Temperature management for heterogeneous multi-core FPGAs using adaptive evolutionary multi-objective approaches

Heterogeneous multi-core FPGAs contain different types of cores, which can improve efficiency when used with an effective online task scheduler. However, it is not easy to find the right cores for tasks when there are multiple objectives or dozens of cores. Inappropriate scheduling may cause hot spots which decrease the reliability of the chip. Given that, our research builds a simulating platform to evaluate all kinds of scheduling algorithms on a variety of architectures. On this platform, we provide an online scheduler which uses multi-objective evolutionary algorithm (EA). Comparing the EA and current algorithms such as Predictive Dynamic Thermal Management (PDTM) and Adaptive Temperature Threshold Dynamic Thermal Management (ATDTM), we find some drawbacks in previous work. First, current algorithms are overly dependent on manually set constant parameters. Second, those algorithms neglect optimization for heterogeneous architectures. Third, they use single-objective methods, or use linear weighting method to convert a multi-objective optimization into a single-objective optimization. Unlike other algorithms, the EA is adaptive and does not require resetting parameters when workloads switch from one to another. EAs also improve performance when used on heterogeneous architecture. A efficient Pareto front can be obtained with EAs for the purpose of multiple objectives.

Robust aerodynamic design optimisation of morphing aerofoil/wing using distributed moga

In this paper, the shape design optimisation using morphing aerofoil/wing techniques, namely the leading and/or trailing edge deformation of a natural laminar flow RAE 5243 aerofoil is investigated to reduce transonic drag without taking into account of the piezo actuator mechanism. Two applications using a Multi-Objective Genetic Algorithm (MOGA)coupled with Euler and boundary analyser (MSES) are considered: the first example minimises the total drag with a lift constraint by optimising both the trailing edge actuator position and trailing edge deformation angle at a constant transonic Mach number (M! = 0.75)and boundary layer transition position (xtr = 45%c). The second example consists of finding reliable designs that produce lower mean total drag (μCd) and drag sensitivity ("Cd) at different uncertainty flight conditions based on statistical information. Numerical results illustrate how the solution quality in terms of mean drag and its sensitivity can be improved using MOGA software coupled with a robust design approach taking account of uncertainties (lift and boundary transition positions) and also how transonic flow over aerofoil/wing can be controlled to the best advantage using morphing techniques.

Enhancing and developing the practical optimisation capabilities and intelligence of automatic design software

In the modern engineering design cycle the use of computational tools becomes a neces- sity. The complexity of the engineering systems under consideration for design increases dramatically as the demands for advanced and innovative design concepts and engineering products is expanding. At the same time the advancements in the available technology in terms of computational resources and power, as well as the intelligence of the design software, accommodate these demands and make them a viable approach towards the chal- lenge of real-world engineering problems. This class of design optimisation problems is by nature multi-disciplinary. In the present work we establish enhanced optimisation capabil- ities within the Nimrod/O tool for massively distributed execution of computational tasks through cluster and computational grid resources, and develop the potential to combine and benefit from all the possible available technological advancements, both software and hardware. We develop the interface between a Free Form Deformation geometry manage- ment in-house code with the 2D airfoil aerodynamic efficiency evaluation tool XFoil, and the well established multi-objective heuristic optimisation algorithm NSGA-II. A simple airfoil design problem has been defined to demonstrate the functionality of the design sys- tem, but also to accommodate a framework for future developments and testing with other state-of-the-art optimisation algorithms such as the Multi-Objective Genetic Algorithm (MOGA) and the Multi-Objective Tabu Search (MOTS) techniques. Ultimately, heav- ily computationally expensive industrial design cases can be realised within the presented framework that could not be investigated before. © 2012 by the authors. Published by the American Institute of Aeronautics and Astronautics, Inc.

