References of "Ernst, Damien"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailA collaborative framework for multi-area dynamic security assessment of large scale systems
Wehenkel, Louis ULg; Glavic, Mevludin; Ernst, Damien ULg

in Proceedings of the 2007 Power Tech (2007)

In this paper we propose a collaborative framework to carry out multi-area dynamic security assessment over an interconnection operated by a team of TSOs responsible of different areas. In this framework ... [more ▼]

In this paper we propose a collaborative framework to carry out multi-area dynamic security assessment over an interconnection operated by a team of TSOs responsible of different areas. In this framework each TSO does his part of the work and, thanks to information exchange and coordination rules, potential security problems can be detected by all the involved TSOs. We find that distributed multi-area security assessment is achievable and useful if, on the one hand, each TSO can provide an appropriate dynamic equivalent model of his area and if, on the other hand, he is able to publish stability bounds on his inflows under which the dynamic performance of his system would remain acceptable. We then discuss the notions of dynamic equivalent model and external stability domain characterization of an area and identify techniques for deriving such equivalents and stability bounds within the proposed framework. [less ▲]

Detailed reference viewed: 29 (2 ULg)
Full Text
Peer Reviewed
See detailNash equilibrium as the minimum of a function. Application to electricity markets with large number of actors
Beck, Elena Vdovina; Cherkaoui, Rachid; Minoia, Anna et al

in Proceedings of the 2007 Power Tech (2007)

We introduce in this paper a new approach for efficiently identifying Nash equilibria for games composed of large numbers of players having discrete and not too large strategy spaces. The approach is ... [more ▼]

We introduce in this paper a new approach for efficiently identifying Nash equilibria for games composed of large numbers of players having discrete and not too large strategy spaces. The approach is based on a characterization of Nash equilibria in terms of minima of a function and relies on stochastic optimization algorithms to find these minima. The approach is applied to compute Nash equilibria of some electricity markets and, based on the simulation results, its performances are discussed. [less ▲]

Detailed reference viewed: 49 (4 ULg)
Full Text
Peer Reviewed
See detailThe cross-entropy method for power system combinatorial optimization problems
Ernst, Damien ULg; Glavic, Mevludin; Stan, Guy-Bart et al

in Proceedings of the 2007 Power Tech (2007)

We present an application of a cross-entropy based combinatorial optimization method for solving some unit commitment problems. We report simulation results and analyze, under several perspectives ... [more ▼]

We present an application of a cross-entropy based combinatorial optimization method for solving some unit commitment problems. We report simulation results and analyze, under several perspectives (accuracy, computing times, ability to solve efficiently large-scale problems), the performances of the approach. [less ▲]

Detailed reference viewed: 33 (2 ULg)
Full Text
Peer Reviewed
See detailModel predictive control and reinforcement learning as two complementary frameworks
Ernst, Damien ULg; Glavic, Mevludin; Capitanescu, Florin ULg et al

in International Journal of Tomography & Statistics (2007), 6

Model predictive control (MPC) and reinforcement learning (RL) are two popular families of methods to control system dynamics. In their traditional setting, they formulate the control problem as a ... [more ▼]

Model predictive control (MPC) and reinforcement learning (RL) are two popular families of methods to control system dynamics. In their traditional setting, they formulate the control problem as a discrete-time optimal control problem and compute a suboptimal control policy. We present in this paper in a unified framework these two families of methods. We run for MPC and RL algorithms simulations on a benchmark control problem taken from the power system literature and discuss the results obtained. [less ▲]

Detailed reference viewed: 55 (12 ULg)
Full Text
Peer Reviewed
See detailE-SIME- A method for transient stability closed-loop emergency control: achievements and prospects
Glavic, Mevludin; Ernst, Damien ULg; Ruiz-Vega, Daniel et al

in Proceedings of 2007 IREP Symposium - Bulk Power Systems Dynamics and Control - VII (2007)

A general response-based technique is presented for closed-loop transient stability emergency control. It relies on E-SIME, derived from the hybrid transient stability method, SIME. E-SIME uses real-time ... [more ▼]

