Search

Through this position paper we aim at providing a prototype cognitive security service for anomaly detection in Software Defined Networks (SDNs). We equally look at strengthening attack detection capabilities in SDNs, through the addition of predictive analytics capabilities. For this purpose, we build a learning-based anomaly detection service called Learn2Defend, based on functionalities provided by Opendaylight. A potential path to cognition is detailed, by means of a Gaussian Processes driven engine that makes use of traffic characteristics/behavior profiles e.g. smoothness of the frequency of flows traversing a given node. Learn2Defend follows a two-fold approach, with unsupervised learning and prediction mechanisms, all in an on-line dynamic SDN context. The prototype does not target to provide an universally valid predictive analytics framework for security, but rather to offer a tool that supports the integration of cognitive techniques in the SDN security services.

The large-scale applicability and use of evolutionary computing for complex real-life systems determined a need to ensure strong analytical and theoretical grounds. The special issue, with respect to these concerns, aims at building a bridge between probability, statistics, set oriented numerics and evolutionary computing. A strong interest for identifying new common and challenging research topics is considered, addressing both theoretical and applied aspects in highly complex systems. Uncertainty, error propagation or poor analysis and design, all may lead to catastrophic failures or losses in, for example, high-sensitivity, large scale complex systems; examples can be found by looking at financial markets, surveillance and defense systems, etc. Therefore, algorithms capable of delivering robust solutions while subject to erroneous or abnormal inputs, resilient to failures or with performance guarantees, are of a foremost importance. To this end, a collection of 13 papers is included in this issue, carefully selected from a total of 80 submissions we received. A series of high impact directions are brought into discussion like the design of efficient algorithms for highly complex systems, new algorithms, e.g. extended compact genetic algorithm, multi-objective artificial physics algorithm or service oriented algorithms, performance measures in dynamic optimization, Bayesian networks learning or highdimensional optimization. Real-world application examples are given towards the end, with a view of mobile large-scale networks and GPGPU-based track-beforedetect systems.

The paper deals with an important problem in the Voice over IP (VoIP) domain, namely being able to understand and predict the structure of traffic over some given period of time. VoIP traffic has a time variant structure, e.g. due to sudden peaks, daily or weekly moving patterns of activities, which in turn makes prediction difficult. Obtaining insights about the structure and trends of traffic has important implications when dealing with the nowadays cloud-deployed VoIP services. Prediction techniques are applied to anticipate the incoming traffic, for an efficient distribution of the traffic in the system and allocation of resources. The article looks in a critical manner at a series of machine learning techniques. We namely compare and review (using real VoIP data) the results obtained when using a Gaussian Mixture Model (GMM), Gaussian Processes (GP), and an evolutionary-like Interacting Particle Systems based (sampling) algorithm. The experiments consider different setups as to verify the time variant traffic assumption.

The interest in sparse antenna arrays is growing, mainly due to cost concerns, array size limitations, etc. Formally, it can be shown that their design can be expressed as a constrained multidimensional nonlinear optimization problem. Generally, through lack of convex property, such a multiextrema problem is very tricky to solve by usual deterministic optimization methods. In this article, a recent stochastic approach, called Cross-Entropy method, is applied to the continuous constrained design problem. The method is able to construct a random sequence of solutions which converges probabilistically to the optimal or the near-optimal solution. Roughly speaking, it performs adaptive changes to probability density functions according to the Kullback-Leibler cross-entropy. The approach efficiency is illustrated in the design of a sparse antenna array with various requirements.

This article outlines the recent developments in the field of large-scale parallel computing applied to molecular simulations, also including some original, preliminary contributions of the authors. It is not meant to be an exhaustive review paper, but rather an introductive material aimed at narrowing the "cultural gap" between the developers and users of molecular simulations (chemists, medicinal chemists and biologists - typical workstation users) and the informatics experts in massively parallel computing. The article starts with a brief overview of the existing molecular simulation techniques, in emphasizing the weaknesses of present approaches and the need for more computer-intensive methods. Docking procedures are the most discussed, given the high importance of this application in computer-aided drug design. An introduction to computer grids is logically pursued with the presentation of some of the most promising large-scale parallel molecular simulations already performed. Eventually, the author's own research program, Docking@Grid, is briefly discussed.

The rise of the data centers industry, together with the emergence of large cloud computing that require large quantities of resources to be maintained, brought the need of providing a sustainable development process. Through this paper we aim to provide an introductory insight on the status and tools available to tackle this perspective within the evolutionary and genetic algorithms community. Existing advancements are also emphasized and perspectives outlined.

