A hybrid metaheuristic approach to the university course timetabling problem

This paper describes the development of a novel metaheuristic that combines an electromagnetic-like mechanism (EM) and the great deluge algorithm (GD) for the University course timetabling problem. This well-known timetabling problem assigns lectures to specific numbers of timeslots and rooms maximizing the overall quality of the timetable while taking various constraints into account. EM is a population-based stochastic global optimization algorithm that is based on the theory of physics, simulating attraction and repulsion of sample points in moving toward optimality. GD is a local search procedure that allows worse solutions to be accepted based on some given upper boundary or ‘level’. In this paper, the dynamic force calculated from the attraction-repulsion mechanism is used as a decreasing rate to update the ‘level’ within the search process. The proposed method has been applied to a range of benchmark university course timetabling test problems from the literature. Moreover, the viability of the method has been tested by comparing its results with other reported results from the literature, demonstrating that the method is able to produce improved solutions to those currently published. We believe this is due to the combination of both approaches and the ability of the resultant algorithm to converge all solutions at every search process.

Quantum annealing of an ising spin-glass by Green's function Monte Carlo

We present an implementation of quantum annealing (QA) via lattice Green's function Monte Carlo (GFMC), focusing on its application to the Ising spin glass in transverse field. In particular, we study whether or not such a method is more effective than the path-integral Monte Carlo- (PIMC) based QA, as well as classical simulated annealing (CA), previously tested on the same optimization problem. We identify the issue of importance sampling, i.e., the necessity of possessing reasonably good (variational) trial wave functions, as the key point of the algorithm. We performed GFMC-QA runs using such a Boltzmann-type trial wave function, finding results for the residual energies that are qualitatively similar to those of CA (but at a much larger computational cost), and definitely worse than PIMC-QA. We conclude that, at present, without a serious effort in constructing reliable importance sampling variational wave functions for a quantum glass, GFMC-QA is not a true competitor of PIMC-QA.

Monte Carlo studies of quantum and classical annealing on a double well

We present results for a variety of Monte Carlo annealing approaches, both classical and quantum, benchmarked against one another for the textbook optimization exercise of a simple one-dimensional double well. In classical (thermal) annealing, the dependence upon the move chosen in a Metropolis scheme is studied and correlated with the spectrum of the associated Markov transition matrix. In quantum annealing, the path integral Monte Carlo approach is found to yield nontrivial sampling difficulties associated with the tunneling between the two wells. The choice of fictitious quantum kinetic energy is also addressed. We find that a "relativistic" kinetic energy form, leading to a higher probability of long real-space jumps, can be considerably more effective than the standard nonrelativistic one.

Efficient Marginal Likelihood Computation for Gaussian Process Regression

In a Bayesian learning setting, the posterior distribution of a predictive model arises from a trade-off between its prior distribution and the conditional likelihood of observed data. Such distribution functions usually rely on additional hyperparameters which need to be tuned in order to achieve optimum predictive performance; this operation can be efficiently performed in an Empirical Bayes fashion by maximizing the posterior marginal likelihood of the observed data. Since the score function of this optimization problem is in general characterized by the presence of local optima, it is necessary to resort to global optimization strategies, which require a large number of function evaluations. Given that the evaluation is usually computationally intensive and badly scaled with respect to the dataset size, the maximum number of observations that can be treated simultaneously is quite limited. In this paper, we consider the case of hyperparameter tuning in Gaussian process regression. A straightforward implementation of the posterior log-likelihood for this model requires O(N^3) operations for every iteration of the optimization procedure, where N is the number of examples in the input dataset. We derive a novel set of identities that allow, after an initial overhead of O(N^3), the evaluation of the score function, as well as the Jacobian and Hessian matrices, in O(N) operations. We prove how the proposed identities, that follow from the eigendecomposition of the kernel matrix, yield a reduction of several orders of magnitude in the computation time for the hyperparameter optimization problem. Notably, the proposed solution provides computational advantages even with respect to state of the art approximations that rely on sparse kernel matrices.

Optimization strategy for minimizing damage in postbuckling stiffened panels

Composite materials are finding increasing use on primary aerostructures to meet demanding performance targets while reducing environmental impact. This paper presents a finite-element-based preliminary optimization methodology for postbuckling stiffened panels, which takes into account damage mechanisms that lead to delamination and subsequent failure by stiffener debonding. A global-local modeling approach is adopted in which the boundary conditions on the local model are extracted directly from the global model. The optimization procedure is based on a genetic algorithm that maximizes damage resistance within the postbuckling regime. This routine is linked to a finite element package and the iterative procedure automated. For a given loading condition, the procedure optimized the stacking sequence of several areas of the panel, leading to an evolved panel that displayed superior damage resistance in comparison with nonoptimized designs.

Surrogate-based analysis and optimization for the design of heat sinks with jet impingement

Heat sinks are widely used for cooling electronic devices and systems. Their thermal performance is usually determined by the material, shape, and size of the heat sink. With the assistance of computational fluid dynamics (CFD) and surrogate-based optimization, heat sinks can be designed and optimized to achieve a high level of performance. In this paper, the design and optimization of a plate-fin-type heat sink cooled by impingement jet is presented. The flow and thermal fields are simulated using the CFD simulation; the thermal resistance of the heat sink is then estimated. A Kriging surrogate model is developed to approximate the objective function (thermal resistance) as a function of design variables. Surrogate-based optimization is implemented by adaptively adding infill points based on an integrated strategy of the minimum value, the maximum mean square error approach, and the expected improvement approaches. The results show the influence of design variables on the thermal resistance and give the optimal heat sink with lowest thermal resistance for given jet impingement conditions. 