Enhancing and developing the practical optimisation capabilities and intelligence of automatic design software

In the modern engineering design cycle the use of computational tools becomes a necessity. The complexity of the engineering systems under consideration for design increases dramatically as the demands for advanced and innovative design concepts and engineering products is expanding. At the same time the advancements in the available technology in terms of computational resources and power, as well as the intelligence of the design software, accommodate these demands and make them a viable approach towards the challenge of real-world engineering problems. This class of design optimisation problems is by nature multi-disciplinary. In the present work we establish enhanced optimisation capabilities within the Nimrod/O tool for massively distributed execution of computational tasks through cluster and computational grid resources, and develop the potential to combine and benefit from all the possible available technological advancements, both software and hardware. We develop the interface between a Free Form Deformation geometry management in-house code with the 2D airfoil aerodynamic efficiency evaluation tool XFoil, and the well established multi-objective heuristic optimisation algorithm NSGA-II. A simple airfoil design problem has been defined to demonstrate the functionality of the design system, but also to accommodate a framework for future developments and testing with other state-of-the-art optimisation algorithms such as the Multi-Objective Genetic Algorithm (MOGA) and the Multi-Objective Tabu Search (MOTS) techniques. Ultimately, heavily computationally expensive industrial design cases can be realised within the presented framework that could not be investigated before. ©2012 AIAA.

Design optimization of the APF DTL in the SSC-linac

A linear accelerator as a new injector for the SSC (Separated Sector Cyclotron) of the HIRFL (Heavy ton Research Facility Lanzhou) is being designed. The DTL (Drift-Tube-Linac) has been designed to accelerate U-238(34+) from 0.140 MeV/u to 0.97 MeV/u. To the first accelerating tank which accelerates U-238(34+) to 0.54 MeV/u, the approach of Alternating-Phase-Focusing (APF) is applied. The phase array is obtained by coupling optimization software Dakota and beam optics code LINREV. With the hybrid of Multi-objective Genetic Algorithm (MOGA) and a pattern search method, an optimum array of asynchronous phases is determined. The final growth, both transversely and longitudinally, can meet the design requirements. In this paper, the deign optimization of the APF DTL is presented.

Optimisation of Kinetic Parameters for an After-treatment Catalyst

Mathematical modelling has become an essential tool in the design of modern catalytic systems. Emissions legislation is becoming increasingly stringent, and so mathematical models of aftertreatment systems must become more accurate in order to provide confidence that a catalyst will convert pollutants over the required range of conditions. 
Automotive catalytic converter models contain several sub-models that represent processes such as mass and heat transfer, and the rates at which the reactions proceed on the surface of the precious metal. Of these sub-models, the prediction of the surface reaction rates is by far the most challenging due to the complexity of the reaction system and the large number of gas species involved. The reaction rate sub-model uses global reaction kinetics to describe the surface reaction rate of the gas species and is based on the Langmuir Hinshelwood equation further developed by Voltz et al. [1] The reactions can be modelled using the pre-exponential and activation energies of the Arrhenius equations and the inhibition terms. 
The reaction kinetic parameters of aftertreatment models are found from experimental data, where a measured light-off curve is compared against a predicted curve produced by a mathematical model. The kinetic parameters are usually manually tuned to minimize the error between the measured and predicted data. This process is most commonly long, laborious and prone to misinterpretation due to the large number of parameters and the risk of multiple sets of parameters giving acceptable fits. Moreover, the number of coefficients increases greatly with the number of reactions. Therefore, with the growing number of reactions, the task of manually tuning the coefficients is becoming increasingly challenging. 
In the presented work, the authors have developed and implemented a multi-objective genetic algorithm to automatically optimize reaction parameters in AxiSuite®, [2] a commercial aftertreatment model. The genetic algorithm was developed and expanded from the code presented by Michalewicz et al. [3] and was linked to AxiSuite using the Simulink add-on for Matlab. 
The default kinetic values stored within the AxiSuite model were used to generate a series of light-off curves under rich conditions for a number of gas species, including CO, NO, C_{3H8 and C3H6. These light-off curves were used to generate an objective function.} 
This objective function was used to generate a measure of fit for the kinetic parameters. The multi-objective genetic algorithm was subsequently used to search between specified limits to attempt to match the objective function. In total the pre-exponential factors and activation energies of ten reactions were simultaneously optimized. 
The results reported here demonstrate that, given accurate experimental data, the optimization algorithm is successful and robust in defining the correct kinetic parameters of a global kinetic model describing aftertreatment processes.