This work presents an asymmetric quadratic approximation model and an $\epsilon$-archiving algorithm. The model allows to construct, under local convexity assumptions, descriptors for local optima points in continuous functions. A descriptor can be used to extract confidence radius information. The $\epsilon$-archiving algorithm is designed to maintain and update a set of such asymmetric descriptors, spaced at some given threshold distance. An in-depth analysis is conducted on the stability and performance of the asymmetric model, comparing the results with the ones obtained by a quadratic polynomial approximation. A series of different applications are possible in areas such as dynamic and robust optimization.

We would like to express our great pleasure in welcoming you to the GECCO Workshop on Green and Efficient Energy Applications of Genetic and Evolutionary Computation (GreenGEC Workshop'14), held in conjunction with the GECCO 2014 International Conference. A main characteristic of the studies in the area of green and energy-efficient applications is the strong connection with real-world environments and constraints. As such, there is only little place for errors and leading edge algorithms alone can be used. The potential impact and outcomes are also of foremost importance. Global increases in living standards, diminishing natural resources and environmental concerns place energy amongst the most important global issues today. On the consumer side, there is an increasing need for more efficient, smart, uses of energy, be it in large-scale computing systems and data warehouses, in homes or in office buildings. On the producer side, there is a push toward the use of sustainable, green, energy sources, which often come in the form of less reliable sources such as wind energy. In addition, future energy systems are often envisioned to be "smart", consisting of massive amounts of small generators, such as solar panels, located at consumers, effectively turning consumers into potential producers whenever they have a surplus of energy. The management, control and planning of, and efficient use of energy in (future) energy systems brings about many important challenges. Energy systems are not only real-world systems, they are also one of the most important foundations of the modern world. Especially with the upcoming required changes to make more efficient use of energy and to shift towards a global use of sustainable, green energy sources, there are many challenges in mathematics and computer science. Real-world challenges, such as those arising in (future) energy systems, are typically highly complex because of the many aspects to be considered that are often disregarded in theoretical research such as dynamic changes, uncertainty and multiple objectives. In many situations therefore, problem-specific algorithms are infeasible or impractical. Instead, flexible and powerful approaches such as evolutionary algorithms (EAs) can often provide viable solutions. Typical real-world challenges that are addressed by EAs are of the optimization type. This covers the use of EAs to optimize issues ranging from energy consumption (e.g. scheduling, memory/storage management, communication protocols, smart sensors, etc.) to the planning and design of energy systems at many levels, ranging from small printed circuit boards to entire transmission networks.

BackgroundThere exist several computational tools which allow for the optimisation and inference of biological networks using a Boolean formalism. Nevertheless, the results from such tools yield only limited quantitative insights into the complexity of biological systems because of the inherited qualitative nature of Boolean networks.ResultsWe introduce optPBN, a Matlab-based toolbox for the optimisation of probabilistic Boolean networks (PBN) which operates under the framework of the BN/PBN toolbox. optPBN offers an easy generation of probabilistic Boolean networks from rule-based Boolean model specification and it allows for flexible measurement data integration from multiple experiments. Subsequently, optPBN generates integrated optimisation problems which can be solved by various optimisers. In term of functionalities, optPBN allows for the construction of a probabilistic Boolean network from a given set of potential constitutive Boolean networks by optimising the selection probabilities for these networks so that the resulting PBN fits experimental data. Furthermore, the optPBN pipeline can also be operated on large-scale computational platforms to solve complex optimisation problems. Apart from exemplary case studies which we correctly inferred the original network, we also successfully applied optPBN to study a large-scale Boolean model of apoptosis where it allows identifying the inverse correlation between UVB irradiation, NFκB and Caspase 3 activations, and apoptosis in primary hepatocytes quantitatively. Also, the results from optPBN help elucidating the relevancy of crosstalk interactions in the apoptotic network.SummaryThe optPBN toolbox provides a simple yet comprehensive pipeline for integrated optimisation problem generation in the PBN formalism that can readily be solved by various optimisers on local or grid-based computational platforms. optPBN can be further applied to various biological studies such as the inference of gene regulatory networks or the identification of the interaction's relevancy in signal transduction networks.

Probabilistic Boolean network (PBN) modelling is a semi-quantitative approach widely used for the study of the topology and dynamic aspects of biological systems. The combined use of rule-based representation and probability makes PBN appealing for large-scale modelling of biological networks where degrees of uncertainty need to be considered. A considerable expansion of our knowledge in the field of theoretical research on PBN can be observed over the past few years, with a focus on network inference, network intervention and control. With respect to areas of applications, PBN is mainly used for the study of gene regulatory networks though with an increasing emergence in signal transduction, metabolic, and also physiological networks. At the same time, a number of computational tools, facilitating the modelling and analysis of PBNs, are continuously developed. A concise yet comprehensive review of the state-of-the-art on PBN modelling is offered in this article, including a comparative discussion on PBN versus similar models with respect to concepts and biomedical applications. Due to their many advantages, we consider PBN to stand as a suitable modelling framework for the description and analysis of complex biological systems, ranging from molecular to physiological levels.