A biogeography-based optimization algorithm with mutation strategies for model parameter estimation of solar and fuel cells

Mathematical models are useful tools for simulation, evaluation, optimal operation and control of solar cells and proton exchange membrane fuel cells (PEMFCs). To identify the model parameters of these two type of cells efficiently, a biogeography-based optimization algorithm with mutation strategies (BBO-M) is proposed. The BBO-M uses the structure of biogeography-based optimization algorithm (BBO), and both the mutation motivated from the differential evolution (DE) algorithm and the chaos theory are incorporated into the BBO structure for improving the global searching capability of the algorithm. Numerical experiments have been conducted on ten benchmark functions with 50 dimensions, and the results show that BBO-M can produce solutions of high quality and has fast convergence rate. Then, the proposed BBO-M is applied to the model parameter estimation of the two type of cells. The experimental results clearly demonstrate the power of the proposed BBO-M in estimating model parameters of both solar and fuel cells.

Investigation of Utilizing Single Surface Depressions in Optimization of NLF Aerofoil Design

An environment has been created for the optimisation of aerofoil profiles with inclusion of small surface features. For TS wave dominated flows, the paper examines the consequences of the addition of a depression on the aerodynamic optimisation of an NLF aerofoil, and describes the geometry definition fidelity and optimisation algorithm employed in the development process. The variables that define the depression for this optimisation investigation have been fixed, however a preliminary study is presented demonstrating the sensitivity of the flow to the depression characteristics. Solutions to the optimisation problem are then presented using both gradient-based and genetic algorithm techniques, and for accurate representation of the inclusion of small surface perturbations it is concluded that a global optimisation method is required for this type of aerofoil optimisation task due to the nature of the response surface generated. When dealing with surface features, changes in the transition onset are likely to be of a non-linear nature so it is highly critical to have an optimisation algorithm that is robust, suggesting that for this framework, gradient-based methods alone are not suited.

Building information modeling based building design optimization for sustainability

Environmental problems, especially climate change, have become a serious global issue waiting for people to solve. In the construction industry, the concept of sustainable building is developing to reduce greenhouse gas emissions. In this study, a building information modeling (BIM) based building design optimization method is proposed to facilitate designers to optimize their designs and improve buildings’ sustainability. A revised particle swarm optimization (PSO) algorithm is applied to search for the trade-off between life cycle costs (LCC) and life cycle carbon emissions (LCCE) of building designs. In order tovalidate the effectiveness and efficiency of this method, a case study of an office building is conducted in Hong Kong. The result of the case study shows that this method can enlarge the searching space for optimal design solutions and shorten the processing time for optimal design results, which is really helpful for designers to deliver an economic and environmental friendly design scheme.

Energy Optimization of Memory Intensive Parallel Workloads

Energy consumption is an important concern in modern multicore processors. The energy consumed by a multicore processor during the execution of an application can be minimized by tuning the hardware state utilizing knobs such as frequency, voltage etc. The existing theoretical work on energy minimization using Global DVFS (Dynamic Voltage and Frequency Scaling), despite being thorough, ignores the time and the energy consumed by the CPU on memory accesses and the dynamic energy consumed by the idle cores. This article presents an analytical energy-performance model for parallel workloads that accounts for the time and the energy consumed by the CPU chip on memory accesses in addition to the time and energy consumed by the CPU on CPU instructions. In addition, the model we present also accounts for the dynamic energy consumed by the idle cores. The existing work on global DVFS for parallel workloads shows that using a single frequency for the entire duration of a parallel application is not energy optimal and that varying the frequency according to the changes in the parallelism of the workload can save energy. We present an analytical framework around our energy-performance model to predict the operating frequencies (that depend upon the amount of parallelism) for global DVFS that minimize the overall CPU energy consumption. We show how the optimal frequencies in our model differ from the optimal frequencies in a model that does not account for memory accesses. We further show how the memory intensity of an application affects the optimal frequencies.

Implementing a structural continuity constraint and a halting method for the topology optimization of energy absorbers

This study investigates topology optimization of energy absorbing structures in which material damage is accounted for in the optimization process. The optimization objective is to design the lightest structures that are able to absorb the required mechanical energy. A structural continuity constraint check is introduced that is able to detect when no feasible load path remains in the finite element model, usually as a result of large scale fracture. This assures that designs do not fail when loaded under the conditions prescribed in the design requirements. This continuity constraint check is automated and requires no intervention from the analyst once the optimization process is initiated. Consequently, the optimization algorithm proceeds towards evolving an energy absorbing structure with the minimum structural mass that is not susceptible to global structural failure. A method is also introduced to determine when the optimization process should halt. The method identifies when the optimization method has plateaued and is no longer likely to provide improved designs if continued for further iterations. This provides the designer with a rational method to determine the necessary time to run the optimization and avoid wasting computational resources on unnecessary iterations. A case study is presented to demonstrate the use of this method.