A theoretical justification of the set covering greedy heuristic of Caprara et al.

Large scale set covering problems have often been approached by constructive greedy heuristics, and much research has been devoted to the design and evaluation of various greedy criteria for such heuristics. A criterion proposed by Caprara et al. (1999) is based on reduced costs with respect to the yet unfulfilled constraints, and the resulting greedy heuristic is reported to be superior to those based on original costs or ordinary reduced costs.We give a theoretical justification of the greedy criterion proposed by Caprara et al. by deriving it from a global optimality condition for general non-convex optimisation problems. It is shown that this criterion is in fact greedy with respect to incremental contributions to a quantity which at termination coincides with the deviation between a Lagrangian dual bound and the objective value of the feasible solution found.     

Empirical and analytical study of many-objective optimization problems: analysing distribution of nondominated solutions and population size for scalability of randomized heuristics

Nature inspired randomized heuristics have been used successfully for single-objective and multi-objective optimization problems. However, with increasing number of objectives, what are called as “dominance resistant solutions” present a challenge to heuristics because they make it harder to locate and converge to the Pareto-optimal front. In the present work, the scalability of population-based heuristics for many-objective problems is studied using techniques from probability theory. Work in this domain tends to be more problem-specific and is largely empirical. Here a more general theoretical framework to study the problem arising from escalation of objectives is developed. This framework allows application of probability concentration inequalities to complicated multiobjective optimization heuristics. It also helps isolate the effects of escalation of objective space dimension from those of problem structure and of design space dimension. It opens up the possibility of combining the framework with more problem-specific models and with empirical work, to tune algorithms and to make problems amenable to heuristic search.     

Analysis of Classes of Heuristics for Scheduling a Two-Stage Flow Shop with Parallel Machines at One Stage

This paper addresses two-stage flow shop scheduling with parallel machines at one stage. For finding a minimum makespan schedule, which is strongly NP-hard, some efficient heuristics have been proposed in the literature. In this paper we enrich the set of heuristics by introducing a few classes of heuristics, and show that the existing heuristics can be put into this classification scheme. Furthermore, we give a complete theoretical analysis of the worst-case performance of the classes. Some empirical evaluations and comparisons for the average-case performance of a few typical heuristics in the classes are also performed.     

General Purpose Heuristics for Integer Programming—Part II

In spite of the many special purpose heuristics for specific classes of integer programming (IP) problems, there are few developments that focus on general purpose integer programming heuristics. This stems partly from the perception that general purpose methods are likely to be less effective than specialized procedures for specific problems, and partly from the perception that there is no unifying theoretical basis for creating general purpose heuristics. Still, there is a general acknowledgment that methods which are not limited to solving IP problems on a class by class basis, but which apply to a broader range of problems, have significant value. We provide a theoretical framework and associated explicit proposals for generating general purpose IP heuristics. Our development, makes use of cutting plane derivations that also give a natural basis for marrying heuristics with exact branch and cut methods for integer programming problems.     

A framework for the probabilistic analysis of hierarchical planning systems

As we have argued in previous papers, multi-level decision problems can often be modeled as multi-stage stochastic programs, and hierarchical planning systems designed for their solution, when viewed as stochastic programming heuristics, can be subjected to analytical performance evaluation. The present paper gives a general formulation of such stochastic programs and provides a framework for the design and analysis of heuristics for their solution. The various ways to measure the performance of such heuristics are reviewed, and some relations between these measures are derived. Our concepts are illustrated on a simple two-level planning problem of a general nature and on a more complicated two-level scheduling problem.     

Heuristics and their design: a survey

The purpose of this paper is a design oriented survey of heuristics. Since the main application fields of heuristics are problems of the combinatorial type, an introductory synopsis of combinatorial problems is first presented (Section 2). Heuristics are a specific kind of algorithms; therefore, the position of heuristics within the system of algorithms is described (Section 3). The design of heuristics requires decisions, and decisions are choices among alternatives which have to be explicitly available; a basis for this is presented in a morphological classification of heuristics (Section 4). Based on the classification, some aspects of the design process will be considered (Section 5).     