A general response-based technique is presented for closed-loop transient stability emergency control. It relies on E-SIME, derived from the hybrid transient stability method, SIME. E-SIME uses real-time information supposed to be furnished by phasor measurement units to predict the stability status of the power system, and, in view of an imminent instability, to design and trigger appropriate countermeasures, while continuing monitoring in order to check their effectiveness or to apply additional ones. Performance of the method in terms of accuracy and rapidity is scrutinized and illustrated on several real-world power system examples. New technical solutions and algorithms for the accurate estimation and prediction of power system quantities most relevant to the method are discussed. The observations from a recent investigation and conclusions that could prove useful for improving further the method are summarized together with some realistic timing considerations. A natural coupling of the two SIME based emergency control techniques: open-loop emergency control and E-SIME, so as to combine their complementary features is also discussed. [less ▲]

Detailed reference viewed: 117 (7 ULg)
Full Text
Peer Reviewed
See detailContinuous-state reinforcement learning with fuzzy approximation
Busoniu, Lucian; Ernst, Damien ULg; Babuska, Robert et al

in Proceedings of the 7th European Symposium on Adaptive Learning Agents and Multi-Agent Systems (ALAMAS-07) (2007)

Reinforcement learning (RL) is a widely used learning paradigm for adaptive agents. Well-understood RL algorithms with good convergence and consistency properties exist. In their original form, these ... [more ▼]

Reinforcement learning (RL) is a widely used learning paradigm for adaptive agents. Well-understood RL algorithms with good convergence and consistency properties exist. In their original form, these algorithms require that the environment states and agent actions take values in a relatively small discrete set. Fuzzy representations for approximate, model-free RL have been proposed in the literature for the more difficult case where the state-action space is continuous. In this work, we propose a fuzzy approximation structure similar to those previously used for Q-learning, but we combine it with the model-based Q-value iteration algorithm. We show that the resulting algorithm converges. We also give a modif ed, serial variant of the algorithm that converges at least as fast as the original version. An illustrative simulation example is provided. [less ▲]

Detailed reference viewed: 14 (3 ULg)
Full Text
Peer Reviewed
See detailA comparison of Nash equilibria analysis and agent-based modelling for power markets
Krause, Thilo; Beck, Elena Vdovina; Cherkaoui, Rachid et al

in International Journal of Electrical Power & Energy Systems (2006), 28(9), 599-607

In this paper we compare Nash equilibria analysis and agent-based modelling for assessing the market dynamics of network-constrained pool markets. Power suppliers submit their bids to the market place in ... [more ▼]

In this paper we compare Nash equilibria analysis and agent-based modelling for assessing the market dynamics of network-constrained pool markets. Power suppliers submit their bids to the market place in order to maximize their payoffs, where we apply reinforcement learning as a behavioral agent model. The market clearing mechanism is based on the locational marginal pricing scheme. Simulations are carried out on a benchmark power system. We show how the evolution of the agent-based approach relates to the existence of a unique Nash equilibrium or multiple equilibria in the system. Additionally, the parameter sensitivity of the results is discussed. (C) 2006 Elsevier Ltd. All rights reserved. [less ▲]

Detailed reference viewed: 27 (6 ULg)
Full Text
Peer Reviewed
See detailExtremely randomized trees
Geurts, Pierre ULg; Ernst, Damien ULg; Wehenkel, Louis ULg

in Machine Learning (2006), 63(1), 3-42

This paper proposes anew tree-based ensemble method for supervised classification and regression problems. It essentially consists of randomizing strongly both attribute and cut-point choice while ... [more ▼]

This paper proposes anew tree-based ensemble method for supervised classification and regression problems. It essentially consists of randomizing strongly both attribute and cut-point choice while splitting a tree node. In the extreme case, it builds totally randomized trees whose structures are independent of the output values of the learning sample. The strength of the randomization can be tuned to problem specifics by the appropriate choice of a parameter. We evaluate the robustness of the default choice of this parameter, and we also provide insight on how to adjust it in particular situations. Besides accuracy, the main strength of the resulting algorithm is computational efficiency. A bias/variance analysis of the Extra-Trees algorithm is also provided as well as a geometrical and a kernel characterization of the models induced. [less ▲]

