'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus learning can amount to 'counting' in the case of multinomial distributions. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

'Exploiting problem structure in a genetic algorithm approach to a nurse rostering problem'

There is considerable interest in the use of genetic algorithms to solve problems arising in the areas of scheduling and timetabling. However, the classical genetic algorithm paradigm is not well equipped to handle the conflict between objectives and constraints that typically occurs in such problems. In order to overcome this, successful implementations frequently make use of problem specific knowledge. This paper is concerned with the development of a GA for a nurse rostering problem at a major UK hospital. The structure of the constraints is used as the basis for a co-evolutionary strategy using co-operating sub-populations. Problem specific knowledge is also used to define a system of incentives and disincentives, and a complementary mutation operator. Empirical results based on 52 weeks of live data show how these features are able to improve an unsuccessful canonical GA to the point where it is able to provide a practical solution to the problem.

Exploiting problem structure in a genetic algorithm approach to a nurse rostering problem

There is considerable interest in the use of genetic algorithms to solve problems arising in the areas of scheduling and timetabling. However, the classical genetic algorithm paradigm is not well equipped to handle the conflict between objectives and constraints that typically occurs in such problems. In order to overcome this, successful implementations frequently make use of problem specific knowledge. This paper is concerned with the development of a GA for a nurse rostering problem at a major UK hospital. The structure of the constraints is used as the basis for a co-evolutionary strategy using co-operating sub-populations. Problem specific knowledge is also used to define a system of incentives and disincentives, and a complementary mutation operator. Empirical results based on 52 weeks of live data show how these features are able to improve an unsuccessful canonical GA to the point where it is able to provide a practical solution to the problem.

'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus learning can amount to 'counting' in the case of multinomial distributions. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

An Indirect Genetic Algorithm for a Nurse Scheduling Problem

This paper describes a Genetic Algorithms approach to a manpower-scheduling problem arising at a major UK hospital. Although Genetic Algorithms have been successfully used for similar problems in the past, they always had to overcome the limitations of the classical Genetic Algorithms paradigm in handling the conflict between objectives and constraints. The approach taken here is to use an indirect coding based on permutations of the nurses, and a heuristic decoder that builds schedules from these permutations. Computational experiments based on 52 weeks of live data are used to evaluate three different decoders with varying levels of intelligence, and four well-known crossover operators. Results are further enhanced by introducing a hybrid crossover operator and by making use of simple bounds to reduce the size of the solution space. The results reveal that the proposed algorithm is able to find high quality solutions and is both faster and more flexible than a recently published Tabu Search approach.

'Exploiting problem structure in a genetic algorithm approach to a nurse rostering problem'

There is considerable interest in the use of genetic algorithms to solve problems arising in the areas of scheduling and timetabling. However, the classical genetic algorithm paradigm is not well equipped to handle the conflict between objectives and constraints that typically occurs in such problems. In order to overcome this, successful implementations frequently make use of problem specific knowledge. This paper is concerned with the development of a GA for a nurse rostering problem at a major UK hospital. The structure of the constraints is used as the basis for a co-evolutionary strategy using co-operating sub-populations. Problem specific knowledge is also used to define a system of incentives and disincentives, and a complementary mutation operator. Empirical results based on 52 weeks of live data show how these features are able to improve an unsuccessful canonical GA to the point where it is able to provide a practical solution to the problem.