Advanced optical modulation and format conversion

Over the years, the increased search and exchange of information lead to an increase of traffic intensity in todays optical communication networks. Coherent communications, using the amplitude and phase of the signal, reappears as one of the transmission techniques to increase the spectral efficiency and throughput of optical channels. In this context, this work present a study on format conversion of modulated signals using MZI-SOAs, based exclusively on all- optical techniques through wavelength conversion. This approach, when applied in interconnection nodes between optical networks with different bit rates and modulation formats, allow a better efficiency and scalability of the network. We start with an experimental characterization of the static and dynamic properties of the MZI-SOA. Then, we propose a semi-analytical model to describe the evolution of phase and amplitude at the output of the MZI-SOA. The model’s coefficients are obtained using a multi-objective genetic algorithm. We validate the model experimentally, by exploring the dependency of the optical signal with the operational parameters of the MZI-SOA. We also propose an all-optical technique for the conversion of amplitude modulation signals to a continuous phase modulation format. Finally, we study the potential of MZI-SOAs for the conversion of amplitude signals to QPSK and QAM signals. We show the dependency of the conversion process with the operational parameters deviation from the optimal values. The technique is experimentally validated for QPSK modulation.

Intelligent predictive control for thermal comfort and energy savings in public buildings

This talk addresses the problem of controlling a heating ventilating and air conditioning system with the purpose of achieving a desired thermal comfort level and energy savings. The formulation uses the thermal comfort, assessed using the predicted mean vote (PMV) index, as a restriction and minimises the energy spent to comply with it. This results in the maintenance of thermal comfort and on the minimisation of energy, which in most operating conditions are conflicting goals requiring some sort of optimisation method to find appropriate solutions over time. In this work a discrete model based predictive control methodology is applied to the problem. It consists of three major components: the predictive models, implemented by radial basis function neural networks identifed by means of a multi-objective genetic algorithm [1]; the cost function that will be optimised to minimise energy consumption and provide adequate thermal comfort; and finally the optimisation method, in this case a discrete branch and bound approach. Each component will be described, with a special emphasis on a fast and accurate computation of the PMV indices [2]. Experimental results obtained within different rooms in a building of the University of Algarve will be presented, both in summer [3] and winter [4] conditions, demonstrating the feasibility and performance of the approach. Energy savings resulting from the application of the method are estimated to be greater than 50%.

Model comparison for temperature estimation inside buildings

This paper presents a comparison between a physical model and an artificial neural network model (NN) for temperature estimation inside a building room. Despite the obvious advantages of the physical model for structure optimisation purposes, this paper will test the performance of neural models for inside temperature estimation. The great advantage of the NN model is a big reduction of human effort time, because it is not needed to develop the structural geometry and structural thermal capacities and to simulate, which consumes a great human effort and great computation time. The NN model deals with this problem as a “black box” problem. We describe the use of the Radial Basis Function (RBF), the training method and a multi-objective genetic algorithm for optimisation/selection of the RBF neural network inputs and number of neurons.

Manipulator trajectory planning using a MOEA

Generating manipulator trajectories considering multiple objectives and obstacle avoidance is a non-trivial optimization problem. In this paper a multi-objective genetic algorithm based technique is proposed to address this problem. Multiple criteria are optimized considering up to five simultaneous objectives. Simulation results are presented for robots with two and three degrees of freedom, considering two and five objectives optimization. A subsequent analysis of the spread and solutions distribution along the converged non-dominated Pareto front is carried out, in terms of the achieved diversity.

GA approach for finding Rough Set decision rules based on bireducts

Feature selection plays an important role in knowledge discovery and data mining nowadays. In traditional rough set theory, feature selection using reduct - the minimal discerning set of attributes - is an important area. Nevertheless, the original definition of a reduct is restrictive, so in one of the previous research it was proposed to take into account not only the horizontal reduction of information by feature selection, but also a vertical reduction considering suitable subsets of the original set of objects. Following the work mentioned above, a new approach to generate bireducts using a multi--objective genetic algorithm was proposed. Although the genetic algorithms were used to calculate reduct in some previous works, we did not find any work where genetic algorithms were adopted to calculate bireducts. Compared to the works done before in this area, the proposed method has less randomness in generating bireducts. The genetic algorithm system estimated a quality of each bireduct by values of two objective functions as evolution progresses, so consequently a set of bireducts with optimized values of these objectives was obtained. Different fitness evaluation methods and genetic operators, such as crossover and mutation, were applied and the prediction accuracies were compared. Five datasets were used to test the proposed method and two datasets were used to perform a comparison study. Statistical analysis using the one-way ANOVA test was performed to determine the significant difference between the results. The experiment showed that the proposed method was able to reduce the number of bireducts necessary in order to receive a good prediction accuracy. Also, the influence of different genetic operators and fitness evaluation strategies on the prediction accuracy was analyzed. It was shown that the prediction accuracies of the proposed method are comparable with the best results in machine learning literature, and some of them outperformed it.