Detailed reference viewed: 396 (53 ULg)
Full Text
Peer Reviewed
See detailReference transmission network: A game theory approach
Minoia, Anna; Ernst, Damien ULg; Dicorato, Maria et al

in IEEE Transactions on Power Systems (2006), 21(1), 249-259

The transmission network plays a key role in an oligopolistic electricity market. In fact, the capacity of a transmission network determines the degree to which the generators in different locations ... [more ▼]

The transmission network plays a key role in an oligopolistic electricity market. In fact, the capacity of a transmission network determines the degree to which the generators in different locations compete with others and could also greatly influence the strategic behaviors of market participants. In such an oligopolistic framework, different agents may have distinct and sometimes opposite interests in urging or hindering certain transmission expansions. Therefore, the regulatory authority, starting from the existing grid, faces the challenge of defining an optimal network upgrade to be used as benchmark for approval or rejection of a given transmission expansion. The aim of this paper is to define the concept of reference transmission network (RTN) from an economic point of view and to provide a tool for the RTN assessment in a deregulated framework where strategic behaviors are likely to appear. A general game-theoretic model for the RTN evaluation is presented, and the solution procedure is discussed. The strategic behavior of market agents in the spot market is modeled according to a Supply Function Equilibrium approach. The impact of transmission capacity expansion on market participants' strategic behavior is studied on a three-bus test network. The RTN is computed and compared with the optimal expansion found when perfect competition among power producers is assumed. [less ▲]

Detailed reference viewed: 44 (3 ULg)
Full Text
Peer Reviewed
See detailModel predictive control and reinforcement learning as two complementary frameworks
Ernst, Damien ULg; Glavic, Mevludin; Capitanescu, Florin ULg et al

in Proceedings of the 13th IFAC Workshop on Control Applications of Optimisation (2006)

Model predictive control (MPC) and reinforcement learning (RL) are two popular families of methods to control system dynamics. In their traditional setting, they formulate the control problem as a ... [more ▼]

Model predictive control (MPC) and reinforcement learning (RL) are two popular families of methods to control system dynamics. In their traditional setting, they formulate the control problem as a discrete-time optimal control problem and compute a suboptimal control policy. We present in this paper in a unified framework these two families of methods. We run for MPC and RL algorithms simulations on a benchmark control problem taken from the power system literature and discuss the results obtained. [less ▲]

Detailed reference viewed: 103 (6 ULg)
Full Text
Peer Reviewed
See detailReinforcement learning with raw image pixels as input state
Ernst, Damien ULg; Marée, Raphaël ULg; Wehenkel, Louis ULg

in Advances in machine vision, image processing & pattern analysis (Lecture notes in computer science, Vol. 4153) (2006)

We report in this paper some positive simulation results obtained when image pixels are directly used as input state of a reinforcement learning algorithm. The reinforcement learning algorithm chosen to ... [more ▼]

We report in this paper some positive simulation results obtained when image pixels are directly used as input state of a reinforcement learning algorithm. The reinforcement learning algorithm chosen to carry out the simulation is a batch-mode algorithm known as fitted Q iteration. [less ▲]

Detailed reference viewed: 40 (8 ULg)
Full Text
Peer Reviewed
See detailApplications of security-constrained optimal power flows
Capitanescu, Florin ULg; Glavic, Mevludin; Ernst, Damien ULg et al

in In Proceedings of Modern Electric Power Systems Symposium, MEPS06 (2006)

This paper proposes to formulate security control as a sequential decision making problem and presents new developments in automatic learning of sequential decision making strategies from simulations and ... [more ▼]