International audience; The development of large scale data center and cloud computing optimization models led to a wide range of complex issues like scaling, operation cost and energy efficiency. Different approaches were proposed to this end, including classical resource allocation heuristics, machine learning or stochastic optimization. No consensus exists but a trend towards using many-objective stochastic models became apparent over the past years. This work reviews in brief some of the more recent studies on cloud computing modeling and optimization, and points at notions on stability, convergence, definitions or results that could serve to analyze, respectively build accurate cloud computing models. A very brief discussion of simulation frameworks that include support for energy-aware components is also given.

Energy systems are not only real-world systems; they are also one of the most important foundations of the modern world. Especially with the upcoming required changes to make more efficient use of energy and to shift towards a global use of sustainable, green energy sources, there are many challenges in mathematics and computer science. Thus, with the current increase in living standards, diminishing natural resources and environmental concerns, the management of energy production and use became one of the most important global issues today.First, on the consumer side, there is an increasing need for more efficient, smart uses of energy, be it in large-scale computing systems and data warehouses, in homes or in office buildings. Second, on the producer side, there is a push toward the use of sustainable, green, energy sources, which are often less reliable, e.g. wind energy. In addition, future energy systems are often envisioned to be "smart", consisting of massive amounts of small generators, such as solar panels, located at consumers, effectively turning consumers into potential producers whenever they have a surplus of energy. The management, control and planning of, and efficient use of energy in (future) energy systems brings about as many important questions. Real-world challenges, such as those arising in (future) energy systems, are\ typically highly complex because of the many aspects to be considered that are often disregarded in theoretical research such as dynamic changes, uncertainty and multiple objectives. In many situations therefore, problem-specific algorithms are infeasible or impractical. Instead, flexible and powerful approaches such as evolutionary algorithms (EAs) can often provide viable solutions. Typical real-world challenges that are addressed by EAs are of the optimization type. This covers the use of EAs to optimize issues ranging from energy consumption (e.g. scheduling, memory/storage management, communication protocols, smart sensors, etc.) to the planning and design of energy systems at many levels, ranging from small printed circuit boards to entire transmission networks.The aim of this workshop is therefore to bring together researchers interested in addressing challenging issues related to the use of evolutionary computation for applications in (future) energy systems. The workshop is a follow up of the GreenIT Evolutionary Computation workshop held at GECCO 2011.

The herein paper addresses the issue of providing a model and guidelines for constructing a sustainable ICT environment at the University of Luxembourg. A particular context is thus considered, based on a real-life project that has as aim to provide a sustainable environment for the ICT infrastructure of the university. According to the different environment constraints and requirements, the objectives are to minimize electricity consumption by employing virtualization techniques and also to reduce carbon emissions by creating a load balanced charge of the computers that build the infrastructure. The quality of service is also addressed by provisioning factors. A multi-objective dynamic approach is considered in order to cope with the simultaneous optimization of the mentioned objectives and the dynamic nature of the system.

In this work we focus on defining how dynamism can be modeled in the context of multi-objective optimization. Based on this, we construct a component oriented classification for dynamic multi-objective optimization problems. For each category we provide synthetic examples that depict in a more explicit way the defined model. We do this either by positioning existing synthetic benchmarks with respect to the proposed classification or through new problem formulations. In addition, an online dynamic MNK-landscape formulation is introduced together with a new comparative metric for the online dynamic multi-objective context.

Nowadays distributed systems face a new challenge, almost nonexistent a decade ago: energy-efficient computing. Due to the rising environmental and economical concerns and with trends driving operational costs beyond the acquisition ones, green computing is of more actuality than never before. The aspects to deal with, e.g. dynamic systems, stochastic models or time-dependent factors, call nonetheless for paradigms combining the expertise of multiple research areas. An agent-based dynamic multi-objective evolutionary algorithm relying on simulation and anticipation mechanisms is presented in this chapter. A first aim consists in addressing several difficult energy-efficiency optimization issues, in a second phase, different open questions being outlined for future research.

A comparison analysis of dynamic mutation operators is proposed, having the conformational sampling problem as a case study. The analysis is sustained by a parallel Optimal Computing Budget Allocation (OCBA) selection procedure, employed in order to attain computational speedup. A Pearson system distribution based mutation operator is proposed, allowing for a highly flexible construction. As defined by a set of four parameters, the mean, variance, skewness and kurtosis, a large number of distributions can be simulated. As determined by the analysis outcomes, the class of operators exhibiting significant energy minimization or Root Mean Square Deviation (RMSD) bias is identified. Experiments are carried out on a large number of computational resources, allowing for the outline of an automatic a priori operator tuning and selection methodology. Although not presented in this chapter, similar complementary studies have been conducted on intensification operators and local search algorithms.

