed: 45 (6 ULg)
Full Text
Peer Reviewed
See detailA hybrid human-computer approach for large-scale image-based measurements using web services and machine learning
Marée, Raphaël ULg; Rollus, Loïc ULg; Stevens, Benjamin ULg et al

in Proceedings IEEE International Symposium on Biomedical Imaging (2014, May)

We present a novel methodology combining web-based software development practices, machine learning, and spatial databases for computer-aided quantification of regions of interest (ROIs) in large-scale ... [more ▼]

We present a novel methodology combining web-based software development practices, machine learning, and spatial databases for computer-aided quantification of regions of interest (ROIs) in large-scale imaging data. We describe our main methodological choices, and then illustrate the benefits of the approach (workload reduction, improved precision, scalability, and traceability) on hundreds of whole-slide images of biological tissue slices in cancer research. [less ▲]

Detailed reference viewed: 152 (39 ULg)
Full Text
Peer Reviewed
See detailExploiting SNP Correlations within Random Forest for Genome-Wide Association Studies
Botta, Vincent ULg; Louppe, Gilles ULg; Geurts, Pierre ULg et al

in PLoS ONE (2014)

The primary goal of genome-wide association studies (GWAS) is to discover variants that could lead, in isolation or in combination, to a particular trait or disease. Standard approaches to GWAS, however ... [more ▼]

The primary goal of genome-wide association studies (GWAS) is to discover variants that could lead, in isolation or in combination, to a particular trait or disease. Standard approaches to GWAS, however, are usually based on univariate hypothesis tests and therefore can account neither for correlations due to linkage disequilibrium nor for combinations of several markers. To discover and leverage such potential multivariate interactions, we propose in this work an extension of the Random Forest algorithm tailored for structured GWAS data. In terms of risk prediction, we show empirically on several GWAS datasets that the proposed T-Trees method significantly outperforms both the original Random Forest algorithm and standard linear models, thereby suggesting the actual existence of multivariate non-linear effects due to the combinations of several SNPs. We also demonstrate that variable importances as derived from our method can help identify relevant loci. Finally, we highlight the strong impact that quality control procedures may have, both in terms of predictive power and loci identification. [less ▲]

Detailed reference viewed: 36 (7 ULg)
Full Text
Peer Reviewed
See detailOptimized look-ahead tree policies: a bridge between look-ahead tree policies and direct policy search
Jung, Tobias ULg; Wehenkel, Louis ULg; Ernst, Damien ULg et al

in International Journal of Adaptive Control and Signal Processing (2014), 28(3-5), 255-289

Direct policy search (DPS) and look-ahead tree (LT) policies are two popular techniques for solving difficult sequential decision-making problems. They both are simple to implement, widely applicable ... [more ▼]

Direct policy search (DPS) and look-ahead tree (LT) policies are two popular techniques for solving difficult sequential decision-making problems. They both are simple to implement, widely applicable without making strong assumptions on the structure of the problem, and capable of producing high performance control policies. However, computationally both of them are, each in their own way, very expensive. DPS can require huge offline resources (effort required to obtain the policy) to first select an appropriate space of parameterized policies that works well for the targeted problem, and then to determine the best values of the parameters via global optimization. LT policies do not require any offline resources; however, they typically require huge online resources (effort required to calculate the best decision at each step) in order to grow trees of sufficient depth. In this paper, we propose optimized look-ahead trees (OLT), a model-based policy learning scheme that lies at the intersection of DPS and LT. In OLT, the control policy is represented indirectly through an algorithm that at each decision step develops, as in LT using a model of the dynamics, a small look-ahead tree until a prespecified online budget is exhausted. Unlike LT, the development of the tree is not driven by a generic heuristic; rather, the heuristic is optimized for the target problem and implemented as a parameterized node scoring function learned offline via DPS. We experimentally compare OLT with pure DPS and pure LT variants on optimal control benchmark domains. The results show that the LT-based representation is a versatile way of compactly representing policies in a DPS scheme (which results in OLT being easier to tune and having lower offline complexity than pure DPS); while at the same time, DPS helps to significantly reduce the size of the look-ahead trees that are required to take high-quality decisions (which results in OLT having lower online complexity than pure LT). Moreover, OLT produces overall better performing policies than pure DPS and pure LT and also results in policies that are robust with respect to perturbations of the initial conditions. [less ▲]

Detailed reference viewed: 83 (32 ULg)
Full Text
See detailPower system transient stability preventive and emergency control
Ruiz-Vega, Daniel; Wehenkel, Louis ULg; Ernst, Damien ULg et al

in Savulescu, Savu (Ed.) Real-Time Stability in Power Systems 2nd Edition (2014)