General purpose heuristics for integer programming—Part I

In spite of the many special purpose heuristics for specific classes of integer programming (IP) problems, there are few developments that focus on general purpose integer programming heuristics. This stems partly from the perception that general purpose methods are likely to be less effective than specialized procedures for specific problems, and partly from the perception that there is no unifying theoretical basis for creating general purpose heuristics. Still, there is a general acknowledgment that methods which are not limited to solving IP problems on a class by class basis, but which apply to a broader range of problems, have significant value. We show that certain ideas proposed in the 1970s, which are often overlooked, can be reformulated and linked with more recent developments to give a useful theoretical framework for generating general purpose IP heuristics. This framework, which has the appeal of being highly visual, makes use of cutting plane derivations that also give a natural basis for marrying heuristics with exact branch and cut methods for integer programming problems.     

Heuristics for the multi-level capacitated minimum spanning tree problem

The capacitated minimum spanning tree (CMST) problem is fundamental to the design of centralized communication networks. In this paper we consider the multi-level capacitated minimum spanning tree problem, a generalization of the well-known CMST problem. Based on work previously done in the field, three heuristics are presented, addressing unit and non-unit demand cases. The proposed heuristics have been also integrated into a mixed integer programming solver. Evaluation results are presented, for an extensive set of experiments, indicating the improvements that the heuristics bring to the particular problem.     

Experimental investigation of heuristics for resource-constrained project scheduling: An update

This paper considers heuristics for the well-known resource-constrained project scheduling problem (RCPSP). It provides an update of our survey which was published in 2000. We summarize and categorize a large number of heuristics that have recently been proposed in the literature. Most of these heuristics are then evaluated in a computational study and compared on the basis of our standardized experimental design. Based on the computational results we discuss features of good heuristics. The paper closes with some remarks on our test design and a summary of the recent developments in research on heuristics for the RCPSP.     

A comprehensive review and evaluation of permutation flowshop heuristics

In this work we present a review and comparative evaluation of heuristics and metaheuristics for the well-known permutation flowshop problem with the makespan criterion. A number of reviews and evaluations have already been proposed. However, the evaluations do not include the latest heuristics available and there is still no comparison of metaheuristics. Furthermore, since no common benchmarks and computing platforms are used, the results cannot be generalised. We propose a comparison of 25 methods, ranging from the classical Johnson's algorithm or dispatching rules to the most recent metaheuristics, including tabu search, simulated annealing, genetic algorithms, iterated local search and hybrid techniques. For the evaluation we use the standard test of Taillard [Eur. J. Operation. Res. 64 (1993) 278] composed of 120 instances of different sizes. In the evaluations we use the experimental design approach to obtain valid conclusions on the effectiveness and efficiency of the different methods tested.     

Classical and new heuristics for the open-shop problem: A computational evaluation

We study the problem of constructing minimum makespan schedules for the Open-Shop problem. This paper presents two new heuristics: the first one is a list scheduling algorithm with two priorities. The second is based on the construction of matchings in a bipartite graph. We develop several versions of these two heuristics. A computational evaluation shows that around 90% of randomly generated instances are solvable optimally, whereas classical (list scheduling) heuristics achieve less than 20% on average. Therefore, our algorithms make most Open-Shop instances easy to solve in practice, and this raises the problem of generating hard instances. We extend the evaluation to two kinds of such instances: the results are not so good, but remain better than classical heuristics.     