International audience; A hierarchical hybrid model of parallel metaheuristics is proposed, combining an evolutionary algorithm and an adaptive simulated annealing. The algorithms are executed inside a grid environment with different parallelization strategies: the synchronous multi-start model, parallel evaluation of different solutions and an insular model with asynchronous migrations. Furthermore, a conjugated gradient local search method is employed at different stages of the exploration process. The algorithms were evaluated using the protein structure prediction problem, having as benchmarks the tryptophan-cage protein (Brookhaven Protein Data Bank ID: 1L2Y), the tryptophan-zipper protein (PDB ID: 1LE1) and the α-Cyclodextrin complex. Experimentations were performed on a nation-wide grid infrastructure, over six distinct administrative domains and gathering nearly 1,000 CPUs. The complexity of the protein structure prediction problem remains prohibitive as far as large proteins are concerned, making the use of parallel computing on the computational grid essential for its efficient resolution.

International audience; Computational simulations of conformational sampling in general, and of macromolecular folding in particular represent one of the most important and yet one of the most challenging applications of computer science in biology and medicinal chemistry. The advent of GRID computing may trigger some major progress in this field. This paper presents our first attempts to design GRID-based conformational sampling strategies, exploring the extremely rugged energy response surface in function of molecular geometry, in search of low energy zones through phase spaces of hundreds of degrees of freedom. We have generalized the classical island model deployment of genetic algorithms (GA) to a "planetary" model where each node of the grid is assimilated to a "planet" harboring quasi-independent multi-island simulations based on a hybrid GA-driven sampling approach. Although different "planets" do not communicate to each other-thus minimizing inter-CPU exchanges on the GRID-each new simulation will benefit from the preliminary knowledge extracted from the centralized pool of already visited geometries, located on the dispatcher machine, and which is disseminated to any new "planet". This "panspermic" strategy allows new simulations to be conducted such as to either be attracted towards an apparently promising phase space zone (biasing strategies, intensification procedures) or to avoid already in-depth sampled (tabu) areas. Successful folding of mini-proteins typically used in benchmarks for all- atoms protein simulations has been observed, although the reproducibility of these highly stochastic simulations in huge problem spaces is still in need of improvement. Work on two structured peptides (the "tryptophane cage" 1L2Y and the "tryptophane zipper" 1LE1) used as benchmarks for all-atom protein folding simulations has shown that the planetary model is able to reproducibly sample conformers from the neighborhood of the native geometries. However, within these neighborhoods (within - ensembles of conformers similar to models published on hand of experimental geometry determinations), the energy landscapes are still extremely rugged. Therefore, simulations in general produce "correct" geometries (similar enough to experimental model for any practical purposes) which sometimes unfortunately correspond to relatively high energy levels and therefore are less stable than the most stable among misfolded conformers. The method thus reproducibly visits the native phase space zone, but fails to reproducibly hit the bottom of its rugged energy well. Intensifications of local sampling may in principle solve this problematic behavior, but is limited by computational resources. The quest for the optimal time point at which a phase space zone should stop being intensively searched and declared tabu, a very difficult problem, is still awaiting for a practically useful solution.

International audience

International audience; The exploration of potential multidimensional surfaces in protein folding is a non-trivial problem of extreme importance in computational biology. An evolutionary bicriterion grid-enabled protein folding approach is reported, classical molecular mechanics equations being employed for modeling inter-atomic interactions. Afferent computations were distributed on a nation-wide grid - GRID5000. A layered software design composed of dedicated frameworks is adopted due to the highly complex aspects inherent for the underlying volatile and dynamic execution environment. A brief insight on the existing approaches and the mathematical basis describing physical molecular interactions is offered, including derived semi-empirical and purely-empirical models. Introductory multicriterion formalisms enclosing the exposed approach are also presented

International audience; Solving the structure prediction problem for complex proteins is difficult and computationally expensive. In this paper, we propose a bicriterion parallel hybrid genetic algorithm (GA) in order to efficiently deal with the problem using the computational grid. The use of a near-optimal metaheuristic, such as a GA, allows a significant reduction in the number of explored potential structures. However, the complexity of the problem remains prohibitive as far as large proteins are concerned, making the use of parallel computing on the computational grid essential for its efficient resolution. A conjugated gradient-based Hill Climbing local search is combined with the GA in order to intensify the search in the neighborhood of its provided configurations. In this paper we consider two molecular complexes: the tryptophan-cage protein (Brookhaven Protein Data Bank ID 1L2Y) and α-cyclodextrin. The experimentation results obtained on a computational grid show the effectiveness of the approach.