This paper proposes to formulate security control as a sequential decision making problem and presents new developments in automatic learning of sequential decision making strategies from simulations and/or information collected from real-life system measurements. The exploitation of these methods for the design of decision making strategies and control policies in the context of preventive and emergency mode dynamic security assessment and control is discussed and further opportunities for research in this area are highlighted. [less ▲]

Detailed reference viewed: 83 (0 ULg)
Full Text
Peer Reviewed
See detailClinical data based optimal STI strategies for HIV: a reinforcement learning approach
Ernst, Damien ULg; Stan, Guy-Bart; Gonçalves, Jorge et al

in Proceedings of the 45th IEEE Conference on Decision and Control (CDC 2006) (2006)

This paper addresses the problem of computing optimal structured treatment interruption strategies for HIV infected patients. We show that reinforcement learning may be useful to extract such strategies ... [more ▼]

This paper addresses the problem of computing optimal structured treatment interruption strategies for HIV infected patients. We show that reinforcement learning may be useful to extract such strategies directly from clinical data, without the need of an accurate mathematical model of HIV infection dynamics. To support our claims, we report simulation results obtained by running a recently proposed batch-mode reinforcement learning algorithm, known as fitted Q iteration, on numerically generated data. [less ▲]

Detailed reference viewed: 22 (8 ULg)
Full Text
Peer Reviewed
See detailClinical data based optimal STI strategies for HIV: a reinforcement learning approach
Ernst, Damien ULg; Stan, Guy-Bart; Gonçalves, Jorge et al

in Proceedings of the 15th Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn 2006) (2006)

This paper addresses the problem of computing optimal structured treatment interruption strategies for HIV infected patients. We show that reinforcement learning may be useful to extract such strategies ... [more ▼]

This paper addresses the problem of computing optimal structured treatment interruption strategies for HIV infected patients. We show that reinforcement learning may be useful to extract such strategies directly from clinical data, without the need of an accurate mathematical model of HIV infection dynamics. To support our claims, we report simulation results obtained by running a recently proposed batch-mode reinforcement learning algorithm, known as tted Q iteration, on numerically generated data. [less ▲]

Detailed reference viewed: 48 (20 ULg)
Full Text
Peer Reviewed
See detailMulti-area security assessment: results using efficient bounding method
Wehenkel, Louis ULg; Glavic, Mevludin; Ernst, Damien ULg

in Proceedings of the 38th North American Power Symposium (NAPS 2006) (2006)

We present our recent results on using previously introduced framework for multi-area security assessment in large interconnections. The basic idea of the framework is exchanging just enough information ... [more ▼]

We present our recent results on using previously introduced framework for multi-area security assessment in large interconnections. The basic idea of the framework is exchanging just enough information so that each operator can evaluate the impact in his control area of contingencies both internal and external to his area. We provide illustrations based on a localization concept known as efficient bounding method and recently introduced approximate DC model of the European interconnected system. In this paper we focus on four transmission system operators (within the approximate DC model): Belgium, France, Germany, and Netherlands (for both Summer and Winter-peak load conditions). [less ▲]

Detailed reference viewed: 22 (3 ULg)
Full Text
Peer Reviewed
See detailDamping control by fusion of reinforcement learning and control Lyapunov functions
Glavic, Mevludin; Wehenkel, Louis ULg; Ernst, Damien ULg

in Proceedings of the 38th North American Power Symposium (NAPS 2006) (2006)

The main idea behind the concept, proposed in the paper, is the opportunity to make control systems with increased capabilities by synergetic fusion of the domain-specific knowledge and the methodologies ... [more ▼]

The main idea behind the concept, proposed in the paper, is the opportunity to make control systems with increased capabilities by synergetic fusion of the domain-specific knowledge and the methodologies from control theory and artificial intelligence. The particular approach considered combines Control Lyapunov Functions (CLF), a constructive control technique, an Reinforcement Learning (RL) in attempt to optimize a mix of system stability and performance. Two control schemes are proposed and the capabilities of the resulting controllers are illustrated on a control problem involving a Thyristor Controlled Series Capacitor (TCSC) for damping oscillations in a four-machine power system. [less ▲]