Adaptive automated construction of hybrid heuristics for exam timetabling and graph colouring problems

In this paper, we present a random iterative graph based hyper-heuristic to produce a collection of heuristic sequences to construct solutions of different quality. These heuristic sequences can be seen as dynamic hybridisations of different graph colouring heuristics that construct solutions step by step. Based on these sequences, we statistically analyse the way in which graph colouring heuristics are automatically hybridised. This, to our knowledge, represents a new direction in hyper-heuristic research. It is observed that spending the search effort on hybridising Largest Weighted Degree with Saturation Degree at the early stage of solution construction tends to generate high quality solutions. Based on these observations, an iterative hybrid approach is developed to adaptively hybridise these two graph colouring heuristics at different stages of solution construction. The overall aim here is to automate the heuristic design process, which draws upon an emerging research theme on developing computer methods to design and adapt heuristics automatically. Experimental results on benchmark exam timetabling and graph colouring problems demonstrate the effectiveness and generality of this adaptive hybrid approach compared with previous methods on automatically generating and adapting heuristics. Indeed, we also show that the approach is competitive with the state of the art human produced methods.     

Mathematical justification of a heuristic for statistical correlation of real-life time series

Many of the analyses of time series that arise in real-life situations require the adoption of various simplifying assumptions so as to cope with the complexity of the phenomena under consideration. Whilst accepting that these simplifications lead to heuristics providing less accurate processing of information compared to the solution of analytical equations, the intelligent choice of the simplifications coupled with the empirical verification of the resulting heuristic has proven itself to be a powerful systems modelling paradigm. In this study, we look at the theoretical underpinning of a successful heuristic for estimation of urban travel times from lane occupancy measurements. We show that by interpreting time series as statistical processes with a known distribution it is possible to estimate travel time as a limit value of an appropriately defined statistical process. The proof of the theorem asserting the above, supports the conclusion that it is possible to design a heuristic that eliminates the adverse effect of spurious readings without loosing temporal resolution of data (as implied by the standard method of data averaging). The original contribution of the paper concerning the link between the analytical modelling and the design of heuristics is general and relevant to a broad spectrum of applications.     

Hyper-heuristics: a survey of the state of the art

Hyper-heuristics comprise a set of approaches that are motivated (at least in part) by the goal of automating the design of heuristic methods to solve hard computational search problems. An underlying strategic research challenge is to develop more generally applicable search methodologies. The term hyper-heuristic is relatively new; it was first used in 2000 to describe heuristics to choose heuristics in the context of combinatorial optimisation. However, the idea of automating the design of heuristics is not new; it can be traced back to the 1960s. The definition of hyper-heuristics has been recently extended to refer to a search method or learning mechanism for selecting or generating heuristics to solve computational search problems. Two main hyper-heuristic categories can be considered: heuristic selection and heuristic generation. The distinguishing feature of hyper-heuristics is that they operate on a search space of heuristics (or heuristic components) rather than directly on the search space of solutions to the underlying problem that is being addressed. This paper presents a critical discussion of the scientific literature on hyper-heuristics including their origin and intellectual roots, a detailed account of the main types of approaches, and an overview of some related areas. Current research trends and directions for future research are also discussed.     

Heuristics for flight and maintenance planning of mission aircraft

Flight and Maintenance Planning (FMP) of mission aircraft addresses the question of which available aircraft to fly and for how long, and which grounded aircraft to perform maintenance operations on, in a group of aircraft that comprise a unit. The objective is to achieve maximum fleet availability of the unit over a given planning horizon, while also satisfying certain flight and maintenance requirements. The application of exact methodologies for the solution of the problem is quite limited, as a result of their excessive computational requirements. In this work, we prove several important properties of the FMP problem, and we use them to develop two heuristic procedures for solving large-scale FMP instances. The first heuristic is based on a graphical procedure which is currently used for generating flight and maintenance plans of mission aircraft by many Air Force organizations worldwide. The second heuristic is based on the idea of splitting the original problem into smaller sub-problems and solving each sub-problem separately. Both heuristics have been roughly sketched in earlier works that have appeared in the related literature. The present paper develops the theoretical background on which these heuristics are based, provides in detail the algorithmic steps required for their implementation, analyzes their worst-case computational complexity, presents computational results illustrating their computational performance on random problem instances, and evaluates the quality of the solutions that they produce. The size and parameter values of some of the randomly tested problem instances are quite realistic, making it possible to infer the performance of the heuristics on real world problem instances. Our computational results demonstrate that, under careful consideration, even large FMP instances can be handled quite effectively. The theoretical results and insights that we develop establish a fundamental background that can be very useful for future theoretical and practical developments related to the FMP problem.     