Web Service Composition Systems for the Web Service Challenge - A Detailed Review

This report gives a detailed discussion on the system, algorithms, and techniques that we have applied in order to solve the Web Service Challenges (WSC) of the years 2006 and 2007. These international contests are focused on semantic web service composition. In each challenge of the contests, a repository of web services is given. The input and output parameters of the services in the repository are annotated with semantic concepts. A query to a semantic composition engine contains a set of available input concepts and a set of wanted output concepts. In order to employ an offered service for a requested role, the concepts of the input parameters of the offered operations must be more general than requested (contravariance). In contrast, the concepts of the output parameters of the offered service must be more specific than requested (covariance). The engine should respond to a query by providing a valid composition as fast as possible. We discuss three different methods for web service composition: an uninformed search in form of an IDDFS algorithm, a greedy informed search based on heuristic functions, and a multi-objective genetic algorithm.

A clustering based hybrid system for mass spectrometry data analysis

Recently, much attention has been given to the mass spectrometry (MS) technology based disease classification, diagnosis, and protein-based biomarker identification. Similar to microarray based investigation, proteomic data generated by such kind of high-throughput experiments are often with high feature-to-sample ratio. Moreover, biological information and pattern are compounded with data noise, redundancy and outliers. Thus, the development of algorithms and procedures for the analysis and interpretation of such kind of data is of paramount importance. In this paper, we propose a hybrid system for analyzing such high dimensional data. The proposed method uses the k-mean clustering algorithm based feature extraction and selection procedure to bridge the filter selection and wrapper selection methods. The potential informative mass/charge (m/z) markers selected by filters are subject to the k-mean clustering algorithm for correlation and redundancy reduction, and a multi-objective Genetic Algorithm selector is then employed to identify discriminative m/z markers generated by k-mean clustering algorithm. Experimental results obtained by using the proposed method indicate that it is suitable for m/z biomarker selection and MS based sample classification.

A generic classifier-ensemble approach for biomedical named entity recognition

In named entity recognition (NER) for biomedical literature, approaches based on combined classifiers have demonstrated great performance improvement compared to a single (best) classifier. This is mainly owed to sufficient level of diversity exhibited among classifiers, which is a selective property of classifier set. Given a large number of classifiers, how to select different classifiers to put into a classifier-ensemble is a crucial issue of multiple classifier-ensemble design. With this observation in mind, we proposed a generic genetic classifier-ensemble method for the classifier selection in biomedical NER. Various diversity measures and majority voting are considered, and disjoint feature subsets are selected to construct individual classifiers. A basic type of individual classifier – Support Vector Machine (SVM) classifier is adopted as SVM-classifier committee. A multi-objective Genetic algorithm (GA) is employed as the classifier selector to facilitate the ensemble classifier to improve the overall sample classification accuracy. The proposed approach is tested on the benchmark dataset – GENIA version 3.02 corpus, and compared with both individual best SVM classifier and SVM-classifier ensemble algorithm as well as other machine learning methods such as CRF, HMM and MEMM. The results show that the proposed approach outperforms other classification algorithms and can be a useful method for the biomedical NER problem.

Dilema da diversidade-acurácia: um estudo empírico no contexto de multiclassificadores

Multi-classifier systems, also known as ensembles, have been widely used to solve several problems, because they, often, present better performance than the individual classifiers that form these systems. But, in order to do so, it s necessary that the base classifiers to be as accurate as diverse among themselves this is also known as diversity/accuracy dilemma. Given its importance, some works have investigate the ensembles behavior in context of this dilemma. However, the majority of them address homogenous ensemble, i.e., ensembles composed only of the same type of classifiers. Thus, motivated by this limitation, this thesis, using genetic algorithms, performs a detailed study on the dilemma diversity/accuracy for heterogeneous ensembles