Evolutionary algorithms for the modeling of bioreactors

This work aims to study the application of Genetic Algorithms in anaerobic digestion modeling, in particular when using dynamical models. Along the work, different types of bioreactors are shown, such as batch, semi-batch and continuous, as well as their mathematical modeling. The work intendeds to estimate the parameter values of two biological reaction model. For that, simulated results, where only one output variable, the produced biogas, is known, are fitted to the model results. For this reason, the problems associated with reverse optimization are studied, using some graphics that provide clues to the sensitivity and identifiability associated with the problem. Particular solutions obtained by the identifiability analysis using GENSSI and DAISY softwares are also presented. Finally, the optimization is performed using genetic algorithms. During this optimization the need to improve the convergence of genetic algorithms was felt. This need has led to the development of an adaptation of the genetic algorithms, which we called Neighbored Genetic Algorithms (NGA1 and NGA2). In order to understand if this new approach overcomes the Basic Genetic Algorithms (BGA) and achieves the proposed goals, a study of 100 full optimization runs for each situation was further developed. Results show that NGA1 and NGA2 are statistically better than BGA. However, because it was not possible to obtain consistent results, the Nealder-Mead method was used, where the initial guesses were the estimated results from GA; Algoritmos Evolucionários para a Modelação de Bioreactores Resumo: Neste trabalho procura-se estudar os algoritmos genéticos com aplicação na modelação da digestão anaeróbia e, em particular, quando se utilizam modelos dinâmicos. Ao longo do mesmo, são apresentados diferentes tipos de bioreactores, como os batch, semi-batch e contínuos, bem como a modelação matemática dos mesmos. Neste trabalho procurou-se estimar o valor dos parâmetros que constam num modelo de digestão anaeróbia para o ajustar a uma situação simulada onde apenas se conhece uma variável de output, o biogas produzido. São ainda estudados os problemas associados à optimização inversa com recurso a alguns gráficos que fornecem pistas sobre a sensibilidade e identifiacabilidade associadas ao problema da modelação da digestão anaeróbia. São ainda apresentadas soluções particulares de idenficabilidade obtidas através dos softwares GENSSI e DAISY. Finalmente é realizada a optimização do modelo com recurso aos algoritmos genéticos. No decorrer dessa optimização sentiu-se a necessidade de melhorar a convergência e, portanto, desenvolveu-se ainda uma adaptação dos algoritmos genéticos a que se deu o nome de Neighboured Genetic Algorithms (NGA1 e NGA2). No sentido de se compreender se as adaptações permitiam superar os algoritmos genéticos básicos e atingir as metas propostas, foi ainda desenvolvido um estudo em que o processo de optimização foi realizado 100 vezes para cada um dos métodos, o que permitiu concluir, estatisticamente, que os BGA foram superados pelos NGA1 e NGA2. Ainda assim, porque não foi possivel obter consistência nos resultados, foi usado o método de Nealder-Mead utilizado como estimativa inicial os resultados obtidos pelos algoritmos genéticos.

Aptidão agrícola e algoritmos genéticos na organização espacial em projetos de reforma agrária

A definição das parcelas familiares em projetos de reforma agrária envolve questões técnicas e sociais. Essas questões estão associadas principalmente às diferentes aptidões agrícolas do solo nestes projetos. O objetivo deste trabalho foi apresentar método para realizar o processo de ordenamento territorial em assentamentos de reforma agrária empregando Algoritmo Genético (AG). O AG foi testado no Projeto de Assentamento Veredas, em Minas Gerais, e implementado com base no sistema de aptidão agrícola das terras.

A simulation-based evolutionary multiobjective approach to manufacturing cell formation

The purpose of this paper is to propose a multiobjective optimization approach for solving the manufacturing cell formation problem, explicitly considering the performance of this said manufacturing system. Cells are formed so as to simultaneously minimize three conflicting objectives, namely, the level of the work-in-process, the intercell moves and the total machinery investment. A genetic algorithm performs a search in the design space, in order to approximate to the Pareto optimal set. The values of the objectives for each candidate solution in a population are assigned by running a discrete-event simulation, in which the model is automatically generated according to the number of machines and their distribution among cells implied by a particular solution. The potential of this approach is evaluated via its application to an illustrative example, and a case from the relevant literature. The obtained results are analyzed and reviewed. Therefore, it is concluded that this approach is capable of generating a set of alternative manufacturing cell configurations considering the optimization of multiple performance measures, greatly improving the decision making process involved in planning and designing cellular systems. (C) 2010 Elsevier Ltd. All rights reserved.

Simulated annealing applied to the irregular rotational placement of shapes over containers with fixed dimensions

This work deals with the problem of minimizing the waste of space that occurs on a rotational placement of a set of irregular two dimensional polygons inside a two dimensional container. This problem is approached with an heuristic based on simulated annealing. Traditional 14 external penalization"" techniques are avoided through the application of the no-fit polygon, that determinates the collision free area for each polygon before its placement. The simulated annealing controls: the rotation applied, the placement and the sequence of placement of the polygons. For each non placed polygon, a limited depth binary search is performed to find a scale factor that when applied to the polygon, would allow it to be fitted in the container. It is proposed a crystallization heuristic, in order to increase the number of accepted solutions. The bottom left and larger first deterministic heuristics were also studied. The proposed process is suited for non convex polygons and containers, the containers can have holes inside. (C) 2009 Elsevier Ltd. All rights reserved.