Detailed reference viewed: 28 (2 ULg)
Full Text
Peer Reviewed
See detailAutomatic learning of sequential decision strategies for dynamic security assessment and control
Wehenkel, Louis ULg; Glavic, Mevludin; Geurts, Pierre ULg et al

in Proceedings of the IEEE Power Engineering Society General Meeting 2006 (2006)

This paper proposes to formulate security control as a sequential decision making problem and presents new developments in automatic learning of sequential decision making strategies from simulations and ... [more ▼]

This paper proposes to formulate security control as a sequential decision making problem and presents new developments in automatic learning of sequential decision making strategies from simulations and/or information collected from real-life system measurements. The exploitation of these methods for the design of decision making strategies and control policies in the context of preventive and emergency mode dynamic security assessment and control is discussed and further opportunities for research in this area are highlighted. [less ▲]

Detailed reference viewed: 26 (4 ULg)
Full Text
Peer Reviewed
See detailEnsembles of extremely randomized trees and some generic applications
Wehenkel, Louis ULg; Ernst, Damien ULg; Geurts, Pierre ULg

in Proceedings of Robust Methods for Power System State Estimation and Load Forecasting (2006)

In this paper we present a new tree-based ensemble method called “Extra-Trees”. This algorithm averages predictions of trees obtained by partitioning the inputspace with randomly generated splits, leading ... [more ▼]

In this paper we present a new tree-based ensemble method called “Extra-Trees”. This algorithm averages predictions of trees obtained by partitioning the inputspace with randomly generated splits, leading to significant improvements of precision, and various algorithmic advantages, in particular reduced computational complexity and scalability. We also discuss two generic applications of this algorithm, namely for time-series classification and for the automatic inference of near-optimal sequential decision policies from experimental data. [less ▲]

Detailed reference viewed: 51 (5 ULg)
Full Text
Peer Reviewed
See detailOn multi-area security assessment of large interconnected power systems
Wehenkel, Louis ULg; Glavic, Mevludin; Ernst, Damien ULg

in Proceedings of the Second Carnegie Mellon Conference in Electric Power Systems: Monitoring, Sensing, Software and its Valuation for the Changing electric Power Industry (2006)

The paper introduces a framework for information exchange and coordination of security assessment suitable for distributed multi-area control in large interconnections operated by a team of transmission ... [more ▼]

The paper introduces a framework for information exchange and coordination of security assessment suitable for distributed multi-area control in large interconnections operated by a team of transmission system operators. The basic idea of the proposed framework consists of exchanging just enough information so that each operator can evaluate the impact in his control area of contingencies both internal and external to his area. The framework has been thought out with the European perspective in mind where it is presently not possible to set up a transnational security coordinator that would have authority to handle security control over the whole or part of the European interconnection. Nevertheless, it can also be considered as an approach to handle security control in North-American Mega-RTOs, where it could help to circumvent problems of scalability of algorithms and maintainability of data by distributing them over the TSOs under the authority of the RTO. [less ▲]

Detailed reference viewed: 31 (0 ULg)
Full Text
Peer Reviewed
See detailAbout automatic learning for advanced sensing, monitoring and control of electric power systems
Wehenkel, Louis ULg; Glavic, Mevludin; Geurts, Pierre ULg et al

in Proceedings of the Second Carnegie Mellon Conference in Electric Power Systems: Monitoring, Sensing, Software and its Valuation for the Changing electric Power Industry (2006)

The paper considers the possible uses of automatic learning for improving power system performance by software methodologies. Automatic learning per se is first reviewed and recent developements of the ... [more ▼]

The paper considers the possible uses of automatic learning for improving power system performance by software methodologies. Automatic learning per se is first reviewed and recent developements of the field are highlighted. Then the authors’ views of its main actual or potential applications related to power system operation and control are described, and in each application present status and needs for further developments are discussed. [less ▲]

Detailed reference viewed: 54 (4 ULg)