A general approach to real-time transient stability control is described, yielding various complementary techniques: pure preventive, open loop emergency, and closed loop emergency controls. Recent ... [more ▼]

A general approach to real-time transient stability control is described, yielding various complementary techniques: pure preventive, open loop emergency, and closed loop emergency controls. Recent progress in terms of a global transient stability constrained optimal power flow are presented, yielding in a scalable nonlinear programming formulation which allows to take near-optimal decisions for preventive control with a computing budget corresponding only to a few runs of standard optimal power flow and time domain simulations. These complementary techniques meet the stringent conditions imposed by the real-life applications. [less ▲]

Detailed reference viewed: 18 (2 ULg)
Full Text
See detailA Supervised Machine Learning Approach to Variable Branching in Branch-And-Bound
Marcos Alvarez, Alejandro ULg; Louveaux, Quentin ULg; Wehenkel, Louis ULg

E-print/Working paper (2014)

We present in this paper a new approach that uses supervised machine learning techniques to improve the performances of optimization algorithms in the context of mixed-integer programming (MIP). We focus ... [more ▼]

We present in this paper a new approach that uses supervised machine learning techniques to improve the performances of optimization algorithms in the context of mixed-integer programming (MIP). We focus on the branch-and-bound (B&B) algorithm, which is the traditional algorithm used to solve MIP problems. In B&B, variable branching is the key component that most conditions the efficiency of the optimization. Good branching strategies exist but are computationally expensive and usually hinder the optimization rather than improving it. Our approach consists in imitating the decisions taken by a supposedly good branching strategy, strong branching in our case, with a fast approximation. To this end, we develop a set of features describing the state of the ongoing optimization and show how supervised machine learning can be used to approximate the desired branching strategy. The approximated function is created by a supervised machine learning algorithm from a set of observed branching decisions taken by the target strategy. The experiments performed on randomly generated and standard benchmark (MIPLIB) problems show promising results. [less ▲]

Detailed reference viewed: 40 (1 ULg)
Full Text
Peer Reviewed
See detailApprentissage par renforcement batch fondé sur la reconstruction de trajectoires artificielles
Fonteneau, Raphaël ULg; Murphy, Susan A.; Wehenkel, Louis ULg et al

in Proceedings of the 9èmes Journées Francophones de Planification, Décision et Apprentissage (JFPDA 2014) (2014)

Cet article se situe dans le cadre de l’apprentissage par renforcement en mode batch, dont le problème central est d’apprendre, à partir d’un ensemble de trajectoires, une politique de décision optimisant ... [more ▼]

Cet article se situe dans le cadre de l’apprentissage par renforcement en mode batch, dont le problème central est d’apprendre, à partir d’un ensemble de trajectoires, une politique de décision optimisant un critère donné. On considère plus spécifiquement les problèmes pour lesquels l’espace d’état est continu, problèmes pour lesquels les schémas de résolution classiques se fondent sur l’utilisation d’approxima- teurs de fonctions. Cet article propose une alternative fondée sur la reconstruction de “trajectoires arti- ficielles” permettant d’aborder sous un angle nouveau les problèmes classiques de l’apprentissage par renforcement batch. [less ▲]

Detailed reference viewed: 24 (5 ULg)
Full Text
Peer Reviewed
See detailOn the Encoding of Proteins for Disordered Regions Prediction
Becker, Julien ULg; Maes, Francis; Wehenkel, Louis ULg

in PLoS ONE (2013)

Disordered regions, i.e., regions of proteins that do not adopt a stable three-dimensional structure, have been shown to play various and critical roles in many biological processes. Predicting and ... [more ▼]

Disordered regions, i.e., regions of proteins that do not adopt a stable three-dimensional structure, have been shown to play various and critical roles in many biological processes. Predicting and understanding their formation is therefore a key sub-problem of protein structure and function inference. A wide range of machine learning approaches have been developed to automatically predict disordered regions of proteins. One key factor of the success of these methods is the way in which protein information is encoded into features. Recently, we have proposed a systematic methodology to study the relevance of various feature encodings in the context of disulfide connectivity pattern prediction. In the present paper, we adapt this methodology to the problem of predicting disordered regions and assess it on proteins from the 10th CASP competition, as well as on a very large subset of proteins extracted from PDB. Our results, obtained with ensembles of extremely randomized trees, highlight a novel feature function encoding the proximity of residues according to their accessibility to the solvent, which is playing the second most important role in the prediction of disordered regions, just after evolutionary information. Furthermore, even though our approach treats each residue independently, our results are very competitive in terms of accuracy with respect to the state-of-the-art. A web-application is available at http://m24.giga.ulg.ac.be:81/x3Disorder. [less ▲]