Placement over containers with fixed dimensions solved with adaptive neighborhood simulated annealing

This work deals with the problem of minimizing the waste of space that occurs on a rotational placement of a set of irregular bi-dimensional items inside a bi-dimensional container. This problem is approached with a heuristic based on Simulated Annealing (SA) with adaptive neighborhood. The objective function is evaluated in a constructive approach, where the items are placed sequentially. The placement is governed by three different types of parameters: sequence of placement, the rotation angle and the translation. The rotation applied and the translation of the polygon are cyclic continuous parameters, and the sequence of placement defines a combinatorial problem. This way, it is necessary to control cyclic continuous and discrete parameters. The approaches described in the literature deal with only type of parameter (sequence of placement or translation). In the proposed SA algorithm, the sensibility of each continuous parameter is evaluated at each iteration increasing the number of accepted solutions. The sensibility of each parameter is associated to its probability distribution in the definition of the next candidate.

A hybrid probabilistic criterion for market-based transmission expansion planning

Market-based transmission expansion planning gives information to investors on where is the most cost efficient place to invest and brings benefits to those who invest in this grid. However, both market issue and power system adequacy problems are system planers’ concern. In this paper, a hybrid probabilistic criterion of Expected Economical Loss (EEL) is proposed as an index to evaluate the systems’ overall expected economical losses during system operation in a competitive market. It stands on both investors’ and planner’s point of view and will further improves the traditional reliability cost. By applying EEL, it is possible for system planners to obtain a clear idea regarding the transmission network’s bottleneck and the amount of losses arises from this weak point. Sequentially, it enables planners to assess the worth of providing reliable services. Also, the EEL will contain valuable information for moneymen to undertake their investment. This index could truly reflect the random behaviors of power systems and uncertainties from electricity market. The performance of the EEL index is enhanced by applying Normalized Coefficient of Probability (NCP), so it can be utilized in large real power systems. A numerical example is carried out on IEEE Reliability Test System (RTS), which will show how the EEL can predict the current system bottleneck under future operational conditions and how to use EEL as one of planning objectives to determine future optimal plans. A well-known simulation method, Monte Carlo simulation, is employed to achieve the probabilistic characteristic of electricity market and Genetic Algorithms (GAs) is used as a multi-objective optimization tool.

Surgical correction of scoliosis: Numerical analysis and optimization of the procedure

A previously developed model is used to numerically simulate real clinical cases of the surgical correction of scoliosis. This model consists of one-dimensional finite elements with spatial deformation in which (i) the column is represented by its axis; (ii) the vertebrae are assumed to be rigid; and (iii) the deformability of the column is concentrated in springs that connect the successive rigid elements. The metallic rods used for the surgical correction are modeled by beam elements with linear elastic behavior. To obtain the forces at the connections between the metallic rods and the vertebrae geometrically, non-linear finite element analyses are performed. The tightening sequence determines the magnitude of the forces applied to the patient column, and it is desirable to keep those forces as small as possible. In this study, a Genetic Algorithm optimization is applied to this model in order to determine the sequence that minimizes the corrective forces applied during the surgery. This amounts to find the optimal permutation of integers 1, ... , n, n being the number of vertebrae involved. As such, we are faced with a combinatorial optimization problem isomorph to the Traveling Salesman Problem. The fitness evaluation requires one computing intensive Finite Element Analysis per candidate solution and, thus, a parallel implementation of the Genetic Algorithm is developed.

Optimal design of piezolaminated structures using B-spline strip finite element models

A package of B-spline finite strip models is developed for the linear analysis of piezolaminated plates and shells. This package is associated to a global optimization technique in order to enhance the performance of these types of structures, subjected to various types of objective functions and/or constraints, with discrete and continuous design variables. The models considered are based on a higher-order displacement field and one can apply them to the static, free vibration and buckling analyses of laminated adaptive structures with arbitrary lay-ups, loading and boundary conditions. Genetic algorithms, with either binary or floating point encoding of design variables, were considered to find optimal locations of piezoelectric actuators as well as to determine the best voltages applied to them in order to obtain a desired structure shape. These models provide an overall economy of computing effort for static and vibration problems.

GA topology optimization using random keys for tree encoding of structures

Topology optimization consists in finding the spatial distribution of a given total volume of material for the resulting structure to have some optimal property, for instance, maximization of structural stiffness or maximization of the fundamental eigenfrequency. In this paper a Genetic Algorithm (GA) employing a representation method based on trees is developed to generate initial feasible individuals that remain feasible upon crossover and mutation and as such do not require any repairing operator to ensure feasibility. Several application examples are studied involving the topology optimization of structures where the objective functions is the maximization of the stiffness and the maximization of the first and the second eigenfrequencies of a plate, all cases having a prescribed material volume constraint.