Adaptive sequencing of primal,dual, and design steps in simulation based optimization

Many researchers have used Oneshot optimization methods based on user-specified primal state iterations, the corresponding adjoint iterations, and appropriately preconditioned design steps. Our goal here is to develop heuristics for sequencing these three subtasks, in order to optimize the convergence rate of the resulting coupled iteration cycle. A key ingredient is the preconditioning in the design step by a BFGS approximation of the projected Hessian. We provide a hard bound on the spectral radius of the coupled iteration cycle at local minima satisfying second order sufficiency conditions. Finally, we show how certain problem specific parameters can be estimated by local samples and be used to steer the whole process adaptively. We present limited numerical results that confirm the theoretical analysis.     

Dynamics of Local Search Trajectory in Traveling Salesman Problem

This paper investigates dynamics of a local search trajectory generated by running the Or-opt heuristic on the traveling salesman problem. This study evaluates the dynamics of the local search heuristic by estimating the correlation dimension for the search trajectory, and finds that the local heuristic search process exhibits the transition from high-dimensional stochastic to low-dimensional chaotic behavior. The detection of dynamical complexity for a heuristic search process has both practical as well as theoretical relevance. The revealed dynamics may cast new light on design and analysis of heuristics and result in the potential for improved search process.     

Minimizing the number of machines with limited workload capacity for scheduling jobs with interval constraints

In this paper, we consider a parallel machine scheduling problem in which machines have a limited workload capacity and jobs have deadlines and release dates. The problem is motivated by the operation of energy storage management systems for microgrids under emergency conditions and generalizes some problems that have already been studied in the literature for their theoretical value. In this work, we propose heuristic and exact algorithms to solve the problem. The heuristics are adaptations of classical bin packing heuristics in which additional conditions on the feasibility of a solution are imposed, whereas the exact method is a branch-and-price approach. The results show that the branch-and-price approach is able to optimally solve random instances with up to 250 jobs within a time limit of one hour, while the heuristic procedures provide near optimal solution within reduced running times. Finally, we also provide additional complexity results for a special case of the problem.     

A survey of algorithms for the generalized assignment problem

This paper surveys algorithms for the well-known problem of finding the minimum cost assignment of jobs to agents so that each job is assigned exactly once and agents are not overloaded. All approaches seem to be based on branch-and-bound with bound supplied through heuristics and through relaxations of the primal problem formulation. From the survey one can select building blocks for the design of one's own tailor-made algorithm. The survey also reveals that although just about every mathematical programming technique was tried on this problem, there is still a lack of a representative set of test problems on which competing enumeration algorithms can be compared, as well as a shortage of effective heuristics.     

The effect of material flow and workload on the performance of machine location heuristics

Depending on the problem structure and routing strategies a machine location problem plays an important role in controlling the material flow of work-in-process in discrete product manufacturing environment. In this paper we investigate the effect of material flow and workload on the performance of heuristics for solving an important design problem for job routing and material flow in a manufacturing system. In this research we first develop a model for workload or traffic intensity between machines in a shop floor and then identify different structures of the problems, especially the data. This measure is then used to evaluate the effect of workload on efficiency of the heuristics to solve machine location problems. Some concluding remarks are made on to the effect of the workload or the traffic intensity of materials within the machine cell on the performance of some known heuristics. Conclusions are also made on the performance measures such as makespan, transporter utilization and machine utilization, depending on the problem and data structures.