Detailed reference viewed: 13 (4 ULg)
Full Text
Peer Reviewed
See detailUnderstanding variable importances in forests of randomized trees
Louppe, Gilles ULg; Wehenkel, Louis ULg; Sutera, Antonio ULg et al

in Advances in Neural Information Processing Systems 26 (2013, December)

Despite growing interest and practical use in various scientific areas, variable importances derived from tree-based ensemble methods are not well understood from a theoretical point of view. In this work ... [more ▼]

Despite growing interest and practical use in various scientific areas, variable importances derived from tree-based ensemble methods are not well understood from a theoretical point of view. In this work we characterize the Mean Decrease Impurity (MDI) variable importances as measured by an ensemble of totally randomized trees in asymptotic sample and ensemble size conditions. We derive a three-level decomposition of the information jointly provided by all input variables about the output in terms of i) the MDI importance of each input variable, ii) the degree of interaction of a given input variable with the other input variables, iii) the different interaction terms of a given degree. We then show that this MDI importance of a variable is equal to zero if and only if the variable is irrelevant and that the MDI importance of a relevant variable is invariant with respect to the removal or the addition of irrelevant variables. We illustrate these properties on a simple example and discuss how they may change in the case of non-totally randomized trees such as Random Forests and Extra-Trees. [less ▲]

Detailed reference viewed: 1041 (132 ULg)
Full Text
Peer Reviewed
See detailA rich internet application for remote visualization and collaborative annotation of digital slide images in histology and cytology
Marée, Raphaël ULg; Stevens, Benjamin ULg; Rollus, Loïc ULg et al

in Diagnostic Pathology (2013), 8(S1), 26

This work proposes a new web-based tool to ease collaborative projects in digital histology and cytology.

Detailed reference viewed: 121 (40 ULg)
Full Text
Peer Reviewed
See detailBatch mode reinforcement learning based on the synthesis of artificial trajectories
Fonteneau, Raphaël ULg; Murphy, Susan A.; Wehenkel, Louis ULg et al

in Annals of Operations Research (2013), 208(1), 383-416

Detailed reference viewed: 46 (18 ULg)
Full Text
Peer Reviewed
See detailComputation of worst operation scenarios under uncertainty for static security management
Capitanescu, Florin; Wehenkel, Louis ULg

in IEEE Transactions on Power Systems (2013), 28(2), 1697-1705

This paper deals with day-ahead static security assessment with respect to a postulated set of contingencies while taking into account uncertainties about the next day system conditions. We propose a ... [more ▼]

This paper deals with day-ahead static security assessment with respect to a postulated set of contingencies while taking into account uncertainties about the next day system conditions. We propose a heuristic approach to compute the worst-case under operation uncertainty for a contingency with respect to overloads. We formulate this problem as a non-convex nonlinear bilevel program that we solve approximately by a heuristic approach which relies on the solution of successive optimal power flow (OPF) and security-constrained optimal power flow (SCOPF) problems of a special type. The method aims at revealing those combinations of uncertainties and contingencies for which the best combination of preventive and corrective actions would not suffice to ensure security. Extensive numerical results on a small, a medium, and a very large system prove the interest of the approach. [less ▲]

Detailed reference viewed: 58 (9 ULg)
Full Text
Peer Reviewed
See detailAn efficient algorithm to perform multiple testing in epistasis screening
Van Lishout, François ULg; Mahachie John, Jestinah ULg; Gusareva, Elena ULg et al

in BMC Bioinformatics (2013), 14

Background: Research in epistasis or gene-gene interaction detection for human complex traits has grown over the last few years. It has been marked by promising methodological developments, improved ... [more ▼]

Background: Research in epistasis or gene-gene interaction detection for human complex traits has grown over the last few years. It has been marked by promising methodological developments, improved translation efforts of statistical epistasis to biological epistasis and attempts to integrate different omics information sources into the epistasis screening to enhance power. The quest for gene-gene interactions poses severe multiple-testing problems. In this context, the maxT algorithm is one technique to control the false-positive rate. However, the memory needed by this algorithm rises linearly with the amount of hypothesis tests. Gene-gene interaction studies will require a memory proportional to the squared number of SNPs. A genome-wide epistasis search would therefore require terabytes of memory. Hence, cache problems are likely to occur, increasing the computation time. In this work we present a new version of maxT, requiring an amount of memory independent from the number of genetic effects to be investigated. This algorithm was implemented in C++ in our epistasis screening software MBMDR-3.0.3. We evaluate the new implementation in terms of memory efficiency and speed using simulated data. The software is illustrated on real-life data for Crohn's disease. Results: In the case of a binary (affected/unaffected) trait, the parallel workflow of MBMDR-3.0.3 analyzes all gene-gene interactions with a dataset of 100,000 SNPs typed on 1000 individuals within 4 days and 9 hours, using 999 permutations of the trait to assess statistical significance, on a cluster composed of 10 blades, containing each four Quad-Core AMD Opteron Processor 2352 2.1 GHz. In the case of a continuous trait, a similar run takes 9 days. Our program found 14 SNP-SNP interactions with a multiple-testing corrected p-value of less than 0.05 on real-life Crohn's disease data. Conclusions: Our software is the first implementation of the MB-MDR methodology able to solve large-scale SNP-SNP interactions problems within a few days, without using much memory, while adequately controlling the type I error rates. A new implementation to reach genome-wide epistasis screening is under construction. In the context of Crohn's disease, MBMDR-3.0.3 could identify epistasis involving regions that are well known in the field and could be explained from a biological point of view. This demonstrates the power of our software to find relevant phenotype-genotype higher-order associations. [less ▲]

Detailed reference viewed: 54 (17 ULg)
Full Text
Peer Reviewed
See detailOn the Relevance of Sophisticated Structural Annotations for Disulfide Connectivity Pattern Prediction
Becker, Julien ULg; Maes, Francis; Wehenkel, Louis ULg

in PLoS ONE (2013), 8(2), 56621

Disulfide bridges strongly constrain the native structure of many proteins and predicting their formation is therefore a key sub-problem of protein structure and function inference. Most recently proposed ... [more ▼]

Disulfide bridges strongly constrain the native structure of many proteins and predicting their formation is therefore a key sub-problem of protein structure and function inference. Most recently proposed approaches for this prediction problem adopt the following pipeline: first they enrich the primary sequence with structural annotations, second they apply a binary classifier to each candidate pair of cysteines to predict disulfide bonding probabilities and finally, they use a maximum weight graph matching algorithm to derive the predicted disulfide connectivity pattern of a protein. In this paper, we adopt this three step pipeline and propose an extensive study of the relevance of various structural annotations and feature encodings. In particular, we consider five kinds of structural annotations, among which three are novel in the context of disulfide bridge prediction. So as to be usable by machine learning algorithms, these annotations must be encoded into features. For this purpose, we propose four different feature encodings based on local windows and on different kinds of histograms. The combination of structural annotations with these possible encodings leads to a large number of possible feature functions. In order to identify a minimal subset of relevant feature functions among those, we propose an efficient and interpretable feature function selection scheme, designed so as to avoid any form of overfitting. We apply this scheme on top of three supervised learning algorithms: k-nearest neighbors, support vector machines and extremely randomized trees. Our results indicate that the use of only the PSSM (position-specific scoring matrix) together with the CSP (cysteine separation profile) are sufficient to construct a high performance disulfide pattern predictor and that extremely randomized trees reach a disulfide pattern prediction accuracy of on the benchmark dataset SPX+, which corresponds to +3.2% improvement over the state of the art. A web-application is available at http://m24.giga.ulg.ac.be:81/x3CysBridge​s. [less ▲]

Detailed reference viewed: 40 (15 ULg)
Full Text
Peer Reviewed
See detailExtremely Randomized Trees and Random Subwindows for Image Classification, Annotation, and Retrieval
Marée, Raphaël ULg; Wehenkel, Louis ULg; Geurts, Pierre ULg

in Criminisi, A; Shotton, J (Eds.) Decision Forests in Computer Vision and Medical Image Analysis, Advances in Computer Vision and Pattern Recognition (2013)

We present a unified framework involving the extraction of random subwindows within images and the induction of ensembles of extremely randomized trees. We discuss the specialization of this framework for ... [more ▼]

We present a unified framework involving the extraction of random subwindows within images and the induction of ensembles of extremely randomized trees. We discuss the specialization of this framework for solving several general problems in computer vision, ranging from image classification and segmentation to content-based image retrieval and interest point detection. The methods are illustrated on various applications and datasets from the biomedical domain [less ▲]

Detailed reference viewed: 230 (45 ULg)